CN116910593B - Signal noise suppression method and system for chemiluminescent instrument - Google Patents
Signal noise suppression method and system for chemiluminescent instrument Download PDFInfo
- Publication number
- CN116910593B CN116910593B CN202311180930.5A CN202311180930A CN116910593B CN 116910593 B CN116910593 B CN 116910593B CN 202311180930 A CN202311180930 A CN 202311180930A CN 116910593 B CN116910593 B CN 116910593B
- Authority
- CN
- China
- Prior art keywords
- chemiluminescent
- sequence
- sensing data
- maximum point
- maximum
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000001629 suppression Effects 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 117
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 5
- 230000001953 sensory effect Effects 0.000 claims description 16
- 239000003550 marker Substances 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 4
- 239000011324 bead Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000427 antigen Substances 0.000 description 1
- 102000036639 antigens Human genes 0.000 description 1
- 108091007433 antigens Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000007850 fluorescent dye Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007790 solid phase Substances 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/75—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated
- G01N21/76—Chemiluminescence; Bioluminescence
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/53—Immunoassay; Biospecific binding assay; Materials therefor
- G01N33/543—Immunoassay; Biospecific binding assay; Materials therefor with an insoluble carrier for immobilising immunochemicals
- G01N33/54313—Immunoassay; Biospecific binding assay; Materials therefor with an insoluble carrier for immobilising immunochemicals the carrier being characterised by its particulate form
- G01N33/54326—Magnetic particles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/53—Immunoassay; Biospecific binding assay; Materials therefor
- G01N33/543—Immunoassay; Biospecific binding assay; Materials therefor with an insoluble carrier for immobilising immunochemicals
- G01N33/551—Immunoassay; Biospecific binding assay; Materials therefor with an insoluble carrier for immobilising immunochemicals the carrier being inorganic
- G01N33/553—Metal or metal coated
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Urology & Nephrology (AREA)
- Biomedical Technology (AREA)
- Hematology (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Pathology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Cell Biology (AREA)
- Biotechnology (AREA)
- Microbiology (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Plasma & Fusion (AREA)
- Inorganic Chemistry (AREA)
- Investigating Or Analysing Materials By The Use Of Chemical Reactions (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a signal noise suppression method and a system for a chemiluminescent instrument, comprising the following steps: obtaining a chemiluminescent sensing sequence and a maximum point, and obtaining a chemiluminescent maximum sequence according to the chemiluminescent sensing sequence and the maximum point; obtaining a target maximum point according to the chemiluminescent maximum sequence; obtaining a sensing data cluster according to the target maximum point; obtaining interference evaluation according to the sensor data cluster; obtaining a chemiluminescent sensing data demarcation point, and further obtaining a first local sequence; obtaining similar characteristics of fluctuation trend according to the first local sequence and interference evaluation; constructing an anomaly detection coordinate system according to the similar characteristics of the fluctuation trend; thereby obtaining outliers; and obtaining a denoised chemiluminescent sensing sequence according to the outlier and storing the sequence into a computer system. The invention improves the accuracy of identifying noise points and improves the accuracy of detection results.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a signal noise suppression method and a signal noise suppression system for a chemiluminescent instrument.
Background
The chemiluminescence of the chemiluminescent instrument mainly uses magnetic beads as a solid phase carrier, the magnetic beads are coated with specific antigens or antibodies, and interfering substances or other impurities are removed by washing through the adsorption of the magnets on the magnetic beads, so that accurate detection is realized; in the detection process, the photoelectric converter can convert the optical signal into the electric signal, but because the photoelectric converter itself can have noise floor, the measurement signal can be interfered, so that the accuracy of the detection result is reduced. Therefore, the noise floor needs to be positioned and suppressed, so that the accuracy of the detection result is improved.
Although the conventional denoising method can realize denoising to a certain extent, the special condition that the photoelectric converter is possibly affected by noise floor and further generates signal misjudgment exists for the photoelectric converter when the photoelectric converter does not emit light; for this special case, the conventional denoising method cannot be effectively avoided, thereby reducing the accuracy of the detection result.
Disclosure of Invention
The invention provides a signal noise suppression method and a system for a chemiluminescent instrument, which are used for solving the existing problems: for the photoelectric converter, there is a special case that the photoelectric converter is possibly affected by noise floor when not emitting light, so that signal misjudgment is generated; for this special case, conventional denoising methods cannot be effectively avoided.
The signal noise suppression method and system for the chemiluminescent instrument adopt the following technical scheme:
one embodiment of the present invention provides a signal noise suppression method for a chemiluminescent instrument, the method comprising the steps of:
acquiring a chemiluminescent sensing sequence comprising a plurality of chemiluminescent sensing data;
obtaining a plurality of maximum points of the chemiluminescent sensing sequence, and sequencing the maximum points according to chemiluminescent sensing data to obtain a chemiluminescent maximum sequence; obtaining a second initial sensing data maximum point and a third initial sensing data maximum point according to the chemiluminescent maximum sequence; obtaining a plurality of target maximum points according to the second initial sensing data maximum points and the third initial sensing data maximum points; clustering the target maximum points to obtain a plurality of sensor data clusters; obtaining interference evaluation of each sensing data cluster according to the number of target maximum points in the sensing data cluster;
acquiring a chemiluminescent sensing data demarcation point, and obtaining a first local sequence of each target maximum value point according to the chemiluminescent sensing data demarcation point; obtaining a first interference evaluation and a second interference evaluation of each target maximum point according to the first local sequence and the interference evaluation; obtaining a third interference evaluation of each target maximum point, and obtaining a fluctuation trend similar characteristic of each target maximum point according to the first interference evaluation, the second interference evaluation and the third interference evaluation;
Constructing an anomaly detection coordinate system according to the similar characteristics of the fluctuation trend of each target maximum point; obtaining a plurality of outliers according to the anomaly detection coordinate system; and performing noise suppression according to the outliers to obtain a denoised chemiluminescent sensing sequence, and storing the sequence into a computer system.
