CN112716494A - Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm - Google Patents
Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm Download PDFInfo
- Publication number
- CN112716494A CN112716494A CN202110060419.6A CN202110060419A CN112716494A CN 112716494 A CN112716494 A CN 112716494A CN 202110060419 A CN202110060419 A CN 202110060419A CN 112716494 A CN112716494 A CN 112716494A
- Authority
- CN
- China
- Prior art keywords
- micro
- expression
- brain wave
- analysis algorithm
- mental health
- 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.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/06—Children, e.g. for attention deficit diagnosis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention relates to the technical field of mental assessment, in particular to a mental health condition analysis algorithm based on micro-expressions and brain wave analysis algorithms, excessive subjective factors are avoided by collecting brain wave signals and micro-expressions of children, and meanwhile, the recognition effect of mental anxiety conditions of children is improved by scientific intersection of computer technology and psychology, so that the recognition result has high accuracy and interpretability for clinical application requirements, and the problems of inaccurate recognition and untimely intervention on the anxiety disorders of children in the current research can be really solved.
Description
Technical Field
The invention relates to the technical field of mental assessment, in particular to a mental health condition analysis algorithm based on a micro-expression and brain wave analysis algorithm.
Background
At present, the development of domestic micro-expression recognition research is very fast in the transfer learning of micro-expression recognition, and a lot of achievements and applications have been obtained in the aspects of focusing brain wave research on motor imagery to control external equipment and providing rehabilitation training for disabled people, wherein the development has a certain application in the aspect of utilizing brain wave signals to perform mental health assessment.
However, in the research on the anxiety of children, some scholars adopt big data technologies to collect behaviors for analysis in actual work, and the detection technologies are not very friendly to children, are very easy to have the situations of data loss, unreal data and the like, and cannot be popularized in a large range.
The study proves that the current technology for evaluating the anxiety of children has the following defects: 1. due to the special properties of the micro-expressions, the micro-expressions can be generated spontaneously by people only by designing a complex experiment, and the difficulty in manually identifying the micro-expressions is high, so that the labeling of the data set is difficult; 2. the strong continuity of brain wave signals on a time sequence and the relevance among multiple channels are easy to ignore, how to improve the existing feature extraction algorithm of the signals also becomes a big problem, and meanwhile, the reliability of the signals needs to be improved, and the prediction accuracy is also improved; 3. the corresponding relation among expressions, micro-expressions and emotions is still unclear, a large number of experiments and sample analysis are needed for exploration and verification, and meanwhile, the problems that how to quantify the anxiety disorder characteristics of children from the perspective of computer science, how to determine the brain wave characteristics of anxiety disorder children and how to fuse with the brain wave field are all problems to be solved urgently; 4. in the traditional mode, the psychological condition of the child is judged by filling a form by a guardian, and in the mode, because the guardian subjectively judges, the evaluation of the psychological condition is not necessarily accurate.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a mental health condition analysis algorithm based on a micro-expression and brain wave analysis algorithm, and the technical problem to be solved is how to avoid too many subjective factors by collecting brain wave signals and micro-expression data of children, improve the recognition effect of mental anxiety conditions of children and enable the recognition result to have high accuracy.
In order to solve the technical problems, the technical scheme provided by the invention is as follows: a mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm comprises the following steps:
s1: the software/webpage is opened by the tested person, the software/webpage is subjected to psychological test to obtain a test result, brain wave signals and human face micro-expression data of the tested person are collected during the test, and the face long video of the tested person is recorded;
s2: learning the brain wave signals and the human face micro-expression data obtained in the step S1 to obtain a data model, inputting the data into the data model, and combining the test results obtained in the step S1 to form an analysis result;
s3: preprocessing the brainwave signals of the tested person in the S1, performing multi-scale analysis on the time sequence of the processed brainwave signals, and obtaining the most effective selected feature combination through a feature selection experiment;
s4: rapidly identifying a region containing a human face from a video containing the human face by using a traditional pattern recognition and deep learning method for a long video of the face of a tested person in S1, then eliminating the interference of a non-expression segment, a conventional expression segment and other facial action segments, and extracting a segment containing a micro-expression from the long video which has finished the positioning of the human face;
s5: identifying the starting point, the vertex and the ending point of the video clip which is determined to contain the micro expression in the S4 according to the action amplitude, thereby obtaining micro expression characteristics of the three points;
s6: combining the micro-expression characteristics obtained in the S5 with the selected characteristics obtained in the S3 to obtain the mental health condition of the tested person through a deep neural network model suggested by a deep learning neural network;
s7: combining the analysis result obtained in the S2 with the mental health condition obtained in the S6 to obtain results of three categories, namely health, mild and severe, adopting different treatments according to different results, and simultaneously carrying out research and analysis on the data model obtained in the S2.
Further, in step S1, brain wave data corresponding to the person under test under different stimuli is collected.
Further, in step S3, the preprocessing is performed by denoising and channel division.
Further, in step S2, an appropriate algorithm is designed based on the preprocessed electroencephalogram data to integrate the features into the input layer, and a machine learning model is used for training to obtain the model.
Further, in step S2, the algorithm adjustment model is optimized according to the feedback and evaluation of the experiment.
The beneficial effect that this technical scheme brought is: according to the mental health condition analysis algorithm based on the micro-expression and brain wave analysis algorithm, too many subjective factors are avoided by collecting brain wave signals and micro-expression data of children, and meanwhile, the recognition effect of the mental anxiety condition of the children is improved by scientifically crossing computer technology and psychology, so that the recognition result has high accuracy and interpretability for clinical application requirements, and the problems of inaccurate recognition and untimely intervention on the anxiety disorder of the children in the current research can be really solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart illustrating the steps of a mental health analysis algorithm based on a micro-expression and brain wave analysis algorithm according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, and it should be understood that the preferred embodiments described herein are merely for purposes of illustration and explanation, and are not intended to limit the present invention.
As shown in fig. 1, the mental health condition analysis algorithm based on the micro-expression and brain wave analysis algorithm includes the following steps:
s1: the software/webpage is opened by the tested person, the software/webpage is subjected to psychological test to obtain a test result, brain wave signals and human face micro-expression data of the tested person are collected during the test, and the face long video of the tested person is recorded;
s2: learning the brain wave signals and the human face micro-expression data obtained in the step S1 to obtain a data model, inputting the data into the data model, and combining the test results obtained in the step S1 to form an analysis result;
s3: preprocessing the brainwave signals of the tested person in the S1, performing multi-scale analysis on the time sequence of the processed brainwave signals, and obtaining the most effective selected feature combination through a feature selection experiment;
s4: rapidly identifying a region containing a human face from a video containing the human face by using a traditional pattern recognition and deep learning method for a long video of the face of a tested person in S1, then eliminating the interference of a non-expression segment, a conventional expression segment and other facial action segments, and extracting a segment containing a micro-expression from the long video which has finished the positioning of the human face;
s5: identifying the starting point, the vertex and the ending point of the video clip which is determined to contain the micro expression in the S4 according to the action amplitude, thereby obtaining micro expression characteristics of the three points;
s6: combining the micro-expression characteristics obtained in the S5 with the selected characteristics obtained in the S3 to obtain the mental health condition of the tested person through a deep neural network model suggested by a deep learning neural network;
s7: combining the analysis result obtained in the S2 with the mental health condition obtained in the S6 to obtain results of three categories, namely health, mild and severe, adopting different treatments according to different results, and simultaneously carrying out research and analysis on the data model obtained in the S2.
Therefore, the technical scheme starts from the cognitive psychology theory, takes the computer vision and electroencephalogram signal processing technology as a tool, and judges the existence, tendency and degree of the anxiety disorder of the children from the interdisciplinary angle.
Firstly, the mental health condition of the child is analyzed by using a micro-expression and expression recognition technology, the expression and the micro-expression expressed by the child under the external influence are analyzed by using a computer vision technology, the emotional state of the child can be effectively sensed, and the real mental state of the child is deduced. In the technical scheme, the existing brain wave analysis algorithm is fused, a model for evaluating the mental state of the child is obtained according to the brain wave characteristics, and a new visual angle and thought are provided for mental health evaluation from the perspective of objective evidence by combining with micro-expression sum analysis. Meanwhile, the computer vision and brain-computer interface technology is further utilized to quantify the characteristics and the degree of the anxiety disorder of the children, so that a tester can more accurately identify the condition of the anxiety disorder of the children, and timely intervention is achieved.
In this embodiment, in step S1, brain wave data corresponding to the person under test under different stimuli is collected.
In this embodiment, in step S3, the preprocessing is performed by denoising and channel division, so as to improve the data accuracy.
In this embodiment, in step S2, an appropriate algorithm is designed based on the preprocessed electroencephalogram data to integrate the features into the input layer, and a model is trained by using a machine learning model, so that the obtained model result is reasonable and accurate.
In this embodiment, in step S2, the algorithm adjustment model is optimized according to the feedback and evaluation of the experiment, so as to improve the accuracy of the result.
In conclusion, according to the mental health condition analysis algorithm based on the micro-expression and brain wave analysis algorithm, excessive subjective factors are avoided by collecting brain wave signals and micro-expression data of children, and meanwhile, the recognition effect of the mental anxiety condition of the children is improved by scientifically crossing computer technology and psychology, so that the recognition result has high accuracy, and has interpretability for clinical application requirements, and the problems of inaccurate recognition and untimely intervention on the anxiety disorder of the children in the current research can be really solved.
It should be noted that the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the inventive concepts described herein may be implemented using a variety of programming languages.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. 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.
Claims (5)
1. Mental health condition analysis algorithm based on micro expression and brain wave analysis algorithm, which is characterized in that: the method comprises the following steps:
s1: the software/webpage is opened by the tested person, the software/webpage is subjected to psychological test to obtain a test result, brain wave signals and human face micro-expression data of the tested person are collected during the test, and the face long video of the tested person is recorded;
s2: learning the brain wave signals and the human face micro-expression data obtained in the step S1 to obtain a data model, inputting the data into the data model, and combining the test results obtained in the step S1 to form an analysis result;
s3: preprocessing the brainwave signals of the tested person in the S1, performing multi-scale analysis on the time sequence of the processed brainwave signals, and obtaining the most effective selected feature combination through a feature selection experiment;
s4: rapidly identifying a region containing a human face from a video containing the human face by using a traditional pattern recognition and deep learning method for a long video of the face of a tested person in S1, then eliminating the interference of a non-expression segment, a conventional expression segment and other facial action segments, and extracting a segment containing a micro-expression from the long video which has finished the positioning of the human face;
s5: identifying the starting point, the vertex and the ending point of the video clip which is determined to contain the micro expression in the S4 according to the action amplitude, thereby obtaining micro expression characteristics of the three points;
s6: combining the micro-expression characteristics obtained in the S5 with the selected characteristics obtained in the S3 to obtain the mental health condition of the tested person through a deep neural network model suggested by a deep learning neural network;
s7: combining the analysis result obtained in the S2 with the mental health condition obtained in the S6 to obtain results of three categories, namely health, mild and severe, adopting different treatments according to different results, and simultaneously carrying out research and analysis on the data model obtained in the S2.
2. The mental health analysis algorithm based on micro-expression and brain wave analysis algorithm of claim 1, wherein: in step S1, brain wave data corresponding to the person under test under different stimuli is collected.
3. The mental health analysis algorithm based on micro-expression and brain wave analysis algorithm of claim 1, wherein: in step S3, the preprocessing is performed in a noise reduction and channel division manner.
4. The mental health analysis algorithm based on micro-expression and brain wave analysis algorithm of claim 1, wherein: in step S2, an appropriate algorithm is designed based on the preprocessed electroencephalogram data to integrate the features into the input layer, and a machine learning model is used to train the input layer to obtain a model.
5. The mental health analysis algorithm based on micro-expression and brain wave analysis algorithm of claim 1, wherein: in step S2, the algorithm adjustment model is optimized based on the feedback and evaluation of the experiment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110060419.6A CN112716494A (en) | 2021-01-18 | 2021-01-18 | Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110060419.6A CN112716494A (en) | 2021-01-18 | 2021-01-18 | Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112716494A true CN112716494A (en) | 2021-04-30 |
Family
ID=75591987
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110060419.6A Pending CN112716494A (en) | 2021-01-18 | 2021-01-18 | Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112716494A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107242876A (en) * | 2017-04-20 | 2017-10-13 | 合肥工业大学 | A kind of computer vision methods for state of mind auxiliary diagnosis |
CN107518906A (en) * | 2017-09-05 | 2017-12-29 | 天津市悠游科技有限公司 | One kind carries out psychological assistant diagnosis system and diagnosis and treatment method based on brain wave |
CN107799165A (en) * | 2017-09-18 | 2018-03-13 | 华南理工大学 | A kind of psychological assessment method based on virtual reality technology |
CN109730701A (en) * | 2019-01-03 | 2019-05-10 | 中国电子科技集团公司电子科学研究院 | A kind of acquisition methods and device of mood data |
US20190311188A1 (en) * | 2018-12-05 | 2019-10-10 | Sichuan University | Face emotion recognition method based on dual-stream convolutional neural network |
CN111887867A (en) * | 2020-07-10 | 2020-11-06 | 衡阳师范学院 | Method and system for analyzing character formation based on expression recognition and psychological test |
CN112182339A (en) * | 2020-11-03 | 2021-01-05 | 深圳市艾利特医疗科技有限公司 | Psychological assessment method and system |
-
2021
- 2021-01-18 CN CN202110060419.6A patent/CN112716494A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107242876A (en) * | 2017-04-20 | 2017-10-13 | 合肥工业大学 | A kind of computer vision methods for state of mind auxiliary diagnosis |
CN107518906A (en) * | 2017-09-05 | 2017-12-29 | 天津市悠游科技有限公司 | One kind carries out psychological assistant diagnosis system and diagnosis and treatment method based on brain wave |
CN107799165A (en) * | 2017-09-18 | 2018-03-13 | 华南理工大学 | A kind of psychological assessment method based on virtual reality technology |
US20190311188A1 (en) * | 2018-12-05 | 2019-10-10 | Sichuan University | Face emotion recognition method based on dual-stream convolutional neural network |
CN109730701A (en) * | 2019-01-03 | 2019-05-10 | 中国电子科技集团公司电子科学研究院 | A kind of acquisition methods and device of mood data |
CN111887867A (en) * | 2020-07-10 | 2020-11-06 | 衡阳师范学院 | Method and system for analyzing character formation based on expression recognition and psychological test |
CN112182339A (en) * | 2020-11-03 | 2021-01-05 | 深圳市艾利特医疗科技有限公司 | Psychological assessment method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10984674B2 (en) | System and method to teach and evaluate image grading performance using prior learned expert knowledge base | |
Palestro et al. | Some task demands induce collapsing bounds: Evidence from a behavioral analysis | |
KR101247748B1 (en) | Apparatus for analysing focus and nonfocus states and method therof | |
Cecotti et al. | Convolutional neural networks for P300 detection with application to brain-computer interfaces | |
Fang et al. | Depression prevalence in postgraduate students and its association with gait abnormality | |
CN113197579A (en) | Intelligent psychological assessment method and system based on multi-mode information fusion | |
Couceiro et al. | Spotting problematic code lines using nonintrusive programmers' biofeedback | |
KR102424403B1 (en) | Method and apparatus for predicting user state | |
CN110059232A (en) | A kind of data visualization method based on user experience measurement | |
Du et al. | Deep learning-based mental health monitoring scheme for college students using convolutional neural network | |
CN112773378A (en) | Electroencephalogram emotion recognition method for feature weight adaptive learning | |
Zou et al. | Integrating biometric sensors, VR, and machine learning to classify EEG signals in alternative architecture designs | |
Vallabhaneni et al. | Deep learning algorithms in eeg signal decoding application: a review | |
Hu et al. | Acrophobia quantified by EEG based on CNN incorporating Granger causality | |
CN113658697A (en) | Psychological assessment system based on video fixation difference | |
CN112716494A (en) | Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm | |
KR20200126793A (en) | Method and appratus to measure cognitive load based on a time-series analysis of psychophysiological responses in video-based learning | |
CN116110578A (en) | Screening device for diagnosis of depression symptoms assisted by computer | |
Kang et al. | Development of intelligent learning tool for improving foreign language skills based on EEG and eye tracker | |
CN112274154B (en) | Cross-subject fatigue driving classification method based on electroencephalogram sample weight adjustment | |
Hu et al. | On fatigue detection for air traffic controllers based on fuzzy fusion of multiple features | |
Hollenstein | Leveraging Cognitive Processing Signals for Natural Language Understanding | |
Akinci et al. | A video-based eye pupil detection system for diagnosing bipolar disorder | |
Valenzuela et al. | A spatio-temporal hypomimic deep descriptor to discriminate parkinsonian patients | |
Tian et al. | Automated analysis of seizure behavior in video: methods and challenges |
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 |