CN117031136B - Detection method, device, equipment and storage medium of millimeter wave therapeutic instrument - Google Patents
Detection method, device, equipment and storage medium of millimeter wave therapeutic instrument Download PDFInfo
- Publication number
- CN117031136B CN117031136B CN202311228206.5A CN202311228206A CN117031136B CN 117031136 B CN117031136 B CN 117031136B CN 202311228206 A CN202311228206 A CN 202311228206A CN 117031136 B CN117031136 B CN 117031136B
- Authority
- CN
- China
- Prior art keywords
- data
- radiation
- target
- millimeter wave
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000001225 therapeutic effect Effects 0.000 title claims abstract description 151
- 238000001514 detection method Methods 0.000 title claims abstract description 48
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 230000005855 radiation Effects 0.000 claims abstract description 586
- 238000009826 distribution Methods 0.000 claims abstract description 214
- 238000004458 analytical method Methods 0.000 claims abstract description 149
- 239000013598 vector Substances 0.000 claims abstract description 94
- 230000008859 change Effects 0.000 claims abstract description 38
- 238000010276 construction Methods 0.000 claims abstract description 35
- 238000007405 data analysis Methods 0.000 claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims description 66
- 230000006870 function Effects 0.000 claims description 57
- 238000000034 method Methods 0.000 claims description 52
- 238000012706 support-vector machine Methods 0.000 claims description 37
- 238000010586 diagram Methods 0.000 claims description 26
- 238000000605 extraction Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 24
- 238000013507 mapping Methods 0.000 claims description 14
- 238000001228 spectrum Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 10
- 238000000926 separation method Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012731 temporal analysis Methods 0.000 claims description 9
- 238000000700 time series analysis Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 8
- 230000008030 elimination Effects 0.000 claims description 6
- 238000003379 elimination reaction Methods 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 description 76
- 230000008569 process Effects 0.000 description 25
- 230000003595 spectral effect Effects 0.000 description 20
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 9
- 239000000284 extract Substances 0.000 description 7
- 238000005457 optimization Methods 0.000 description 7
- 230000008439 repair process Effects 0.000 description 7
- 238000000638 solvent extraction Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 6
- 238000003909 pattern recognition Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 206010028980 Neoplasm Diseases 0.000 description 4
- 206010028391 Musculoskeletal Pain Diseases 0.000 description 3
- 208000007613 Shoulder Pain Diseases 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 206010003246 arthritis Diseases 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 210000002478 hand joint Anatomy 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 206010028836 Neck pain Diseases 0.000 description 1
- 208000020307 Spinal disease Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000002917 arthritic effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000001959 radiotherapy Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 208000017520 skin disease Diseases 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 230000000451 tissue damage Effects 0.000 description 1
- 231100000827 tissue damage Toxicity 0.000 description 1
- 208000029761 vertebral disease Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R29/00—Arrangements for measuring or indicating electric quantities not covered by groups G01R19/00 - G01R27/00
- G01R29/08—Measuring electromagnetic field characteristics
- G01R29/0807—Measuring electromagnetic field characteristics characterised by the application
- G01R29/0814—Field measurements related to measuring influence on or from apparatus, components or humans, e.g. in ESD, EMI, EMC, EMP testing, measuring radiation leakage; detecting presence of micro- or radiowave emitters; dosimetry; testing shielding; measurements related to lightning
- G01R29/0857—Dosimetry, i.e. measuring the time integral of radiation intensity; Level warning devices for personal safety use
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/02—Radiation therapy using microwaves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R29/00—Arrangements for measuring or indicating electric quantities not covered by groups G01R19/00 - G01R27/00
- G01R29/08—Measuring electromagnetic field characteristics
- G01R29/0864—Measuring electromagnetic field characteristics characterised by constructional or functional features
- G01R29/0871—Complete apparatus or systems; circuits, e.g. receivers or amplifiers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R29/00—Arrangements for measuring or indicating electric quantities not covered by groups G01R19/00 - G01R27/00
- G01R29/08—Measuring electromagnetic field characteristics
- G01R29/0864—Measuring electromagnetic field characteristics characterised by constructional or functional features
- G01R29/0892—Details related to signal analysis or treatment; presenting results, e.g. displays; measuring specific signal features other than field strength, e.g. polarisation, field modes, phase, envelope, maximum value
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
Abstract
The invention relates to the technical field of equipment detection, and discloses a detection method, a detection device, detection equipment and a storage medium of a millimeter wave therapeutic apparatus, which are used for improving the detection accuracy of the millimeter wave therapeutic apparatus. Comprising the following steps: acquiring radiation data of the millimeter wave therapeutic instrument to obtain target radiation data; performing radiation distribution data analysis to obtain radiation distribution data; extracting features to obtain radiation feature data; performing kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and performing hyperplane construction to obtain a target hyperplane and a classification boundary; carrying out support vector construction on the radiation characteristic data to obtain a target support vector, and carrying out radiation source analysis to determine a target radiation source; carrying out radiation intensity change trend analysis on the radiation distribution data to obtain radiation intensity change trend data; generating a radiation intensity distribution map from the radiation intensity variation trend data to obtain a radiation intensity distribution map; and performing fault analysis on the millimeter wave therapeutic instrument to determine a fault analysis result.
Description
Technical Field
The present invention relates to the field of device detection technologies, and in particular, to a method, an apparatus, a device, and a storage medium for detecting a millimeter wave therapeutic apparatus.
Background
Millimeter wave therapeutic devices are devices used in the medical or industrial fields that utilize millimeter wave radiation for treatment or detection. Millimeter wave radiation has the advantages of strong penetrability, strong absorption property to biological tissues and the like, so that the millimeter wave radiation has wide application prospect in the fields of medical treatment, communication, safety detection and the like. However, the high frequency and energy characteristics of millimeter wave radiation also present a series of technical challenges in radiation therapy.
Conventional radiation source positioning methods often rely on relatively complex measurement equipment, such as electromagnetic field detectors, with the problems of inaccurate positioning and complex operation. This limits the ability of the millimeter wave therapeutic device to accurately target. The traditional radiation intensity analysis method often needs to process radiation data offline, so that the change of the radiation intensity cannot be monitored in real time, and the accuracy of radiation coverage is difficult to adjust in real time. The traditional millimeter wave therapeutic apparatus fault diagnosis mainly depends on manual experience and inspection, and has low efficiency and possibly problems of subjectivity and misjudgment.
Disclosure of Invention
The invention provides a detection method, a detection device and a storage medium of a millimeter wave therapeutic apparatus, which are used for improving the detection accuracy of the millimeter wave therapeutic apparatus.
The first aspect of the present invention provides a detection method of a millimeter wave therapeutic apparatus, the detection method of the millimeter wave therapeutic apparatus comprising:
starting a millimeter wave therapeutic apparatus, and acquiring radiation data of the millimeter wave therapeutic apparatus through an intelligent pixel array detector to obtain target radiation data;
performing radiation distribution data analysis on the target radiation data to obtain radiation distribution data;
inputting the radiation distribution data into a preset support vector machine model for feature extraction to obtain radiation feature data;
performing kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and performing hyperplane construction through the target linear kernel function to obtain a target hyperplane and a classification boundary;
based on the target hyperplane and the classification boundary, carrying out support vector construction on the radiation characteristic data to obtain a target support vector, and carrying out radiation source analysis through the target support vector to determine a target radiation source corresponding to the millimeter wave therapeutic instrument;
carrying out radiation intensity variation trend analysis on the radiation distribution data to obtain radiation intensity variation trend data;
generating a radiation intensity distribution map based on the target radiation source, and obtaining the radiation intensity distribution map;
And carrying out fault analysis on the millimeter wave therapeutic instrument based on the radiation intensity distribution diagram, determining a fault analysis result, and transmitting the fault analysis result to a preset data display terminal.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the performing radiation distribution data analysis on the target radiation data to obtain radiation distribution data includes:
carrying out data noise identification on the target radiation data to obtain a noise data set;
performing data noise elimination on the target radiation data through the noise data set to obtain standard radiation data;
performing linear interpolation processing on the standard radiation data to obtain corresponding interpolation radiation data;
performing radiation range calibration on the interpolation radiation data to obtain a target radiation range;
based on the target radiation range, carrying out gridding treatment on the interpolation radiation data to obtain gridding radiation data;
and performing contour analysis on the grid radiation data, determining a plurality of contour lines, and performing radiation distribution data analysis through the contour lines to obtain radiation distribution data.
With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, the inputting the radiation distribution data into a preset support vector machine model to perform feature extraction to obtain radiation feature data includes:
Inputting the radiation distribution data into the support vector machine model for spectrum feature analysis, and determining a corresponding spectrum feature set;
performing high-dimensional feature space mapping on the frequency spectrum feature set to obtain a corresponding high-dimensional feature vector;
and carrying out distributed feature matching on the high-dimensional feature vector to obtain corresponding radiation feature data.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, performing kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and performing hyperplane construction through the target linear kernel function to obtain a target hyperplane and a classification boundary, where the method includes:
linearly dividing the radiation characteristic data to obtain a plurality of groups of sub-characteristic data;
performing kernel function matching on a plurality of groups of sub-feature data to obtain the target linear kernel function;
carrying out data point separation processing on a plurality of groups of sub-feature data through the target linear kernel function to obtain a plurality of data points;
classifying the data points to obtain a plurality of corresponding sub-data point groups;
performing hyperplane construction based on a plurality of sub-data point groups to obtain corresponding target hyperplanes;
Extracting a plane equation corresponding to the target hyperplane to obtain a corresponding target hyperplane equation;
and carrying out three-dimensional classification boundary division through the target hyperplane equation to obtain the classification boundary.
