CN113298006B - Novel abnormal target detection method based on brain-computer fusion cognition and decision - Google Patents
Novel abnormal target detection method based on brain-computer fusion cognition and decision Download PDFInfo
- Publication number
- CN113298006B CN113298006B CN202110622678.3A CN202110622678A CN113298006B CN 113298006 B CN113298006 B CN 113298006B CN 202110622678 A CN202110622678 A CN 202110622678A CN 113298006 B CN113298006 B CN 113298006B
- Authority
- CN
- China
- Prior art keywords
- computer
- brain
- fusion
- abnormal
- target
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 230000004927 fusion Effects 0.000 title claims abstract description 30
- 230000019771 cognition Effects 0.000 title claims abstract description 17
- 210000004556 brain Anatomy 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000000007 visual effect Effects 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 230000006698 induction Effects 0.000 claims description 2
- 238000000513 principal component analysis Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000003786 synthesis reaction Methods 0.000 claims description 2
- 238000002474 experimental method Methods 0.000 abstract description 2
- 230000010354 integration Effects 0.000 abstract 1
- 238000011160 research Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007177 brain activity Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a novel abnormal target detection method based on brain-computer fusion cognition and decision, which comprises the following steps: 1. and calculating a classification value of the abnormal target image through a computer vision target detection algorithm. 2. Designing an electroencephalogram signal corresponding to the abnormal target image induced by the rapid sequence visual presentation experiment, extracting characteristics, classifying the electroencephalogram signal, and calculating a classification value of the abnormal target image. 3. And evaluating the classification performance of the computer and the human brain on the abnormal target image, and calculating the trust weight. 4. And establishing a D-S evidence theory brain-computer fusion cognition and decision model, and calculating a brain-computer fusion classification value of whether an abnormal target exists in the image according to the classification values of the trust weight fusion computer and the human brain to obtain an abnormal target detection result. The method can fully integrate the decision information of the computer and the human brain, reduce the decision contradiction of the computer and the human brain, improve the performance of brain-computer integration and effectively solve the problem of low detection accuracy of abnormal targets.
Description
Technical Field
The invention belongs to the field of brain-computer interface, computer vision and intelligent information fusion cross research.
Background
Target detection is to find out target feature expression in an image to distinguish a target from a non-target. The development of machine learning and deep learning promotes the development of computer vision target detection, and the accuracy is greatly improved. However, for abnormal targets in scenes with low visibility at night, on snow, etc., the imaging quality of the targets is poor, and the computer lacks sufficient recognition capability, so that the accuracy requirement cannot be met. The human has strong recognition capability, can acquire key visual information in the image at a glance, and can rapidly detect the interested target in the image. The brain-computer interface is a communication and control technology, which can enable people to communicate with the outside directly through brain activities and can effectively realize detection of abnormal targets by the human brain. The invention provides a method for detecting abnormal targets by fusing information of a computer and human brain, which enables the advantages of the computer and the human brain to be complementary and improves the accuracy of abnormal target detection.
In recent years, researchers at home and abroad have carried out more researches on abnormal target detection, and the researches mainly focus on improvement of a computer abnormal target detection model, feature extraction and classification of brain electrical signals in a target state and fusion cognition of a computer and human brain, and the researches have been advanced well, but still have more problems: (1) the computer detection accuracy is very low. The image characteristics of the abnormal target are greatly changed, so that the analysis difficulty of the image characteristics is improved, and the accuracy of computer detection is reduced. (2) The fusion cognition of the human brain and the computer has a decision contradiction. At present, a fusion cognitive method of a human brain and a computer is only applied to a target detection task in a normal scene, but not applied to an abnormal target detection task in a scene with low visibility. False detection occurs when the computer detects an abnormal target which is not learned, and false detection occurs when the human brain is not focused. The reasons for false detection of the computer and the human brain are different, and the inconsistent detection results of the computer and the human brain can occur, so that the computer and the human brain are in contradiction with each other.
The novel method for detecting the abnormal target based on the brain-computer fusion cognition and decision provided by the invention has the advantages that the detection information of the computer and the human brain on the abnormal target is fully fused by establishing the brain-computer fusion cognition and decision model, so that the decision contradiction between the computer and the human brain is reduced, the accuracy is higher than that of a method for independently detecting the computer and the human brain, the problems are effectively solved, and the method can be applied to the fields of automatic driving, intelligent monitoring and the like.
Disclosure of Invention
The invention provides a novel abnormal target detection method based on brain-computer fusion cognition and decision, which fuses machine intelligence and human brain intelligence, and effectively improves the accuracy of abnormal target detection by utilizing the powerful computing power of a computer and the cognition capability of the human brain.
