CN109190658A - Video degree of awakening classification method, device and computer equipment - Google Patents
Video degree of awakening classification method, device and computer equipment Download PDFInfo
- Publication number
- CN109190658A CN109190658A CN201810794177.1A CN201810794177A CN109190658A CN 109190658 A CN109190658 A CN 109190658A CN 201810794177 A CN201810794177 A CN 201810794177A CN 109190658 A CN109190658 A CN 109190658A
- Authority
- CN
- China
- Prior art keywords
- video
- awakening
- data
- electroencephalogram
- degree
- 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
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
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06F18/2136—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on sparsity criteria, e.g. with an overcomplete basis
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Abstract
The invention discloses a kind of video degree of awakening classification method, device and and computer equipment, wherein classification method includes the following steps: step 1: collecting test person watch video when EEG signal, obtain EEG data；Step 2: the EEG data of acquisition is standardized by column；Step 3: feature selecting is carried out to the EEG data after standardization, obtains electroencephalogram characteristic of division；Step 4: the classification of video degree of awakening is carried out to video according to the electroencephalogram characteristic of division obtained.The embodiment of the present invention is by being standardized collected data, then using SBMLR algorithm the data after standardization are carried out with the electroencephalogram characteristic of division extracted from EEG signal, classify again according to electroencephalogram characteristic of division to video, improves the degree of awakening classification accuracy of video.
Description
Technical field
The present invention relates to emotion recognition technical field more particularly to a kind of video degree of awakening classification methods, device and calculating
Machine equipment.
Background technique
Recessive affection computation is a cross discipline for coming in grow up, it is intended to watch video, music etc. using the mankind
Collected brain corresponding signal identifies the emotion in video, music when multimedia, is related to computation vision, engineering
The multiple fields such as habit.The degree of awakening identification of video is the pith in recessive affection computation, for measuring the density of emotion,
The degree of big capsules of brain video-enable is characterized, the low expression brain of video degree of awakening is activated, and degree is low, inactive, and video cannot allow
Brain is interested, and degree of awakening height expression brain is activated, and degree is high, relatively more active, and video can allow brain interested, video awakening
Degree identification has a wide range of applications future in fields such as visual classification, retrieval, video ads designs.
However video degree of awakening analysis accuracy rate of the tradition based on EEG signal be not high, traditional electroencephalogram time domain is special
Frequency domain character of seeking peace fails to get effective characteristic of division from a large amount of EEG data, also far from the practical need of satisfaction
It wants, there are also very big rooms for promotion for the video degree of awakening classification accuracy based on EEG signal.
Summary of the invention
The embodiment of the present invention provides a kind of video degree of awakening classification method, device and computer equipment, existing to solve
The not high problem of video degree of awakening classification accuracy present in technology.
In a first aspect, provided in an embodiment of the present invention, described method includes following steps:
Step 1: collecting test person watches EEG signal when video, obtains EEG data；
Step 2: the EEG data of acquisition is standardized by column；
Step 3: feature selecting is carried out to the EEG data after standardization, obtains electroencephalogram characteristic of division；
Step 4: the classification of video degree of awakening is carried out to video according to the electroencephalogram characteristic of division obtained.
Optionally, in the step 1: collecting test person watches EEG signal when video, obtains EEG data,
It include: by several electroencephalogram acquisition channels, collecting test person watches EEG signal when several videos, obtains each
The corresponding EEG data of acquisition channel.
Optionally, in the step 2, to collected EEG data by the method that is standardized of column are as follows:
The EEG data of each electroencephalogram acquisition channel acquisition is standardized using the first formula by column respectively.
Optionally, in the step 3, EEG Characteristics are obtained method particularly includes: utilize SBMLR algorithm from each brain
Electroencephalogram characteristic of division is selected in data after the standardization of electrograph acquisition channel.
Optionally, described that the classification of video degree of awakening is carried out to video method particularly includes: according to the electroencephalogram characteristic of division
The video degree of awakening of each video is labeled, carries out the classification of video degree of awakening according to annotation results.