With reference to the third implementation manner of the first aspect, in a fourth implementation manner of the first aspect of the present invention, the performing support vector construction on the radiation characteristic data based on the target hyperplane and the classification boundary to obtain a target support vector, performing radiation source analysis through the target support vector, and determining a target radiation source corresponding to the millimeter wave therapeutic apparatus includes:
based on the classification boundary, carrying out boundary distance calculation on a plurality of groups of sub data point groups to obtain a corresponding boundary distance set;
classifying the data of the boundary distance set based on a plurality of preset boundary distance thresholds to obtain a plurality of groups of sub-boundary distance data;
data screening is carried out on the multiple groups of sub-boundary distance data to obtain target sub-boundary distance data;
constructing a support vector through the target sub-boundary distance data to obtain the target support vector;
performing spatial position analysis on the target support vector to determine a target spatial position;
Performing spatial distribution analysis on the target support vector based on the target spatial position to determine spatial distribution data;
and carrying out radiation source analysis on the target support vector based on the spatial distribution data, and determining a target radiation source corresponding to the millimeter wave therapeutic instrument.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the performing radiation intensity variation trend analysis on the radiation distribution data to obtain radiation intensity variation trend data includes:
performing time series analysis on the radiation distribution data to determine corresponding time series data;
performing time marking on the radiation distribution data based on the time sequence data to obtain radiation distribution data with marking information;
carrying out space position division on the radiation distribution data with the marking information to determine radiation distribution data to be processed of a plurality of areas;
and carrying out radiation intensity change trend analysis on the radiation distribution data to be processed of the plurality of areas to obtain the radiation intensity change trend data.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, the performing, based on the radiation intensity distribution diagram, fault analysis on the millimeter wave therapeutic apparatus, determining a fault analysis result, and transmitting the fault analysis result to a preset data display terminal, includes:
Extracting an abnormal shape of the radiation intensity distribution diagram to obtain at least one abnormal shape data;
performing type matching on at least one piece of abnormal shape data, and determining the corresponding abnormal shape type;
and performing fault matching on the abnormal shape type based on a preset fault database to obtain a corresponding fault analysis result, and transmitting the fault analysis result to the data display terminal.
A second aspect of the present invention provides a detection device of a millimeter wave therapeutic apparatus, the detection device of the millimeter wave therapeutic apparatus comprising:
the starting module is used for starting the millimeter wave therapeutic apparatus, and acquiring radiation data of the millimeter wave therapeutic apparatus through the intelligent pixel array detector to obtain target radiation data;
the data analysis module is used for carrying out radiation distribution data analysis on the target radiation data to obtain radiation distribution data;
the extraction module is used for inputting the radiation distribution data into a preset support vector machine model to perform feature extraction to obtain radiation feature data;
the construction module is used for carrying out kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and carrying out hyperplane construction through the target linear kernel function to obtain a target hyperplane and a classification boundary;
The determining module is used for carrying out support vector construction on the radiation characteristic data based on the target hyperplane and the classification boundary to obtain a target support vector, carrying out radiation source analysis through the target support vector and determining a target radiation source corresponding to the millimeter wave therapeutic instrument;
the trend analysis module is used for carrying out radiation intensity change trend analysis on the radiation distribution data to obtain radiation intensity change trend data;
the generation module is used for generating a radiation intensity distribution map based on the target radiation source and carrying out radiation intensity distribution map generation on the radiation intensity change trend data to obtain the radiation intensity distribution map;
and the transmission module is used for carrying out fault analysis on the millimeter wave therapeutic instrument based on the radiation intensity distribution diagram, determining a fault analysis result and transmitting the fault analysis result to a preset data display terminal.
A third aspect of the present invention provides a detection apparatus of a millimeter wave therapeutic apparatus, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the detection device of the millimeter wave therapeutic apparatus to perform the detection method of the millimeter wave therapeutic apparatus described above.
A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which when executed on a computer, cause the computer to perform the above-described method of detecting a millimeter wave therapeutic apparatus.
In the technical scheme provided by the invention, a millimeter wave therapeutic apparatus is started, and radiation data acquisition is carried out on the millimeter wave therapeutic apparatus through an intelligent pixel array detector, so that target radiation data are obtained; performing radiation distribution data analysis on the target radiation data to obtain radiation distribution data; inputting the radiation distribution data into a preset support vector machine model for feature extraction to obtain radiation feature data; performing kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and performing hyperplane construction through the target linear kernel function to obtain a target hyperplane and a classification boundary; based on the target hyperplane and the classification boundary, carrying out support vector construction on the radiation characteristic data to obtain a target support vector, and carrying out radiation source analysis through the target support vector to determine a target radiation source corresponding to the millimeter wave therapeutic apparatus; carrying out radiation intensity change trend analysis on the radiation distribution data to obtain radiation intensity change trend data; generating a radiation intensity distribution map based on the target radiation source, and obtaining the radiation intensity distribution map; and performing fault analysis on the millimeter wave therapeutic instrument based on the radiation intensity distribution diagram, determining a fault analysis result, and transmitting the fault analysis result to a preset data display terminal. In the scheme, the high-precision radiation source positioning is realized by combining the target radiation data acquired by the intelligent pixel array detector with a support vector machine and a pattern recognition algorithm. This will ensure that the millimeter wave therapeutic apparatus can be aimed at the therapeutic target accurately, improving the therapeutic effect. By analyzing the radiation distribution data of the target radiation data, the radiation distribution data is obtained, and the millimeter wave therapeutic apparatus can monitor the distribution condition of the radiation intensity in real time. This helps to adjust the treatment parameters, ensure accuracy and uniformity of radiation coverage, and avoid excessive or insufficient radiation. And performing fault analysis on the millimeter wave therapeutic instrument by using the radiation characteristic data and the support vector machine model. And (5) timely finding out the fault or abnormal condition of the equipment through the generation of the radiation intensity distribution diagram. And transmitting the radiation distribution data, the radiation intensity change trend data and the fault analysis result to a preset data display terminal. An operator can view and analyze the data in real time through the data display terminal, and remotely monitor the state and the treatment effect of the equipment. The convenience and the real-time performance of equipment management are improved, and meanwhile, decision support is provided for equipment maintenance and optimization. By analyzing the radiation intensity distribution diagram, the treatment parameters are optimized, the treatment area is ensured to be fully covered, and the treatment accuracy and effect are improved. Meanwhile, the analysis of the radiation intensity change trend is beneficial to monitoring the radiation dose change in the treatment process, so that the treatment safety is ensured. By adopting an artificial intelligence algorithm, the data are subjected to feature extraction and pattern recognition, and an operator is assisted in decision making and optimization. This helps to ease the workload of the operator and to increase the level of intelligence of the device. And the transmission of the fault analysis result and the data display terminal is beneficial to the maintenance personnel to quickly acquire the equipment state and the fault information and quickly formulate a repair scheme. This will shorten the equipment maintenance time, reduce production and treatment interruptions, and improve the stability and reliability of the equipment.
Drawings
Fig. 1 is a schematic diagram showing an embodiment of a method for detecting a millimeter wave therapeutic apparatus according to an embodiment of the present invention;
FIG. 2 is a flow chart of feature extraction performed by inputting radiation distribution data into a preset support vector machine model in an embodiment of the present invention;
FIG. 3 is a flow chart of performing kernel matching on radiation characteristic data in an embodiment of the present invention;
FIG. 4 is a flow chart of support vector construction for radiation characteristic data in an embodiment of the invention;
fig. 5 is a schematic diagram showing an embodiment of a detection apparatus of a millimeter wave therapeutic apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a detection apparatus of a millimeter wave therapeutic apparatus according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a detection method, a detection device and a detection equipment of a millimeter wave therapeutic apparatus and a storage medium, which are used for improving the detection accuracy of the millimeter wave therapeutic apparatus. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a specific flow of an embodiment of the present invention is described below with reference to fig. 1, and one embodiment of a detection method of a millimeter wave therapeutic apparatus in an embodiment of the present invention includes:
s101, starting a millimeter wave therapeutic apparatus, and acquiring radiation data of the millimeter wave therapeutic apparatus through an intelligent pixel array detector to obtain target radiation data;
it is to be understood that the execution body of the present invention may be a detection device of the millimeter wave therapeutic apparatus, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, the millimeter wave therapeutic apparatus is started. Before starting, the therapeutic apparatus must be connected to a power supply and calibrated and preheated as necessary to ensure that the device is in normal operation. These operations may be accomplished through a control panel or computer interface of the device. For example, assume that the server has a millimeter wave therapeutic apparatus named "microwaveHealPro" for treating arthritis. Before starting, the operator inserts the power plug of the therapeutic apparatus into the power socket and ensures that the power switch is in the off state. The operator presses the power button to activate the therapeutic apparatus. The display screen of the device can display welcome information and system self-checking progress, so that normal operation of all components is ensured. Subsequently, a radiation data acquisition phase is entered. An intelligent pixel array detector is used to collect data related to the radiation output of the millimeter wave therapeutic device. The smart pixel array detector is a high sensitivity sensor capable of detecting radiation at the micro or nano level and converting it into an electrical signal. For example, a "microwavehealth pro" therapeutic apparatus generates millimeter wave radiation via an antenna system that irradiates an area of skin in need of treatment. The intelligent pixel array detector is mounted on the head or sensor area of the therapeutic apparatus as part of the device. Once the therapeutic device is in operation and ready for treatment, the smart pixel array detector is also put into standby. Subsequently, when the treatment process begins, the treatment apparatus emits millimeter wave radiation. The intelligent pixel array detector monitors information such as the intensity, frequency, direction and the like of the radiation in real time and converts the data into electrical signals. For example, during treatment, an operator irradiates millimeter wave radiation to a patient's right knee using a "microwavehealth pro" therapeutic instrument. The intelligent pixel array detector detects radiation reflected by the treatment head, monitors information such as intensity and frequency of the radiation in real time, and converts the information into electric signals. The collected radiation data can be transmitted to a control unit of the therapeutic apparatus for recording and processing through digital signals. These data can be used to monitor the effect of the treatment, adjust parameters such as radiation power and treatment time, to ensure the accuracy and safety of the treatment. The control unit of the microwaveHealPro therapeutic apparatus receives the radiation data transmitted by the intelligent pixel array detector and records the radiation data in a data log of the therapeutic process. These data can be used to evaluate the treatment effect, for example, to determine if the radiation intensity reaches a desired level, and to adjust the treatment parameters if necessary.
