CN115345527A - Chemical experiment abnormal operation detection method, device, equipment and readable storage medium - Google Patents
Chemical experiment abnormal operation detection method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN115345527A CN115345527A CN202211269703.5A CN202211269703A CN115345527A CN 115345527 A CN115345527 A CN 115345527A CN 202211269703 A CN202211269703 A CN 202211269703A CN 115345527 A CN115345527 A CN 115345527A
- Authority
- CN
- China
- Prior art keywords
- video data
- experiment
- abnormal operation
- feature
- feature set
- 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.)
- Granted
Links
- 238000002474 experimental method Methods 0.000 title claims abstract description 108
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 96
- 238000001514 detection method Methods 0.000 title claims abstract description 76
- 239000000126 substance Substances 0.000 title claims abstract description 48
- 239000011159 matrix material Substances 0.000 claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000013178 mathematical model Methods 0.000 claims abstract description 26
- 238000000605 extraction Methods 0.000 claims abstract description 21
- 238000006243 chemical reaction Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 44
- 230000009466 transformation Effects 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Technology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method, a device, equipment and a readable storage medium for detecting abnormal operation of a chemical experiment, which relate to the technical field of information and comprise the following steps: acquiring real-time experiment video data and historical experiment video data, wherein the historical experiment video data information comprises normal operation video data and abnormal operation video data; preprocessing historical experimental video data and then performing feature extraction to obtain a first feature set and a weight set; clustering operation is carried out on the historical experimental video based on the first feature set and the weight set to obtain classified video data; performing feature conversion on the classified video data to obtain a second feature set; and establishing an experiment abnormal operation detection mathematical model according to the second feature set and the classified video data, taking the real-time experiment video data as an input value, and solving the experiment abnormal operation detection mathematical model to obtain a detection result. The invention changes the characteristic matrix of the classified video data into linear divisibility by establishing the low-dimensional matrix, thereby improving the accuracy of abnormal operation in the real-time video.
Description
Technical Field
The invention relates to the technical field of information, in particular to a method, a device and equipment for detecting abnormal operation of a chemical experiment and a readable storage medium.
Background
When a chemical experiment operation examination is carried out, examination clerks are required to carry out invigilation on site, the operation steps of students are observed to supervise, and meanwhile, abnormal operations are recorded and corrected. What is needed is a method and apparatus for detecting abnormal operation of real-time experimental video based on wavelet feature extraction and feature transformation, so as to detect chemical experiments in real time, thereby reducing the dependence on manual invigilation and ensuring the accuracy of abnormal operation detection of chemical experiments.
Disclosure of Invention
The present invention is directed to a method, an apparatus, a device and a readable storage medium for detecting abnormal operation in chemical experiment, so as to improve the above problems. In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides a method for detecting abnormal operation in a chemical experiment, comprising:
acquiring real-time experiment video data and historical experiment video data, wherein the historical experiment video data information comprises normal operation video data and abnormal operation video data;
preprocessing the historical experimental video data and then extracting features to obtain a first feature set and a weight set;
clustering the historical experimental videos based on the first feature set and the weight set to obtain classified video data;
performing feature conversion on the classified video data to obtain a second feature set;
and establishing an experiment abnormal operation detection mathematical model according to the second feature set and the classified video data, taking the real-time experiment video data as an input value, and solving the experiment abnormal operation detection mathematical model to obtain a detection result.
In a second aspect, the present application also provides a chemical experiment abnormal operation detection apparatus, including:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring real-time experiment video data and historical experiment video data, and the historical experiment video data information comprises normal operation video data and abnormal operation video data;
the extraction module is used for preprocessing the historical experimental video data and then extracting features to obtain a first feature set and a weight set;
the analysis module is used for carrying out clustering operation on the historical experimental video based on the first feature set and the weight set to obtain classified video data;
the conversion module is used for performing feature conversion on the classified video data to obtain a second feature set;
and the detection module is used for establishing an experiment abnormal operation detection mathematical model according to the second feature set and the classified video data, taking the real-time experiment video data as an input value, and solving the experiment abnormal operation detection mathematical model to obtain a detection result.
In a third aspect, the present application further provides a chemical experiment abnormal operation detection apparatus, including:
a memory for storing a computer program;
a processor for implementing the steps of the method for detecting abnormal operation of chemical experiment when the computer program is executed.