Optionally, first formula are as follows:
D (j)=(D (j)-μ (D (j)))/σ (D (j))；
D (j), j indicate that columns, D (j) indicate that the column data of j-th of electroencephalogram acquisition channel acquisition, μ (D (j)) indicate D
(j) average value of data, σ (D (j)) indicate the standard deviation of D (j) data.
Second aspect, the embodiment of the present invention provide a kind of video degree of awakening sorter, comprising:
EEG signal acquisition module watches EEG signal when several videos for collecting test person, obtains brain electricity
Diagram data；
Processing module is standardized the EEG data of acquisition by column；
Selecting module carries out feature selecting to the EEG data after standardization, obtains electroencephalogram characteristic of division；
Categorization module, for carrying out the classification of video degree of awakening to video according to the electroencephalogram characteristic of division obtained.
Optionally, the EEG signal acquisition module specifically includes several electroencephalogram acquisition channels, each electroencephalogram
EEG signal when acquisition channel watches several videos for collecting test person, to obtain each acquisition channel corresponding brain electricity
Diagram data.
Optionally, the processing module, specifically for respectively to the EEG data benefit of each electroencephalogram acquisition channel acquisition
It is standardized with the first formula by column.
Optionally, the selecting module, specifically for utilizing standard of the SBMLR algorithm from each electroencephalogram acquisition channel
Change and selects electroencephalogram characteristic of division in treated data.
Optionally, the categorization module, specifically for being awakened according to video of the electroencephalogram characteristic of division to each video
Degree is labeled, and carries out the classification of video degree of awakening according to annotation results.
The third aspect, the embodiment of the present invention provide a kind of computer equipment, including memory, processor and are stored in institute
The computer program that can be run on memory and on the processor is stated, it is real when the computer program is executed by processor
The step of method described in existing above-mentioned any one.
The embodiment of the present invention is by being standardized collected data, then using SBMLR algorithm to standard
Change treated data and carry out feature selecting, to extract electroencephalogram characteristic of division from EEG signal, then according to electroencephalogram
Characteristic of division classifies to video, improves the video degree of awakening classification accuracy of video.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are general for this field
Logical technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to this hair
Bright limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is the flow chart of first embodiment of the invention classification method；
Fig. 2 is the structural block diagram of second embodiment of the invention sorter；
Fig. 3 is third embodiment of the invention classification method flow chart.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing this public affairs in attached drawing
The exemplary embodiment opened, it being understood, however, that may be realized in various forms the disclosure without the implementation that should be illustrated here
Example is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the disclosure
Range is fully disclosed to those skilled in the art.
First embodiment of the invention provides a kind of video degree of awakening classification method, as shown in Figure 1, including walking in detail below
Rapid S101-S104:
S101: collecting test person watches EEG signal when video, obtains EEG data；
S102: the EEG data of acquisition is standardized by column；
S103: feature selecting is carried out to the EEG data after standardization, obtains electroencephalogram characteristic of division；
S104: the classification of video degree of awakening is carried out to video according to the electroencephalogram characteristic of division obtained.
The embodiment of the present invention is by being standardized collected data, then using SBMLR algorithm to standard
Change treated data and carry out feature selecting, to extract electroencephalogram characteristic of division from EEG signal, then according to electroencephalogram
Characteristic of division classifies to video, improves the video degree of awakening classification accuracy of video.
Second embodiment of the invention provides a kind of video degree of awakening classification method, includes the following steps:
S201: collecting test person watches EEG signal when video, obtains EEG data；
In this step, when watching several videos particular by several electroencephalograms acquisition channel collecting test person
EEG signal, obtain the corresponding EEG data of each acquisition channel；Wherein the number of acquisition channel can be according to practical need
It sets.
S202: the EEG data of acquisition is standardized by column；
In this step, the first formula: D (j)=(D (j)-μ (D (j)))/σ (D (j)) is specifically utilized, it is logical to each acquisition
The EEG data of road acquisition is standardized by column, wherein j indicates that columns, D (j) indicate j-th of electroencephalogram acquisition
The column data of channel acquisition, μ (D (j)) indicate that the average value of D (j) data, σ (D (j)) indicate the standard deviation of D (j) data.
S203: feature selecting is carried out to the EEG data after standardization, obtains electroencephalogram characteristic of division；
In this step, specifically utilize SBMLR algorithm from the number after the standardization of each electroencephalogram acquisition channel
According to middle selection electroencephalogram characteristic of division.
S204: the classification of video degree of awakening is carried out to video according to the electroencephalogram characteristic of division obtained.
In this step, it is specifically labeled according to video degree of awakening of the electroencephalogram characteristic of division to each video,
The classification of video degree of awakening is carried out according to annotation results；Such as give a mark to video, the high video score of degree of awakening is high, awakening
It is low to spend low video score, classifies according to marking result to the degree of awakening of video, is divided into high low with degree of awakening of degree of awakening
's.Specific video can be music video or image/video.
In the present embodiment, the selection of electroencephalogram characteristic of division, specifically includes:
Assuming thatData set is represented, whereinFor n-th of input feature value, tn∈T
=t | t ∈ { 0,1 }c,||t||1It=1 } is corresponding desired output vector, wherein c presentation class classification number.Multinomial is patrolled
It collects to return and constructs generalized linear model using softmax reverse connection function, so that output is represented as the probability priori of class members
Estimation, formula are as follows:
Assuming that D represents the independent same distribution sample set from condition multinomial distribution, then measured as data mismatch
Negative log-likelihood function can be write as:
Parameter w=(the w of multinomial logistic regression1, w2..., wd) can be looked for by maximizing the likelihood score of training sample
It arrives, or equally minimizes the negative likelihood logarithm of training sample, by negative log-likelihood function EDOn the basis of add canonical
Change item to introduce sparse model.Therefore, the estimation of parameter w is quasi- by minimizing the maximum likelihood training with penalty coefficient
Then provide
Wherein, α is a regularization parameter, the balance of control biasing variance.In a minimum point of L, L relative to
The partially reciprocal of model parameter will be zero to get arriving without exception
If negative log-likelihood is about model parameter wijSusceptibility be lower than α, then the value of the parameter will be arranged accurately
It is zero, and corresponding input feature vector will be trimmed away from model, it is final to obtain electroencephalogram characteristic of division.
On the basis of above-mentioned second embodiment, it is further proposed that the modification of above-described embodiment.
In third embodiment of the invention, the number of data acquisition channel is 32, and video number is 40, each data
EEG data when acquisition channel collecting test person watches each video in 1 minute, wherein each data acquisition channel 1 divides
The data length acquired in clock is 8064, and long column are 8064.
The collected data of each data acquisition channel are standardized by column；Then using SBMLR algorithm to mark
Data after standardization carry out feature selecting, obtain each EEG data acquisition channel of tester for the brain electricity of 40 videos
Figure characteristic of division；Felt using the video that the corresponding electroencephalogram characteristic of division of each electroencephalogram acquisition channel watches video to tester
Awake degree is classified；The brain electricity of each electroencephalogram acquisition channel of the tester is calculated using algorithm of support vector machine simultaneously
Figure characteristic of division to the degree of awakening classification accuracies of 40 videos, feel by the video for then obtaining 32 electroencephalogram acquisition channels
Degree classification accuracy of waking up is averaged, and obtains this tester EEG data to the degree of awakening classification accuracy of 40 videos.
In order to keep classification results relatively reliable, one shares 32 testers and implemented in conjunction with Fig. 3 in the present embodiment
Journey is as follows:
1, EEG signal standardization:
The when watching N number of video to i-th testerjThe EEG data D of a electroencephalogram acquisition channel acquisition by arrange into
Row standardization, standardization formula are as follows:
D (j)=(D (j)-μ (D (j)))/σ (D (j)) (1)
2, feature selecting is carried out to EEG signal:
To i-th testerjData D after a electroencephalogram acquisition channel standardization carries out D using SBMLR algorithm
Feature selecting obtains i-th testerjThe EEG Characteristics Feature of a electroencephalogram acquisition channel.SBMLR is a kind of base
In the sparse polynomial logistic regression algorithm of Bayesian regularization, selection algorithm is based on the embedding of sparse polynomial logistic regression
Enter formula selection algorithm.Principle is as follows:
Assuming thatData set is represented, whereinFor n-th of input feature value, tn∈T
=t | t ∈ { 0,1 }c,||t||1It=1 } is corresponding desired output vector, wherein c presentation class classification number.Multinomial is patrolled
It collects to return and constructs a generalized linear model using softmax reverse connection function, output is made to be represented as the probability of class members
Prior estimate.
Assuming that D represents the independent same distribution sample set from condition multinomial distribution, then being used as data mismatch degree
The negative log-likelihood function of amount can be write as
Parameter w=(the w of its multinomial logistic regression1, w2..., wd) likelihood score of maximization training sample can be passed through
Find, or equally minimize training sample negative likelihood logarithm, however the model generated in this way be it is fully dense, strictly
For no one of model parameter w element be accurately be zero.Ideally, it is desirable to which obtained model is to be based on containing
The sub-fraction feature of most information, and extra feature will be trimmed from model.By in negative log-likelihood function ED
On the basis of can introduce sparse model plus regularization term.Therefore, the estimation of parameter w is by minimizing one with punishment system
Several maximum likelihood training criterion provide:
Wherein, α is a regularization parameter, controls the balance for biasing variance.In a minimum point of L, L is opposite
Partially reciprocal in model parameter will be zero to get arriving without exception
If negative log-likelihood is about model parameter wijSusceptibility be lower than α, then the value of the parameter will be arranged accurately
It is zero, and corresponding input feature vector will be trimmed away from model, that is, achieve the purpose that feature selecting.
3, video degree of awakening is classified:
Using the corresponding electroencephalogram characteristic of division Feature of j-th electroencephalogram acquisition channel to N number of view of the tester
The degree of awakening of frequency is classified；J-th of electroencephalogram acquisition channel of i-th tester is obtained using algorithm of support vector machine simultaneously
Degree of awakening classification accuracy of the feature Feature to N number of video, the vision sorter for then obtaining V electroencephalogram acquisition channel
Accuracy rate is averaged, and obtains i-th tester EEG data to the degree of awakening classification accuracy of N number of video.
When being classified using support vector machines to j-th of electroencephalogram acquisition channel data of i-th tester, we are adopted
Cross validation is rolled over M, i.e., j-th of electroencephalogram acquisition channel data of i-th tester are divided into M parts, every time using M-1 parts of works
It is input in algorithm of support vector machine for training set, remaining 1 part is tested as test set, is repeated M times, is guaranteed every number
According to being all tested, M test result is averaged, obtains j-th of electroencephalogram acquisition channel data pair of i-th tester
The classification accuracy of video degree of awakening.
EEG data is acquired by multiple electroencephalogram acquisition channels in the embodiment of the present invention, obtains data more
Completely, the accuracy rate of video degree of awakening classification comprehensively, is improved.
Four embodiment of the invention provides a kind of computer equipment, including memory, processor and is stored in described deposit
On reservoir and the computer program that can run on the processor, realized such as when the computer program is executed by processor
Lower step:
Step 1: collecting test person watches EEG signal when video, obtains EEG data；
Step 2: the EEG data of acquisition is standardized by column；
Step 3: feature selecting is carried out to the EEG data after standardization, obtains electroencephalogram characteristic of division；
Step 4: the classification of video degree of awakening is carried out to video according to the electroencephalogram characteristic of division obtained.
The specific embodiment process of above method step can be found in one embodiment, second embodiment or third
Embodiment, it is no longer repeated herein for the present embodiment.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant be intended to it is non-
It is exclusive to include, so that the process, method, article or the device that include a series of elements not only include those elements,
It but also including other elements that are not explicitly listed, or further include for this process, method, article or device institute
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or device including the element.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but many situations
It is lower the former be more preferably embodiment.Based on this understanding, technical solution of the present invention is substantially in other words to the prior art
The part to contribute can be embodied in the form of software products, which is stored in a storage and is situated between
In matter (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal (can be mobile phone, computer, clothes
Business device, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned tools
Body embodiment, the above mentioned embodiment is only schematical, rather than restrictive, the ordinary skill of this field
Personnel under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, can also make
Many forms, all of these belong to the protection of the present invention.
Claims (10)
1. a kind of video degree of awakening classification method, which is characterized in that described method includes following steps:
Step 1: collecting test person watches EEG signal when video, obtains EEG data；
Step 2: the EEG data of acquisition is standardized by column；
Step 3: feature selecting is carried out to the EEG data after standardization, obtains electroencephalogram characteristic of division；
Step 4: the classification of video degree of awakening is carried out to video according to the electroencephalogram characteristic of division obtained.
2. the video degree of awakening classification method based on EEG signal as described in claim 1, which is characterized in that the step
In one: collecting test person watches EEG signal when video, obtains EEG data, specifically includes: passing through several brains electricity
Figure acquisition channel, collecting test person watch EEG signal when several videos, obtain the corresponding electroencephalogram of each acquisition channel
Data.
3. the video degree of awakening classification method based on EEG signal as claimed in claim 2, which is characterized in that the step
In two, to collected EEG data by the method that is standardized of column are as follows: adopted respectively to each electroencephalogram acquisition channel
The EEG data of collection is standardized using the first formula by column.
4. the video degree of awakening classification method based on EEG signal as claimed in claim 3, which is characterized in that the step
In three, EEG Characteristics are obtained method particularly includes: using SBMLR algorithm from the standardization of each electroencephalogram acquisition channel
Electroencephalogram characteristic of division is selected in data afterwards.
5. the video degree of awakening classification method based on EEG signal as described in claim 1, which is characterized in that described pair of view
Frequency carries out the classification of video degree of awakening method particularly includes: is carried out according to video degree of awakening of the electroencephalogram characteristic of division to each video
Mark carries out the classification of video degree of awakening according to annotation results.
6. the video degree of awakening classification method based on EEG signal as claimed in claim 3, which is characterized in that described first
Formula are as follows:
D (j)=(D (j)-μ (D (j)))/σ (D (j))；
Wherein, j indicates that columns, D (j) indicate that the column data of j-th of electroencephalogram acquisition channel acquisition, μ (D (j)) indicate D (j) number
According to average value, σ (D (j)) indicate D (j) data standard deviation.
7. a kind of video degree of awakening sorter characterized by comprising
EEG signal acquisition module watches EEG signal when several videos for collecting test person, obtains electroencephalogram number
According to；
Processing module is standardized the EEG data of acquisition by column；
Selecting module carries out feature selecting to the EEG data after standardization, obtains electroencephalogram characteristic of division；
Categorization module, for carrying out the classification of video degree of awakening to video according to the electroencephalogram characteristic of division obtained.
8. video degree of awakening sorter as claimed in claim 7, which is characterized in that the selecting module is specifically used for benefit
Electroencephalogram characteristic of division is selected from the data after the standardization of each electroencephalogram acquisition channel with SBMLR algorithm.
9. video degree of awakening sorter as claimed in claim 7, which is characterized in that the categorization module is specifically used for root
It is labeled according to video degree of awakening of the electroencephalogram characteristic of division to each video, carries out video degree of awakening point according to annotation results
Class.
10. a kind of computer equipment, which is characterized in that including memory, processor and be stored on the memory and can be
The computer program run on the processor is realized when the computer program is executed by processor as in claim 1 to 6
The step of method described in any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810794177.1A CN109190658A (en) | 2018-07-19 | 2018-07-19 | Video degree of awakening classification method, device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810794177.1A CN109190658A (en) | 2018-07-19 | 2018-07-19 | Video degree of awakening classification method, device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109190658A true CN109190658A (en) | 2019-01-11 |
Family
ID=64936280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810794177.1A Pending CN109190658A (en) | 2018-07-19 | 2018-07-19 | Video degree of awakening classification method, device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190658A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109998525A (en) * | 2019-04-03 | 2019-07-12 | 哈尔滨理工大学 | A kind of arrhythmia cordis automatic classification method based on discriminate depth confidence network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268577A (en) * | 2014-06-27 | 2015-01-07 | 大连理工大学 | Human body behavior identification method based on inertial sensor |
| US20150313496A1 (en) * | 2012-06-14 | 2015-11-05 | Medibotics Llc | Mobile Wearable Electromagnetic Brain Activity Monitor |
| CN107080546A (en) * | 2017-04-18 | 2017-08-22 | 安徽大学 | Mood sensing system and method, the stimulation Method of Sample Selection of teenager's Environmental Psychology based on electroencephalogram |
| CN107292296A (en) * | 2017-08-04 | 2017-10-24 | 西南大学 | A kind of human emotion wake-up degree classifying identification method of use EEG signals |
| CN108205686A (en) * | 2017-12-06 | 2018-06-26 | 中国电子科技集团公司电子科学研究院 | Video feeling sorting technique and device |
-
2018
- 2018-07-19 CN CN201810794177.1A patent/CN109190658A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150313496A1 (en) * | 2012-06-14 | 2015-11-05 | Medibotics Llc | Mobile Wearable Electromagnetic Brain Activity Monitor |
| CN104268577A (en) * | 2014-06-27 | 2015-01-07 | 大连理工大学 | Human body behavior identification method based on inertial sensor |
| CN107080546A (en) * | 2017-04-18 | 2017-08-22 | 安徽大学 | Mood sensing system and method, the stimulation Method of Sample Selection of teenager's Environmental Psychology based on electroencephalogram |
| CN107292296A (en) * | 2017-08-04 | 2017-10-24 | 西南大学 | A kind of human emotion wake-up degree classifying identification method of use EEG signals |
| CN108205686A (en) * | 2017-12-06 | 2018-06-26 | 中国电子科技集团公司电子科学研究院 | Video feeling sorting technique and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109998525A (en) * | 2019-04-03 | 2019-07-12 | 哈尔滨理工大学 | A kind of arrhythmia cordis automatic classification method based on discriminate depth confidence network |
| CN109998525B (en) * | 2019-04-03 | 2022-05-20 | 哈尔滨理工大学 | Arrhythmia automatic classification method based on discriminant deep belief network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109558942B (en) | Neural network migration method based on shallow learning | |
| EP2528034B1 (en) | Image management device, image management method, program, recording medium, and integrated circuit | |
| CN106339416B (en) | Educational data clustering method based on grid fast searching density peaks | |
| CN111291261A (en) | Cross-domain recommendation method integrating label and attention mechanism and implementation system thereof | |
| CN109002492B (en) | Performance point prediction method based on LightGBM | |
| CN103810274B (en) | Multi-characteristic image tag sorting method based on WordNet semantic similarities | |
| Mellor et al. | Application of data mining to “big data” acquired in audiology: Principles and potential | |
| CN109448703A (en) | In conjunction with the audio scene recognition method and system of deep neural network and topic model | |
| CN110993102A (en) | Campus big data-based student behavior and psychological detection result accurate analysis method and system | |
| Ikawati et al. | Student behavior analysis to detect learning styles in Moodle learning management system | |
| Jiao et al. | Golf swing classification with multiple deep convolutional neural networks | |
| CN109086794A (en) | A kind of driving behavior mode knowledge method based on T-LDA topic model | |
| Vicari et al. | Model based clustering of customer choice data | |
| CN110957039A (en) | Campus psychological coaching method and device based on deep learning | |
| CN114358014A (en) | Work order intelligent diagnosis method, device, equipment and medium based on natural language | |
| Behnisch et al. | Urban data-mining: spatiotemporal exploration of multidimensional data | |
| CN109190658A (en) | Video degree of awakening classification method, device and computer equipment | |
| CN108804491A (en) | item recommendation method, device, computing device and storage medium | |
| CN114860922B (en) | Method for obtaining classification model of psychological assessment scale, screening method and system | |
| CN115358260A (en) | Electroencephalogram sleep staging method and device, electronic equipment and storage medium | |
| Mazarura | Topic modelling for short text | |
| CN112530546B (en) | Psychological pre-judging method and system based on K-means clustering and XGBoost algorithm | |
| Wade et al. | Identifying representative textual sources in blog networks | |
| CN111767402A (en) | Limited domain event detection method based on counterstudy | |
| Chuan et al. | An exploratory study on students’ performance classification using hybrid of decision tree and naïve Bayes approaches |
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 |
Application publication date: 20190111 |
|
| RJ01 | Rejection of invention patent application after publication |