S102, performing radiation distribution data analysis on target radiation data to obtain radiation distribution data;
specifically, the millimeter wave therapeutic apparatus is started and radiation data acquisition is performed on the target area through the intelligent pixel array detector. The resulting target radiation data is subjected to data noise identification to detect abnormal data points that may be caused by environmental or sensor interference, thereby resulting in a noisy data set. And carrying out data noise elimination on the target radiation data through the noise data set, eliminating abnormal data, obtaining standard radiation data, and ensuring the accuracy of the data. And carrying out linear interpolation processing on the standard radiation data, filling blank or missing parts in the data, and obtaining corresponding interpolation radiation data, so that the radiation data becomes continuous and complete. And then, calibrating the radiation range according to the target radiation range, determining the radiation coverage area of the therapeutic instrument, ensuring that the radiation of the therapeutic instrument is only carried out in the target area, and increasing the treatment accuracy. Based on the target radiation range, the interpolation radiation data is subjected to gridding treatment, and the data is divided according to grids, so that subsequent analysis and display are facilitated. And carrying out contour analysis on the gridding radiation data, determining a plurality of contour lines, and displaying areas with different radiation intensities. The radiation distribution data analysis is performed through a plurality of contour lines, information about the radiation intensities of different areas is obtained, and the data can be used for evaluating the treatment effect and the safety. For example, a millimeter wave therapeutic apparatus named "MMWaveCare" is being used to treat cervical pain in patients. In the treatment process, the MMWaveCare starts the millimeter wave therapeutic apparatus, and radiation data acquisition is carried out on the neck of the patient through the intelligent pixel array detector. After data noise identification of the collected target radiation data, abnormal data points are found, which may be caused by patient movement or external interference. The MMWaveCare eliminates the abnormal data points according to the noise data set, and accurate standard radiation data is obtained. The MMWaveCare carries out linear interpolation processing on the standard radiation data, fills some missing data points, and obtains corresponding interpolation radiation data. Subsequently, "MMWaveCare" performs radiation range calibration to determine the area of coverage of the therapeutic apparatus radiation as a specific area of the patient's neck to ensure treatment accuracy. Based on the target radiation range, the MMWaveCare carries out gridding processing on the interpolation radiation data, and the data is divided according to grids. And performing contour analysis to determine a plurality of contours, and displaying areas with different radiation intensities. By analyzing the multiple contours, the "MMWaveCare" obtains radiation distribution data about the patient's neck region, which can be used for evaluation of therapeutic efficacy and safety, providing more reference basis for treatment. By the detection method, the MMWaveCare millimeter wave therapeutic instrument can analyze the target radiation data more accurately, and provides more effective treatment and attention for patients.
S103, inputting the radiation distribution data into a preset support vector machine model for feature extraction to obtain radiation feature data;
specifically, the radiation distribution data is input into a support vector machine model for spectral feature analysis. Support vector machines are a common supervised learning algorithm used for classification and regression tasks. By inputting radiation distribution data into a support vector machine model, the model is able to analyze the data and extract a set of spectral features. These spectral features are key information extracted from the data to describe the spectral characteristics of the radiation distribution. A high-dimensional feature space mapping is performed on the set of spectral features. High-dimensional feature space mapping is the process of mapping original features from a low-dimensional space to a higher-dimensional space. The purpose of this is to increase the complexity and expressive power of the features, thereby better distinguishing between features of different radiation distributions. And carrying out distributed feature matching on the high-dimensional feature vectors to obtain corresponding radiation feature data. Distribution feature matching refers to comparing and matching high-dimensional feature vectors with predefined feature distributions to determine radiation feature data. These radiation profile data will be used to further analyze and evaluate the performance and effectiveness of the therapeutic device. For example, consider a millimeter wave therapeutic apparatus named "mmwaveAnalyzer" for treating shoulder pain in a patient. In the treatment process, the MMWaveAnalyzer starts the millimeter wave therapeutic apparatus, and radiation data acquisition is carried out on the shoulder region of the patient through the intelligent pixel array detector. The collected radiation distribution data will be used for feature extraction. The MMWaveAnalyzer inputs the radiation distribution data into a preset support vector machine model for spectral feature analysis. Through analysis of the support vector machine model, the "MMWaveAnalyzer" extracts a set of spectral features from the radiation distribution data, which features are used to describe the radiation spectrum of the shoulder pain region. The "mmwaveAnalyzer" performs a high-dimensional feature space mapping on the set of spectral features. Mapping spectral features from a low-dimensional space to a higher-dimensional space increases the complexity and expressive power of the features, enabling better discrimination of the radiation features of different shoulder regions. "mmwaveAnalyzer" performs distributed feature matching on high-dimensional feature vectors. It compares and matches the high-dimensional feature vector with a predefined feature distribution to determine the radiation signature data for the shoulder pain region. These radiation profile data will be used to further analyze and evaluate the performance and therapeutic effect of the therapeutic device.
S104, performing kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and performing hyperplane construction through the target linear kernel function to obtain a target hyperplane and a classification boundary;
specifically, firstly, the radiation characteristic data is linearly divided to obtain a plurality of groups of sub-characteristic data. The linear division is to classify and group the feature data according to a certain rule so as to facilitate subsequent kernel function matching and hyperplane construction. And performing kernel function matching on the multiple groups of sub-feature data to obtain a target linear kernel function. The kernel function is a function for mapping low-dimensional features to high-dimensional feature space, and the difference of the features can be increased through kernel function matching, so that data separation and classification are better performed. And carrying out data point separation processing on multiple groups of sub-feature data through a target linear kernel function to obtain multiple data points. The data point separation process is to divide and separate the data points in a high-dimensional feature space for subsequent classification processing. And classifying the plurality of data points to obtain a plurality of corresponding sub-data point groups. The classification processing is to divide the data points mapped by the kernel function into different class groups according to the positions of the data points in the high-dimensional feature space, so as to obtain a plurality of sub-data point groups. And carrying out hyperplane construction based on a plurality of sub-data point groups to obtain a corresponding target hyperplane. Hyperplane is a linear classification boundary separating data points in a high-dimensional feature space. And extracting a plane equation corresponding to the target hyperplane to obtain a corresponding target hyperplane equation. Plane equations are mathematical expressions used to represent hyperplanes that can be used for subsequent three-dimensional classification boundary partitioning. And carrying out three-dimensional classification boundary division through a target hyperplane equation to obtain a classification boundary. Three-dimensional classification boundary partitioning is the mapping of a target hyperplane into classification boundaries in the original feature space for classifying data points into different classes. For example, a millimeter wave therapeutic apparatus named "mmwaveAnalyzer" is being used to treat patients suffering from tumors. During treatment, the "mmwaveAnalyzer" collects target radiation profile data for the patient's tumor region via the smart pixel array detector. The collected radiation characteristic data are linearly divided to obtain a plurality of groups of sub-characteristic data. And performing kernel function matching on multiple groups of sub-feature data by using the MMWaveAnalyzer to obtain a target linear kernel function. And carrying out data point separation processing on multiple groups of sub-feature data through a target linear kernel function to obtain multiple data points. The MMWaveAnalyzer classifies the data points to obtain corresponding groups of sub-data points. The hyperplane construction is performed based on multiple sets of sub-data points, and the "MMWaveAnalyzer" obtains the target hyperplane. The MMWaveAnalyzer extracts the corresponding plane equation from the target hyperplane for subsequent three-dimensional classification boundary partitioning. And (3) carrying out three-dimensional classification boundary division through a target hyperplane equation, and obtaining a classification boundary of the tumor region by using the MMWaveAnalyzer. These classification boundaries will help the "mmwaveAnalyzer" determine tumor and normal tissue regions, providing more accurate ancillary information for treatment.
S105, constructing a support vector for the radiation characteristic data based on the target hyperplane and the classification boundary to obtain a target support vector, and analyzing a radiation source through the target support vector to determine a target radiation source corresponding to the millimeter wave therapeutic apparatus;
specifically, first, based on the classification boundary, boundary distance calculation is performed on multiple groups of sub-data point groups, so as to obtain a corresponding boundary distance set. The boundary distance calculation is to balance the distance between the sub-data point group and the classification boundary for subsequent data classification. And classifying the data of the boundary distance set based on a plurality of preset boundary distance thresholds to obtain a plurality of groups of sub-boundary distance data. Data classification is the classification of groups of data points into different categories according to set thresholds for subsequent data screening and support vector construction. And carrying out data screening on the multiple groups of sub-boundary distance data to obtain target sub-boundary distance data. Data screening is to select the set of data points closest to the classification boundary that will be candidates for support vectors. And constructing a support vector through the target sub-boundary distance data to obtain a target support vector. Support vectors are the set of data points closest to the classification boundary and critical to classification decisions, which play an important role in radiation source analysis. And carrying out space position analysis on the target support vector to determine the target space position. The spatial location analysis is to determine the location of the target support vector in physical space, which will facilitate subsequent radiation source analysis and spatial distribution analysis. And carrying out spatial distribution analysis on the target support vector based on the target spatial position to determine spatial distribution data. The spatial distribution analysis is to combine the position information of the target support vector with the anatomical structure and other information of the treatment area to analyze the spatial distribution rule of the target support vector. And carrying out radiation source analysis on the target support vector based on the spatial distribution data, and determining a target radiation source corresponding to the millimeter wave therapeutic instrument. The radiation source analysis is to determine the source and intensity of the radiation produced by the therapeutic apparatus for further evaluation and optimization of the treatment. For example, a millimeter wave therapeutic apparatus named "mmwaveAnalyzer" is being used to treat patients suffering from spinal disorders. During treatment, the "mmwaveAnalyzer" collects target radiation profile data for the patient's spinal region via the smart pixel array detector. And the collected radiation characteristic data is subjected to classified boundary calculation and boundary distance calculation to obtain a plurality of groups of sub-boundary distance data. The MMWaveAnalyzer classifies the sub-boundary distance data according to a preset boundary distance threshold value, and performs data screening to obtain target sub-boundary distance data. These target sub-boundary distance data will become candidates for the support vector. And constructing a support vector through the target sub-boundary distance data, and obtaining a target support vector by using the MMWaveAnalyzer. The spatial location analysis of the target support vectors determines their specific locations in the spinal region. The spatial distribution analysis of the target support vector based on the target spatial location, the "mmwaveAnalyzer" found that the target support vector was primarily distributed near the damaged disc in the patient's spinal region, indicating that the therapeutic radiation was primarily concentrated in the diseased region. Radiation source analysis is performed on the target support vector based on the spatial distribution data, and the MMWaveAnalyzer determines the target radiation source corresponding to the therapeutic apparatus. Such information will help the "mmwaveAnalyzer" optimize the treatment plan, ensuring the accuracy and effectiveness of the treatment. Through the radiation source analysis process, the MMWaveAnalyzer millimeter wave therapeutic apparatus can more accurately know the source and distribution condition of radiation, and provides more comprehensive support for the treatment of the vertebra diseases.