Preferably, the sorting the maximum points according to the chemiluminescence sensing data to obtain a chemiluminescence maximum sequence includes the following specific steps:
and (3) marking each maximum point of the chemiluminescent sensing sequence as an initial sensing data maximum point, arranging the maximum points of the initial sensing data in a descending order according to chemiluminescent sensing data corresponding to the initial sensing data maximum points, and marking the sequence formed after arrangement as a chemiluminescent maximum sequence.
Preferably, the method for obtaining the second initial sensing data maximum point and the third initial sensing data maximum point according to the chemiluminescent maximum sequence includes the following specific steps:
marking any two adjacent initial sensing data maximum points in the chemiluminescent maximum sequence as mark maximum points, and marking the absolute value of the difference value of chemiluminescent sensing data corresponding to the two mark maximum points as a reference difference absolute value; acquiring each reference difference absolute value in the chemiluminescent maximum sequence, and marking two initial sensing data maximum value points corresponding to the maximum reference difference absolute values as initial sensing data pairs; in the initial sensing data pair, marking an initial sensing data maximum value point with the minimum chemiluminescence sensing data as a second initial sensing data maximum value point; in the chemiluminescent maximum sequence, the initial sensing data maximum point with the maximum chemiluminescent sensing data is marked as a third initial sensing data maximum point.
Preferably, the obtaining a plurality of target maximum points according to the second initial sensing data maximum point and the third initial sensing data maximum point includes the following specific steps:
in the chemiluminescence maximum sequence, a set formed by all initial sensing data maximum points between the second initial sensing data maximum point and the third initial sensing data maximum point is recorded as a target maximum point set; and marking each initial sensing data maximum point in the target maximum point set as a target maximum point.
Preferably, the method for obtaining the interference evaluation of each sensing data cluster according to the number of the target maximum points in the sensing data cluster includes the following specific steps:
any one of the sensor data clusters is marked as a marked sensor data cluster, wherein,representing interference evaluation of the marked sensing data cluster; />Representing the number of target maximum points in the marker sensing data cluster; />Is shown in the cluster of marked sensor data +.>Chemiluminescent sensory data for each target maximum point; />Representing the average value of chemiluminescent sensing data of all target maximum points in the marked sensing data cluster; / >Representing standard deviations of chemiluminescent sensory data for all target maxima points within the cluster of labeled sensory data; />The chemiluminescent sensor data with the largest value among the chemiluminescent sensor data of all target maximum points in the marker sensor data cluster is represented; />The chemiluminescent sensor data with the smallest value in the chemiluminescent sensor data of all target maximum points in the marker sensor data cluster is represented;
and obtaining interference evaluation of each sensing data cluster.
Preferably, the obtaining the chemiluminescence sensing data demarcation point obtains a first local sequence of each target maximum point according to the chemiluminescence sensing data demarcation point, including the specific method:
marking any one target maximum point of any one sensing data cluster as a first mark maximum point, and marking the maximum chemiluminescence sensing data as a chemiluminescence sensing data demarcation point in a chemiluminescence sensing sequence; dividing the chemiluminescent sensing sequence by taking the chemiluminescent sensing data demarcation point as the center to obtain two sections of local chemiluminescent sensing sequences; recording a local chemiluminescent sensing sequence comprising chemiluminescent sensing data of a first marked maximum point as a first local sequence;
A first local sequence of each target maximum point is obtained.
Preferably, the method for obtaining the first interference evaluation and the second interference evaluation of each target maximum point according to the first local sequence and the interference evaluation includes the following specific steps:
marking any one target maximum point as a marked maximum point, marking a first local sequence of the marked maximum point as a marked first local sequence, marking all the target maximum points in the marked first local sequence as the same sensing data cluster, marking the same sensing data cluster as a first matching cluster, obtaining interference evaluation of the first matching cluster and marking the interference evaluation of the marked maximum point as a first interference evaluation of the marked maximum point; eliminating the marked maximum value points in the marked first local sequence, marking the marked first local sequence after eliminating as a second local sequence, taking all the target maximum value points in the second local sequence as the same sensing data cluster, marking as a second matching cluster, obtaining interference evaluation of the second matching cluster, and marking as second interference evaluation of the marked maximum value points;
and acquiring a first interference evaluation and a second interference evaluation of each target maximum point.
Preferably, the obtaining the third interference evaluation of each target maximum point obtains the fluctuation trend similar feature of each target maximum point according to the first interference evaluation, the second interference evaluation and the third interference evaluation, and the specific method includes:
Marking any one target maximum point as a marked maximum point, marking a sensing data cluster to which the marked maximum point belongs as a first cluster, and marking the interference evaluation of the first cluster after the marked maximum point is removed as a third interference evaluation of the marked maximum point;
in the method, in the process of the invention,representing similar characteristics of fluctuation trend of the marked maximum point; />An interference assessment representing a first cluster; />Indicating that the mark is extremely largeThird interference evaluation of the value points; />A first disturbance evaluation indicating a marked maximum point; />A second disturbance evaluation indicating a marked maximum point; />Representing the super-parameters; />Chemiluminescent sensor data representing a target maximum point preceding the marker maximum point in the chemiluminescent sensor sequence; />Chemiluminescent sensor data representing a target maximum point subsequent to the marker maximum point in the chemiluminescent sensor sequence; />Chemiluminescent sensor data representing a marked maximum point; />The representation takes absolute value.