In a fourth aspect, the present application further provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the above method for detecting abnormal operation based on chemical experiment.
The beneficial effects of the invention are as follows:
according to the invention, the historical experiment video and the real-time experiment video are subjected to wavelet transformation and the characteristics are extracted, and the advantages of wavelet transformation fast decomposition and local characteristic extraction are utilized, so that the detection speed of abnormal operation in the real-time video is increased.
According to the method, clustering is carried out after feature extraction is carried out on the historical experimental video, then feature conversion is carried out again in the classified video data, a low-dimensionality matrix is established to enable the feature matrix of the classified video data to become linearly separable, and the accuracy rate of abnormal operation in the real-time video is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart of a method for detecting abnormal operation in a chemical experiment according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an abnormal operation detection apparatus for a chemical experiment according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of the abnormal operation detection device for the chemical experiment according to the embodiment of the present invention.
The labels in the figure are: 1. an acquisition module; 2. an extraction module; 21. a first processing unit; 22. a second processing unit; 23. a first calculation unit; 3. an analysis module; 31. a second calculation unit; 32. a third processing unit; 33. a fourth processing unit; 34. a fifth processing unit; 4. a conversion module; 41. a sixth processing unit; 42. a third calculation unit; 43. a fourth calculation unit; 44. a seventh processing unit; 5. a detection module; 51. an eighth processing unit; 52. a ninth processing unit; 53. a tenth processing unit; 54. an eleventh processing unit; 541. a twelfth processing unit; 542. a first analysis unit; 543. a first judgment unit; 544. a second judgment unit; 800. abnormal operation detection equipment for chemical experiments; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a method for detecting abnormal operation of a chemical experiment.
Referring to fig. 1, it is shown that the method includes step S100, step S200, step S300, step S400, step S500.
Step S100, real-time experiment video data and historical experiment video data are obtained, wherein the historical experiment video data information comprises normal operation video data and abnormal operation video data.
It can be understood that, in this step, historical experiment video data is uploaded and stored, real-time experiment video data is detected based on the uploaded and stored data, whether current operators are abnormal operations is judged, normal operations in a chemical experiment examination include experiment standard actions and human body common actions, abnormal operations include medicine wrong taking modes, wrong use of a rubber head dropper and the like, in this embodiment, historical experiment video data does not need to be subdivided, and only the historical experiment video data needs to be divided into "normal" or "abnormal" and corresponding labels are marked.
And S200, preprocessing the historical experimental video data and then extracting features to obtain a first feature set and a weight set.
It can be understood that in this step, by performing feature extraction after performing unification processing on the historical experimental video data, the action feature parameters of the operator in the continuous frame images during normal operation or abnormal operation are extracted. It should be noted that step S200 includes step S210, step S220, and step S230.
And step S210, performing time-averaged sampling and uniform-size cutting on the historical experimental video data to obtain frame image data.
It can be understood that in this step, image pyramid downsampling processing is performed on historical experimental video data, each historical experimental video is subjected to average sampling of image frames, the fixed frame number of each obtained historical experimental video image set is 30, the frame rate is 10 frames per second, and the sizes of the images are uniformly cut into the size of 240 × 143 pixel points.
S220, pre-extracting the features of the frame image data based on a preset Gaussian mixture model to obtain a first feature set.
It can be understood that in this step, a plurality of gaussian distributions are established for each pixel point in the frame image data, background modeling is performed by combining the plurality of gaussian distributions, a foreground picture is segmented, and then median filtering and gray level processing are performed on the foreground picture to obtain a feature set. When the examinee is subjected to experimental operation, a machine position arranged in front of the examinee for overlooking is usually adopted for real-time recording, the background is basically unchanged, the image data is processed by adopting a Gaussian mixture model so as to accurately segment the image, the characteristic image is extracted and then filtered to obtain a characteristic image, and the processing speed of the subsequent steps is improved.
S230, calculating the first feature set based on a preset activation function to obtain a weight value corresponding to each feature, and combining all the weight values to obtain a weight set.
It can be understood that in this step, the first feature set is processed by the activation function to obtain the weight of each feature, so as to prepare for performing subsequent clustering operation.