S106, carrying out radiation intensity change trend analysis on the radiation distribution data to obtain radiation intensity change trend data;
specifically, time series analysis is implemented, and the acquired radiation distribution data is converted into time series data. By recording the time stamp of the radiation data acquisition, the radiation intensity is correlated with time for subsequent time stamping and trend analysis. And (3) time-marking the radiation distribution data based on the time sequence data, and adding time information to each radiation data point to obtain the radiation distribution data with marking information. The purpose of the time-stamping is to accurately distinguish radiation data at different time points in the analysis of the trend of the radiation intensity. The method comprises the steps of carrying out space position division on radiation distribution data with marking information, classifying and grouping the data according to space positions, and determining radiation distribution data to be processed of a plurality of areas. In this way, the server performs trend analysis on the radiation data of different areas respectively, so as to obtain finer radiation intensity change trend data. And carrying out radiation intensity change trend analysis on the radiation distribution data to be processed of the plurality of areas to obtain the radiation intensity change trend data. This analysis process may use various time series analysis methods, such as moving averages, trend line fitting, periodic analysis, etc., to reveal the law of variation of radiation intensity over time. For example, assume that a millimeter wave therapeutic apparatus named "MMWaveTracker" is being used to treat patients suffering from arthritis. During treatment, "MMWaveTracker" collects radiation distribution data of the patient joint region in real time through the intelligent pixel array detector. The MMWaveTracker performs time series analysis on the radiation distribution data, converts the radiation distribution data into time series data, and records the time stamp of each radiation data acquisition. Based on the time series data, an "MMWaveTracker" adds a time stamp to each radiation data point, resulting in radiation distribution data with the stamp information. For example, one set of data may be labeled as the radiation intensity at the beginning of the treatment and another set of data may be labeled as the radiation intensity after a period of time has elapsed from the treatment. The MMWaveTracker divides the radiation distribution data with the marking information into space positions according to different areas of the joint of the patient to obtain the radiation distribution data to be processed of a plurality of areas. For example, the left hand joint, the right hand joint, and the affected joint region are distinguished. The MMWaveTracker analyzes the radiation intensity variation trend of the radiation distribution data to be processed of the areas. It may be found that in the initial stages of treatment, the radiation intensity is higher in arthritic patients and gradually decreases as the treatment progresses. Through the trend analysis, the MMWavetracker can monitor the change of the radiation intensity in the treatment process of a patient in real time so as to adjust the treatment plan and ensure the safety and the effectiveness of the treatment.
S107, generating a radiation intensity distribution map based on the target radiation source, and obtaining the radiation intensity distribution map;
specifically, the extraction of the abnormal shape is realized, the collected radiation intensity distribution diagram is analyzed, and the abnormal shape data in the radiation intensity distribution diagram is found out. An abnormal shape may refer to a region in the radiation intensity profile that is inconsistent with expectations, that is outside of normal ranges, or that has mutations. And performing type matching on at least one abnormal shape data, and determining the corresponding abnormal shape type. The types of abnormal shapes may be classified into various possible types of faults, such as uneven radiation, leakage of radiation, excessive or insufficient radiation intensity, and the like. And performing fault matching on the abnormal shape type based on a preset fault database. The fault database contains mapping relations between various abnormal shape types and possible fault reasons. By matching, a corresponding fault analysis result can be obtained, namely, possible fault reasons or problems are identified. And transmitting the fault analysis result to a preset data display terminal. The data display terminal can be a monitoring interface of the therapeutic apparatus, a doctor computer or mobile equipment, or a remote monitoring center. And transmitting the fault analysis result to a data display terminal, so that an operator or doctor can acquire fault information in time and take corresponding measures to repair or adjust. For example, a millimeter wave therapeutic apparatus named "MMWaveTester" is being used to treat patients suffering from skin disorders. During treatment, the "MMWaveTester" collects radiation intensity profiles of the patient's skin area in real time by means of an intelligent pixel array detector. The MMWaveTester performs abnormal shape extraction on the radiation intensity profiles to find an abnormal shape data, i.e., an area in the skin area where an abnormal increase in radiation intensity occurs. The MMWaveTester performs type matching on the abnormal shape data, and determines that the abnormal shape data is an abnormal shape type with excessively high radiation intensity. The MMWaveTester matches the abnormal shape type with high radiation intensity with possible fault reasons according to a preset fault database. Through matching, the 'MMWaveTester' obtains a fault analysis result, which suggests that the radiation intensity is possibly out of a normal range due to equipment adjustment errors. The MMWaveTester transmits the fault analysis result to a preset data display terminal, so that operators or doctors can know the problem of abnormal radiation intensity of the therapeutic equipment in time, and corresponding measures are taken to repair or adjust the equipment.
S108, performing fault analysis on the millimeter wave therapeutic apparatus based on the radiation intensity distribution diagram, determining a fault analysis result, and transmitting the fault analysis result to a preset data display terminal.
It should be noted that, at first, the module is started, and the module is responsible for starting the millimeter wave therapeutic apparatus, and performs radiation data acquisition on the therapeutic apparatus through the intelligent pixel array detector, so as to obtain target radiation data. The intelligent pixel array detector is a sensor for collecting radiation data, and can acquire radiation signals sent by the millimeter wave therapeutic instrument in real time. For example, when the therapeutic apparatus starts to operate, the starting module triggers the intelligent pixel array detector to start collecting radiation data emitted by the therapeutic apparatus. The data analysis module then performs a radiation profile data analysis on the obtained target radiation data to obtain radiation profile data. The radiation distribution data reflects the spatial distribution of the radiation intensity. For example, the data analysis module can convert the acquired radiation data into a radiation intensity distribution diagram, and clearly display the radiation intensity of the therapeutic apparatus. And then an extraction module, wherein the module inputs the radiation distribution data into a preset support vector machine model to perform feature extraction, so as to obtain radiation feature data. The support vector machine is a machine learning algorithm that extracts features from data. By means of the extraction module, complex radiation distribution data can be converted into more compact, more representative radiation characteristic data. And then a construction module, which performs kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and performs hyperplane construction through the target linear kernel function to obtain a target hyperplane and a classification boundary. The target hyperplane and classification boundary describe the distribution of the radiation characteristic data in the high-dimensional characteristic space, and can effectively classify different radiation characteristics. And the determining module is used for constructing a support vector for the radiation characteristic data based on the target hyperplane and the classification boundary to obtain a target support vector, analyzing the radiation source through the target support vector and determining a target radiation source corresponding to the millimeter wave therapeutic instrument. The target support vector is a set of data points that play a critical role in hyperplane construction, from which the primary radiation source of the therapeutic instrument can be determined by radiation source analysis. The trend analysis module is used for carrying out radiation intensity change trend analysis on the radiation distribution data to obtain radiation intensity change trend data. The radiation intensity variation trend data reflects the variation of the radiation intensity with time. For example, during treatment, the trend analysis module may monitor the trend of the change in radiation intensity to assess the effectiveness of the treatment. Then, a generation module generates a radiation intensity distribution map based on the target radiation source, and obtains the radiation intensity distribution map. The radiation intensity distribution diagram displays the distribution of the radiation intensity in space in a graphical mode, and the intensity distribution of the radiation source is reflected more intuitively. And finally, a transmission module which is used for carrying out fault analysis on the millimeter wave therapeutic instrument based on the radiation intensity distribution diagram, determining a fault analysis result and transmitting the fault analysis result to a preset data display terminal. The data display terminal can be a monitoring interface, a doctor's computer or mobile device, or a remote monitoring center. The fault analysis result can be timely fed back to an operator or a doctor through the transmission module so as to take corresponding measures for repair or adjustment.