Preferably, an anomaly detection coordinate system is constructed according to the similar characteristics of the fluctuation trend of each target maximum point; obtaining a plurality of outliers according to the anomaly detection coordinate system; noise suppression is carried out according to outliers to obtain a denoised chemiluminescent sensing sequence, and the denoised chemiluminescent sensing sequence is stored in a computer system, and the method comprises the following steps:
The horizontal axis represents the target maximum value points, and the ordering sequence of the target maximum value points is ordered according to the ordering sequence of the chemiluminescent sensing sequence; the vertical axis represents the fluctuation trend similarity feature; the coordinate system formed by the horizontal axis and the vertical axis is marked as an abnormality detection coordinate system;
inputting the similar characteristics of the fluctuation trend of each target maximum point into an anomaly detection coordinate system; LOF anomaly detection is carried out on the anomaly detection coordinate system to obtain local outlier factors of each target maximum point, linear normalization is carried out on the local outlier factors of all the target maximum points, and the local outlier factors of each target maximum point after normalization are recorded as outlier degrees; marking any one target maximum point as a second marked maximum point, and marking the second marked maximum point as an outlier if the outlier degree of the second marked maximum point is larger than a preset outlier degree threshold; if the outlier degree of the second marked maximum point is smaller than or equal to a preset outlier degree threshold, not performing any processing on the second marked maximum point; acquiring all outliers;
marking any one outlier as a marked outlier, marking chemiluminescence sensing data of one target maximum point before the marked outlier as first data, marking chemiluminescence sensing data of one target maximum point after the marked outlier as second data, and taking the average value of the summation of the first data and the second data as corrected chemiluminescence sensing data of the marked outlier in a chemiluminescence sensing sequence; marking the chemiluminescent sensing sequence after the corrected chemiluminescent sensing data of all outliers are acquired as a denoising chemiluminescent sensing sequence; and storing the denoised chemiluminescent sensing sequence into a computer system.
The embodiment of the invention provides a signal noise suppression system for a chemiluminescent instrument, which comprises a chemiluminescent sensing sequence acquisition module, an interference evaluation acquisition module, a fluctuation trend similar characteristic acquisition module and a noise suppression module, wherein:
a chemiluminescent sensing sequence acquisition module for acquiring a chemiluminescent sensing sequence comprising a plurality of chemiluminescent sensing data;
the interference evaluation acquisition module is used for acquiring a plurality of maximum points of the chemiluminescent sensing sequence, and sequencing the maximum points according to the chemiluminescent sensing data to obtain a chemiluminescent maximum sequence; obtaining a second initial sensing data maximum point and a third initial sensing data maximum point according to the chemiluminescent maximum sequence; obtaining a plurality of target maximum points according to the second initial sensing data maximum points and the third initial sensing data maximum points; clustering the target maximum points to obtain a plurality of sensor data clusters; obtaining interference evaluation of each sensing data cluster according to the number of target maximum points in the sensing data cluster;
the fluctuation trend similar characteristic acquisition module is used for acquiring chemiluminescent sensing data demarcation points and acquiring a first local sequence of each target maximum value point according to the chemiluminescent sensing data demarcation points; obtaining a first interference evaluation and a second interference evaluation of each target maximum point according to the first local sequence; obtaining a third interference evaluation of each target maximum point, and obtaining a fluctuation trend similar characteristic of each target maximum point according to the first interference evaluation, the second interference evaluation and the third interference evaluation;
The noise suppression module is used for constructing an anomaly detection coordinate system according to the fluctuation trend similar characteristics of each target maximum point; obtaining a plurality of outliers according to the anomaly detection coordinate system; and performing noise suppression according to the outliers to obtain a denoised chemiluminescent sensing sequence, and storing the sequence into a computer system.
The technical scheme of the invention has the beneficial effects that: obtaining a plurality of target maximum points according to the chemiluminescent sensing data and the maximum points, clustering the target maximum points to obtain a sensing data cluster, obtaining interference evaluation of the sensing data cluster according to the number of the target maximum points in the sensing data cluster, obtaining a first interference evaluation, a second interference evaluation and a third interference evaluation according to the interference evaluation, obtaining fluctuation trend similar characteristics of the target maximum points, obtaining outliers according to the fluctuation trend similar characteristics, and performing noise suppression according to the outliers; compared with the prior art, the special situation that the photoelectric converter is possibly influenced by noise floor when not emitting light so as to generate signal misjudgment exists; the accuracy of identifying noise points is improved, so that noise interference is effectively restrained, and the accuracy of detection results is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of a signal noise suppression method for a chemiluminescent instrument of the present invention;
fig. 2 is a block diagram of the signal noise suppression system for a chemiluminescent instrument of the present invention.
Detailed Description
In order to further describe the technical means and effects of the present invention for achieving the intended purpose, the following detailed description refers to the specific embodiments, structures, features and effects of the signal noise suppression method and system for a chemiluminescent apparatus according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the signal noise suppression method and system for a chemiluminescent instrument provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of the steps of a signal noise suppression method for a chemiluminescent apparatus according to an embodiment of the present invention is shown, the method comprises the steps of:
step S001: obtaining a chemiluminescent sensing sequence.
It should be noted that, although the conventional denoising method can implement denoising to a certain extent, there is a special case that the photoelectric converter is possibly affected by noise floor when not emitting light, so as to generate signal misjudgment; for this special case, the conventional denoising method cannot be effectively avoided, thereby reducing the accuracy of the detection result. To this end, the present embodiment proposes a signal noise floor suppression method for a chemiluminescent instrument.
Specifically, in order to implement the signal noise floor suppression method for a chemiluminescent apparatus according to the present embodiment, chemiluminescent sensing data needs to be collected first, but the present embodiment is not described with respect to a sample to be tested, such as a fluorescent dye, by taking the sample to be tested as an example, and the specific process is as follows: exciting a sample to be detected through an incandescent lamp, detecting the sample to be detected by using a chemiluminescent instrument to obtain a plurality of luminescent signals, inputting the luminescent signals into a photoelectric converter to obtain a plurality of conversion signals, inputting the conversion signals into a signal amplifier to obtain a plurality of amplified conversion signals, inputting the amplified conversion signals into a data recording system of the chemiluminescent instrument, outputting signal data every 30 seconds, recording the signal data as chemiluminescent sensing data, and collecting the chemiluminescent sensing data for 60 minutes; and acquiring a plurality of chemiluminescent sensing data, arranging the chemiluminescent sensing data according to the sequence from the early to the late of the acquisition time, and marking the sequence formed after arrangement as a chemiluminescent sensing sequence.
