CN108965625A - A kind of automatic calling unit and its training method based on brain-computer interface - Google Patents
A kind of automatic calling unit and its training method based on brain-computer interface Download PDFInfo
- Publication number
- CN108965625A CN108965625A CN201810705313.5A CN201810705313A CN108965625A CN 108965625 A CN108965625 A CN 108965625A CN 201810705313 A CN201810705313 A CN 201810705313A CN 108965625 A CN108965625 A CN 108965625A
- Authority
- CN
- China
- Prior art keywords
- module
- brain
- value
- peak
- user
- 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.)
- Granted
Links
- 238000012549 training Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 title claims abstract description 16
- 210000004556 brain Anatomy 0.000 claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000001537 neural effect Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 241001269238 Data Species 0.000 claims description 2
- 230000003321 amplification Effects 0.000 claims description 2
- 230000005611 electricity Effects 0.000 claims description 2
- 210000002569 neuron Anatomy 0.000 claims description 2
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 230000003993 interaction Effects 0.000 abstract description 2
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 2
- 241001062009 Indigofera Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M11/00—Telephonic communication systems specially adapted for combination with other electrical systems
- H04M11/02—Telephonic communication systems specially adapted for combination with other electrical systems with bell or annunciator systems
- H04M11/022—Paging systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M11/00—Telephonic communication systems specially adapted for combination with other electrical systems
- H04M11/02—Telephonic communication systems specially adapted for combination with other electrical systems with bell or annunciator systems
- H04M11/027—Annunciator systems for hospitals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/90—Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2242/00—Special services or facilities
- H04M2242/04—Special services or facilities for emergency applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2242/00—Special services or facilities
- H04M2242/18—Automated outdialling systems
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Emergency Management (AREA)
- Environmental & Geological Engineering (AREA)
- Public Health (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Mobile Radio Communication Systems (AREA)
- Rehabilitation Tools (AREA)
Abstract
The present invention relates to a kind of automatic calling unit and its training method based on brain-computer interface, belongs to field of human-computer interaction.The present invention includes wireless headset, calling set.When user has call demand under certain conditions, wireless headset can be put on, open headset switch, wireless headset is sent user's brain wave acquisition in this case to calling set and by bluetooth, its internal brain-computer interface module parses the calling result of calling set generation according to the characteristic value of EEG signals.The design that the present invention combines brain-computer interface with neural network, so that the degree of automation of calling set increases, while providing great convenience for user, especially in user not very convenient in the action.The present apparatus has the advantages that easily and fast, and uses comparatively simple.
Description
Technical field
The present invention relates to automatic calling units and its training method based on brain-computer interface, belong to human-computer interaction technique field.
Background technique
Brain-computer interface is used as a kind of emerging communication device in recent years, by the concern of all circles.Brain-computer interface device can
The information of brain is preferably passed directly to the external world, and this process does not have to limbs and the participation of muscle and can complete.
It directly acts on external equipment after capable of parsing the EEG signals of brain, and external equipment can be according to the finger of EEG signals
Order goes to complete certain task.Especially in rehabilitation field, its application and research are more extensive.
RBF neural is suffered from many aspects and is widely applied, such as in terms of prediction, classification.Its mapping energy
Power be it is stronger, when its number of plies is suitable and its data volume of training is enough, it can approach a certain nonlinear function.
Traditional calling set is mostly to need hand-held calling set or caller is needed to call to platform is called, however right
In for people not very convenient in the action, just seeming, some are inconvenient.In addition, again due to face a danger situation when, user
Under this dangerous situation, it can be yelled for help automatically by wireless headset.Traditional calling set shows biggish inconvenience
Property, it is difficult to meet the needs of life.
Summary of the invention
The present invention provides a kind of automatic calling unit based on brain-computer interface, for solving traditional calling device for handicapped
Person's inconvenient problem with use.