In the embodiment of the invention, the high-precision radiation source positioning is realized by combining the target radiation data acquired by the intelligent pixel array detector with a support vector machine and a pattern recognition algorithm. This will ensure that the millimeter wave therapeutic apparatus can be aimed at the therapeutic target accurately, improving the therapeutic effect. By analyzing the radiation distribution data of the target radiation data, the radiation distribution data is obtained, and the millimeter wave therapeutic apparatus can monitor the distribution condition of the radiation intensity in real time. This helps to adjust the treatment parameters, ensure accuracy and uniformity of radiation coverage, and avoid excessive or insufficient radiation. And performing fault analysis on the millimeter wave therapeutic instrument by using the radiation characteristic data and the support vector machine model. And (5) timely finding out the fault or abnormal condition of the equipment through the generation of the radiation intensity distribution diagram. And transmitting the radiation distribution data, the radiation intensity change trend data and the fault analysis result to a preset data display terminal. An operator can view and analyze the data in real time through the data display terminal, and remotely monitor the state and the treatment effect of the equipment. The convenience and the real-time performance of equipment management are improved, and meanwhile, decision support is provided for equipment maintenance and optimization. By analyzing the radiation intensity distribution diagram, the treatment parameters are optimized, the treatment area is ensured to be fully covered, and the treatment accuracy and effect are improved. Meanwhile, the analysis of the radiation intensity change trend is beneficial to monitoring the radiation dose change in the treatment process, so that the treatment safety is ensured. By adopting an artificial intelligence algorithm, the data are subjected to feature extraction and pattern recognition, and an operator is assisted in decision making and optimization. This helps to ease the workload of the operator and to increase the level of intelligence of the device. And the transmission of the fault analysis result and the data display terminal is beneficial to the maintenance personnel to quickly acquire the equipment state and the fault information and quickly formulate a repair scheme. This will shorten the equipment maintenance time, reduce production and treatment interruptions, and improve the stability and reliability of the equipment.
In a specific embodiment, the process of executing step S102 may specifically include the following steps:
(1) Carrying out data noise identification on target radiation data to obtain a noise data set;
(2) Performing data noise elimination on the target radiation data through the noise data set to obtain standard radiation data;
(3) Performing linear interpolation processing on the standard radiation data to obtain corresponding interpolation radiation data;
(4) Performing radiation range calibration on the interpolation radiation data to obtain a target radiation range;
(5) Based on the target radiation range, performing gridding treatment on the interpolation radiation data to obtain gridding radiation data;
(6) Performing contour analysis on the grid radiation data, determining a plurality of contour lines, and performing radiation distribution data analysis through the plurality of contour lines to obtain radiation distribution data.
Specifically, data noise identification is performed on the target radiation data. Data noise may be inaccurate data due to interference or errors in the acquisition process. Noise data points are identified from the radiation data by analyzing the radiation data, and the data points are collected to form a noise data set. And carrying out data noise elimination on the target radiation data through the noise data set. And using the information in the noise data set to reject the noise data points in the target radiation data, thereby obtaining more accurate standard radiation data. And carrying out linear interpolation processing on the standard radiation data. In some cases, the acquisition of radiation data may not be continuous, resulting in a lack of data points at certain locations. By linear interpolation, the radiation data at the missing position can be deduced through the existing data points, so that the corresponding interpolation radiation data is obtained. And calibrating the radiation range of the interpolation radiation data. The radiation range refers to the spatial range of the radiation data, i.e. the radiation coverage area of the therapeutic apparatus. And analyzing the interpolated radiation data to determine the boundary of the radiation data, thereby obtaining the position information of the target radiation range. And performing gridding processing on the interpolation radiation data based on the target radiation range. The interpolated radiation data is divided into a plurality of grids, each representing a small area, forming gridded radiation data. And performing contour analysis on the gridding radiation data. The contour line is a curve connecting points with the same radiation intensity, and the distribution condition of the radiation intensity in different areas can be determined by carrying out contour line analysis on the radiation data. In contour analysis, multiple contours can be obtained. And carrying out radiation distribution data analysis through a plurality of contour lines. The density, shape, distribution and other information of the contour lines can provide important clues about radiation distribution, so as to help know the intensity distribution of radiation and possible abnormal or uneven conditions. For example, assume that a millimeter wave therapeutic apparatus called "MMWaveDetector" is being used to treat patients suffering from deep tissue damage. During treatment, an "MMWaveDetector" initiates acquisition of target radiation data and radiation data is acquired by the smart pixel array detector. The "MMWaveDetector" performs data noise identification on the acquired radiation data, finds noise data points that may exist therein, and forms a noise data set. The MMWaveDetector performs data noise elimination on the target radiation data through the noise data set, so that more accurate standard radiation data is obtained. The MMWaveDetector carries out linear interpolation processing on the standard radiation data, and interpolates the missing position through the existing data points to obtain corresponding interpolation radiation data. Then, the MMWaveDetector performs radiation range calibration on the interpolated radiation data, determines the boundary of the radiation data, and obtains the position information of the target radiation range. The "MMWaveDetector" performs gridding processing on the interpolated radiation data based on the target radiation range, dividing the radiation data into a plurality of small areas. The MMWaveDetector performs a contour analysis on the gridded radiation data to obtain a plurality of contours, which connect points having the same radiation intensity. The MMWaveDetector analyzes radiation distribution data through a plurality of contour lines, and knows the intensity distribution condition of radiation and the possible abnormal or uneven condition from the density, shape, distribution condition and the like of the contour lines, thereby obtaining radiation distribution data and providing important reference information for the treatment process.
In a specific embodiment, as shown in fig. 2, the process of performing step S103 may specifically include the following steps:
s201, inputting radiation distribution data into a support vector machine model for spectrum feature analysis, and determining a corresponding spectrum feature set;
s202, performing high-dimensional feature space mapping on the frequency spectrum feature set to obtain a corresponding high-dimensional feature vector;
s203, carrying out distribution feature matching on the high-dimensional feature vectors to obtain corresponding radiation feature data.
The radiation distribution data is input into a support vector machine model for spectral feature analysis. Support vector machines are a commonly used machine learning algorithm for classification and regression problems. In the spectrum characteristic analysis, the support vector machine model processes the radiation distribution data and extracts spectrum characteristic information in the radiation distribution data. These spectral features may include information about radiation intensity, spectral distribution shape, etc. over different frequency ranges. For example, assume a radiation detection device called a "radiation detector" that can detect radiation in an environment. When the "radiodetector" is activated, it collects radiation data from the environment via the sensor. These data contain radiation intensity values at different frequencies. The "radiation detector" inputs these radiation distribution data into the support vector machine model. The support vector machine model performs spectral feature analysis on the input radiation distribution data, and extracts spectral feature information therein. For example, it may analyze the variation of the radiation intensity at different frequencies to obtain a set of spectral features containing information about the radiation intensity in different frequency ranges. A high-dimensional feature space mapping is performed on the set of spectral features. In the operation of support vector machines, data is typically mapped into a high-dimensional feature space such that otherwise linearly inseparable data becomes linearly separable in the high-dimensional space. By such mapping, the support vector machine can better classify and analyze the data. For example, in the spectral feature analysis result of "radiodetector", a set of spectral features is obtained, which contains radiation intensity information in different frequency ranges. The support vector machine performs a high-dimensional feature space mapping on the spectral feature data. It is assumed that in high-dimensional space, the support vector machine can better distinguish radiation intensities at different frequencies. And carrying out distributed feature matching on the high-dimensional feature vectors to obtain corresponding radiation feature data. In the high-dimensional feature space, the support vectors can be classified and matched according to the distribution condition of the data points. Through the process, the support vector machine correlates the high-dimensional feature vector with the specific radiation feature to obtain corresponding radiation feature data. For example, in a high-dimensional feature space, the support vector machine classifies and matches radiation intensities at different frequencies. It is possible to classify data points with similar spectral characteristics into a class, resulting in corresponding radiation characteristic data describing the radiation intensity distribution over different frequency ranges.
In a specific embodiment, as shown in fig. 3, the process of executing step S104 may specifically include the following steps:
s301, linearly dividing the radiation characteristic data to obtain a plurality of groups of sub-characteristic data;
s302, performing kernel function matching on a plurality of groups of sub-feature data to obtain a target linear kernel function;
s303, carrying out data point separation processing on a plurality of groups of sub-feature data through a target linear kernel function to obtain a plurality of data points;
s304, classifying the plurality of data points to obtain a plurality of corresponding sub-data point groups;
s305, carrying out hyperplane construction based on a plurality of sub-data point groups to obtain a corresponding target hyperplane;
s306, extracting a plane equation corresponding to the target hyperplane to obtain a corresponding target hyperplane equation;
s307, three-dimensional classification boundary division is carried out through the target hyperplane equation, and classification boundaries are obtained.
The radiation characteristic data is divided linearly. Linear partitioning is the process of classifying radiation characteristic data according to some criteria or rule. The radiation characteristic data is divided into a plurality of groups of sub-characteristic data through linear division, and each group of sub-characteristic data has certain similarity or characteristics. For example, assume that the server has a set of radiation characteristic data that includes radiation intensity information at different frequencies. By linear partitioning, the server divides the set of data into three sets of sub-feature data: the first group is radiation intensity data at low frequencies, the second group is radiation intensity data at medium frequencies, and the third group is radiation intensity data at high frequencies. And performing kernel function matching on the multiple groups of sub-feature data. A kernel function is a mathematical function that can map data to a high-dimensional feature space such that the data is more easily separated in the high-dimensional space. By kernel function matching, a target linear kernel function can be obtained, which describes the distribution of multiple groups of sub-feature data in a high-dimensional feature space. For example, for the three sets of sub-feature data described above, the server uses a kernel function to map them to a high-dimensional feature space. In high-dimensional space, the server better distinguishes radiation intensity data at low, medium and high frequencies. And carrying out data point separation processing on multiple groups of sub-feature data through a target linear kernel function. Data point separation refers to dividing different sets of data points in a high-dimensional feature space such that the different sets of data points are separated in space. For example, in a high-dimensional feature space, radiation intensity data at low, medium, and high frequencies may be separated using a target linear kernel function to form a plurality of data point clusters. And classifying the plurality of data points to obtain a plurality of corresponding sub-data point groups. Through classification processing, data points in a high-dimensional space are classified according to a certain rule or standard to form a plurality of sub-data point groups. For example, in a high-dimensional feature space, the server classifies data points into different sub-data point groups that belong to radiation intensity data at low, medium and high frequencies, based on their location and features. The hyperplane construction is performed based on the multiple sets of sub-data points. Hyperplane is a linear division in high-dimensional space that can divide different sets of data points in space to form classification boundaries. For example, by hyperplane construction of multiple sets of sub-data points, the server finds classification boundaries in the high-dimensional feature space that can separate radiation intensity data at low, medium, and high frequencies. And extracting a plane equation corresponding to the target hyperplane to obtain a corresponding target hyperplane equation. The target hyperplane equations may be used to describe equations of classification boundaries to help the server understand and analyze the distribution of data in the high-dimensional feature space. For example, by extracting the plane equation corresponding to the target hyperplane, the server obtains an equation describing the classification boundary separating the radiation intensity data at low, medium and high frequencies.