To this end, chemiluminescent sensing sequences were obtained by the method described above.
Step S002: obtaining a plurality of maximum points of the chemiluminescent sensing sequence, and sequencing the maximum points according to chemiluminescent sensing data to obtain a chemiluminescent maximum sequence; obtaining a second initial sensing data maximum point and a third initial sensing data maximum point according to the chemiluminescent maximum sequence; obtaining a plurality of target maximum points according to the second initial sensing data maximum points and the third initial sensing data maximum points; clustering the target maximum points to obtain a plurality of sensor data clusters; and obtaining interference evaluation of each sensing data cluster according to the number of the target maximum points in the sensing data cluster.
It should be noted that, the noise floor is usually from a hardware device, so that the chemiluminescent sensing data is offset to a certain extent; for a sample to be detected, when the sample to be detected is detected by using a chemiluminescent instrument, the sample to be detected can generate luminous intensities with different degrees at different moments, so that collected chemiluminescent data generate different amplitudes, and the luminous intensities and the amplitudes are in positive correlation to carry out numerical value change; for any one of the chemiluminescent sensor data, the more the maximum points around the chemiluminescent sensor data, the stronger the photoelectric signal of the chemiluminescent sensor data, the less likely the chemiluminescent sensor data will be disturbed by noise. Therefore, the intensity of the noise floor can be judged through the similarity of amplitude variation among the chemiluminescent sensing data points, so that the interference position of the noise floor is positioned, and self-adaptive inhibition is carried out through the intensity variation connection of the noise floor among a plurality of interference positions.
Specifically, all maximum points of the chemiluminescent sensing sequence are obtained and marked as initial sensing data maximum points, the chemiluminescent sensing data maximum points corresponding to the initial sensing data maximum points are arranged in descending order according to the chemiluminescent sensing data corresponding to the initial sensing data maximum points, and the sequence formed after arrangement is marked as the chemiluminescent maximum sequence; taking any two adjacent initial sensing data maximum value points in the chemiluminescence maximum value sequence as an example, and recording the absolute value of the difference value of the chemiluminescence sensing data corresponding to the two initial sensing data maximum value points as a reference difference absolute value; acquiring all reference difference absolute values in a chemiluminescent maximum sequence, and marking two initial sensing data maximum value points corresponding to the maximum reference difference absolute values as initial sensing data pairs; and in the initial sensing data pair, marking an initial sensing data maximum point with the smallest chemiluminescence sensing data as a second initial sensing data maximum point. The chemiluminescent maximum sequence comprises a plurality of initial sensing data maximum points, and each initial sensing data maximum point corresponds to one chemiluminescent sensing data.
Further, in the chemiluminescence maximum sequence, the initial sensing data maximum point with the maximum chemiluminescence sensing data is marked as a third initial sensing data maximum point; in the chemiluminescence maximum sequence, a set formed by all initial sensing data maximum points between the second initial sensing data maximum point and the third initial sensing data maximum point is recorded as a target maximum point set; marking each initial sensing data maximum point in the target maximum point set as a target maximum point; the target maximum point set comprises a second initial sensing data maximum point and a third initial sensing data maximum point.
Further, in the chemiluminescent maximum sequence, DBSCAN clustering is carried out on the target maximum point to obtain a plurality of clusters, and the clusters are recorded as sensing data clusters; the chemiluminescent maximum value sequence comprises a plurality of target maximum value points, the distance length between any two adjacent target maximum value points is not unique, and each cluster comprises a plurality of target maximum value points; in addition, DBSCAN clustering is a known technique, and requires presetting of a neighborhood radiusAnd the minimum sample point number in the neighborhood +.>In this embodiment, the ∈10 is preset>，/>This embodiment will not be described.
Further, taking any one sensing data cluster as an example, obtaining interference evaluation of the sensing data cluster according to the number of target maximum value points in the sensing data cluster; the method for calculating the interference evaluation of the sensing data cluster comprises the following steps:
in the method, in the process of the invention,an interference evaluation representing the sensor data cluster; />Representing the number of target maximum points in the sensing data cluster;/>is represented in the sensor data cluster +.>Chemiluminescent sensory data for each target maximum point; />Representing the mean value of chemiluminescent sensing data of all target maximum points in the sensing data cluster; / >Representing standard deviations of chemiluminescent sensory data for all target maxima points within the sensory data cluster; />The chemiluminescent sensor data with the largest value among the chemiluminescent sensor data of all target maximum value points in the sensor data cluster is represented; />Chemiluminescent sensor data of the smallest value among the chemiluminescent sensor data of all target maxima points in the sensor data cluster; />The sense data cluster is shown as a 4-degree enlarged numerical variation based on 0. And obtaining interference evaluation of all the sensing data clusters. The larger the interference evaluation of the sensing data cluster is, the more target maximum points of the sensing data cluster are, the larger the corresponding change amplitude is, the more obvious the luminous condition of the sensing data cluster is reflected, and the lower the interference degree of noise floor is.
So far, the interference evaluation of all the sensor data clusters is obtained through the method.
Step S003: acquiring a chemiluminescent sensing data demarcation point, and obtaining a first local sequence of each target maximum value point according to the chemiluminescent sensing data demarcation point; obtaining a first interference evaluation and a second interference evaluation of each target maximum point according to the first local sequence and the interference evaluation; and obtaining a third interference evaluation of each target maximum point, and obtaining a fluctuation trend similar characteristic of each target maximum point according to the first interference evaluation, the second interference evaluation and the third interference evaluation.