The basic scheme is as follows:
(1) And detecting an abnormal target image through a computer vision target detection algorithm, and calculating a computer classification value of whether a target exists in the image.
(2) Designing an abnormal target detection rapid sequence visual presentation experiment, transmitting target information to the brain of a person at a higher image presentation rate, inducing an electroencephalogram signal corresponding to an abnormal target image, and collecting and recording through an electroencephalogram detector.
(3) The acquired brain-computer interface technology is used for decoding the acquired brain-computer signals, carrying out frequency band filtering, data segmentation and baseline calibration preprocessing, time domain space domain feature extraction and Bayesian linear discrimination and classification on the brain-computer signals, and calculating whether a human brain classification value of a target exists in an image.
(4) And evaluating the classification performance of the computer and the human brain on the abnormal target image, and determining the trust weight of the classification values of the computer and the human brain through the confusion matrix.
(5) And establishing a D-S evidence theory brain-computer fusion cognition and decision model, taking the trust weight and classification value of the computer and the human brain as the input of the model, and calculating whether a brain-computer fusion classification value of a target exists in the image to obtain an abnormal target detection result.
Compared with the existing method, the invention has the innovation and advantages that: the decision information of the computer and the human brain for detecting the abnormal target is fused, so that the decision information is more abundant, and the abnormal target can be detected more comprehensively; the established D-S evidence theory brain-computer fusion cognition and decision model can fully fuse the decision information of the computer and the human brain, reduce the decision contradiction between the computer and the human brain and effectively improve the accuracy of abnormal target detection.
Drawings
FIG. 1 is a flow chart of a novel method for detecting abnormal targets based on brain-computer fusion cognition and decision according to the invention
FIG. 2 is a schematic diagram of a rapid sequence visual presentation experimental paradigm for abnormal target detection
FIG. 3 is a graph comparing ROC curves of a novel method for detecting abnormal targets based on brain-computer fusion cognition and decision with a method for detecting the abnormal targets in a computer and a human brain alone
Detailed Description
The method according to the invention is described in further detail below with reference to the accompanying drawings. The flow of the method is shown in fig. 1, and the specific implementation mode is as follows:
(1) And detecting the abnormal target image by using a training set to realize a computer vision target detection algorithm, so as to obtain the classification probability of a target detection frame in the image, wherein the classification probability is a computer classification value of whether the target exists in the image.
(2) The abnormal target detection rapid sequence vision is designed to present the electroencephalogram signals related to experimental induction tasks, and an experimental paradigm is shown in figure 2. The image stimulus with abnormal target is 15% of all image stimulus, the image stimulus without target is 85% of all image stimulus, all image stimulus is presented to the tested in the form of image stream, and the interval of image stimulus is 200ms.
(3) And acquiring the induced brain electrical signals, and preprocessing to obtain brain electrical signals corresponding to the image stimulation. Taking the time corresponding to the image stimulus as a reference, subtracting the average value of the first 50ms data of the reference time from the last 400ms data of the reference time, and calculating the obtained 400ms data as the electroencephalogram signal corresponding to the image stimulus.
(4) And extracting the characteristics of the preprocessed electroencephalogram signals. The data structure of the electroencephalogram signal is D multiplied by T multiplied by N, D is the number of leads, T=400 is the number of time points, and N is the number of training set samples. Dividing the data in the training set into 400N multiplied by D matrixes according to time points, respectively taking the N multiplied by D matrixes as target classes and non-target classes, inputting the N multiplied by D1 vectors to each time point as weight of each lead, and obtaining the weighted data of the airspace. And carrying out principal component analysis on the weighted electroencephalogram data to reduce the dimension of the time domain, and reducing the dimension of the electroencephalogram data at 400 time points to the electroencephalogram data at 6 time points.
(5) And classifying the extracted brain electrical characteristics through Bayesian linear discriminant analysis to obtain classification probability, namely, whether the target brain classification value exists in the image.
(6) Using the classification value as a threshold value, calculating a classification confusion matrix corresponding to the threshold value, and calculating a classification value trust weight p through the confusion matrix t And p nt As shown in equation 1:
where TP means the number of samples in which the target is correctly predicted as the target class, FN means the number of samples in which the target is incorrectly predicted as the non-target class, FP means the number of samples in which the non-target is incorrectly predicted as the target class, and TN means the number of samples in which the non-target is correctly predicted as the non-target class.