In a specific embodiment, as shown in fig. 4, the process of performing step S105 may specifically include the following steps:
s401, calculating boundary distances of a plurality of groups of sub data point groups based on classification boundaries to obtain corresponding boundary distance sets;
s402, classifying data of the boundary distance set based on a plurality of preset boundary distance thresholds to obtain a plurality of groups of sub-boundary distance data;
s403, data screening is carried out on a plurality of groups of sub-boundary distance data to obtain target sub-boundary distance data;
s404, constructing a support vector through target sub-boundary distance data to obtain a target support vector;
s405, performing spatial position analysis on the target support vector to determine a target spatial position;
s406, performing spatial distribution analysis on the target support vector based on the target spatial position to determine spatial distribution data;
s407, performing radiation source analysis on the target support vector based on the spatial distribution data to determine a target radiation source corresponding to the millimeter wave therapeutic apparatus.
Specifically, based on the classification boundary, boundary distance calculation is performed on multiple groups of sub-data point groups, so as to obtain a corresponding boundary distance set. The boundary distance is the distance from the data point to the classification boundary and can be used to measure the proximity of the data point to the classification boundary. And obtaining a boundary distance set by calculating the distances from the plurality of groups of sub-data point groups to the classification boundary. For example, assume that the server has obtained a classification boundary, i.e., a hyperplane separating radiation characteristic data at different frequencies in a high-dimensional characteristic space. The server now performs a distance calculation of the plurality of sets of sub-data points from the classification boundary to obtain a set of boundary distances, including a distance value from each set of sub-data points to the classification boundary. And classifying the data of the boundary distance set based on a plurality of preset boundary distance thresholds to obtain a plurality of groups of sub-boundary distance data. The preset boundary distance threshold is a threshold set according to a specific problem, and is used for classifying data in the boundary distance set. Data having a distance less than the threshold is classified as target sub-boundary distance data. For example, in the set of boundary distances, the server sets a boundary distance threshold. For each set of sub-data points, if less than a threshold value, it is classified as target sub-boundary distance data, indicating that the set of sub-data points is closer to the classification boundary, possibly associated with the target radiation source. And carrying out data screening on the multiple groups of sub-boundary distance data to obtain target sub-boundary distance data. The data screening is to remove possible noise or abnormal values and ensure the accuracy and reliability of the target sub-boundary distance data. For example, after obtaining multiple sets of sub-boundary distance data, the server screens the data to remove data which does not meet preset conditions or is possibly abnormal, and retains target sub-boundary distance data actually related to the target radiation source. And constructing a support vector through the target sub-boundary distance data to obtain a target support vector. Support vectors refer to data points located on classification boundaries that play a decisive role in the location and shape of the classification boundary. With the target sub-boundary distance data, the server determines target support vectors that will help the server determine the target spatial location. For example, by support vector construction of the target sub-boundary distance data, the server obtains support vectors that lie on the classification boundary, which may represent data points associated with the target radiation source. And carrying out space position analysis on the target support vector to determine the target space position. Spatial location analysis refers to determining the position and distribution of support vectors in space, and thus inferring the likely location of the target radiation source. For example, by spatially analyzing the target support vector, the server presumes that the target radiation source may be located at a certain spatial location near the classification boundary. And carrying out radiation source analysis on the target support vector based on the spatial distribution data, and determining a target radiation source corresponding to the millimeter wave therapeutic instrument. The server considers the spatial distribution of the support vectors and combines the results of the previous analysis to determine the possible target radiation sources. For example, by analyzing the spatial distribution of the target support vector and combining the previous analysis of the distance and the characteristic data, the server determines the position and the characteristics of the target radiation source corresponding to the millimeter wave therapeutic apparatus.
In a specific embodiment, the process of executing step S106 may specifically include the following steps:
(1) Performing time series analysis on the radiation distribution data to determine corresponding time series data;
(2) Performing time marking on the radiation distribution data based on the time sequence data to obtain radiation distribution data with marking information;
(3) Carrying out space position division on the radiation distribution data with the marking information, and determining to-be-processed radiation distribution data of a plurality of areas;
(4) And carrying out radiation intensity change trend analysis on the radiation distribution data to be processed of the plurality of areas to obtain radiation intensity change trend data.
Specifically, the radiation distribution data is subjected to time series analysis, and corresponding time series data is determined. Time series analysis refers to the process of arranging and analyzing radiation distribution data in time sequence to obtain the trend and rule of the data over time. For example, assume that the server has a set of radiation distribution data, each data point corresponding to a particular point in time. By time series analysis of this set of data, the server obtains trends in the radiation over time, such as increases and decreases in the radiation intensity over time. And time-marking the radiation distribution data based on the time sequence data to obtain the radiation distribution data with marking information. Time stamping means adding time information to the radiation distribution data such that each data point carries a corresponding time stamp. For example, by time stamping, the server knows the specific time corresponding to each data point, so that the change of the data with time can be better understood. For example, after adding a time stamp to the radiation distribution data, the server obtains the following data: time 1-radiation data point 1, time 2-radiation data point 2, and so on. And carrying out space position division on the radiation distribution data with the marking information to determine the radiation distribution data to be processed of a plurality of areas. Spatial location partitioning refers to partitioning radiation distribution data according to spatial location information, classifying data points into different regions or sectors. For example, assume that the server has a set of time-stamped radiation distribution data, each data point corresponding to a particular temporal and spatial location. Through spatial position division, the server divides the data points into corresponding areas according to different spatial positions where the data points are located. And carrying out radiation intensity change trend analysis on the radiation distribution data to be processed of the plurality of areas to obtain radiation intensity change trend data. The radiation intensity variation trend analysis refers to comparing and analyzing radiation data of different areas to obtain the trend of the radiation intensity variation of different areas with time. For example, assume that the server divides the radiation distribution data into three regions: region a, region B, and region C. By performing radiation intensity variation trend analysis on the radiation data of the three areas, the server obtains trend data of the radiation intensity variation of the area A, the area B and the area C along with time.
In a specific embodiment, the process of executing step S108 may specifically include the following steps:
(1) Extracting an abnormal shape of the radiation intensity distribution diagram to obtain at least one abnormal shape data;
(2) Performing type matching on at least one abnormal shape data, and determining a corresponding abnormal shape type;
(3) And performing fault matching on the abnormal shape type based on a preset fault database to obtain a corresponding fault analysis result, and transmitting the fault analysis result to the data display terminal.
Specifically, the abnormal shape extraction is performed on the radiation intensity distribution map to obtain at least one abnormal shape data. Abnormal shape extraction refers to identifying areas from the radiation intensity profile that do not conform to normal shapes or are abnormal, possibly representing data of faults or abnormal conditions. For example, assume that the server has a radiation intensity profile that includes the intensity profile of the millimeter wave therapeutic device radiation. By performing an abnormal shape extraction on the image, the server identifies one or more areas that do not conform to the normal shape, which areas may correspond to a fault or abnormal condition. And performing type matching on at least one abnormal shape data, and determining the corresponding abnormal shape type. The abnormal shape type matching means that the extracted abnormal shape is compared with a preset abnormal shape type to determine which type the abnormal shape belongs to. For example, suppose that the server extracts an abnormal shape data, which takes on an irregular shape. By performing type matching on the abnormal shape, the server compares the abnormal shape with a preset abnormal shape type, and possibly judges that the abnormal shape belongs to the type of 'spot-like abnormality' or 'mutation-like abnormality'. And performing fault matching on the abnormal shape type based on a preset fault database to obtain a corresponding fault analysis result. The fault matching refers to matching the abnormal shape type with a pre-established fault database to find possible fault reasons or abnormal conditions corresponding to the abnormal shape type. For example, assume that the server has built a fault database that contains various anomaly shape types and corresponding fault causes. By matching the type of the abnormal shape obtained in the foregoing with the failure database, the server finds the failure cause corresponding thereto, such as "antenna failure", "signal interference", and the like. And transmitting the fault analysis result to the data display terminal. The fault analysis result is transmitted to the data display terminal so that related personnel can view and analyze the detection result in time, and corresponding measures are taken for processing or repairing. For example, it is assumed that the failure cause corresponding to the abnormal shape obtained by the server through the failure matching is "antenna failure". After the fault analysis result is transmitted to the data display terminal, related personnel can acquire the information in time and further check and repair work is carried out according to the fault reason.
The method for detecting a millimeter wave therapeutic apparatus according to the embodiment of the present invention is described above, and the detecting device for a millimeter wave therapeutic apparatus according to the embodiment of the present invention is described below, referring to fig. 5, one embodiment of the detecting device for a millimeter wave therapeutic apparatus according to the embodiment of the present invention includes:
the starting module 501 is used for starting the millimeter wave therapeutic apparatus, and acquiring radiation data of the millimeter wave therapeutic apparatus through the intelligent pixel array detector to obtain target radiation data;
the data analysis module 502 is configured to perform radiation distribution data analysis on the target radiation data to obtain radiation distribution data;
an extracting module 503, configured to input the radiation distribution data into a preset support vector machine model for feature extraction, so as to obtain radiation feature data;
a construction module 504, configured to perform kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and perform hyperplane construction through the target linear kernel function to obtain a target hyperplane and a classification boundary;
the determining module 505 is configured to perform support vector construction on the radiation characteristic data based on the target hyperplane and the classification boundary to obtain a target support vector, and perform radiation source analysis through the target support vector to determine a target radiation source corresponding to the millimeter wave therapeutic apparatus;
The trend analysis module 506 is configured to perform radiation intensity variation trend analysis on the radiation distribution data to obtain radiation intensity variation trend data;
the generating module 507 is configured to generate a radiation intensity distribution map based on the target radiation source, so as to obtain a radiation intensity distribution map;
and the transmission module 508 is used for carrying out fault analysis on the millimeter wave therapeutic apparatus based on the radiation intensity distribution diagram, determining a fault analysis result and transmitting the fault analysis result to a preset data display terminal.