It should be noted that, for any one sensing data cluster, the chemiluminescent sensing data of the normal target maximum point will generate a certain value change along with the change of the luminous intensity of the sample to be detected, while the chemiluminescent sensing data of the target maximum point interfered by the background noise will generate a change rule which does not conform to the chemiluminescent sensing data according to the luminous intensity of the sample to be detected, thereby generating an outlier deviation position; for outlier chemiluminescent sensory data, the change in luminous intensity at that location may produce an uneven appearance with the change in luminous intensity of the chemiluminescent sensory data at surrounding neighboring locations. Therefore, in the embodiment, the outlier characteristics of each target maximum point can be obtained by splitting and calculating the variation significant characteristics of the target maximum point on the local time sequence range according to the variation direction of the chemiluminescent sensing data of the target maximum point.
Specifically, taking any one target maximum value point of any one sensing data cluster as an example, in a chemiluminescent sensing sequence, the maximum chemiluminescent sensing data is recorded as a chemiluminescent sensing data demarcation point; dividing the chemiluminescent sensing sequence by taking the chemiluminescent sensing data demarcation point as the center to obtain two sections of local chemiluminescent sensing sequences; the method comprises the steps of recording a local chemiluminescent sensing sequence of chemiluminescent sensing data containing target maximum points as a first local sequence, referring to a calculation method of interference evaluation of sensing data clusters, regarding all target maximum points in the first local sequence as the same sensing data cluster, recording the same sensing data cluster as a first matching cluster, acquiring interference evaluation of the first matching cluster and recording the interference evaluation of the target maximum points as first interference evaluation of the target maximum points; removing the target maximum value point in the first local sequence, and marking the removed first local sequence as a second local sequence; regarding all target maximum points in a second local sequence as the same sensing data cluster, marking the same sensing data cluster as a second matching cluster, acquiring interference evaluation of the second matching cluster, and marking the interference evaluation as second interference evaluation of the target maximum points; each local chemiluminescent sensing sequence contains chemiluminescent sensing data demarcation points.
Further, the sensing data cluster to which the target maximum point belongs is marked as a first cluster, and the interference evaluation of the first cluster after the target maximum point is removed is marked as a third interference evaluation of the target maximum point; obtaining a fluctuation trend similar characteristic of the target maximum point according to the first interference evaluation, the second interference evaluation, the third interference evaluation and the interference evaluation of the sensor data cluster; the calculation method of the fluctuation trend similar characteristics of the target maximum point comprises the following steps:
in the method, in the process of the invention,representing the similar characteristics of the fluctuation trend of the target maximum point; />An interference assessment representing a first cluster; />A third interference evaluation indicating the target maximum point; />A first interference assessment representing the target maximum point;a second interference assessment representing the target maximum point; />Indicating hyper-parameters, preset +.>For preventing denominator from being 0; />Chemiluminescent sensor data representing a target maximum point preceding the target maximum point in a chemiluminescent sensor sequence; />Chemiluminescent sensor data representing a target maximum point subsequent to the target maximum point in a chemiluminescent sensor sequence; / >Chemiluminescent sensory data representing the target maximum point; />The representation takes absolute value; />The reduction degree of the outlier degree of the whole data after the target maximum point is removed is shown; />Representing the position fluctuation condition of partial target maximum value points in the sensing data cluster to which the target maximum value points belong; />And the difference of the chemiluminescence sensing data of the target maximum point and the two target maximum points before and after time sequence is represented. And obtaining similar characteristics of fluctuation trend of all the target maximum points. The larger the similar characteristic of the fluctuation trend of the target maximum point is, the larger the amplitude of the outlier fluctuation generated by the target maximum point is, the outlier characteristic of the local data area where the target maximum point is located is more obvious, and the larger the probability that the target maximum point belongs to the outlier is reflected. Is required toIt is noted that if ++is not present>Or->Then 0 is given +.>Or->。
So far, the similar characteristics of the fluctuation trend of all the target maximum points are obtained through the method.
Step S004: constructing an anomaly detection coordinate system according to the similar characteristics of the fluctuation trend of each target maximum point; obtaining a plurality of outliers according to the anomaly detection coordinate system; and performing noise suppression according to the outliers to obtain a denoised chemiluminescent sensing sequence, and storing the sequence into a computer system.
Specifically, an anomaly detection coordinate system is constructed according to the similar characteristics of the fluctuation trend of all the target maximum points: the horizontal axis represents the target maximum value points, and the ordering sequence of the target maximum value points is ordered according to the ordering sequence of the chemiluminescent sensing sequence; the vertical axis represents the fluctuation trend similarity feature; LOF anomaly detection is carried out on the anomaly detection coordinate system to obtain local outlier factors of each target maximum point, linear normalization is carried out on the local outlier factors of all the target maximum points, and the local outlier factors of each target maximum point after normalization are recorded as outlier degrees.
Further, an outlier degree threshold P is preset, where the embodiment is described by taking p=0.7 as an example, and the embodiment is not specifically limited, where P may be determined according to the specific implementation situation; taking any one target maximum point as an example, if the outlier degree of the target maximum point is greater than an outlier degree threshold value P, marking the target maximum point as an outlier; if the outlier degree of the target maximum point is smaller than or equal to an outlier degree threshold value P, not performing any processing on the target maximum point; acquiring all outliers; the LOF algorithm is a known technique, and needs to preset a field size T2, determine a threshold T3, preset t2=10, t3=30 in this embodiment, and use the euclidean distance for the distance measurement, which is not specifically limited in this embodiment, where T2, T3 and the distance measurement may be specific to the implementation situation.
Further, taking any outlier as an example, in the chemiluminescence sensing sequence, the chemiluminescence sensing data of a target maximum point before the outlier is recorded as first data, the chemiluminescence sensing data of a target maximum point after the outlier is recorded as second data, and the average value of the first data and the second data is used as corrected chemiluminescence sensing data of the outlier; marking the chemiluminescent sensing sequence after the corrected chemiluminescent sensing data of all outliers are acquired as a denoising chemiluminescent sensing sequence; storing the denoised chemiluminescent sensing sequence in a computer system for subsequent analysis.
Through the steps, the signal noise suppression method of the chemiluminescent instrument is completed.
Referring to FIG. 2, a block diagram of a signal noise suppression system for a chemiluminescent instrument according to one embodiment of the present invention is shown, the system comprising the following modules:
a chemiluminescent sensing sequence acquisition module for acquiring a chemiluminescent sensing sequence comprising a plurality of chemiluminescent sensing data;
the interference evaluation acquisition module is used for acquiring a plurality of maximum points of the chemiluminescent sensing sequence, and sequencing the maximum points according to the chemiluminescent sensing data to obtain a chemiluminescent maximum sequence; obtaining a second initial sensing data maximum point and a third initial sensing data maximum point according to the chemiluminescent maximum sequence; obtaining a plurality of target maximum points according to the second initial sensing data maximum points and the third initial sensing data maximum points; clustering the target maximum points to obtain a plurality of sensor data clusters; obtaining interference evaluation of each sensing data cluster according to the number of target maximum points in the sensing data cluster;
The fluctuation trend similar characteristic acquisition module is used for acquiring chemiluminescent sensing data demarcation points and acquiring a first local sequence of each target maximum value point according to the chemiluminescent sensing data demarcation points; obtaining a first interference evaluation and a second interference evaluation of each target maximum point according to the first local sequence; obtaining a third interference evaluation of each target maximum point, and obtaining a fluctuation trend similar characteristic of each target maximum point according to the first interference evaluation, the second interference evaluation and the third interference evaluation;
the noise suppression module is used for constructing an anomaly detection coordinate system according to the fluctuation trend similar characteristics of each target maximum point; obtaining a plurality of outliers according to the anomaly detection coordinate system; and performing noise suppression according to the outliers to obtain a denoised chemiluminescent sensing sequence, and storing the sequence into a computer system.
According to the embodiment, a plurality of target maximum points are obtained according to chemiluminescent sensing data and the maximum points, a sensing data cluster is obtained by clustering the target maximum points, interference evaluation of the sensing data cluster is obtained according to the number of the target maximum points in the sensing data cluster, a first interference evaluation, a second interference evaluation and a third interference evaluation are obtained according to the interference evaluation, so that fluctuation trend similar characteristics of the target maximum points are obtained, outliers are obtained according to the fluctuation trend similar characteristics, and noise suppression is carried out according to the outliers; compared with the prior art, the special situation that the photoelectric converter is possibly influenced by noise floor when not emitting light so as to generate signal misjudgment exists; the accuracy of identifying noise points is improved, so that noise interference is effectively restrained, and the accuracy of detection results is improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. A method for signal noise suppression for a chemiluminescent instrument, the method comprising the steps of:
acquiring a chemiluminescent sensing sequence comprising a plurality of chemiluminescent sensing data;
obtaining a plurality of maximum points of the chemiluminescent sensing sequence, and sequencing the maximum points according to chemiluminescent sensing data to obtain a chemiluminescent maximum sequence; obtaining a second initial sensing data maximum point and a third initial sensing data maximum point according to the chemiluminescent maximum sequence; obtaining a plurality of target maximum points according to the second initial sensing data maximum points and the third initial sensing data maximum points; clustering the target maximum points to obtain a plurality of sensor data clusters; obtaining interference evaluation of each sensing data cluster according to the number of target maximum points in the sensing data cluster;
acquiring a chemiluminescent sensing data demarcation point, and obtaining a first local sequence of each target maximum value point according to the chemiluminescent sensing data demarcation point; obtaining a first interference evaluation and a second interference evaluation of each target maximum point according to the first local sequence and the interference evaluation; obtaining a third interference evaluation of each target maximum point, and obtaining a fluctuation trend similar characteristic of each target maximum point according to the first interference evaluation, the second interference evaluation and the third interference evaluation;
Constructing an anomaly detection coordinate system according to the similar characteristics of the fluctuation trend of each target maximum point; obtaining a plurality of outliers according to the anomaly detection coordinate system; and performing noise suppression according to the outliers to obtain a denoised chemiluminescent sensing sequence, and storing the sequence into a computer system.
2. The method for suppressing signal noise of a chemiluminescent apparatus of claim 1 wherein the sorting of maximum points according to chemiluminescent sensor data results in a sequence of chemiluminescent maxima comprises the following steps:
and (3) marking each maximum point of the chemiluminescent sensing sequence as an initial sensing data maximum point, arranging the maximum points of the initial sensing data in a descending order according to chemiluminescent sensing data corresponding to the initial sensing data maximum points, and marking the sequence formed after arrangement as a chemiluminescent maximum sequence.
3. The method for suppressing signal noise of a chemiluminescent apparatus of claim 1 wherein the obtaining the second initial sensory data maximum point and the third initial sensory data maximum point from the sequence of chemiluminescent maxima comprises the specific steps of:
marking any two adjacent initial sensing data maximum points in the chemiluminescent maximum sequence as mark maximum points, and marking the absolute value of the difference value of chemiluminescent sensing data corresponding to the two mark maximum points as a reference difference absolute value; acquiring each reference difference absolute value in the chemiluminescent maximum sequence, and marking two initial sensing data maximum value points corresponding to the maximum reference difference absolute values as initial sensing data pairs; in the initial sensing data pair, marking an initial sensing data maximum value point with the minimum chemiluminescence sensing data as a second initial sensing data maximum value point; in the chemiluminescent maximum sequence, the initial sensing data maximum point with the maximum chemiluminescent sensing data is marked as a third initial sensing data maximum point.
4. The method for suppressing signal noise of a chemiluminescent apparatus of claim 1 wherein the obtaining a plurality of target maximum points from the second initial sensed data maximum point and the third initial sensed data maximum point comprises the specific steps of:
in the chemiluminescence maximum sequence, a set formed by all initial sensing data maximum points between the second initial sensing data maximum point and the third initial sensing data maximum point is recorded as a target maximum point set; and marking each initial sensing data maximum point in the target maximum point set as a target maximum point.
5. The method for suppressing signal noise of a chemiluminescent apparatus of claim 1 wherein the interference evaluation of each sensor data cluster is obtained based on the number of target maxima points within the sensor data cluster comprises the following steps:
any one of the sensor data clusters is marked as a marked sensor data cluster, wherein,representing interference evaluation of the marked sensing data cluster; />Representing the number of target maximum points in the marker sensing data cluster; />Is shown in the cluster of marked sensor data +. >Chemiluminescent sensory data for each target maximum point; />Representing the average value of chemiluminescent sensing data of all target maximum points in the marked sensing data cluster; />Representing standard deviations of chemiluminescent sensory data for all target maxima points within the cluster of labeled sensory data; />The chemiluminescent sensor data with the largest value among the chemiluminescent sensor data of all target maximum points in the marker sensor data cluster is represented; />The chemiluminescent sensor data with the smallest value in the chemiluminescent sensor data of all target maximum points in the marker sensor data cluster is represented;
and obtaining interference evaluation of each sensing data cluster.
6. The method for signal noise suppression for a chemiluminescent apparatus of claim 1 wherein the obtaining the chemiluminescent sensory data interface point and the obtaining the first local sequence of each target maximum point based on the chemiluminescent sensory data interface point comprises the specific steps of:
marking any one target maximum point of any one sensing data cluster as a first mark maximum point, and marking the maximum chemiluminescence sensing data as a chemiluminescence sensing data demarcation point in a chemiluminescence sensing sequence; dividing the chemiluminescent sensing sequence by taking the chemiluminescent sensing data demarcation point as the center to obtain two sections of local chemiluminescent sensing sequences; recording a local chemiluminescent sensing sequence comprising chemiluminescent sensing data of a first marked maximum point as a first local sequence;
A first local sequence of each target maximum point is obtained.
7. The method for suppressing signal noise of a chemiluminescent apparatus of claim 1 wherein the first interference assessment and the second interference assessment for each target maximum point are obtained from the first local sequence and the interference assessment comprises the following specific steps:
marking any one target maximum point as a marked maximum point, marking a first local sequence of the marked maximum point as a marked first local sequence, marking all the target maximum points in the marked first local sequence as the same sensing data cluster, marking the same sensing data cluster as a first matching cluster, obtaining interference evaluation of the first matching cluster and marking the interference evaluation of the marked maximum point as a first interference evaluation of the marked maximum point; eliminating the marked maximum value points in the marked first local sequence, marking the marked first local sequence after eliminating as a second local sequence, taking all the target maximum value points in the second local sequence as the same sensing data cluster, marking as a second matching cluster, obtaining interference evaluation of the second matching cluster, and marking as second interference evaluation of the marked maximum value points;
and acquiring a first interference evaluation and a second interference evaluation of each target maximum point.
8. The method for suppressing signal noise of a chemiluminescent apparatus of claim 1 wherein the obtaining a third interference estimate for each target maximum point based on the first interference estimate, the second interference estimate, and the third interference estimate results in a trend-like characteristic of fluctuation for each target maximum point comprises the following steps:
marking any one target maximum point as a marked maximum point, marking a sensing data cluster to which the marked maximum point belongs as a first cluster, and marking the interference evaluation of the first cluster after the marked maximum point is removed as a third interference evaluation of the marked maximum point;
in the method, in the process of the invention,representing similar characteristics of fluctuation trend of the marked maximum point; />An interference assessment representing a first cluster; />A third interference assessment representing a marked maximum point; />A first disturbance evaluation indicating a marked maximum point; />A second disturbance evaluation indicating a marked maximum point; />Representing the super-parameters; />Chemiluminescent sensor data representing a target maximum point preceding the marker maximum point in the chemiluminescent sensor sequence; />Chemiluminescent sensor data representing a target maximum point subsequent to the marker maximum point in the chemiluminescent sensor sequence; / >Chemiluminescent sensor data representing a marked maximum point; />The representation takes absolute value.
9. The method for suppressing signal noise of a chemiluminescent apparatus of claim 1 wherein the anomaly detection coordinate system is constructed based on a trend-like characteristic of fluctuation of each target maximum point; obtaining a plurality of outliers according to the anomaly detection coordinate system; noise suppression is carried out according to outliers to obtain a denoised chemiluminescent sensing sequence, and the denoised chemiluminescent sensing sequence is stored in a computer system, and the method comprises the following steps:
the horizontal axis represents the target maximum value points, and the ordering sequence of the target maximum value points is ordered according to the ordering sequence of the chemiluminescent sensing sequence; the vertical axis represents the fluctuation trend similarity feature; the coordinate system formed by the horizontal axis and the vertical axis is marked as an abnormality detection coordinate system;
inputting the similar characteristics of the fluctuation trend of each target maximum point into an anomaly detection coordinate system; LOF anomaly detection is carried out on the anomaly detection coordinate system to obtain local outlier factors of each target maximum point, linear normalization is carried out on the local outlier factors of all the target maximum points, and the local outlier factors of each target maximum point after normalization are recorded as outlier degrees; marking any one target maximum point as a second marked maximum point, and marking the second marked maximum point as an outlier if the outlier degree of the second marked maximum point is larger than a preset outlier degree threshold; if the outlier degree of the second marked maximum point is smaller than or equal to a preset outlier degree threshold, not performing any processing on the second marked maximum point; acquiring all outliers;
Marking any one outlier as a marked outlier, marking chemiluminescence sensing data of one target maximum point before the marked outlier as first data, marking chemiluminescence sensing data of one target maximum point after the marked outlier as second data, and taking the average value of the summation of the first data and the second data as corrected chemiluminescence sensing data of the marked outlier in a chemiluminescence sensing sequence; marking the chemiluminescent sensing sequence after the corrected chemiluminescent sensing data of all outliers are acquired as a denoising chemiluminescent sensing sequence; and storing the denoised chemiluminescent sensing sequence into a computer system.