(7) And establishing a D-S evidence theory brain-machine fusion cognition and decision model. The identification frames of the target hypothesis T, the non-target hypothesis NT and the uncertain hypothesis I are determined, the basic probability distribution is carried out on the hypotheses of the identification frames according to the trust weight, and the basic probability distribution of three hypotheses of a computer and a human brain can be respectively obtained, as shown in a formula 2:
m is in i For the basic probability distribution of a computer or a human brain s i For the classification value of computer or human brain, p t And p nt The trust weight corresponding to the classification value of the computer or the human brain is i=1, i=2 is the human brain.
The basic probability distribution of the computer and the human brain is fused through the Dempster synthesis rule, so that the fused basic probability distribution can be obtained, as shown in a formula 3:
wherein m is the basic probability distribution after fusion, and N is shown in formula 4:
N=1-m 1 (T)m 2 (NT)-m 1 (NT)m 2 (T) (4)
the classification value after brain-computer fusion is shown in formula 5:
s f =m(T)-m(NT) (5)
(8) The experimental result of the novel method for detecting abnormal targets based on brain-computer fusion cognition and decision is shown in figure 3, and the AUC of the novel method is higher than that of the method for independently detecting the abnormal targets by a computer and the brain, so that the accuracy is higher.
Claims (1)
1. The novel brain-computer fusion cognition and decision-based abnormal target detection method is characterized in that the detection results of a computer and human brain on abnormal targets in an image sequence are given out through a computer vision method and a rapid sequence vision presentation brain-computer interface method respectively, a D-S evidence theory brain-computer fusion model is established to give out the brain-computer fusion detection results of the abnormal targets, and the accurate detection of the abnormal targets is realized; the method comprises the following steps:
s1, detecting an image through a computer vision target detection algorithm, and calculating a computer classification value of whether a target exists in the image;
s2, acquiring an electroencephalogram signal through a rapid sequence visual presentation paradigm induction, sequentially carrying out frequency band filtering, data segmentation and baseline calibration preprocessing, time domain space domain feature extraction and Bayesian linear discrimination classification on the electroencephalogram signal, and calculating a human brain classification value of whether an abnormal target exists in an image; the specific time domain and space domain feature extraction is that Fisher linear judgment is adopted in a space domain to find out the optimal weight of each channel capable of projecting two types of data into a separable feature space, and principal component analysis is adopted in the time domain to reduce the dimension of the obtained space weighting matrix;
s3, establishing a D-S evidence theory brain-computer fusion model, determining an identification framework { T, NT, I }, and carrying out basic probability dynamic allocation on all assumptions in the identification framework, wherein the allocation formula is as follows:
wherein target hypothesis T, non-target hypothesis NT, uncertain hypothesis I, m i For the basic probability distribution of a computer or a human brain s i For the classification value of computer or human brain, p t And p nt For the accuracy of target and non-target obtained based on the confusion matrix, i=1 is a computer, i=2 is a human brain;
s4, obtaining basic probability distribution after fusion through a Dempster synthesis rule, and calculating a brain-computer fusion classification value to obtain a detection result of whether an abnormal target exists in the image;
wherein m is the basic probability distribution after fusion, and N=1-m 1 (T)m 2 (NT)+m 1 (NT)m 2 (T);
The classification value after brain-computer fusion is: s is(s) f =m(T)-m(NT)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110622678.3A CN113298006B (en) | 2021-06-04 | 2021-06-04 | Novel abnormal target detection method based on brain-computer fusion cognition and decision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110622678.3A CN113298006B (en) | 2021-06-04 | 2021-06-04 | Novel abnormal target detection method based on brain-computer fusion cognition and decision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113298006A CN113298006A (en) | 2021-08-24 |
CN113298006B true CN113298006B (en) | 2024-01-19 |
Family
ID=77327191
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110622678.3A Active CN113298006B (en) | 2021-06-04 | 2021-06-04 | Novel abnormal target detection method based on brain-computer fusion cognition and decision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113298006B (en) |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014170897A1 (en) * | 2013-04-14 | 2014-10-23 | Yissum Research Development Company Of The Hebrew University Of Jerusalem Ltd. | Classifying eeg signals in response to visual stimulus |
CN105868712A (en) * | 2016-03-28 | 2016-08-17 | 中国人民解放军信息工程大学 | Method for searching object image by combining potential vision and machine vision based on posterior probability model |
CN107389732A (en) * | 2017-07-14 | 2017-11-24 | 中国计量大学 | A kind of laser scanning thermal imaging crack detecting method |
CN110008985A (en) * | 2019-02-03 | 2019-07-12 | 河南科技大学 | Based on the shipboard aircraft group target identification method for improving D-S evidence theory rule |
CN110647905A (en) * | 2019-08-02 | 2020-01-03 | 杭州电子科技大学 | Method for identifying terrorist-related scene based on pseudo brain network model |
CN110991406A (en) * | 2019-12-19 | 2020-04-10 | 燕山大学 | RSVP electroencephalogram characteristic-based small target detection method and system |
CN111597990A (en) * | 2020-05-15 | 2020-08-28 | 北京邮电大学 | RSVP-model-based brain-computer combined target detection method and system |
CN111680620A (en) * | 2020-06-05 | 2020-09-18 | 中国人民解放军空军工程大学 | Human-computer interaction intention identification method based on D-S evidence theory |
CN111709487A (en) * | 2020-06-22 | 2020-09-25 | 中国科学院空天信息创新研究院 | Underwater multi-source acoustic image substrate classification method and system based on decision-level fusion |
CN111931833A (en) * | 2020-07-30 | 2020-11-13 | 上海卫星工程研究所 | Multi-source data driving-based space-based multi-dimensional information fusion method and system |
CN112101161A (en) * | 2020-09-04 | 2020-12-18 | 西安交通大学 | Evidence theory fault state identification method based on correlation coefficient distance and iteration improvement |
CN112232375A (en) * | 2020-09-21 | 2021-01-15 | 西北工业大学 | Unknown type target identification method based on evidence theory |
AU2020103407A4 (en) * | 2020-11-12 | 2021-01-28 | Army Academy of Armored Forces | Intention recognition method based on normal cloud generator-bayesian network |
CN112612364A (en) * | 2020-12-21 | 2021-04-06 | 西北工业大学 | Space-time hybrid CSP-PCA target detection method based on rapid sequence vision presentation brain-computer interface |
CN112712717A (en) * | 2019-10-26 | 2021-04-27 | 华为技术有限公司 | Information fusion method and system |
WO2021086218A1 (en) * | 2019-10-29 | 2021-05-06 | Общество С Ограниченной Ответственностью "Нейроассистивные Технологии" | Method for categorizing an object on the basis of an electroencephalogram signal |
AU2021101948A4 (en) * | 2021-04-15 | 2021-06-03 | China Railway Tunnel Group Co. ,Ltd | A concrete durability detection method based on cloud model and D-S evidence theory |
-
2021
- 2021-06-04 CN CN202110622678.3A patent/CN113298006B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014170897A1 (en) * | 2013-04-14 | 2014-10-23 | Yissum Research Development Company Of The Hebrew University Of Jerusalem Ltd. | Classifying eeg signals in response to visual stimulus |
CN105868712A (en) * | 2016-03-28 | 2016-08-17 | 中国人民解放军信息工程大学 | Method for searching object image by combining potential vision and machine vision based on posterior probability model |
CN107389732A (en) * | 2017-07-14 | 2017-11-24 | 中国计量大学 | A kind of laser scanning thermal imaging crack detecting method |
CN110008985A (en) * | 2019-02-03 | 2019-07-12 | 河南科技大学 | Based on the shipboard aircraft group target identification method for improving D-S evidence theory rule |
CN110647905A (en) * | 2019-08-02 | 2020-01-03 | 杭州电子科技大学 | Method for identifying terrorist-related scene based on pseudo brain network model |
CN112712717A (en) * | 2019-10-26 | 2021-04-27 | 华为技术有限公司 | Information fusion method and system |
WO2021086218A1 (en) * | 2019-10-29 | 2021-05-06 | Общество С Ограниченной Ответственностью "Нейроассистивные Технологии" | Method for categorizing an object on the basis of an electroencephalogram signal |
CN110991406A (en) * | 2019-12-19 | 2020-04-10 | 燕山大学 | RSVP electroencephalogram characteristic-based small target detection method and system |
CN111597990A (en) * | 2020-05-15 | 2020-08-28 | 北京邮电大学 | RSVP-model-based brain-computer combined target detection method and system |
CN111680620A (en) * | 2020-06-05 | 2020-09-18 | 中国人民解放军空军工程大学 | Human-computer interaction intention identification method based on D-S evidence theory |
CN111709487A (en) * | 2020-06-22 | 2020-09-25 | 中国科学院空天信息创新研究院 | Underwater multi-source acoustic image substrate classification method and system based on decision-level fusion |
CN111931833A (en) * | 2020-07-30 | 2020-11-13 | 上海卫星工程研究所 | Multi-source data driving-based space-based multi-dimensional information fusion method and system |
CN112101161A (en) * | 2020-09-04 | 2020-12-18 | 西安交通大学 | Evidence theory fault state identification method based on correlation coefficient distance and iteration improvement |
CN112232375A (en) * | 2020-09-21 | 2021-01-15 | 西北工业大学 | Unknown type target identification method based on evidence theory |
AU2020103407A4 (en) * | 2020-11-12 | 2021-01-28 | Army Academy of Armored Forces | Intention recognition method based on normal cloud generator-bayesian network |
CN112612364A (en) * | 2020-12-21 | 2021-04-06 | 西北工业大学 | Space-time hybrid CSP-PCA target detection method based on rapid sequence vision presentation brain-computer interface |
AU2021101948A4 (en) * | 2021-04-15 | 2021-06-03 | China Railway Tunnel Group Co. ,Ltd | A concrete durability detection method based on cloud model and D-S evidence theory |
Non-Patent Citations (8)
Title |
---|
D-S理论多分类器融合的光学遥感图像多目标识别;姬晓飞等;《电子测量与仪器学报》;第34卷(第5期);127-132 * |
Human-autonomy sensor fusion for rapid object detection;Ryan M. Robinson等;《2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)》;305-312 * |
On the limits of evidence accumulation of the preconscious percept;Alberto Avilés等;《Cognition》;20200229;第195卷;1-12 * |
The Classification of EEG Signals with Multi-Domain Fusion Based on D-S Evidence Theory;Rongxiang Ge等;《Journal of Circuits, Systems and Computers》;第28卷(第10期);1-11 * |
基于改进D-S证据理论的数据融合目标分类;周文文等;《半导体光电》;第42卷(第1期);121-126 * |
基于证据理论的海上目标综合识别若干问题研究;陈雁飞;《中国博士学位论文全文数据库 社会科学I辑》;20180615;第2018年卷(第6期);第G112-3页 * |
张明晓主编.模式识别与定性分析.《分析科学》.西南师范大学出版社,2021, * |
葛东旭编著.贝叶斯分类器.《数据挖掘原理与应用》.机械工业出版社,2020, * |
Also Published As
Publication number | Publication date |
---|---|
CN113298006A (en) | 2021-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liao et al. | Deep facial spatiotemporal network for engagement prediction in online learning | |
CN110353673B (en) | Electroencephalogram channel selection method based on standard mutual information | |
US8462996B2 (en) | Method and system for measuring human response to visual stimulus based on changes in facial expression | |
CN107133564B (en) | Tooling cap detection method | |
CN109431523B (en) | Autism primary screening device based on non-social voice stimulation behavior paradigm | |
CN110991348B (en) | Face micro-expression detection method based on optical flow gradient amplitude characteristics | |
CN111582086A (en) | Fatigue driving identification method and system based on multiple characteristics | |
CN105999670A (en) | Shadow-boxing movement judging and guiding system based on kinect and guiding method adopted by same | |
CN101593425A (en) | A kind of fatigue driving monitoring method and system based on machine vision | |
CN110037693A (en) | A kind of mood classification method based on facial expression and EEG | |
CN108920699B (en) | Target identification feedback system and method based on N2pc | |
CN103577804B (en) | Based on SIFT stream and crowd's Deviant Behavior recognition methods of hidden conditional random fields | |
CN113180701A (en) | Electroencephalogram signal depth learning method for image label labeling | |
CN116092119A (en) | Human behavior recognition system based on multidimensional feature fusion and working method thereof | |
Faraji et al. | Drowsiness detection based on driver temporal behavior using a new developed dataset | |
CN116226715A (en) | Multi-mode feature fusion-based online polymorphic identification system for operators | |
Aboah et al. | Deepsegmenter: Temporal action localization for detecting anomalies in untrimmed naturalistic driving videos | |
CN113298006B (en) | Novel abnormal target detection method based on brain-computer fusion cognition and decision | |
Amrouche et al. | Activity segmentation and identification based on eye gaze features | |
CN103366163B (en) | Face detection system and method based on incremental learning | |
Guo et al. | Monitoring and detection of driver fatigue from monocular cameras based on Yolo v5 | |
KR101886416B1 (en) | System for controlling door of vehicle and method thereof | |
Xie et al. | Revolutionizing Road Safety: YOLOv8-Powered Driver Fatigue Detection | |
Song et al. | Early diagnosis of asd based on facial expression recognition and head pose estimation | |
CN116189026A (en) | Pedestrian re-recognition method and device and storage medium |
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 |