Through the cooperation of the components, the high-precision radiation source positioning is realized by combining the support vector machine and the pattern recognition algorithm through the target radiation data acquired by the intelligent pixel array detector. This will ensure that the millimeter wave therapeutic apparatus can be aimed at the therapeutic target accurately, improving the therapeutic effect. By analyzing the radiation distribution data of the target radiation data, the radiation distribution data is obtained, and the millimeter wave therapeutic apparatus can monitor the distribution condition of the radiation intensity in real time. This helps to adjust the treatment parameters, ensure accuracy and uniformity of radiation coverage, and avoid excessive or insufficient radiation. And performing fault analysis on the millimeter wave therapeutic instrument by using the radiation characteristic data and the support vector machine model. And (5) timely finding out the fault or abnormal condition of the equipment through the generation of the radiation intensity distribution diagram. And transmitting the radiation distribution data, the radiation intensity change trend data and the fault analysis result to a preset data display terminal. An operator can view and analyze the data in real time through the data display terminal, and remotely monitor the state and the treatment effect of the equipment. The convenience and the real-time performance of equipment management are improved, and meanwhile, decision support is provided for equipment maintenance and optimization. By analyzing the radiation intensity distribution diagram, the treatment parameters are optimized, the treatment area is ensured to be fully covered, and the treatment accuracy and effect are improved. Meanwhile, the analysis of the radiation intensity change trend is beneficial to monitoring the radiation dose change in the treatment process, so that the treatment safety is ensured. By adopting an artificial intelligence algorithm, the data are subjected to feature extraction and pattern recognition, and an operator is assisted in decision making and optimization. This helps to ease the workload of the operator and to increase the level of intelligence of the device. And the transmission of the fault analysis result and the data display terminal is beneficial to the maintenance personnel to quickly acquire the equipment state and the fault information and quickly formulate a repair scheme. This will shorten the equipment maintenance time, reduce production and treatment interruptions, and improve the stability and reliability of the equipment.
The detection device of the millimeter wave therapeutic apparatus in the embodiment of the present invention is described in detail from the point of view of the modularized functional entity in fig. 5 above, and the detection device of the millimeter wave therapeutic apparatus in the embodiment of the present invention is described in detail from the point of view of hardware processing below.
Fig. 6 is a schematic structural diagram of a detection device of a millimeter wave therapeutic apparatus according to an embodiment of the present invention, where the detection device 600 of the millimeter wave therapeutic apparatus may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the detection device 600 of the millimeter wave therapeutic apparatus. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the detection device 600 of the millimeter wave therapeutic apparatus.
Detection device 600 of the millimeter wave therapeutic apparatus may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the configuration of the detection device of the millimeter wave therapeutic apparatus shown in fig. 6 does not constitute a limitation of the detection device of the millimeter wave therapeutic apparatus, and may include more or less components than those illustrated, or may combine certain components, or may be arranged in different components.
The present invention also provides a detection apparatus for a millimeter wave therapeutic apparatus, which includes a memory and a processor, wherein computer readable instructions are stored in the memory, and when the computer readable instructions are executed by the processor, the processor is caused to execute the steps of the detection method for the millimeter wave therapeutic apparatus in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, where the instructions when executed on a computer cause the computer to perform the steps of the method for detecting a millimeter wave therapeutic apparatus.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or passed as separate products, may be stored in a computer readable storage medium. Based on the understanding that the technical solution of the present invention may be embodied in essence or in a part contributing to the prior art or in whole or in part in the form of a software product stored in a storage medium, comprising instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for detecting a millimeter wave therapeutic apparatus, the method comprising:
starting a millimeter wave therapeutic apparatus, and acquiring radiation data of the millimeter wave therapeutic apparatus through an intelligent pixel array detector to obtain target radiation data;
performing radiation distribution data analysis on the target radiation data to obtain radiation distribution data;
inputting the radiation distribution data into a preset support vector machine model for feature extraction to obtain radiation feature data;
performing kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and performing hyperplane construction through the target linear kernel function to obtain a target hyperplane and a classification boundary; the method specifically comprises the following steps: linearly dividing the radiation characteristic data to obtain a plurality of groups of sub-characteristic data; performing kernel function matching on a plurality of groups of sub-feature data to obtain the target linear kernel function; carrying out data point separation processing on a plurality of groups of sub-feature data through the target linear kernel function to obtain a plurality of data points; classifying the data points to obtain a plurality of corresponding sub-data point groups; performing hyperplane construction based on a plurality of sub-data point groups to obtain corresponding target hyperplanes; extracting a plane equation corresponding to the target hyperplane to obtain a corresponding target hyperplane equation; performing three-dimensional classification boundary division through the target hyperplane equation to obtain the classification boundary;
Based on the target hyperplane and the classification boundary, carrying out support vector construction on the radiation characteristic data to obtain a target support vector, and carrying out radiation source analysis through the target support vector to determine a target radiation source corresponding to the millimeter wave therapeutic instrument; the method specifically comprises the following steps: based on the classification boundary, carrying out boundary distance calculation on a plurality of groups of sub data point groups to obtain a corresponding boundary distance set; classifying the data of the boundary distance set based on a plurality of preset boundary distance thresholds to obtain a plurality of groups of sub-boundary distance data; data screening is carried out on the multiple groups of sub-boundary distance data to obtain target sub-boundary distance data; constructing a support vector through the target sub-boundary distance data to obtain the target support vector; performing spatial position analysis on the target support vector to determine a target spatial position; performing spatial distribution analysis on the target support vector based on the target spatial position to determine spatial distribution data; performing radiation source analysis on the target support vector based on the spatial distribution data to determine a target radiation source corresponding to the millimeter wave therapeutic instrument;
carrying out radiation intensity variation trend analysis on the radiation distribution data to obtain radiation intensity variation trend data;
Generating a radiation intensity distribution map based on the target radiation source, and obtaining the radiation intensity distribution map;
and carrying out fault analysis on the millimeter wave therapeutic instrument based on the radiation intensity distribution diagram, determining a fault analysis result, and transmitting the fault analysis result to a preset data display terminal.
2. The method according to claim 1, wherein the performing radiation distribution data analysis on the target radiation data to obtain radiation distribution data includes:
carrying out data noise identification on the target radiation data to obtain a noise data set;
performing data noise elimination on the target radiation data through the noise data set to obtain standard radiation data;
performing linear interpolation processing on the standard radiation data to obtain corresponding interpolation radiation data;
performing radiation range calibration on the interpolation radiation data to obtain a target radiation range;
based on the target radiation range, carrying out gridding treatment on the interpolation radiation data to obtain gridding radiation data;
and performing contour analysis on the grid radiation data, determining a plurality of contour lines, and performing radiation distribution data analysis through the contour lines to obtain radiation distribution data.
3. The method for detecting a millimeter wave therapeutic apparatus according to claim 1, wherein the inputting the radiation distribution data into a preset support vector machine model for feature extraction to obtain radiation feature data comprises:
inputting the radiation distribution data into the support vector machine model for spectrum feature analysis, and determining a corresponding spectrum feature set;
performing high-dimensional feature space mapping on the frequency spectrum feature set to obtain a corresponding high-dimensional feature vector;
and carrying out distributed feature matching on the high-dimensional feature vector to obtain corresponding radiation feature data.
4. The method according to claim 1, wherein the performing radiation intensity variation trend analysis on the radiation distribution data to obtain radiation intensity variation trend data comprises:
performing time series analysis on the radiation distribution data to determine corresponding time series data;
performing time marking on the radiation distribution data based on the time sequence data to obtain radiation distribution data with marking information;
carrying out space position division on the radiation distribution data with the marking information to determine radiation distribution data to be processed of a plurality of areas;
And carrying out radiation intensity change trend analysis on the radiation distribution data to be processed of the plurality of areas to obtain the radiation intensity change trend data.
5. The method according to claim 1, wherein the performing fault analysis on the millimeter wave therapeutic apparatus based on the radiation intensity distribution map, determining a fault analysis result, and transmitting the fault analysis result to a preset data display terminal, comprises:
extracting an abnormal shape of the radiation intensity distribution diagram to obtain at least one abnormal shape data;
performing type matching on at least one piece of abnormal shape data, and determining the corresponding abnormal shape type;
and performing fault matching on the abnormal shape type based on a preset fault database to obtain a corresponding fault analysis result, and transmitting the fault analysis result to the data display terminal.