And S300, performing clustering operation on the historical experimental video based on the first feature set and the weight set to obtain classified video data.
It can be understood that in the step, the historical videos are divided into a plurality of types by clustering the characteristics of all the videos in combination with the corresponding weights, wherein the types belonging to normal operation can be defined and explained according to experimental operation regulations, and abnormal operation does not need to be particularly defined. It should be noted that step S300 includes steps S310, S320, S330, and S340.
Step S310, performing clustering operation based on distance on the first feature set to obtain at least two clustering clusters, wherein each clustering cluster comprises at least one normal operation clustering cluster and at least one abnormal operation clustering cluster.
It is understood that the present step is based on a clustering algorithm of distance classes, such as a K-nearest neighbor algorithm, to cluster the features of all historical experimental videos, and to separate at least two segment types under the classification of normal operation and abnormal operation, in such a way as to facilitate the recording and analysis in the subsequent use.
And S320, performing feature extraction on each clustering cluster to obtain a third feature set.
It is understood that this step is to calculate a new feature again in each cluster, and the similarity between the feature and the second feature is greater than the set threshold.
S330, performing feature fusion on the first feature set and the third feature set to obtain a fourth feature set;
it can be understood that in this step, the new feature is obtained by performing a weighted calculation on the first feature set used for the initial clustering and the second-extracted third feature set.
And step S340, classifying the historical experimental videos according to a fourth feature set to obtain classified video data.
It can be understood that in this step, the historical videos are classified through the fused fourth feature set, so that the similarity of the video set of each class in the classified video set is guaranteed to be the highest.
And S400, performing feature conversion on the classified video data to obtain a second feature set.
It is understood that this step is to perform feature transformation on the classified video data, so that the video data between the categories can be more easily distinguished. It should be noted that step S400 includes steps S410, S420, S430, and S440.
And S410, performing wavelet transformation on the classified video data to obtain characteristic matrix data.
It will be appreciated that this step is to decompose the frame image using wavelet transforms, preserving more of the useful information of the image.
And step S420, calculating to obtain matrix parameters according to the characteristic matrix data, wherein the matrix parameters comprise a total mean value, a category mean value, an inter-class divergence matrix and an intra-class divergence matrix.
It can be understood that in this step, the frame image data after wavelet transform is recombined into a matrix, and the overall mean value, the class mean value, the inter-class divergence matrix and the intra-class divergence matrix in the classified video are obtained through calculation according to the matrix parameters.
And step S430, calculating the matrix parameters based on a linear discrimination algorithm to obtain an optimal projection matrix.
It can be understood that in the step, a low-dimensional feature space is established according to the matrix parameters by adopting a linear discrimination algorithm, so that the dimensionality can be compressed, and the speed of subsequent classification operation is improved.
Step S440, projecting the feature matrix data to the optimal projection matrix to obtain a second feature set.
It can be understood that in this step, the high-dimensional feature matrix data is projected to the low-dimensional optimal projection matrix, so that the similarity of the projected video data in each category is the highest, and the similarity between the categories is the lowest, and a clear interface is obtained.
Step S500, establishing an experiment abnormal operation detection mathematical model according to the second feature set and the classified video data, taking the real-time experiment video data as an input value, and solving the experiment abnormal operation detection mathematical model to obtain a detection result.
It can be understood that in this step, an abnormal operation detection mathematical model is established by using the second feature set obtained through the secondary conversion, the operation situations in the real-time experimental video data are classified, the currently performed experimental operation is determined to be a normal operation or an abnormal operation, and corresponding measures are taken. It should be noted that step S500 includes steps S510, S520, S530, and S540.
Step S510, training an experiment operation classifier according to the classified video data and the second feature set, and establishing an experiment abnormal operation detection mathematical model based on the experiment operation classifier.
It can be understood that this step is to train an experimentally operated classifier, wherein the weights of the respective layers of the classifier are adjusted by the second feature set, so as to better fit the boundaries between the classified video data of the respective categories. Preferably, in other embodiments, a BP neural network may be used as the classifier of the method, and the use of the BP neural network is common knowledge of those skilled in the art and will not be described in detail in this embodiment.
And step S520, performing wavelet transformation on the real-time experimental video data to obtain a transformed image.
It can be understood that in the step, the real-time experimental video data is decomposed by wavelet transformation to obtain data in a matrix form, so that the subsequent processing speed and the detection accuracy are improved.
And step S530, performing feature extraction on the transformed image to obtain local image data.
It is understood that this step is to extract useful data in the transformed image to obtain local image data, and this step can increase the speed of subsequent processing.
And S540, inputting the local image data into the experiment abnormal operation detection mathematical model for classification and judgment to obtain a detection result.
It can be understood that this step is to automatically detect the category of the current operation by inputting the local image data processed into matrix data and extracting useful data into the mathematical model for detecting the experimental abnormal operation, and to make corresponding response measures according to the category. Note that step S540 includes steps S541, S542, S543, and S544.
Step S541, classifying the characteristic images based on a nearest neighbor algorithm to obtain category information.
It is understood that this step is to identify the partial image data and output the category information.
And S542, obtaining a detection result according to the category information and a preset detection rule.
It can be understood that the preset detection rule in this step is formulated according to the regulations of the experimental operation examination, and the corresponding treatment measure is linked according to the obtained current operation type to obtain the detection result.
Step S543, if it is detected that the category information belongs to the normal experiment operation, the detection result is that no processing is performed.
It can be understood that the obtained detection result shows that the current operation is a normal experiment operation, and does not interfere with the examination process.
And S544, if the type information is detected to belong to abnormal experimental operation, warning information is sent to the examination staff.
It can be understood that if the obtained detection result shows that the current operation is an abnormal experimental operation, a correct processing method is made for the information request sent by the examiner, and the video of the abnormal experimental operation is backed up and marked.
Example 2:
as shown in fig. 2, the present embodiment provides a chemical experiment abnormal operation detecting apparatus, including:
acquiring marks in the block diagram: the system comprises a data processing device and a data processing method, wherein the data processing device is used for acquiring real-time experiment video data and historical experiment video data, and the historical experiment video data information comprises normal operation video data and abnormal operation video data;
the extraction module 2 is used for preprocessing the historical experimental video data and then extracting features to obtain a first feature set and a weight set;
the analysis module 3 is used for carrying out clustering operation on the historical experimental video based on the first feature set and the weight set to obtain classified video data;
the conversion module 4 is used for performing feature conversion on the classified video data to obtain a second feature set;
and the detection module 5 is used for establishing an experimental abnormal operation detection mathematical model according to the second feature set and the classified video data, using the real-time experimental video data as an input value, and solving the experimental abnormal operation detection mathematical model to obtain a detection result.
In a specific embodiment of the present disclosure, the extraction module 2 includes:
the first processing unit 21 is configured to perform time-averaged sampling and uniform-size clipping on the historical experimental video data to obtain frame image data;
the second processing unit 22 performs feature pre-extraction on the frame image data based on a preset gaussian mixture model to obtain a first feature set;
the first calculating unit 23 calculates the first feature set based on a preset activation function to obtain a weight value corresponding to each feature, and combines all the weight values to obtain a weight set.
In a specific embodiment of the present disclosure, the analysis module 3 includes:
the second calculating unit 31 is configured to perform distance-based clustering operation on the first feature set to obtain at least two clustering clusters, where each clustering cluster includes at least one normal operation clustering cluster and at least one abnormal operation clustering cluster;
the third processing unit 32 is configured to perform feature extraction on each cluster to obtain a third feature set;
a fourth processing unit 33, configured to perform feature fusion on the first feature set and the third feature set to obtain a fourth feature set;
and the fifth processing unit 34 is configured to classify the historical experimental video according to a fourth feature set to obtain classified video data.
In a specific embodiment of the present disclosure, the conversion module 4 includes:
a sixth processing unit 41, configured to perform wavelet transform on the classified video data to obtain feature matrix data;
a third calculating unit 42, configured to calculate matrix parameters according to the feature matrix data, where the matrix parameters include a total mean value, a category mean value, an inter-class divergence matrix, and an intra-class divergence matrix;
a fourth calculating unit 43, which calculates the matrix parameters based on a linear discrimination algorithm to obtain an optimal projection matrix;
a seventh processing unit 44, configured to project the feature matrix data to the optimal projection matrix to obtain a second feature set.
In a specific embodiment of the present disclosure, the detection module 5 includes:
an eighth processing unit 51, configured to train an experiment operation classifier according to the classified video data and the second feature set, and establish an experiment abnormal operation detection mathematical model based on the experiment operation classifier;
a ninth processing unit 52, configured to perform wavelet transformation on the real-time experimental video data to obtain a transformed image;
a tenth processing unit 53, configured to perform feature extraction on the transformed image to obtain local image data;
an eleventh processing unit 54, configured to input the local image data into the mathematical model for performing the detection of the experimental abnormal operation, and perform classification and judgment to obtain a detection result.
In a specific embodiment of the present disclosure, the eleventh processing unit 54 includes:
a twelfth processing unit 541, classifying the feature images based on a nearest neighbor algorithm to obtain category information;
the first analysis unit 542 obtains a detection result according to the category information and a preset detection rule;
a first determining unit 543, configured to determine that no processing is performed on the detection result if it is detected that the category information belongs to the normal experiment operation;
a second determining unit 544, configured to send warning information to the test staff if it is detected that the category information belongs to the abnormal experimental operation.
It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be described in detail here.
Example 3:
corresponding to the above method embodiment, the present embodiment further provides a chemical experiment abnormal operation detection device, and a chemical experiment abnormal operation detection device described below and a chemical experiment abnormal operation detection method described above may be referred to in correspondence with each other.
Fig. 3 is a block diagram illustrating a chemical experiment abnormal operation detection apparatus 800 according to an exemplary embodiment. As shown in fig. 3, the chemical experiment abnormal operation detecting apparatus 800 may include: a processor 801, a memory 802. The chemical experiment abnormal operation detection apparatus 800 may further include one or more of a multimedia component 803, an I/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the chemical experiment abnormal operation detection apparatus 800, so as to complete all or part of the steps in the chemical experiment abnormal operation detection method. The memory 802 is used to store various types of data to support the operation of the chemical experiment abnormal operation detection apparatus 800, and the data may include, for example, instructions for any application or method operating on the chemical experiment abnormal operation detection apparatus 800, and application-related data such as contact data, transmitted and received messages, pictures, audio, video, and the like. The Memory 802 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically Erasable Programmable Read-Only Memory (EEPROM), erasable Programmable Read-Only Memory (EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 803 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 802 or transmitted through the communication component 805. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the chemical experiment abnormal operation detection apparatus 800 and other apparatuses. Wireless communication, such as Wi-Fi, bluetooth, near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding communication component 805 may include: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the chemical experiment abnormal operation detecting apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for performing the chemical experiment abnormal operation detecting method.
In another exemplary embodiment, a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the above-described chemical experiment abnormal operation detection method is also provided. For example, the computer readable storage medium may be the above-mentioned memory 802 comprising program instructions executable by the processor 801 of the chemical experiment abnormal operation detection apparatus 800 to perform the above-mentioned chemical experiment abnormal operation detection method.
Example 4:
corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment, and a readable storage medium described below and a method for detecting abnormal operation of a chemical experiment described above may be referred to in correspondence.
A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for detecting abnormal operation in chemical experiments according to the above-mentioned method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other readable storage media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present invention, and shall cover the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for detecting abnormal operation of chemical experiment is characterized by comprising the following steps:
acquiring real-time experiment video data and historical experiment video data, wherein the historical experiment video data information comprises normal operation video data and abnormal operation video data;
preprocessing the historical experimental video data and then extracting features to obtain a first feature set and a weight set;
clustering the historical experimental videos based on the first feature set and the weight set to obtain classified video data;
performing feature conversion on the classified video data to obtain a second feature set;
and establishing an experiment abnormal operation detection mathematical model according to the second feature set and the classified video data, taking the real-time experiment video data as an input value, and solving the experiment abnormal operation detection mathematical model to obtain a detection result.
2. The method for detecting abnormal operation in chemical experiments according to claim 1, wherein the preprocessing the historical experimental video data and then performing feature extraction to obtain a first feature set and a weight set, and the method comprises the following steps:
carrying out time average sampling and uniform size cutting on the historical experimental video data to obtain frame image data;
performing feature pre-extraction on the frame image data based on a preset Gaussian mixture model to obtain a first feature set;
and calculating the first feature set based on a preset activation function to obtain a weight value corresponding to each feature, and combining all the weight values to obtain a weight set.
3. The method of claim 1, wherein the step of performing feature transformation on the classified video data to obtain a set of features including a second feature set comprises:
performing wavelet transformation on the classified video data to obtain characteristic matrix data;
calculating to obtain matrix parameters according to the characteristic matrix data, wherein the matrix parameters comprise a total mean value, a category mean value, an inter-category divergence matrix and an intra-category divergence matrix;
calculating the matrix parameters based on a linear discrimination algorithm to obtain an optimal projection matrix;
and projecting the feature matrix data to the optimal projection matrix to obtain a second feature set.
4. The method for detecting abnormal operation in chemical experiment according to claim 1, wherein the establishing a mathematical model for detecting abnormal operation in experiment according to the second feature set and the classified video data, using the real-time experimental video data as the input value, and solving the mathematical model for detecting abnormal operation in experiment to obtain a detection result comprises:
training an experimental operation classifier according to the classified video data and the second feature set, and establishing an experimental abnormal operation detection mathematical model based on the experimental operation classifier;
performing wavelet transformation on the real-time experimental video data to obtain a transformation image;
performing feature extraction on the transformed image to obtain local image data;
and inputting the local image data into the experiment abnormal operation detection mathematical model for classification and judgment to obtain a detection result.
5. A chemical experiment abnormal operation detecting device, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring real-time experiment video data and historical experiment video data, and the historical experiment video data information comprises normal operation video data and abnormal operation video data;
the extraction module is used for preprocessing the historical experimental video data and then extracting features to obtain a first feature set and a weight set;
the analysis module is used for carrying out clustering operation on the historical experimental video based on the first feature set and the weight set to obtain classified video data;
the conversion module is used for performing feature conversion on the classified video data to obtain a second feature set;
and the detection module is used for establishing an experiment abnormal operation detection mathematical model according to the second feature set and the classified video data, taking the real-time experiment video data as an input value, and solving the experiment abnormal operation detection mathematical model to obtain a detection result.
6. The chemical experiment abnormal operation detection apparatus of claim 5, wherein the extraction module comprises:
the first processing unit is used for carrying out time-averaged sampling and uniform size cutting on the historical experimental video data to obtain frame image data;
the second processing unit is used for carrying out feature pre-extraction on the frame image data based on a preset Gaussian mixture model to obtain a first feature set;
the first computing unit is used for computing the first feature set based on a preset activation function to obtain a weight value corresponding to each feature, and combining all the weight values to obtain a weight set.
7. The chemical experiment abnormal operation detecting device according to claim 5, wherein the converting module includes:
the sixth processing unit is used for performing wavelet transformation on the classified video data to obtain characteristic matrix data;
the third calculation unit is used for calculating matrix parameters according to the characteristic matrix data, wherein the matrix parameters comprise a total mean value, a category mean value, an inter-class divergence matrix and an intra-class divergence matrix;
the fourth calculation unit calculates the matrix parameters based on a linear discrimination algorithm to obtain an optimal projection matrix;
and the seventh processing unit is used for projecting the feature matrix data to the optimal projection matrix to obtain a second feature set.
8. The chemical experiment abnormal operation detection apparatus of claim 5, wherein the detection module comprises:
the eighth processing unit is used for training an experimental operation classifier according to the classified video data and the second feature set and establishing an experimental abnormal operation detection mathematical model based on the experimental operation classifier;
the ninth processing unit is used for performing wavelet transformation on the real-time experimental video data to obtain a transformation image;
a tenth processing unit, configured to perform feature extraction on the transformed image to obtain local image data;
and the eleventh processing unit is used for inputting the local image data into the experiment abnormal operation detection mathematical model for classification and judgment to obtain a detection result.
9. A chemical experiment abnormal operation detecting apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for detecting abnormal operation in a chemical experiment according to any one of claims 1 to 4 when the computer program is executed.
10. A readable storage medium, characterized by: the readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method for detecting abnormal operation in a chemical experiment according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211269703.5A CN115345527B (en) | 2022-10-18 | 2022-10-18 | Chemical experiment abnormal operation detection method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211269703.5A CN115345527B (en) | 2022-10-18 | 2022-10-18 | Chemical experiment abnormal operation detection method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115345527A true CN115345527A (en) | 2022-11-15 |
| CN115345527B CN115345527B (en) | 2023-01-03 |
Family
ID=83957244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211269703.5A Active CN115345527B (en) | 2022-10-18 | 2022-10-18 | Chemical experiment abnormal operation detection method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115345527B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7792770B1 (en) * | 2007-08-24 | 2010-09-07 | Louisiana Tech Research Foundation; A Division Of Louisiana Tech University Foundation, Inc. | Method to indentify anomalous data using cascaded K-Means clustering and an ID3 decision tree |
| US20120041575A1 (en) * | 2009-02-17 | 2012-02-16 | Hitachi, Ltd. | Anomaly Detection Method and Anomaly Detection System |
| CN105913002A (en) * | 2016-04-07 | 2016-08-31 | 杭州电子科技大学 | On-line adaptive abnormal event detection method under video scene |
| CN108805002A (en) * | 2018-04-11 | 2018-11-13 | 杭州电子科技大学 | Monitor video accident detection method based on deep learning and dynamic clustering |
| CN109116834A (en) * | 2018-09-04 | 2019-01-01 | 湖州师范学院 | A kind of batch process fault detection method based on deep learning |
| CN109284705A (en) * | 2018-09-07 | 2019-01-29 | 电子科技大学 | A kind of method for detecting abnormality of Traffic Surveillance Video |
| WO2021078566A1 (en) * | 2019-10-22 | 2021-04-29 | Senseon Tech Ltd | Anomaly detection |
| US20210216877A1 (en) * | 2019-12-16 | 2021-07-15 | Korea Advanced Institute Of Science And Technology | Ultra-high sensitive target signal detection method based on noise analysis using deep learning based anomaly detection and system using the same |
| CN113449660A (en) * | 2021-07-05 | 2021-09-28 | 西安交通大学 | Abnormal event detection method of space-time variation self-coding network based on self-attention enhancement |
| WO2021222495A1 (en) * | 2020-04-30 | 2021-11-04 | Bae Systems Information And Electronic Systems Integration Inc. | Anomaly detection system using multi-layer support vector machines and method thereof |
| CN113936148A (en) * | 2021-09-16 | 2022-01-14 | 北京理工大学 | Image classification method based on random Fourier feature transformation |
| CN114553681A (en) * | 2022-03-08 | 2022-05-27 | 中国人民解放军国防科技大学 | Equipment state abnormity detection method and device and computer equipment |
| US20220233119A1 (en) * | 2021-01-22 | 2022-07-28 | Ethicon Llc | Method of adjusting a surgical parameter based on biomarker measurements |
| CN114937011A (en) * | 2022-05-12 | 2022-08-23 | 北京航空航天大学 | Photovoltaic cell image anomaly detection method based on empirical Garbor wavelet transform |
| CN115019240A (en) * | 2022-08-04 | 2022-09-06 | 成都西交智汇大数据科技有限公司 | Grading method, device and equipment for chemical experiment operation and readable storage medium |
| CN115115826A (en) * | 2022-05-30 | 2022-09-27 | 深圳技术大学 | Feature selection and extraction method and device, anomaly detection model and construction method thereof |
-
2022
- 2022-10-18 CN CN202211269703.5A patent/CN115345527B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7792770B1 (en) * | 2007-08-24 | 2010-09-07 | Louisiana Tech Research Foundation; A Division Of Louisiana Tech University Foundation, Inc. | Method to indentify anomalous data using cascaded K-Means clustering and an ID3 decision tree |
| US20120041575A1 (en) * | 2009-02-17 | 2012-02-16 | Hitachi, Ltd. | Anomaly Detection Method and Anomaly Detection System |
| CN105913002A (en) * | 2016-04-07 | 2016-08-31 | 杭州电子科技大学 | On-line adaptive abnormal event detection method under video scene |
| CN108805002A (en) * | 2018-04-11 | 2018-11-13 | 杭州电子科技大学 | Monitor video accident detection method based on deep learning and dynamic clustering |
| CN109116834A (en) * | 2018-09-04 | 2019-01-01 | 湖州师范学院 | A kind of batch process fault detection method based on deep learning |
| CN109284705A (en) * | 2018-09-07 | 2019-01-29 | 电子科技大学 | A kind of method for detecting abnormality of Traffic Surveillance Video |
| WO2021078566A1 (en) * | 2019-10-22 | 2021-04-29 | Senseon Tech Ltd | Anomaly detection |
| US20210216877A1 (en) * | 2019-12-16 | 2021-07-15 | Korea Advanced Institute Of Science And Technology | Ultra-high sensitive target signal detection method based on noise analysis using deep learning based anomaly detection and system using the same |
| WO2021222495A1 (en) * | 2020-04-30 | 2021-11-04 | Bae Systems Information And Electronic Systems Integration Inc. | Anomaly detection system using multi-layer support vector machines and method thereof |
| US20220233119A1 (en) * | 2021-01-22 | 2022-07-28 | Ethicon Llc | Method of adjusting a surgical parameter based on biomarker measurements |
| CN113449660A (en) * | 2021-07-05 | 2021-09-28 | 西安交通大学 | Abnormal event detection method of space-time variation self-coding network based on self-attention enhancement |
| CN113936148A (en) * | 2021-09-16 | 2022-01-14 | 北京理工大学 | Image classification method based on random Fourier feature transformation |
| CN114553681A (en) * | 2022-03-08 | 2022-05-27 | 中国人民解放军国防科技大学 | Equipment state abnormity detection method and device and computer equipment |
| CN114937011A (en) * | 2022-05-12 | 2022-08-23 | 北京航空航天大学 | Photovoltaic cell image anomaly detection method based on empirical Garbor wavelet transform |
| CN115115826A (en) * | 2022-05-30 | 2022-09-27 | 深圳技术大学 | Feature selection and extraction method and device, anomaly detection model and construction method thereof |
| CN115019240A (en) * | 2022-08-04 | 2022-09-06 | 成都西交智汇大数据科技有限公司 | Grading method, device and equipment for chemical experiment operation and readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 穆荣: "网络域名用户异常访问行为信息精准识别仿真", 《计算机仿真》 * |
| 胡珉等: "多维时间序列异常检测算法综述", 《计算机应用》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115345527B (en) | 2023-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112200081A (en) | Abnormal behavior identification method and device, electronic equipment and storage medium | |
| CN112639431A (en) | Abnormality prediction system and abnormality prediction method | |
| CN111079694A (en) | Counter assistant job function monitoring device and method | |
| CN116129350B (en) | Intelligent monitoring method, device, equipment and medium for safety operation of data center | |
| CN112183289A (en) | Method, device, equipment and medium for detecting patterned screen | |
| Wang et al. | Back to the beginning: Starting point detection for early recognition of ongoing human actions | |
| CN115345527B (en) | Chemical experiment abnormal operation detection method, device, equipment and readable storage medium | |
| CN115362445A (en) | Data sorting device, data sorting method, and data sorting program | |
| US20170309040A1 (en) | Method and device for positioning human eyes | |
| CN114463779A (en) | Smoking identification method, device, equipment and storage medium | |
| CN115019305B (en) | Method, device and equipment for identifying root tip cells and readable storage medium | |
| CN108596068B (en) | Method and device for recognizing actions | |
| CN111178244A (en) | Method for identifying abnormal production scene | |
| US11954955B2 (en) | Method and system for collecting and monitoring vehicle status information | |
| CN115359412A (en) | Hydrochloric acid neutralization experiment scoring method, device, equipment and readable storage medium | |
| Vardhan et al. | Driver’s drowsiness detection based on facial multi-feature fusion | |
| CN115375954B (en) | Chemical experiment solution identification method, device, equipment and readable storage medium | |
| CN115953724B (en) | User data analysis and management method, device, equipment and storage medium | |
| CN117253064A (en) | Method and system capable of customizing monitoring data | |
| KR102190748B1 (en) | Method, apparatus and program for analyzing behavior of an experimental animal | |
| CN117371996B (en) | Electric power communication analysis method based on big data | |
| Harshalatha et al. | Student Attention Monitoring: An Automated Approach | |
| CN114742106A (en) | Integrated pump station management method, device and equipment and readable storage medium | |
| WO2023112214A1 (en) | Video-of-interest detection device, method, and program | |
| Liu et al. | Research on the fatigue detection method of operators in digital main control rooms of nuclear power plants based on multi-feature fusion |
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 |