10. A signal noise suppression system for a chemiluminescent instrument, the system comprising the following modules:
a chemiluminescent sensing sequence acquisition module for acquiring a chemiluminescent sensing sequence comprising a plurality of chemiluminescent sensing data;
the interference evaluation acquisition module is used for acquiring a plurality of maximum points of the chemiluminescent sensing sequence, and sequencing the maximum points according to the chemiluminescent sensing data to obtain a chemiluminescent maximum sequence; obtaining a second initial sensing data maximum point and a third initial sensing data maximum point according to the chemiluminescent maximum sequence; obtaining a plurality of target maximum points according to the second initial sensing data maximum points and the third initial sensing data maximum points; clustering the target maximum points to obtain a plurality of sensor data clusters; obtaining interference evaluation of each sensing data cluster according to the number of target maximum points in the sensing data cluster;
The fluctuation trend similar characteristic acquisition module is used for acquiring chemiluminescent sensing data demarcation points and acquiring a first local sequence of each target maximum value point according to the chemiluminescent sensing data demarcation points; obtaining a first interference evaluation and a second interference evaluation of each target maximum point according to the first local sequence; obtaining a third interference evaluation of each target maximum point, and obtaining a fluctuation trend similar characteristic of each target maximum point according to the first interference evaluation, the second interference evaluation and the third interference evaluation;
the noise suppression module is used for constructing an anomaly detection coordinate system according to the fluctuation trend similar characteristics of each target maximum point; obtaining a plurality of outliers according to the anomaly detection coordinate system; and performing noise suppression according to the outliers to obtain a denoised chemiluminescent sensing sequence, and storing the sequence into a computer system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311180930.5A CN116910593B (en) | 2023-09-14 | 2023-09-14 | Signal noise suppression method and system for chemiluminescent instrument |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311180930.5A CN116910593B (en) | 2023-09-14 | 2023-09-14 | Signal noise suppression method and system for chemiluminescent instrument |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116910593A CN116910593A (en) | 2023-10-20 |
| CN116910593B true CN116910593B (en) | 2023-11-17 |
Family
ID=88367306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311180930.5A Active CN116910593B (en) | 2023-09-14 | 2023-09-14 | Signal noise suppression method and system for chemiluminescent instrument |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116910593B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117540238B (en) * | 2024-01-05 | 2024-03-22 | 长春同泰企业管理服务有限责任公司 | Data security management method for industrial digital information acquisition device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740694A (en) * | 2019-01-24 | 2019-05-10 | 燕山大学 | A kind of smart grid inartful loss detection method based on unsupervised learning |
| WO2022144652A1 (en) * | 2020-12-30 | 2022-07-07 | Verity Ag | System and method for controlling a light source for illuminating a scene of interest |
-
2023
- 2023-09-14 CN CN202311180930.5A patent/CN116910593B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740694A (en) * | 2019-01-24 | 2019-05-10 | 燕山大学 | A kind of smart grid inartful loss detection method based on unsupervised learning |
| WO2022144652A1 (en) * | 2020-12-30 | 2022-07-07 | Verity Ag | System and method for controlling a light source for illuminating a scene of interest |
Non-Patent Citations (4)
| Title |
|---|
| "A novel feature representation method based on original waveforms for acoustic emission signals";Zhensheng Yang 等;《Mechanical Systems and Signal Processing》;全文 * |
| "光纤矢量水听器系统本底噪声的自适应抵消";吴艳群 等;《中国激光》;第38卷(第3期);全文 * |
| "基于稀疏表示理论的微弱核辐射信号检测方法研究及实现";朱庆平;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;全文 * |
| "电晕放电下的SF6气体特征发射光谱与放电程度识别";赵科 等;《山东电力技术》;第50卷(第8期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116910593A (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116910593B (en) | Signal noise suppression method and system for chemiluminescent instrument | |
| CN109948469A (en) | The automatic detection recognition method of crusing robot instrument based on deep learning | |
| US8285056B2 (en) | Method and apparatus for computing degree of matching | |
| CN108535354A (en) | A kind of damaging judge and localization method of steel wire rope Magnetic Flux Leakage Inspecting and magnetic transmitting detection | |
| CN108240978B (en) | Self-learning qualitative analysis method based on Raman spectrum | |
| CN110146589B (en) | High-definition visualization method for pipeline magnetic flux leakage data | |
| CN111967338A (en) | Method and system for distinguishing partial discharge pulse interference signal based on mean shift clustering algorithm | |
| JP5331621B2 (en) | Vehicle inspection device | |
| CN115841488B (en) | PCB hole inspection method based on computer vision | |
| CN112345759A (en) | Method for detecting fluorescence intensity peak | |
| CN108107086A (en) | A kind of gas detection method and gas sensor based on array gas sensor | |
| CN113820333A (en) | Battery pole piece abnormity detection method and device, upper computer and detection system | |
| CN114492629A (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and storage medium | |
| CN113466947B (en) | Automatic dead pixel removal method applied to superconducting transient electromagnetic | |
| JP2019067069A (en) | Abnormality detecting apparatus, abnormality detecting method and abnormality detecting program | |
| CN116740053B (en) | Management system of intelligent forging processing production line | |
| CN108919068B (en) | Intermittent defect signal identification method for power equipment | |
| US20190041434A1 (en) | Method and apparatus for non-intrusive program tracing with bandwith reduction for embedded computing systems | |
| CN116304963B (en) | Data processing system suitable for geological disaster early warning | |
| CN112396603A (en) | Multi-column neural network medical image analysis method and device | |
| CN106778515B (en) | Automatic identification method for axial magnetic flux leakage array signal of flange | |
| CN108734706B (en) | Rotor winding image detection method fusing regional distribution characteristics and edge scale angle information | |
| CN107067034B (en) | Method and system for rapidly identifying infrared spectrum data classification | |
| CN112580741B (en) | Gas type identification method and system based on multi-sensor fast learning | |
| CN111473944B (en) | PIV data correction method and device for observing complex wall surface in flow field |
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 |