6. A detection device of a millimeter wave therapeutic apparatus, characterized in that the detection device of the millimeter wave therapeutic apparatus comprises:
the starting module is used for starting the millimeter wave therapeutic apparatus, and acquiring radiation data of the millimeter wave therapeutic apparatus through the intelligent pixel array detector to obtain target radiation data;
The data analysis module is used for carrying out radiation distribution data analysis on the target radiation data to obtain radiation distribution data;
the extraction module is used for inputting the radiation distribution data into a preset support vector machine model to perform feature extraction to obtain radiation feature data;
the construction module is used for carrying out kernel function matching on the radiation characteristic data to obtain a target linear kernel function, and carrying out hyperplane construction through the target linear kernel function to obtain a target hyperplane and a classification boundary; the method specifically comprises the following steps: linearly dividing the radiation characteristic data to obtain a plurality of groups of sub-characteristic data; performing kernel function matching on a plurality of groups of sub-feature data to obtain the target linear kernel function; carrying out data point separation processing on a plurality of groups of sub-feature data through the target linear kernel function to obtain a plurality of data points; classifying the data points to obtain a plurality of corresponding sub-data point groups; performing hyperplane construction based on a plurality of sub-data point groups to obtain corresponding target hyperplanes; extracting a plane equation corresponding to the target hyperplane to obtain a corresponding target hyperplane equation; performing three-dimensional classification boundary division through the target hyperplane equation to obtain the classification boundary;
The determining module is used for carrying out support vector construction on the radiation characteristic data based on the target hyperplane and the classification boundary to obtain a target support vector, carrying out radiation source analysis through the target support vector and determining a target radiation source corresponding to the millimeter wave therapeutic instrument; the method specifically comprises the following steps: based on the classification boundary, carrying out boundary distance calculation on a plurality of groups of sub data point groups to obtain a corresponding boundary distance set; classifying the data of the boundary distance set based on a plurality of preset boundary distance thresholds to obtain a plurality of groups of sub-boundary distance data; data screening is carried out on the multiple groups of sub-boundary distance data to obtain target sub-boundary distance data; constructing a support vector through the target sub-boundary distance data to obtain the target support vector; performing spatial position analysis on the target support vector to determine a target spatial position; performing spatial distribution analysis on the target support vector based on the target spatial position to determine spatial distribution data; performing radiation source analysis on the target support vector based on the spatial distribution data to determine a target radiation source corresponding to the millimeter wave therapeutic instrument;
The trend analysis module is used for carrying out radiation intensity change trend analysis on the radiation distribution data to obtain radiation intensity change trend data;
the generation module is used for generating a radiation intensity distribution map based on the target radiation source and carrying out radiation intensity distribution map generation on the radiation intensity change trend data to obtain the radiation intensity distribution map;
and the transmission module is used for carrying out fault analysis on the millimeter wave therapeutic instrument based on the radiation intensity distribution diagram, determining a fault analysis result and transmitting the fault analysis result to a preset data display terminal.
7. A detection apparatus of a millimeter wave therapeutic apparatus, characterized in that the detection apparatus of a millimeter wave therapeutic apparatus comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the detection device of the millimeter wave therapeutic apparatus to perform the method of detection of the millimeter wave therapeutic apparatus of any one of claims 1-5.
8. A computer readable storage medium having instructions stored thereon, wherein the instructions when executed by a processor implement the method of detecting a millimeter wave therapeutic device according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311228206.5A CN117031136B (en) | 2023-09-22 | 2023-09-22 | Detection method, device, equipment and storage medium of millimeter wave therapeutic instrument |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311228206.5A CN117031136B (en) | 2023-09-22 | 2023-09-22 | Detection method, device, equipment and storage medium of millimeter wave therapeutic instrument |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117031136A CN117031136A (en) | 2023-11-10 |
| CN117031136B true CN117031136B (en) | 2024-03-29 |
Family
ID=88637597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311228206.5A Active CN117031136B (en) | 2023-09-22 | 2023-09-22 | Detection method, device, equipment and storage medium of millimeter wave therapeutic instrument |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117031136B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109464757A (en) * | 2018-12-29 | 2019-03-15 | 上海联影医疗科技有限公司 | A kind of method, system, device and the storage medium of determining target object position |
| CN110917500A (en) * | 2019-12-02 | 2020-03-27 | 雄安华讯方舟科技有限公司 | Diagnosis and treatment system for burned tissues |
| WO2021034333A1 (en) * | 2019-08-22 | 2021-02-25 | Qualcomm Incorporated | Wireless communication with enhanced maximum permissible exposure (mpe) compliance |
| CN112731380A (en) * | 2020-12-16 | 2021-04-30 | 路晟悠拜(重庆)科技有限公司 | Intelligent human body monitoring method and monitoring equipment based on millimeter waves |
| US11075929B1 (en) * | 2018-02-20 | 2021-07-27 | Facebook, Inc. | Machine learning assisted anomaly detection on a millimeter-wave communications network |
| EP4154810A1 (en) * | 2021-09-28 | 2023-03-29 | Koninklijke Philips N.V. | System and device control using shape clustering |
| CN115913413A (en) * | 2023-02-22 | 2023-04-04 | 西安电子科技大学 | Intelligent spatial millimeter wave propagation characteristic analysis method |
| EP4197586A1 (en) * | 2021-12-20 | 2023-06-21 | Hahn-Schickard-Gesellschaft für angewandte Forschung e.V. | Personalized auricular stimulation electrode interface |
| CN116502252A (en) * | 2023-06-26 | 2023-07-28 | 北京中成康富科技股份有限公司 | Method and system for intelligently collecting millimeter wave therapeutic instrument data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201406134D0 (en) * | 2014-04-04 | 2014-05-21 | Elekta Ab | Image-guided radiation therapy |
| US20210018489A1 (en) * | 2019-07-16 | 2021-01-21 | Jahan Razavi | Apparatus and Method for Detecting and Correcting Blood Clot Events |
| US11320517B2 (en) * | 2019-08-22 | 2022-05-03 | Qualcomm Incorporated | Wireless communication with enhanced maximum permissible exposure (MPE) compliance |
| WO2021036366A1 (en) * | 2019-08-29 | 2021-03-04 | 北京连心医疗科技有限公司 | Standardized artificial intelligence automatic radiotherapy planning method and system |
| US11122397B2 (en) * | 2019-11-20 | 2021-09-14 | Mitsubishi Electric Research Laboratories, Inc. | Localization using millimeter wave beam attributes |
-
2023
- 2023-09-22 CN CN202311228206.5A patent/CN117031136B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11075929B1 (en) * | 2018-02-20 | 2021-07-27 | Facebook, Inc. | Machine learning assisted anomaly detection on a millimeter-wave communications network |
| CN109464757A (en) * | 2018-12-29 | 2019-03-15 | 上海联影医疗科技有限公司 | A kind of method, system, device and the storage medium of determining target object position |
| WO2021034333A1 (en) * | 2019-08-22 | 2021-02-25 | Qualcomm Incorporated | Wireless communication with enhanced maximum permissible exposure (mpe) compliance |
| CN110917500A (en) * | 2019-12-02 | 2020-03-27 | 雄安华讯方舟科技有限公司 | Diagnosis and treatment system for burned tissues |
| CN112731380A (en) * | 2020-12-16 | 2021-04-30 | 路晟悠拜(重庆)科技有限公司 | Intelligent human body monitoring method and monitoring equipment based on millimeter waves |
| EP4154810A1 (en) * | 2021-09-28 | 2023-03-29 | Koninklijke Philips N.V. | System and device control using shape clustering |
| EP4197586A1 (en) * | 2021-12-20 | 2023-06-21 | Hahn-Schickard-Gesellschaft für angewandte Forschung e.V. | Personalized auricular stimulation electrode interface |
| CN115913413A (en) * | 2023-02-22 | 2023-04-04 | 西安电子科技大学 | Intelligent spatial millimeter wave propagation characteristic analysis method |
| CN116502252A (en) * | 2023-06-26 | 2023-07-28 | 北京中成康富科技股份有限公司 | Method and system for intelligently collecting millimeter wave therapeutic instrument data |
Non-Patent Citations (1)
| Title |
|---|
| 基于模糊支持向量机的毫米波辐射计目标识别;李小辉;朱莉;吴坚;;微波学报;20171229(第S1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117031136A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6577607B2 (en) | Automatic feature analysis, comparison, and anomaly detection | |
| Koh et al. | Diagnosis of retinal health in digital fundus images using continuous wavelet transform (CWT) and entropies | |
| Jrad et al. | Automatic detection and classification of high-frequency oscillations in depth-EEG signals | |
| Krishnan et al. | Automated glaucoma detection using hybrid feature extraction in retinal fundus images | |
| US11672427B2 (en) | Systems and methods for tissue assessment | |
| CN104411234B (en) | Sign and system, method and the computerized algorithm of classification for electro physiology Evoked ptential | |
| US10751001B2 (en) | Systems and methods for tracking and analysis of electrical-physiological interference | |
| US20110190621A1 (en) | Methods and Systems for Regional Synchronous Neural Interactions Analysis | |
| EP4057192A1 (en) | Integrated analysis method, integrated analysis device, and integrated analysis program | |
| CN116107194B (en) | Automatic switching control method, device and equipment of laser and storage medium | |
| Sharma et al. | Automated classification of focal and non-focal EEG signals based on bivariate empirical mode decomposition | |
| Gupta et al. | A review of different ECG classification/detection techniques for improved medical applications | |
| EP2384142B1 (en) | Patient monitor and method | |
| Mendonça et al. | Cyclic alternating pattern estimation based on a probabilistic model over an EEG signal | |
| Raja et al. | Glaucoma detection in fundal retinal images using trispectrum and complex wavelet-based features | |
| CN115081486A (en) | Epileptic focus positioning system and method for intracranial electroencephalogram network in early stage of epileptic seizure | |
| CN117031136B (en) | Detection method, device, equipment and storage medium of millimeter wave therapeutic instrument | |
| Deepa et al. | A novel SVMA and K-NN classifier based optical ML technique for seizure detection | |
| JP2015112423A (en) | Epileptic seizure sign detection device, epileptic seizure sign detection model generation device, epileptic seizure sign detection method, epileptic seizure sign detection model generation method, epileptic seizure sign detection program and epileptic seizure sign detection model generating program | |
| Jibon et al. | Epileptic seizure detection from electroencephalogram (EEG) signals using linear graph convolutional network and DenseNet based hybrid framework | |
| CN114468996A (en) | Method for analyzing breast signs based on orderliness, multimodality and symmetry deficiency | |
| CN117370878B (en) | Epidermis extraction and positioning method and system based on spine joint vibration information | |
| CN116269738B (en) | Intelligent control method, device, equipment and storage medium of radio frequency therapeutic apparatus | |
| US11612343B2 (en) | Method and system for determining the intention of a user of a vehicle to brake or accelerate | |
| Tigrini et al. | Gait Event Timeseries Assessment through Spectral Biomarkers and Machine Learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |