CN105816181A - Reading behavior recognition method and equipment based on EOG - Google Patents
Reading behavior recognition method and equipment based on EOG Download PDFInfo
- Publication number
- CN105816181A CN105816181A CN201610140400.1A CN201610140400A CN105816181A CN 105816181 A CN105816181 A CN 105816181A CN 201610140400 A CN201610140400 A CN 201610140400A CN 105816181 A CN105816181 A CN 105816181A
- Authority
- CN
- China
- Prior art keywords
- reading
- eog
- signal
- eog signal
- character string
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4088—Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- 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
- A61B5/398—Electrooculography [EOG], e.g. detecting nystagmus; Electroretinography [ERG]
Abstract
The invention relates to a reading behavior recognition method and equipment based on EOG. The recognition method comprises the following steps: collecting an EOG signal of a person to be detected, and pretreating the collected EOG signal; performing endpoint detection, and recognizing a starting point and an ending point of an EOG signal reading state after pretreatment; performing string encoding on the obtained reading EOG signals through a wavelet packet change method; through an editing distance between the encoded character string and a template character string, realizing character string matching so as to obtain the recognized results. Being a reading disorder diagnosis assisting method, the reading behavior recognition method has the advantages of high recognition right rate, strong extensibility, high potential application value and the like.
Description
Technical field
The present invention relates to eye electricity (Electro-oculogram, EOG) technical field, be specifically related to a kind of reading behavior recognition methods based on EOG and equipment.
Background technology
Modern civilization, mainly with word as carrier, is read as a kind of important knowledge acquisition approach, and the development of its ability is the basis of other learning capacitys development.Reading disorder refer to patient on the premise of the educational opportunities having normal IQ, scholastic motivation and equality, in the difficulty obtaining a kind of persistence produced in terms of normal literacy.Reading disorder commonly betides in adult and child, and especially school age population, its incidence rate is about 5%-10%.Reading disorder not only influences whether the lifting of children for learning achievement, the most also can affect the self-confidence of child and the cultivation of social competence, and emotion and social development to child bring bigger harm.Therefore, how reading disorder screened effectively and diagnose, helping reading disabled child to overcome reading problem as far as possible, improve reading ability, form good reading habit, having important practical significance for promoting national cultural accomplishment.
Present stage, reading disorder is diagnosed main employing based on cognitive and the diagnostic mode of behavior, generally, during diagnosis, in order to improve accuracy rate, it will according to default reading task, by video method, the reading behavior of patient is carried out assistant analysis, including obtaining eye movement, reading the relevant information such as persistent period, reading speed, to judge the reading quality of patient.But, although traditional reading behavior based on video is analyzed method and used more convenient, but the method is affected relatively big by light, and in the case of dark or background environment change, systematic function can drastically decline, even cannot Correct Analysis.
Summary of the invention
The object of the invention is exactly for avoiding weak point present in above-mentioned prior art, it is provided that a kind of recognition correct rate is high, extended capability is strong, application potential is big a kind of based on EOG reading behavior recognition methods and equipment.The method, with EOG as detection means, can realize treating the identification of tester's read state, to assist doctor to judge patient's reading disorder degree.
A kind of reading behavior recognition methods based on EOG, this recognition methods comprises the following steps:
A), gather the horizontal EOG signal of person to be detected, and the EOG signal collected is carried out pretreatment, according to the number of words often gone in reading content, determine the error threshold of template character string and editing distance；
B), pretreated horizontal EOG signal is carried out end-point detection, to determine the starting point and ending point of horizontal EOG signal corresponding to read state；
C) the reading EOG signal obtained, in stepb, is encoded into a series of continuation character strings corresponding with ocular movement by wavelet package transforms；
D), in calculation procedure C obtained by continuation character string and step A in editing distance between the template character string preset, when the error threshold preset during this distance is less than step A, assert that person to be detected is in read state, otherwise, for non-read state.
The equipment of a kind of reading behavior identification based on EOG as claimed in claim 1, equipment includes that signals collecting and pretreatment module, described EOG signal collection and pretreatment module are used for being acquired EOG signal and EOG signal being carried out bandpass filtering operation；And the EOG signal after bandpass filtering is exported to reading endpoint detection module；
Described reading endpoint detection module identifies the starting point and ending point of the read state in EOG signal for the method combined by differential and energy；And by EOG signal output to reading Signal coding module；
Described reading Signal coding module is for being encoded to character string by wavelet package transforms method by reading EOG signal；Character string after coding exports to reading behavior identification module；
Described reading behavior identification module is for realizing string matching by the similarity between editing distance tolerance coded string and template character string, it is judged that whether person to be detected is in read state.
Compared with prior art, the technique effect that the present invention possesses is:
The original level EOG signal of collection is carried out noise-removed filtering pretreatment by the present invention, the starting point and ending point of read state in EOG signal is obtained again by end-point detection method, then wavelet package transforms is passed through, thresholding is set, the steps such as string encoding realize reading the coding of EOG signal, obtain the coded string of signal, similarity finally by editing distance tolerance template character string with coded string realizes string matching, judge whether person to be detected is in read state, recognition correct rate is high, and by a small amount of adjustment of the redesign of recognition template Yu algorithm parameter just can be realized the identification to multiple behavior state, there is stronger autgmentability.Additionally, the present invention uses EOG means to carry out reading behavior detection, the shortcoming that can effectively overcome conventional video method, likely replace traditional video detecting method, or as a kind of important the supplementing of conventional video detection method, the diagnosis of reading disorder has higher theoretical significance and potential using value.
Accompanying drawing explanation
Fig. 1 is the distribution of electrodes figure gathered for EOG signal in the present invention；
Fig. 2 is the horizontal EOG signal in the present invention under read state；
The logic diagram reading recognition methods in Fig. 3 present invention；
Fig. 4 is increment I and the value of ten groups of new thresholdings in the present invention；
Fig. 5 is to use ten groups of new thresholdings to carry out read state identification in the present invention to obtain optimum gate limit value；
Fig. 6 is the logic diagram reading endpoint detection module in the present invention；
Fig. 7 is the end-point detecting method process steps schematic diagram of EOG signal under natural reading normal form in the present invention；
Fig. 8 is the WAVELET PACKET DECOMPOSITION schematic diagram in the present invention；
Fig. 9 is reading EOG signal cataloged procedure in the present invention；
Figure 10 is to use string matching method to carry out the identification process schematic of read state in the present invention；
Figure 11 is that the reading recognition result of band tester in the present invention shows.
Detailed description of the invention
It is further described in conjunction with Fig. 1 to Figure 11 present invention:
A kind of reading behavior recognition methods based on EOG, this recognition methods comprises the following steps:
A), gather the horizontal EOG signal of person to be detected, and the EOG signal collected is carried out pretreatment, according to the number of words often gone in reading content, determine the error threshold of template character string and editing distance；
B), pretreated horizontal EOG signal is carried out end-point detection, to determine the starting point and ending point of horizontal EOG signal corresponding to read state；
C) the reading EOG signal obtained, in stepb, is encoded into a series of continuation character strings corresponding with ocular movement by wavelet package transforms；
D), in calculation procedure C obtained by continuation character string and step A in editing distance between the template character string preset, when the error threshold preset during this distance is less than step A, assert that person to be detected is in read state, otherwise, for non-read state.
The present invention uses reading behavior recognition methods based on EOG, method first uses 3 bioelectrode sensor acquisition original level EOG signal, and this signal is carried out noise-removed filtering pretreatment, the starting point and ending point of read state in EOG signal is obtained again by end-point detection method, then wavelet package transforms is passed through, thresholding is set, the steps such as string encoding realize reading the coding of EOG signal, obtain the coded string of signal, similarity finally by editing distance tolerance template character string with coded string realizes string matching, judge whether experimenter is in read state, recognition correct rate is high；
And, the present invention uses string matching method when realizing reading behavior identification, i.e. calculate the editing distance between the coded string of read state and template character string, the similarity between character string is weighed by editing distance, and judge whether to be in read state, stronger autgmentability can be had by the redesign of recognition template character string is adjusted, with a small amount of of algorithm parameter, the identification realized multiple behavior state；
Additionally, the present invention uses EOG means to carry out reading behavior detection, the shortcoming that can effectively overcome conventional video method, likely replace traditional video detecting method, or as a kind of important the supplementing of conventional video detection method, the diagnosis of reading disorder has higher theoretical significance and potential using value.
In described step A, gathered the horizontal EOG signal of person to be detected by 3 bioelectrodes, and EOG signal is carried out the 32 rank bandpass filtering pretreatment that cut-off frequency is 0.05Hz to 15Hz.
In described step B, using differential and energy method that pretreated EOG signal is carried out end-point detection, differential concretely comprises the following steps with energy method:
A), pretreated EOG signal is carried out framing and windowing process, pretreated EOG signal is carried out window a length of 1000, it is 1 (as a example by data sampling rate is as 250Hz that window moves, window length is set to 1000 sample points, window moves and is set to 1 sample point, and rule of thumb arranges original differential and energy threshold F0 and E0；
B), calculate differential value F in current sliding window, F is limited F0 with derivatives and compares；If F is ＞ F0, then this end points is considered as " reading possible starting point Si " of signal；Otherwise, then sliding window continues to slide backward；；
C), calculate the energy value E of signal in current sliding window, and it is compared with energy threshold E0；If E is ＜ E0, then this end electricity is " reading possible terminating point Ti " of signal；Otherwise, then sliding window continues to slide backward；
D) comprised EOG signal sample point number X between " reading possible starting point Si " and " reading possible terminating point Ti ", is calculated, as X ＞ 1000, i.e. when sample rate is 250Hz, between starting point and terminating point, interval was more than 4 seconds, " read possible starting point Si " and be reading starting point, " read possible terminating point Ti " and be reading terminating point, otherwise judge that this segment signal is as non-read state；
E), sliding window continue to slide, repeat step b to d operation until signal ended.
In described step C, being Haar function to read EOG signal carrying out the wavelet packet generating function in parcel wave conversion step, Decomposition order is 3 layers, and obtains choosing the 3rd coefficient wavelet packet coefficient as Optimal Wavelet Packet coefficient C from decomposition.
For to read EOG signal be configured limit the threshold value of step and be set to: S1、S2、L1、L2, according to these four threshold values to Optimal Wavelet Packet coefficient C divide as follows:
Non-glance district: S2＜ C ＜ S1
Little pan district: S1＜ C ＜ L1Or L2＜ C ＜ S2
Sweep greatly district: C ＞ L1Or C ＜ L2
Carry out in string encoding step reading EOG signal, when Optimal Wavelet Packet coefficient C is divided in " sweeping greatly district ", be encoded to L；When Optimal Wavelet Packet coefficient C is divided in " little pan district ", it is encoded to r；And Optimal Wavelet Packet coefficient C is when being divided in " non-glance district ", do not encode.
Described thresholding S1, S2, L1, L2, initial method is:
Step 1: the value of artificial observation Optimal Wavelet Packet coefficient C, and according to observed result, initial threshold is set as: 5 ,-5,60 ,-60, i.e. S1=5, S2=-5, L1=60, L2=-60.
Step 2: using variable I to represent the incremental change of thresholding, wherein the value of increment is respectively I=1,3,5,7,19.It is worth to ten groups of new threshold values by initial threshold numerically being increased different I, then is respectively adopted ten groups of new threshold values to how group reading EOG data are tested.
Step 3: be respectively adopted ten groups of new threshold values, in order to calculate the reading recognition correct rate reading EOG data, and reads recognition correct rate from the ten of gained and selects the group that accuracy is the highest, and threshold value corresponding to this group is optimum gate limit value.
In described step D, process to string matching is the editing distance between calculation code character string and template character string, is used for judging whether person to be detected is in read state, if editing distance is less than or equal to 1, then representing that this coded string is correctly validated, person to be detected is in read state；Otherwise, it means that person to be detected is in non-read state.
Seeing Fig. 1, the collection of EOG signal uses Ag/AgCl electrode, employs 3 electrode sensors altogether, wherein in order to gather the electrode H of horizontal EOG signal, may be installed at left eye (or right eye) outward flange distance eye pupil central authorities 4.5cm；Ground electrode G is installed on mastoid location after auris dextra, and reference electrode C is respectively arranged in mastoid location after left ear.
See Fig. 2, illustrate the original waveform of the horizontal EOG signal gathered in this example, more can reflect main eye movement characteristics when person to be detected reads due to horizontal EOG signal, so this patent uses horizontal EOG signal as the input signal of algorithm, S in Fig. 21Represent and sweep by a small margin, continuous reading process the most to the right, S2The most left produced pan when representing line feed, F represents the state of staring in reading process, and B represents state nictation in reading.
See Fig. 3, a kind of equipment of reading behavior identification based on EOG as claimed in claim 1, equipment includes that signals collecting and pretreatment module 10, described EOG signal collection are used for being acquired EOG signal and EOG signal being carried out bandpass filtering operation with pretreatment module 10；And the EOG signal after bandpass filtering is exported to reading endpoint detection module 20；
Described reading endpoint detection module 20 identifies the starting point and ending point of the read state in EOG signal for the method combined by differential and energy；And by EOG signal output to reading Signal coding module 30；
Described reading Signal coding module 30 is for being encoded to character string by wavelet package transforms method by reading EOG signal；Character string after coding exports to reading behavior identification module 40；
Described reading behavior identification module 40 is for realizing string matching by the similarity between editing distance tolerance coded string and template character string, it is judged that whether person to be detected is in read state..
See Fig. 4, obtain ten new increment I by incremental method, by four initial threshold S1=5, S2=-5, L1=60, L2=-60 are added with ten new increment I respectively, obtain ten groups of new threshold values.
See Fig. 5, the present embodiment use ten groups of new threshold values the reading EOG data of 6 persons to be detected are identified detection, in figure, abscissa represents ten values of increment I, vertical coordinate be every person to be detected gathered all read EOG data averagely read discrimination, as seen from the figure, starting when increment I is continuously increased, the reading discrimination of 6 persons to be detected increases the most therewith；When I increases to 13, read discrimination and reach maximum, and the average discrimination of reading of now 6 persons to be detected reaches to be 0.9678 to the maximum；But when I continues to increase, read discrimination and present downward trend on the contrary.Therefore when thresholding increment I is 13, and i.e. four threshold values are S1=18, S2=-18, L1=73, L2When=-73, reading discrimination and reach the highest, therefore these four threshold values are the optimum gate limit value of algorithm identification.
Seeing Fig. 6, owing to including read state and non-read state in original EOG signal, therefore needed tip spot check to record the read state comprised in signal before it is carried out read state identification operation, method mainly includes following step:
1), to EOG signal carry out framing windowing (window function is Hamming window, window a length of 1000, and it is 1 that window moves), and the initial value of differential and energy is set；
2), calculate the differential value of each frame signal, and compare with differential initial value, obtain " read may starting point "；
3), calculate the energy value of each frame signal, and compare with energy initial value, obtain " read may terminating point ".
4) interval between " reading possible starting point " and " reading possible terminating point ", is calculated, and the interval set is done (1000 sample points) and is contrasted, if x > 1000, it is determined that go out and read starting point and ending point, otherwise repeated execution of steps 2-4
Seeing Fig. 7, illustrate the end-point detection result figure of EOG signal in this example, Fig. 7 (a) represents one section of random natural reading EOG signal, and Fig. 7 (b) represents the differential of signal, and Fig. 7 (c) represents the energy of signal.
See Fig. 8, Fig. 8 (a) is one section of reading EOG signal randomly selected, Fig. 8 (b)-(o) is the decomposition coefficient figure of wavelet packet, wherein Fig. 8 (b), Fig. 8 (c) represents ground floor WAVELET PACKET DECOMPOSITION coefficient, Fig. 8 (d)-(g) represents second layer WAVELET PACKET DECOMPOSITION coefficient, Fig. 8 (h)-(o) represents third layer WAVELET PACKET DECOMPOSITION coefficient, by Tu Ke get, pan signal can substantially be distinguished by the wavelet packet coefficient represented by second node (as shown in Fig. 8 (i)) in third layer decomposition coefficient, this coefficient is called Optimal Wavelet Packet coefficient C.
Seeing Fig. 9, wherein Fig. 9 (a) is one section of reading EOG signal through pretreatment, Fig. 9 (b) be this EOG signal has been carried out WAVELET PACKET DECOMPOSITION after an Optimum wavelet coefficient C selecting, C is arranged four detection threshold S1、S2、 L1、L2, thus EOG signal is divided in three pan regions, Fig. 9 (c) carries out string encoding to reading EOG signal, and the character string that final reading EOG signal can contain " L " and " r " with continuous print characterizes.
Seeing Figure 10, the editing distance between calculation code character string and template character string is to realize string matching, if editing distance is less than or equal to 1, then it represents that this coded string is correctly validated, and person to be detected is in read state；Otherwise, person to be detected is in non-read state, thus conveniently detects the reading ability of person to be detected.
See Figure 11, illustrate the checking using the data of 6 persons to be detected to carry out reading recognizer in this example altogether, the most every person to be detected gathers 45 groups and reads data, often group reads the acquisition time of data is 5 minutes, in figure, abscissa table is every person to be detected numbering, vertical coordinate be every gathered total data of person to be detected averagely read discrimination, wherein, the reading EOG data average recognition rate minimum 81.14% of person NO.1 to be detected, and the average recognition rate of person NO.5 to be detected is up to 93.72%, the Mean accurate rate of recognition of 6 persons to be detected reaches 90.06%.
Claims (7)
1. a reading behavior recognition methods based on EOG, it is characterised in that: this recognition methods comprises the following steps:
A), gather the horizontal EOG signal of person to be detected, and the EOG signal collected is carried out pretreatment, according to the number of words often gone in reading content, determine the error threshold of template character string and editing distance；
B), pretreated horizontal EOG signal is carried out end-point detection, to determine the starting point and ending point of horizontal EOG signal corresponding to read state；
C) the reading EOG signal obtained, in stepb, is encoded into a series of continuation character strings corresponding with ocular movement by wavelet package transforms；
D), in calculation procedure C obtained by continuation character string and step A in editing distance between the template character string preset, when the error threshold preset during this distance is less than step A, assert that person to be detected is in read state, otherwise, for non-read state.
2. according to the reading behavior recognition methods based on EOG described in claim 1, it is characterized in that: in described step A, gathered the horizontal EOG signal of person to be detected by 3 bioelectrodes, and EOG signal is carried out the 32 rank bandpass filtering pretreatment that cut-off frequency is 0.05Hz to 15Hz.
Reading behavior recognition methods based on EOG the most according to claim 1 and 2, it is characterised in that: in described step B, using differential and energy method that pretreated EOG signal is carried out end-point detection, differential concretely comprises the following steps with energy method:
A), to pretreated EOG signal carry out framing and windowing process, and original differential and energy threshold F0 and E0 are rule of thumb set；
B), calculate the differential value F of signal in current sliding window, F is compared with differential thresholding F0；If F is ＞ F0, then this end points is considered as " reading possible starting point Si " of signal, otherwise, then sliding window continues to slide backward；
C), calculate the energy value E of signal in current sliding window, and it is compared with energy threshold E0；If E is ＜ E0, then this end electricity is " reading possible terminating point Ti " of signal, otherwise, then sliding window continues to slide backward；
D) comprised EOG signal sample point number X between " reading possible starting point Si " and " reading possible terminating point Ti ", is calculated, as X ＞ 1000, i.e. when sample rate is 250Hz, between starting point and terminating point, interval was more than 4 seconds, " read possible starting point Si " for reading starting point, " read possible terminating point Ti " and, for reading terminating point, otherwise judge that this segment signal is in non-read state；
E), sliding window continue to slide backward, repeat step b to d operation until signal ended.
Reading behavior recognition methods based on EOG the most according to claim 1, it is characterized in that: in described step C, it is Haar function to read EOG signal carrying out the wavelet packet generating function in wavelet package transforms step, Decomposition order is 3 layers, and obtain wavelet packet coefficient is chosen the 3rd coefficient as Optimal Wavelet Packet coefficient C from decomposition, and by pre-determined threshold S1、S2、L1、L2Gained Optimal Wavelet Packet coefficient C is divided as follows:
Non-glance district: S2＜ C ＜ S1
Little pan district: S1＜ C ＜ L1Or L2＜ C ＜ S2
Sweep greatly district: C ＞ L1Or C ＜ L2
Carry out in string encoding step reading EOG signal, when Optimal Wavelet Packet coefficient C is divided in " sweeping greatly district ", be encoded to L；When Optimal Wavelet Packet coefficient C is divided in " little pan district ", it is encoded to r；And Optimal Wavelet Packet coefficient C is when being divided in " non-glance district ", do not encode.
Reading behavior recognition methods based on EOG the most according to claim 4, it is characterised in that: described thresholding S1, S2, L1, L2Initial method is:
Step 1: the value of artificial observation Optimal Wavelet Packet coefficient C, and according to observed result, initial threshold is set as: 5 ,-5,60 ,-60, i.e. S1=5, S2=-5, L1=60, L2=-60；
Step 2: using variable I to represent the incremental change of thresholding, wherein the value of increment is respectively I=1,3,5,7 ..., 19.It is worth to ten groups of new threshold values by initial threshold numerically being increased different I, then is respectively adopted ten groups of new threshold values to how group reading EOG data are tested；
Step 3: be respectively adopted ten groups of new threshold values, in order to calculate the reading recognition correct rate reading EOG data, and reads recognition correct rate from the ten of gained and selects the group that accuracy is the highest, and threshold value corresponding to this group is optimum gate limit value.
Reading behavior recognition methods based on EOG the most according to claim 1, it is characterized in that: in described step D, editing distance between calculation code character string and template character string, for judging whether person to be detected is in read state, if editing distance is less than or equal to 1, then representing that this coded string is correctly validated, person to be detected is in read state；Otherwise, it means that person to be detected is in non-read state.
7. the equipment of a reading behavior identification based on EOG as claimed in claim 1, it is characterized in that: equipment includes that signals collecting and pretreatment module (10), described EOG signal collection and pretreatment module (10) are used for being acquired EOG signal and EOG signal being carried out bandpass filtering operation；And the EOG signal after bandpass filtering is exported to reading endpoint detection module (20)；
Described reading endpoint detection module (20) identifies the starting point and ending point of the read state in EOG signal for the method combined by differential and energy；And by EOG signal output to reading Signal coding module (30)；
Described reading Signal coding module (30) is for being encoded to character string by wavelet package transforms method by reading EOG signal；Character string after coding exports to reading behavior identification module (40)；
Described reading behavior identification module (40) is for realizing string matching by the similarity between editing distance tolerance coded string and template character string, it is judged that whether person to be detected is in read state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610140400.1A CN105816181A (en) | 2016-03-11 | 2016-03-11 | Reading behavior recognition method and equipment based on EOG |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610140400.1A CN105816181A (en) | 2016-03-11 | 2016-03-11 | Reading behavior recognition method and equipment based on EOG |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105816181A true CN105816181A (en) | 2016-08-03 |
Family
ID=56987169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610140400.1A Pending CN105816181A (en) | 2016-03-11 | 2016-03-11 | Reading behavior recognition method and equipment based on EOG |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105816181A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480716A (en) * | 2017-08-15 | 2017-12-15 | 安徽大学 | A kind of combination EOG and video pan signal recognition method and system |
| CN107480635A (en) * | 2017-08-15 | 2017-12-15 | 安徽大学 | A kind of pan signal recognition method and system based on the fusion of bimodal disaggregated model |
| CN108491792A (en) * | 2018-03-21 | 2018-09-04 | 安徽大学 | Office scene human-computer interaction Activity recognition method based on electro-ocular signal |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3794017A (en) * | 1971-01-08 | 1974-02-26 | G Servos | Automatic velocity component selector for electronystagmographs |
| CN101599127A (en) * | 2009-06-26 | 2009-12-09 | 安徽大学 | The feature extraction of electro-ocular signal and recognition methods |
| CN103054576A (en) * | 2012-12-20 | 2013-04-24 | 清华大学 | Method and device for reading state recognition based on electrooculogram signals |
| US20140327609A1 (en) * | 2011-08-19 | 2014-11-06 | Thomson Licensing | Method for gaze-controlled text size control, and methods for gaze-based measuring of a text reading speed and of a number of visual saccades per text line |
-
2016
- 2016-03-11 CN CN201610140400.1A patent/CN105816181A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3794017A (en) * | 1971-01-08 | 1974-02-26 | G Servos | Automatic velocity component selector for electronystagmographs |
| CN101599127A (en) * | 2009-06-26 | 2009-12-09 | 安徽大学 | The feature extraction of electro-ocular signal and recognition methods |
| US20140327609A1 (en) * | 2011-08-19 | 2014-11-06 | Thomson Licensing | Method for gaze-controlled text size control, and methods for gaze-based measuring of a text reading speed and of a number of visual saccades per text line |
| CN103054576A (en) * | 2012-12-20 | 2013-04-24 | 清华大学 | Method and device for reading state recognition based on electrooculogram signals |
Non-Patent Citations (2)
| Title |
|---|
| ZHAO LV，ET AL.: "An Algorithm for Reading Activity Recognition based on Electrooculogram", 《INFORMATION, COMMUNICATIONS AND SIGNAL PROCESSING(ICICS),2015 10TH INTERNATIONAL CONFERENCE ON》 * |
| 王波，吴小培: "基于EOG的扫视角度识别与分类的研究", 《信息技术及图像处理》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480716A (en) * | 2017-08-15 | 2017-12-15 | 安徽大学 | A kind of combination EOG and video pan signal recognition method and system |
| CN107480635A (en) * | 2017-08-15 | 2017-12-15 | 安徽大学 | A kind of pan signal recognition method and system based on the fusion of bimodal disaggregated model |
| CN107480635B (en) * | 2017-08-15 | 2020-09-18 | 安徽大学 | Glance signal identification method and system based on bimodal classification model fusion |
| CN107480716B (en) * | 2017-08-15 | 2021-01-29 | 安徽大学 | Method and system for identifying saccade signal by combining EOG and video |
| CN108491792A (en) * | 2018-03-21 | 2018-09-04 | 安徽大学 | Office scene human-computer interaction Activity recognition method based on electro-ocular signal |
| CN108491792B (en) * | 2018-03-21 | 2022-07-12 | 安徽大学 | Office scene human-computer interaction behavior recognition method based on electro-oculogram signals |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108186011A (en) | Atrial fibrillation detection method, device and readable storage medium storing program for executing | |
| CN107837082A (en) | Electrocardiogram automatic analysis method and device based on artificial intelligence self study | |
| CN108511055B (en) | Ventricular premature beat recognition system and method based on classifier fusion and diagnosis rules | |
| CN112353391A (en) | Electroencephalogram signal-based method and device for recognizing sound quality in automobile | |
| CN103989485A (en) | Human body fatigue evaluation method based on brain waves | |
| WO2005089431A2 (en) | Method, apparatus, and computer program product for stochastic psycho-physiological assessment of attentional impairments | |
| Deng et al. | Complexity extraction of electroencephalograms in Alzheimer's disease with weighted-permutation entropy | |
| CN113205074B (en) | Gesture recognition method fusing multi-mode signals of myoelectricity and micro-inertia measurement unit | |
| Ghislieri et al. | Long short-term memory (LSTM) recurrent neural network for muscle activity detection | |
| CN105816181A (en) | Reading behavior recognition method and equipment based on EOG | |
| CN107080545B (en) | A kind of lie detection system based on brain electricity | |
| CN110123342B (en) | Internet addiction detection method and system based on brain waves | |
| CN112869716B (en) | Pulse feature identification system and method based on two-channel convolutional neural network | |
| CN106446765A (en) | Health state evaluation system based on multidimensional physiological big data depth learning | |
| CN112732092A (en) | Surface electromyogram signal identification method based on double-view multi-scale convolution neural network | |
| JP2002541965A (en) | A method for detecting auditory evoked potentials using point optimized variation ratio | |
| CN111062021B (en) | Method and device for identity authentication based on wearable equipment | |
| CN114159079B (en) | Multi-type muscle fatigue detection method based on feature extraction and GRU deep learning model | |
| CN111067513A (en) | Sleep quality detection key brain area judgment method based on characteristic weight self-learning | |
| CN113343869A (en) | Electroencephalogram signal automatic classification and identification method based on NTFT and CNN | |
| CN115905827A (en) | Steam turbine fault diagnosis method and device based on neural network | |
| CN104545911B (en) | Method and system for detection of human physiological status transition | |
| CN106344008A (en) | Method and system for detecting waking state in sleep state analysis | |
| CN113729708A (en) | Lie evaluation method based on eye movement technology | |
| Najafi et al. | Sleep spindle detection in sleep EEG signal using sparse bump modeling |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160803 |
|
| RJ01 | Rejection of invention patent application after publication |