CN108288068A - Electroencephalogram signal data classification method under complex emotion scene - Google Patents
Electroencephalogram signal data classification method under complex emotion scene Download PDFInfo
- Publication number
- CN108288068A CN108288068A CN201711418634.9A CN201711418634A CN108288068A CN 108288068 A CN108288068 A CN 108288068A CN 201711418634 A CN201711418634 A CN 201711418634A CN 108288068 A CN108288068 A CN 108288068A
- Authority
- CN
- China
- Prior art keywords
- data
- formula
- testee
- mood
- eeg signals
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000008451 emotion Effects 0.000 title abstract description 4
- 238000000513 principal component analysis Methods 0.000 claims abstract description 10
- 238000010606 normalization Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 230000036651 mood Effects 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract description 4
- 230000003993 interaction Effects 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract 2
- 230000002996 emotional effect Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 4
- 210000004556 brain Anatomy 0.000 description 3
- 239000003814 drug Substances 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Signal Processing (AREA)
- Psychology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An electroencephalogram data classification method under a complex emotion scene comprises the following steps: (1) collecting original data: letting the testee calm for a plurality of minutes, guiding the emotion of the testee through different movie short films, collecting real-time electroencephalogram data, and finishing the test when a plurality of data are collected; (2) preprocessing the collected data by applying normalization: preprocessing the collected data by normalization to reduce the time complexity of data operation of the method; (3) after the data is preprocessed, the data is first subjected to fast fourier transform, as in equation [1], and then Principal Component Analysis (PCA) is performed on the computed data. The method has the advantages that the method can be effectively applied to effectively classify the electroencephalogram data in various complex emotional scenes, and can be widely applied to the fields of medical detection, lie detection and man-machine interaction.
Description
Technical field
The present invention relates to a kind of data sorting systems of EEG signals, and in particular to the brain electricity under a kind of complexity mood scene
Signal data sorting technique.
Background technology
In recent years, with the research and development of bioengineering field and Data Mining, based on the non-of EEG signals
The development of intrusive brain-computer interface technology it is more and more ripe, researcher, which wishes by EEG signals can to differentiate, become increasingly complex
Categories of emotions, because EEG signals have data dimension high, noise is more, it is real-time the features such as, traditional EEG signals data
Sorting technique may only identify 5 kinds of mood classifications once mostly, and other support high-precision and polytypic EEG signals
Then arithmetic speed is long for data classification method, cannot be satisfied the demand in actual product.
Such as Beijing University of Technology was in application in 2014《A kind of EEG signals feature selection approach based on decision tree》
With University Of Tianjin in application in 2013《One kind is across induction pattern mood electroencephalogramrecognition recognition modeling method》, the needle in actual test
There is a preferable performance for 5 classes and EEG signals data class test below, but the brain telecommunications more than 5 complicated classes
Number classification in all without ideal effect.It is an object of the invention to provide a kind of under 5 kinds or more of complicated mood scene
Eeg data sorting technique, to meet the needs of actual product.
Invention content
The purpose of the present invention is to provide the EEG signals data classification methods under a kind of complicated mood scene, in solution
State the problem of being proposed in background technology.
To achieve the above object, the present invention provides the following technical solutions：
A kind of EEG signals data classification method under complexity mood scene, includes the following steps：
(4) initial data is acquired：Allow testee's several minutes tranquil first, later by different filmlet guiding by
The mood of survey person acquires real-time EEG signals data, collects several data and then terminates to test；
(5) data application being collected normalization is pre-processed：The data application being collected normalization is carried out pre-
Processing, reduces the time complexity of the data operation of this method；
(6) after data are pre-processed, data are subjected to Fast Fourier Transform (FFT) first, it is right later such as formula [1]
Data after operation carry out principal component analysis, and the result of formula [1] is brought into the covariance formula of Principal Component Analysis Algorithm, sample
This training sample set, which is { X (1), X (2) ..., X (K) }, can obtain formula [2], be finally completed entire data characteristics extraction work；
(4) tagsort operation is carried out using the KNN algorithms of weighting：The KNN algorithms of weighting can preferably solve multiclass
Data set classification problem and operation time complexity it is low.Algorithm assumes all examples all in N-dimensional space, each example
It is represented as feature vector<a1(x), a2(x) ... an(x)>Here ar(x) example r-th of attribute value of x is indicated, then two examples
Sub- xi, xjBetween similarity Euclidean distance may be used, if WjWeights are characterized, method of weighting uses the weighting that document proposes
Method, formula can be simplified as：
It is as a further solution of the present invention：The step (1) has chosen ten kinds of different complicated mood scenes altogether.
As the present invention, further scheme is：The calm time of testee is 10min- in the step (1)
20min。
The beneficial effects of the invention are as follows this method can effectively be used under each complicated mood scene for brain electricity number
According to effectively being classified, it can be widely used and be detected in medicine, be detected a lie and field of human-computer interaction.
Description of the drawings
Fig. 1 is the flow diagram of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, in the embodiment of the present invention, the EEG signals data classification method under a kind of complexity mood scene, packet
Include following steps：
(7) initial data is acquired：Allow testee's several minutes tranquil first, later by different filmlet guiding by
The mood of survey person acquires real-time EEG signals data, collects several data and then terminates to test；
(8) data application being collected normalization is pre-processed：The data application being collected normalization is carried out pre-
Processing, reduces the time complexity of the data operation of this method；
(9) after data are pre-processed, data are subjected to Fast Fourier Transform (FFT) first, it is right later such as formula [1]
Data after operation carry out principal component analysis (PCA), and the result of formula [1] is brought into the association of principal component analysis (PCA) algorithm
Formula of variance, the training sample set of sample, which is { X (1), X (2) ..., X (K) }, can obtain formula [2], and it is special to be finally completed entire data
Sign extraction work, the main purpose of the operation be reduced on the basis of effectively extraction data set features value data set dimension and
Reject the noise in data set so that can also be promoted while this method can greatly reduce the time complexity of operation final
Precision；
(4) tagsort operation is carried out using the KNN algorithms of weighting：The KNN algorithms of weighting can preferably solve multiclass
Data set classification problem and operation time complexity it is low.Algorithm assumes all examples all in N-dimensional space, each example
It is represented as feature vector<a1(x), a2(x) ... an(x)>Here ar(x) example r-th of attribute value of x is indicated, then two examples
Sub- xi, xjBetween similarity Euclidean distance may be used, if WjWeights are characterized, method of weighting uses the weighting that document proposes
Method, formula can be simplified as：
The step (1) has chosen ten kinds of different complicated mood scenes altogether.
The calm time of testee is 10min-20min in the step (1).
This method is tested the eeg data sorting technique under 10 kinds of complicated mood scenes, achieves good
As a result, in practice it has proved that this method, which can be effectively used under each complicated mood scene, effectively divides eeg data
Class can be widely used and be detected in medicine, be detected a lie and field of human-computer interaction.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Profit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent requirements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiment being appreciated that.
Claims (3)
1. the EEG signals data classification method under a kind of complexity mood scene, which is characterized in that include the following steps：
(1) initial data is acquired：Testee's several minutes tranquil first are allowed, testee is guided by different filmlets later
Mood, acquire real-time EEG signals data, collect several data and then terminate to test；
(2) data application being collected normalization is pre-processed：The data application being collected normalization is pre-processed,
Reduce the time complexity of the data operation of this method；
(3) after data are pre-processed, data are subjected to Fast Fourier Transform (FFT) first, such as formula [1], later for fortune
Data after calculation carry out principal component analysis, and the result of formula [1] is brought into the covariance formula of Principal Component Analysis Algorithm, sample
Training sample set is { X (1), X (2) ..., X (K) }, can obtain formula [2], is finally completed entire data characteristics extraction work；
(4) tagsort operation is carried out using the KNN algorithms of weighting：The KNN algorithms of weighting can preferably solve the number of multiclass
According to collection classification problem and operation time complexity it is low.Algorithm assumes all examples all in N-dimensional space, each example is by table
It is shown as feature vector<a1(x), a2(x) ... an(x)>Here ar(x) example r-th of attribute value of x is indicated, then two example xi,
xjBetween similarity Euclidean distance may be used, if WjWeights are characterized, method of weighting uses the method for weighting that document proposes,
Formula can be simplified as：
2. the EEG signals data classification method under a kind of complicated mood scene according to claim 1, which is characterized in that
The step (1) has chosen ten kinds of different complicated mood scenes altogether.
3. the EEG signals data classification method under a kind of complicated mood scene according to claim 1, which is characterized in that
The calm time of testee is 10min-20min in the step (1).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711418634.9A CN108288068A (en) | 2017-12-25 | 2017-12-25 | Electroencephalogram signal data classification method under complex emotion scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711418634.9A CN108288068A (en) | 2017-12-25 | 2017-12-25 | Electroencephalogram signal data classification method under complex emotion scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108288068A true CN108288068A (en) | 2018-07-17 |
Family
ID=62832278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711418634.9A Pending CN108288068A (en) | 2017-12-25 | 2017-12-25 | Electroencephalogram signal data classification method under complex emotion scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108288068A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117790A (en) * | 2018-08-14 | 2019-01-01 | 杭州电子科技大学 | A kind of brain line recognition methods based on frequency empty index |
| CN109656366A (en) * | 2018-12-19 | 2019-04-19 | 电子科技大学中山学院 | Emotional state identification method and device, computer equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105395192A (en) * | 2015-12-09 | 2016-03-16 | 恒爱高科(北京)科技有限公司 | Wearable emotion recognition method and system based on electroencephalogram |
| CN105894039A (en) * | 2016-04-25 | 2016-08-24 | 京东方科技集团股份有限公司 | Emotion recognition modeling method, emotion recognition method and apparatus, and intelligent device |
| CN107016345A (en) * | 2017-03-08 | 2017-08-04 | 浙江大学 | A kind of demand model construction method applied to Product Conceptual Design |
-
2017
- 2017-12-25 CN CN201711418634.9A patent/CN108288068A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105395192A (en) * | 2015-12-09 | 2016-03-16 | 恒爱高科(北京)科技有限公司 | Wearable emotion recognition method and system based on electroencephalogram |
| CN105894039A (en) * | 2016-04-25 | 2016-08-24 | 京东方科技集团股份有限公司 | Emotion recognition modeling method, emotion recognition method and apparatus, and intelligent device |
| CN107016345A (en) * | 2017-03-08 | 2017-08-04 | 浙江大学 | A kind of demand model construction method applied to Product Conceptual Design |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117790A (en) * | 2018-08-14 | 2019-01-01 | 杭州电子科技大学 | A kind of brain line recognition methods based on frequency empty index |
| CN109656366A (en) * | 2018-12-19 | 2019-04-19 | 电子科技大学中山学院 | Emotional state identification method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Harwath et al. | Jointly discovering visual objects and spoken words from raw sensory input | |
| CN110163180A (en) | Mental imagery eeg data classification method and system | |
| CN107157477A (en) | EEG signals Feature Recognition System and method | |
| CN106709469A (en) | Automatic sleep staging method based on multiple electroencephalogram and electromyography characteristics | |
| CN108932950A (en) | It is a kind of based on the tag amplified sound scenery recognition methods merged with multifrequency spectrogram | |
| CN110353673A (en) | A kind of brain electric channel selection method based on standard mutual information | |
| CN108776774A (en) | A kind of human facial expression recognition method based on complexity categorization of perception algorithm | |
| CN107066514A (en) | The Emotion identification method and system of the elderly | |
| KR100792016B1 (en) | Apparatus and method for character based video summarization by audio and video contents analysis | |
| CN105117708A (en) | Facial expression recognition method and apparatus | |
| CN110399846A (en) | A kind of gesture identification method based on multichannel electromyography signal correlation | |
| CN108256579A (en) | A kind of multi-modal sense of national identity quantization measuring method based on priori | |
| Zhu et al. | Emotion recognition from users' eeg signals with the help of stimulus videos | |
| Anand et al. | Convoluted feelings convolutional and recurrent nets for detecting emotion from audio data | |
| CN111046969A (en) | Data screening method and device, storage medium and electronic equipment | |
| CN112999490A (en) | Music healing system based on brain wave emotion recognition and processing method thereof | |
| CN110477914A (en) | Mood excitation and EEG signals Emotion identification system based on Android | |
| CN108288068A (en) | Electroencephalogram signal data classification method under complex emotion scene | |
| CN113116361A (en) | Sleep staging method based on single-lead electroencephalogram | |
| Chen et al. | Patient emotion recognition in human computer interaction system based on machine learning method and interactive design theory | |
| Alashban et al. | Speaker gender classification in mono-language and cross-language using BLSTM network | |
| CN111785262B (en) | Speaker age and gender classification method based on residual error network and fusion characteristics | |
| CN113569924A (en) | Emotion identification classification method based on support vector machine multi-core cooperation | |
| CN105787459B (en) | A kind of ERP Modulation recognition method based on the optimal sparse differentiation of scoring | |
| CN108205686A (en) | Video feeling sorting technique and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180717 |