Technical scheme is as follows: the calling set based on brain-computer interface, including wireless headset and calling set, described to exhale
Calling organ includes microprocessor, and there are display screen, button keys in surface；The microprocessor is used for the brain for carrying out wireless headset transmitting
Electric signal pre-processed, feature extraction, tagsort, the decision information of brain-computer interface is passed to institute by 4G network module
Call object；The display screen, button keys complete the work of input with display jointly.The wireless headset is for acquiring user
The EEG signals generated under certain circumstances.
Further, the calling set includes microprocessor and there are display screen, button keys in its surface；The microprocessor point
Not with preprocessing module, characteristic extracting module, tagsort module, bluetooth reception device, power module, 4G network module, deposit
Module is stored up to be connected.The preprocessing module is used to carry out denoising to the EEG signals that wireless headset transmitting comes and signal is put
Greatly；The characteristic extracting module is to the peak-peak of the EEG signals received, minimum peak, EEG signals fluctuation time
Deng characteristic value carry out analysis extraction；The tagsort module is used to exhale using rbf neural network algorithm progress decision user
The affair character value cried；The power module, which is used to run well to calling set, provides electric energy；The bluetooth reception device is used for
Receive the EEG signals that wireless headset is sent；Memory module is for storing information set by user；The 4G network module is used
In the communication with user institute call object.User's character trait value setting module feature introverted, export-oriented for user is set
It is fixed；Call object selecting module selects the object for needing to call for user；Institute's call object information storage module is for storing
Some information of institute's call object.
Further, the wireless headset includes the switching molding for integrating Bluetooth switch, power switch, brain wave acquisition and switching
Block, electrode module；It is described integrate Bluetooth switch, power switch, brain wave acquisition switch switch module for bluetooth choosing, electric
The function of source switch, brain wave acquisition switch；The electrode module is used for the EEG signals generated in head induction brain.
The training method of the above-mentioned automatic calling unit based on brain-computer interface is as follows: firstly, making tester general daily
The demand that calling is generated in life passes through spy using the EEG signals of wireless headset collecting test person under general even in everyday situations
Levy extraction module the EEG signals characteristics extraction of tester at this time, that is, peak-peak, minimum peak, EEG signals is big
Amplitude wave moves time value；The character trait value of this tester is set on calling set again；One group of training data is just obtained at this time, it is defeated
Entering data is peak-peak, minimum peak, EEG signals fluctuation time value, the character trait value of tester, output data
It is 1 for the corresponding characteristic value of ordinary circumstance；At least 500 different testers are tested under general even in everyday situations.Secondly, tight
It is tested in anxious situation, by tester's EEG signals characteristics extraction in case of emergency, and the property of setting tester
Lattice characteristic value, output in case of emergency are 2, and test at least 500 different testers.Finally, in ultra emergency situation
Under tested, by tester's EEG signals characteristics extraction in ultra emergency situation, and the personality of setting tester is special
Value indicative, the output in ultra emergency situation are 3, and test at least 500 different testers.According to the above test obtain to
Few 1500 groups of inputoutput datas come the rbf neural metwork training to the tagsort module of calling set, rbf neural network knot
Structure is as shown in Figure 2.Rbf neural network has a hidden layer, an input layer, an output layer, the output of hidden layer such as formula
(1) shown in
The i ∈ [1 10] in formula (1) indicates 10 neurons of first layer hidden layer；XcIt indicates in Gaussian function
Center value, it is one and X with dimension column vector；σiFor the width of Gaussian function；X is input vector group, as shown in formula (2):
Thus shown in the output such as formula (3) for obtaining the network:
Rbf is trained according at least 1500 groups of data provided above, carries out at least 1500 according to gradient descent method
Secondary repetitive exercise obtains final σi、Xc、ωi1。
Beneficial effects of the present invention: setting character trait value can be carried out on calling set according to the character trait of user and is used
The object of calling is thought at family, and by combining with brain-computer interface, provides very big convenience for user.
Detailed description of the invention
Fig. 1 is the schematic diagram of calling set；
Fig. 2 is the rbf neural network structure figure for tagsort module；
Fig. 3 is the calling set working principle diagram that training is completed.
Specific embodiment
Summary of the invention is described in detail with attached drawing combined with specific embodiments below.
Embodiment 1: this automatic calling unit includes wireless headset and calling set.As shown in Figure 1, including wireless headset and calling
Device has microprocessor inside the calling set, and the microprocessor is mentioned with bluetooth reception device, preprocessing module, feature respectively
Modulus block, tagsort module, 4G network module, power module are connected with memory module, and there are display screen and button keys in surface,
Corresponding operation can be completed according to corresponding prompt on a display screen, button keys are connected with internal microprocessor；The indigo plant
Tooth reception device is for receiving the EEG signals that wireless headset is sent；The preprocessing module is used for the brain telecommunications received
Number carry out denoising and signal amplification；The characteristic extracting module is for peak-peak, the minimum to the EEG signals received
Peak value and EEG signals fluctuation time carry out analysis extraction；The power module, which is used to run well to calling set, provides electricity
Energy；The tagsort module is used to carry out the object that decision user needs to call using rbf neural network；The memory module
For storing information set by user；The 4G network module is used for the communication with user institute call object
The wireless headset is used to acquire the brain electric information of user, is sent to calling set by bluetooth, to be supplied to calling
Microprocessor inside device is further processed；The microprocessor is for parsing the EEG signals received and being sent to
On the communication equipment of institute's call object.
The training method of the automatic calling unit of above-mentioned brain-computer interface, as shown in Figure 3, comprising the following steps:
Step 1: determining the character trait value of testee and set on the display screen of calling set, and setting property
Lattice characteristic value is x4；
Step 2: putting on wireless headset and open switch；
Step 3: EEG signals of the tester under certain specific environment being transmitted to calling set using wireless headset, are called
The characteristic extracting module of device by the EEG signals characteristics extraction of tester in such circumstances, i.e., the peak-peak of EEG signals,
Minimum peak, EEG signals fluctuation time value, simultaneously close off wireless headset switch, and set peak-peak, minimum peak,
EEG signals fluctuation time value is x1、x2、x3；
Step 4: corresponding affair character value under this specific environment is determined, if affair character value is yd；
Step 5: ideal output data of the characteristic value of calling set institute call event as tagsort module, maximum peak
Value, minimum peak, EEG signals fluctuation time, user's character trait value are input data, using these data to feature
The rbf neural network of module is trained；
Step 6: restarting the rbf neural metwork training for replacing different testers to tagsort module from step 1.
Embodiment 2: the calling set needs to use the information and event of the preceding call object that will likely be used in user
Information, according to accordingly prompt is stored on display screen, is referred to table 1,2 to complete, then according to itself personality in calling set
Feature carries out the setting of personality characteristic value and the setting of call object characteristic value, these settings are all corresponding on a display screen
The lower progress of prompt, as shown in Figure 1.Being stored under related technical personnel's guidance for information stores, as long as user is according to certainly
The personality feature of body carries out the setting of personality characteristic value and the setting of institute's call object, so that it may carry out calling and use.
The working principle of the invention: user use calling set before, set according to their own needs first the object of calling with
And set oneself character trait value x4And the storage of event information and institute's call object information, the storage of this information can be with
It is completed under the guidance of related technical personnel referring to table 1,2.
The 1 call object list of feature values of table
| Institute's call object characteristic value | Institute's call object name | Institute's call object contact method |
| 0 | Father | *** |
| 1 | Mother | *** |
| 2 | Elder brother | *** |
| 3 | Elder sister | *** |
| 4 | Younger brother | *** |
| 5 | Younger sister | *** |
| … | … | … |
2 Event Information Table of table
The characteristic value of event information needs consistent with affair character value when calling set training；Then, user puts on wirelessly
Earphone simultaneously opens switch, and when needing to call under certain conditions, wireless headset adopts the EEG signals of user in that case
Collection, calling set is sent to by blue-tooth device, microprocessor characteristic extracting module by the characteristics extraction of EEG signals, i.e.,
x1、x2、x3, according to trained rbf neural network can be obtained by the thing in the case of being presently in tagsort module
Part characteristic value, as shown in formula (4):
Y is the affair character value under present case, and control unit will be according to information corresponding to situation characteristic value in table 2
It is sent on the call object communication equipment of user preset by 4G module, user is using trained calling set schematic diagram as schemed
Shown in 2.
Embodiment 3: the use of the calling set is illustrated for when property is on the hazard.It is assumed that user
Property be on the hazard call request needed to help, user puts on wireless headset and opens switch, and the microprocessor of calling set will
The EEG signals that receive carry out feature extraction, in tagsort module trained rbf according to current input data
The affair character value for predicting present case is 2, and the microprocessor of calling set can carry out effective according to stored information
Communicate information to the communication device of institute's call object.
In use, when user, which is in, has call demand under certain specific environment, if user puts on wireless headset, and
And turn on the switch, it maintains 3 to 5 seconds, calling set can send call information from trend callee.
In above-mentioned use process, the step of needing user's Self-operating, is seldom, defeated in the information for institute's call object
Fashionable, user can voluntarily input, and the technical staff for providing product can also be allowed to complete.It is defeated for the information of institute's call object
Entering can be operated with reference table 1.Microprocessor can use the processor of ARM series.
Although comparing detailed description to the present invention in conjunction with attached drawing and subordinate list above, do not limited
System, so the present invention is not to be only limited to above embodiments.As long as on the basis of the present invention, and not carrying out other time and effort consumings
Work in the case where, be encompassed by scope of the presently claimed invention.
Claims (6)
1. a kind of automatic calling unit based on brain-computer interface, it is characterised in that: including wireless headset and calling set, the calling set
There is microprocessor in inside, and the microprocessor divides with bluetooth reception device, preprocessing module, characteristic extracting module, feature respectively
Generic module, 4G network module, power module are connected with memory module, and there are display screen and button keys in surface, on a display screen may be used
To complete corresponding operation according to corresponding prompt, button keys are connected with internal microprocessor；The bluetooth reception device is used
In the EEG signals that reception wireless headset is sent；The preprocessing module be used for the EEG signals received denoised with
And signal amplification；The characteristic extracting module is used for the peak-peak of the EEG signals received, minimum peak and brain telecommunications
Number fluctuation time carries out analysis extraction；The power module, which is used to run well to calling set, provides electric energy；The feature
Categorization module is used to carry out the object that decision user needs to call using RBF algorithm；The memory module is set for storing user
Fixed information；The 4G network module is used for the communication with user institute call object；
The wireless headset is used to acquire the brain electric information of user, calling set is sent to by bluetooth, to be supplied in calling set
The microprocessor in portion is further processed；The microprocessor is exhaled for parsing the EEG signals received and being sent to
It cries on the communication equipment of object.
2. a kind of training method of the automatic calling unit of brain-computer interface as described in claim 1, which is characterized in that including following
Step:
Step 1: determining the character trait value of testee and set on the display screen of calling set, and set personality spy
Value indicative is x4；
Step 2: putting on wireless headset and open switch；
Step 3: EEG signals of the tester under certain specific environment are transmitted to calling set using wireless headset, calling set
Characteristic extracting module is by the EEG signals characteristics extraction of tester in such circumstances, the i.e. peak-peak, minimum of EEG signals
Peak value, EEG signals fluctuation time value simultaneously close off wireless headset switch, and set peak-peak, minimum peak, brain electricity
Signal fluctuation time value is x1、x2、x3；
Step 4: corresponding affair character value under this specific environment is determined, if affair character value is yd；
Step 5: ideal output data of the characteristic value of calling set institute call event as tagsort module, peak-peak, most
Small leak, EEG signals fluctuation time, user's character trait value are input data, using these data to characteristic module
Rbf neural network is trained；
Step 6: restarting the rbf neural metwork training for replacing different testers to tagsort module from step 1.
3. the training method of the automatic calling unit according to claim 2 based on brain-computer interface, it is characterised in that: the property
The setting of lattice characteristic value and the setting of affair character value are completed by the prompt of calling set display screen, the spy of the event
Value indicative setting is only used for technical staff's training calling set, and ordinary user cannot use.
4. the training method of the automatic calling unit according to claim 2 based on brain-computer interface, it is characterised in that: the spy
Determine environment to be divided into three classes: ordinary circumstance, emergency and ultra emergency situation, and it is 1 that ordinary circumstance, which takes affair character value, promptly
It is 2 that situation, which takes affair character value, and it is 3 that ultra emergency situation, which takes affair character value, and affair character value table can be stored in advance to be deposited
Storage unit, the herein definition of ordinary circumstance are the trifling minor matter that the needs encountered in daily life are sought help；Emergency definition
The case where being damaged for property or interests；Ultra emergency situation is defined as the case where life security is on the hazard.
5. the training method of the automatic calling unit according to claim 2 based on brain-computer interface, it is characterised in that: the property
It is the personality for indicating that comparison is introversive that lattice characteristic value, which includes 0,1,2,0, and 1 indicates neither introversive nor outgoing nature, and 2 indicate export-oriented
Personality, character trait value needs user according to the self-recognition in daily and people at one's side to evaluate.
6. the training method of the automatic calling unit according to claim 2 based on brain-computer interface, it is characterised in that: the spy
The rbf neural network of sign categorization module is trained specific steps are as follows: there are four inputs, one layer of hidden layer and one for this training algorithm
A output, hidden layer do radial basis function, the calculation formula of first layer hidden layer output with Gaussian function are as follows:
Wherein [1,10] i ∈ indicates 10 neurons of first layer hidden layer, XcIndicate the central value of Gaussian function, it is one
With X with dimension column vector, σiFor the width of Gaussian function, X is input vector group,
Thus the output of the network is obtained are as follows:
Wherein σi、XcAnd ωi1It is first random given, calculate the reality output y of first group of input data1, then declined according to gradient
Algorithm is updated σi、Xc、ωi1, continue second group, until all inputoutput datas are to the instruction of rbf neural network
Practice and complete, obtains final σi、Xc、ωi1?.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810705313.5A CN108965625B (en) | 2018-07-02 | 2018-07-02 | Automatic calling device based on brain-computer interface and training method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810705313.5A CN108965625B (en) | 2018-07-02 | 2018-07-02 | Automatic calling device based on brain-computer interface and training method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108965625A true CN108965625A (en) | 2018-12-07 |
| CN108965625B CN108965625B (en) | 2020-07-31 |
Family
ID=64484527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810705313.5A Active CN108965625B (en) | 2018-07-02 | 2018-07-02 | Automatic calling device based on brain-computer interface and training method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108965625B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1833616A (en) * | 2005-12-15 | 2006-09-20 | 西安交通大学 | Multi-conduction brain biological information feedback instrument |
| CN101159086A (en) * | 2007-11-22 | 2008-04-09 | 中国人民解放军国防科学技术大学 | Calling device based on brain electric information demodulation |
| CN101641660A (en) * | 2007-03-23 | 2010-02-03 | 诺基亚公司 | Apparatus, method and computer program product providing a hierarchical approach to command-control tasks using a brain-computer interface |
| CN104503571A (en) * | 2014-12-16 | 2015-04-08 | 重庆邮电大学 | Idea collection device, telephone terminal and system based on brain computer interface |
| CN105302297A (en) * | 2015-09-16 | 2016-02-03 | 国网山东东营市东营区供电公司 | Cell-phone interacting method via brain wave Bluetooth earphone |
| US20160235324A1 (en) * | 2015-02-14 | 2016-08-18 | Massachusetts Institute Of Technology | Methods, Systems, and Apparatus For Self-Calibrating EEG Neurofeedback |
| CN106205048A (en) * | 2016-07-21 | 2016-12-07 | 山东大学 | Stupor automatic alarm system based on brain-computer interface and alarm method |
-
2018
- 2018-07-02 CN CN201810705313.5A patent/CN108965625B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1833616A (en) * | 2005-12-15 | 2006-09-20 | 西安交通大学 | Multi-conduction brain biological information feedback instrument |
| CN101641660A (en) * | 2007-03-23 | 2010-02-03 | 诺基亚公司 | Apparatus, method and computer program product providing a hierarchical approach to command-control tasks using a brain-computer interface |
| CN101159086A (en) * | 2007-11-22 | 2008-04-09 | 中国人民解放军国防科学技术大学 | Calling device based on brain electric information demodulation |
| CN104503571A (en) * | 2014-12-16 | 2015-04-08 | 重庆邮电大学 | Idea collection device, telephone terminal and system based on brain computer interface |
| US20160235324A1 (en) * | 2015-02-14 | 2016-08-18 | Massachusetts Institute Of Technology | Methods, Systems, and Apparatus For Self-Calibrating EEG Neurofeedback |
| CN105302297A (en) * | 2015-09-16 | 2016-02-03 | 国网山东东营市东营区供电公司 | Cell-phone interacting method via brain wave Bluetooth earphone |
| CN106205048A (en) * | 2016-07-21 | 2016-12-07 | 山东大学 | Stupor automatic alarm system based on brain-computer interface and alarm method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108965625B (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111209885B (en) | Gesture information processing method and device, electronic equipment and storage medium | |
| CN103699226B (en) | A kind of three mode serial brain-computer interface methods based on Multi-information acquisition | |
| CN109964226A (en) | Electronic device and its control method | |
| CN106419864A (en) | Cloud expert system for TCM diagnosis | |
| CN103425249A (en) | Electroencephalogram signal classifying and recognizing method based on regularized CSP and regularized SRC and electroencephalogram signal remote control system | |
| CN105615901A (en) | Emotion monitoring method and system | |
| CN111544015B (en) | Cognitive power-based control work efficiency analysis method, device and system | |
| CN107822645B (en) | Emotion recognition method based on WiFi signal | |
| CN112488002B (en) | Emotion recognition method and system based on N170 | |
| CN109448815A (en) | Self-service body building method, device, computer equipment and storage medium | |
| KR102015097B1 (en) | Apparatus and computer readable recorder medium stored program for recognizing emotion using biometric data | |
| CN113208593A (en) | Multi-modal physiological signal emotion classification method based on correlation dynamic fusion | |
| Kwon et al. | Hands-free human activity recognition using millimeter-wave sensors | |
| CN106166065A (en) | A kind of wearable electrocardio health interacting platform based on social networks and its implementation | |
| CN110610754A (en) | Immersive wearable diagnosis and treatment device | |
| CN108958620A (en) | A kind of dummy keyboard design method based on forearm surface myoelectric | |
| CN110141258A (en) | A kind of emotional state detection method, equipment and terminal | |
| Zhang et al. | Real-time activity and fall risk detection for aging population using deep learning | |
| CN114661161A (en) | Gesture interaction method, device and system, wearable device and storage medium | |
| CN104809371A (en) | Device and method for determining validity of authentication information of head-wearing intelligent device | |
| Mariano et al. | An accelerometer-based human computer interface driving an alternative communication system | |
| CN116687409B (en) | Emotion recognition method and system based on digital twin and deep learning | |
| Mesanza et al. | Machine learning based fall detector with a sensorized tip | |
| KR20190080598A (en) | System for recognizing emotion using biometric data and method thereof | |
| CN210697629U (en) | Signal acquisition device, mobile terminal and signal analysis system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |