CN107981997A - A kind of method for controlling intelligent wheelchair and system based on human brain motion intention - Google Patents
A kind of method for controlling intelligent wheelchair and system based on human brain motion intention Download PDFInfo
- Publication number
- CN107981997A CN107981997A CN201711184676.0A CN201711184676A CN107981997A CN 107981997 A CN107981997 A CN 107981997A CN 201711184676 A CN201711184676 A CN 201711184676A CN 107981997 A CN107981997 A CN 107981997A
- Authority
- CN
- China
- Prior art keywords
- wheelchair
- eeg
- eeg signals
- brain
- motion intention
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61G—TRANSPORT, PERSONAL CONVEYANCES, OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS; OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES
- A61G5/00—Chairs or personal conveyances specially adapted for patients or disabled persons, e.g. wheelchairs
- A61G5/04—Chairs or personal conveyances specially adapted for patients or disabled persons, e.g. wheelchairs motor-driven
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61G—TRANSPORT, PERSONAL CONVEYANCES, OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS; OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES
- A61G5/00—Chairs or personal conveyances specially adapted for patients or disabled persons, e.g. wheelchairs
- A61G5/10—Parts, details or accessories
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61G—TRANSPORT, PERSONAL CONVEYANCES, OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS; OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES
- A61G2203/00—General characteristics of devices
- A61G2203/10—General characteristics of devices characterised by specific control means, e.g. for adjustment or steering
- A61G2203/18—General characteristics of devices characterised by specific control means, e.g. for adjustment or steering by patient's head, eyes, facial muscles or voice
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Rehabilitation Tools (AREA)
Abstract
The invention discloses a kind of method for controlling intelligent wheelchair and system based on human brain motion intention, it is related to intelligent wheel chair field;It includes the following steps:1) EEG brain networks are built by the EEG signals of collection;2) classified according to the node diagnostic of EEG brain networks to attention state, judge whether tested object is in notice collected state, if so, starting wheelchair walking mode, and skip to step 3;If it is not, then skip to step 1;3) Motor preparation current potential, ERD features and the eye closing prosodic feature for the EEG signals that extraction gathers, controling wheelchair is instructed according to its generation left-hand rotation, right-hand rotation, straight trip and stopping straight trip;The present invention solves only analyzes local brain area in the prior art, causes EEG Processing inaccurate so that the problem of control accuracy of wheelchair is poor, has reached the effect of the precision and real-time that improve wheelchair control.
Description
Technical field
The present invention relates to intelligent wheel chair field, especially a kind of method for controlling intelligent wheelchair based on human brain motion intention and
System.
Background technology
In recent years, the fast development of brain-computer interface technology cause using people's brain signal directly control the idea of external equipment into
For reality, improve for the quality of life of part quadriplegia but the normal disabled patient of cerebral function and bring hope, among these most
The technology for having application prospect is the intelligent wheel chair based on brain-computer interface control, it can decode the EEG signals of disabled patient,
And the walking of intelligent wheel chair is controlled with it, greatly extend the living space of patient;It is current developed be used for control intelligent wheel
The brain-computer interface type of chair mainly has three kinds:Mental imagery, P300 current potentials and Steady State Visual Evoked Potential;Wherein, P300 current potentials
With Steady State Visual Evoked Potential be both needed to outer bound pair brain in patients carry out stimulate could produce specific brain electrical feature, disabled patient makes
With extremely not convenient;Mental imagery brain-computer interface is not required to environmental stimuli, but real-time is poor, between control is intended to produce and performs
The experience of hysteresis quality extreme influence user and it is easy to cause in complicated home environment and waits danger sexual behavior using colliding
Therefore.
Research finds that being contained in the EEG signals of the preparation stage before people's limbs autokinetic movement can predict and will occur
Movement information, mainly include two category features:One is Motor preparation current potential, 1500~1200ms before Motor execution
Produce, terminate when Motor execution, be negative wave;Two be Event-related desynchronization (ERD), before Motor execution
2000ms is produced, and until Motor execution finishes, shows as the decline of brain electricity Alpha and Beta rhythm and pace of moving things energy, Motor preparation current potential
With ERD foundation is provided for the motion intention of the prediction human brain before movement starts;Intention control based on Motor preparation current potential
Real-time is disturbed larger because Motor preparation current potential is temporal signatures, so as to influence the reaction speed of system, causes its real-time
It is not high;
It is existing by building brain network, taking power spectrum or entropy the methods of extraction brain area feature classify so that area
Divide attention state and non-attention state, but use existing way low so that can not just for local brain area, the accuracy of classification
Determine that notice is concentrated, cause dealing with improperly for corresponding EEG signals, the low precision of wheelchair control;So one kind is needed to be based on people
The method for controlling intelligent wheelchair and system of brain motion intention realize the real-time that control is improved while accurate control.
The content of the invention
It is an object of the invention to:The present invention provides a kind of method for controlling intelligent wheelchair based on human brain motion intention and
System, solves and only analyzes local brain area in the prior art, causes EEG Processing inaccurate so that the control essence of wheelchair
Degree is poor, motion intention corresponds to current potential and is disturbed the problem of real-time for influencing to cause wheelchair control is poor.
The technical solution adopted by the present invention is as follows:
A kind of method for controlling intelligent wheelchair based on human brain motion intention, includes the following steps:
Step 1:EEG brain networks are built by the EEG signals of collection;
Step 2:Classified according to the node diagnostic of EEG brain networks to attention state, judge tested object whether in note
Meaning power collected state, if so, starting wheelchair walking mode, and skips to step 3;If it is not, then skip to step 1;
Step 3:Motor preparation current potential, ERD features and the eye closing prosodic feature of the EEG signals of collection are extracted, according to its life
Into instruction controling wheelchair of turning left, turn right, keep straight on and stop to keep straight on.
Preferably, the step 1 includes the following steps:
Step 1.1:After gathering EEG signals using electrode cap, Hz noise is removed using trapper to EEG signals, is made
Eye electricity artefact is eliminated with template matching method, pretreated EEG signals are obtained after removing motion artifacts using bandpass filter;
Step 1.2:EEG data is obtained based on pretreated EEG signals, the electrode lead of EEG data is defined as
The node of EEG brain networks, the side that the coherence factor calculated based on EEG data between electrode pair is defined as to EEG brain networks are completed
Build EEG brain networks;
Preferably, the step 2 includes the following steps:
Step 2.1:According to the side of EEG brain networks and node structure weighted network calculate node degree, and use supporting vector
Machine grader carries out attention state with node degree feature classification and judges whether to be in notice high concentration state, if so, then
Skip to step 2.2;If it is not, then skip to step 1;
Step 2.2:Generate travel commands and send to wheelchair, wheelchair and skip to step 3 after starting wheelchair pattern.
Preferably, the step 3 includes the following steps:
Step 3.1:By pretreated EEG signals using AR Power estimations method extraction eye closing prosodic feature, Empirical Mode is used
State decomposition method extracts Motor preparation current potential, and ERD is extracted using cospace type method;
Step 3.2:If detecting the relevant Motor preparation current potential of left upper extremity motion intention and ERD based on step 3.1, give birth to
Into instruction of turning left;If detecting the relevant Motor preparation current potential of right upper extremity motion intention and ERD, generation, which is turned right, to be instructed;If not
Detect Motor preparation current potential and ERD, then generation straight trip instruction;Control instruction is sent to wheelchair by ICP/IP protocol and is realized
Left-hand rotation, right-hand rotation and the straight trip of wheelchair;
Step 3.3:Whether the energy for judging eye closing prosodic feature based on 3.2 exceedes threshold value, if exceeding, generation stops row
Walk instruction and send to wheelchair control wheelchair by ICP/IP protocol to stop walking, continue to examine if not exceeded, then skipping to step 3.2
Survey.
Preferably, the eye closing prosodic feature includes Alpha prosodic features.
A kind of intelligent wheelchair control system based on human brain motion intention, including collection amplifying unit, wireless transmission unit,
Analytic unit and intelligent wheel chair, wherein
Amplifying unit is gathered, for amplifying after providing electrode cap collection EEG signals by amplifier and being converted to digital letter
Number;
Wireless transmission unit, for EEG signals to be sent to analytic unit and send control instruction to wheelchair;
Analytic unit, judges whether notice is concentrated, into wheelchair for building EEG networks according to the EEG signals of collection
Eye closing prosodic feature, Motor preparation current potential and ERD are extracted after walking mode, corresponding walking is generated, turns left, turns right, stopping row
Walk instruction;
Intelligent wheel chair, for receiving control instruction driving motor completion walking, left-hand rotation, right-hand rotation, straight trip and stopping walking.
Preferably, the wireless transmission unit includes blue tooth interface and wireless router.
In conclusion by adopting the above-described technical solution, the beneficial effects of the invention are as follows:
1. the present invention classifies attention state with node diagnostic, whether notice is concentrated by building EEG networks
The switch walked as controling wheelchair, improves the accuracy of classification, it is ensured that and notice is concentrated, and by detecting Motor preparation current potential
With ERD features, the interference of time domain is avoided, solves and only analyzes local brain area in the prior art, cause EEG Processing to be not allowed
Really cause the real-time of wheelchair control is poor to ask so that the control accuracy of wheelchair is poor, motion intention corresponds to current potential and is disturbed influence
Topic, has reached the effect of the precision and real-time that improve wheelchair control;
2. the switch that the present invention walks notice as controling wheelchair, it is ensured that state of attention is by building EEG nets
Network, is classified attention state using support vector machine classifier with node diagnostic, reflects the characteristic of each brain area of brain, improves classification
Accuracy, so as to judge whether notice is in high concentration, avoid the methods of only passing through power spectrum in the prior art point
The local brain area of analysis come judge notice whether concentrate cause control accuracy poor the shortcomings that;
3. the ERD of the present invention is frequency domain character, frequency domain character is not easy by noise and baseline interference, with reference to Motor preparation current potential
Realize real time kinematics be intended to control, avoid it is existing only by temporal signatures-Motor preparation current potential come realize be intended to control caused by
The shortcomings that real-time is poor;
4. taking corresponding method to extract corresponding feature after the EEG signals pretreatment of the present invention, brain electricity is further improved
The accuracy and efficiency of signal processing, is conducive to improve the real-time and precision of EEG signals controling wheelchair.
Brief description of the drawings
Examples of the present invention will be described by way of reference to the accompanying drawings, wherein:
Fig. 1 is the flow chart of the present invention;
Fig. 2 is step 3 flow chart of the present invention;
Fig. 3 is the electrode position distribution map of the present invention;
Fig. 4 is the average node degree Value Data figure under each lead two states of the present invention.
Embodiment
All features disclosed in this specification, or disclosed all methods or during the step of, except mutually exclusive
Feature and/or step beyond, can combine in any way.
Elaborate with reference to Fig. 1-4 couples of present invention.
Embodiment 1
A kind of method for controlling intelligent wheelchair based on human brain motion intention, includes the following steps:
Step 1:EEG brain networks are built by the EEG signals of collection;
Step 2:Classified according to the node diagnostic of EEG brain networks to attention state, judge tested object whether in note
Meaning power collected state, if so, starting wheelchair walking mode, and skips to step 3;If it is not, then skip to step 1;
Step 3:Motor preparation current potential, ERD features and the eye closing prosodic feature of the EEG signals of collection are extracted, according to its life
Into instruction controling wheelchair of turning left, turn right, keep straight on and stop to keep straight on.
A kind of intelligent wheelchair control system based on human brain motion intention, including collection amplifying unit, wireless transmission unit,
Analytic unit and intelligent wheel chair, wherein
Amplifying unit is gathered, for amplifying after providing electrode cap collection EEG signals by amplifier and being converted to digital letter
Number;
Wireless transmission unit, for EEG signals to be sent to analytic unit and send control instruction to wheelchair;
Analytic unit, judges whether notice is concentrated, into wheelchair for building EEG networks according to the EEG signals of collection
Eye closing prosodic feature, Motor preparation current potential and ERD are extracted after walking mode, corresponding walking is generated, turns left, turns right, stopping row
Walk instruction;
Intelligent wheel chair, for receiving control instruction driving motor completion walking, left-hand rotation, right-hand rotation, straight trip and stopping walking.
Embodiment 2
Step 1.1:After gathering EEG signals using electrode cap, Hz noise is removed using trapper to EEG signals, is made
Eye electricity artefact is eliminated with template matching method, pretreated EEG signals are obtained after removing motion artifacts using bandpass filter;
Step 1.2:EEG data is obtained based on pretreated EEG signals, the electrode lead of EEG data is defined as
The node of EEG brain networks, the side that the coherence factor calculated based on EEG data between electrode pair is defined as to EEG brain networks are completed
Build EEG brain networks;
Step 2.1:According to the side of EEG brain networks and node structure weighted network calculate node degree, and use supporting vector
Machine grader carries out attention state classification with node degree feature and determines whether notice high concentration state, if so, then jumping
To step 2.2;If it is not, then skip to step 1.1;
Step 2.2:Generate travel commands and send to wheelchair, wheelchair and skip to step 3.1 after starting wheelchair pattern.
Step 3.1:By pretreated EEG signals using AR Power estimations method extraction eye closing prosodic feature, Empirical Mode is used
State decomposition method extracts Motor preparation current potential, and ERD is extracted using cospace type method;
Step 3.2:If detecting the relevant Motor preparation current potential of left upper extremity motion intention and ERD based on step 3.1, give birth to
Into instruction of turning left;If detecting the relevant Motor preparation current potential of right upper extremity motion intention and ERD, generation, which is turned right, to be instructed;If not
Detect Motor preparation current potential and ERD, then generation straight trip instruction;Control instruction is sent to wheelchair by ICP/IP protocol and is realized
Left-hand rotation, right-hand rotation and the straight trip of wheelchair;
Step 3.3:Whether the energy for judging Alpha rhythm and pace of moving things values based on 3.2 exceedes threshold value, if exceeding, generation stops row
Walk instruction and send to wheelchair control wheelchair by ICP/IP protocol to stop walking, continue to examine if not exceeded, then skipping to step 3.2
Survey.
Embodiment 3
EEG signals are gathered using dry electrode and pass through Bluetooth wireless transmission to analytic unit;In specific implementation, by cloth
There are 32 electrode caps for leading dry electrode to be worn on patient's head, electrode is arranged by the 10-20 standards of international standard, 32 conductive electrode
The feeble computer signals that recorded are converted to digital signal after amplifier amplifies, and are wirelessly transmitted to and are provided with by blue tooth interface
In the computer of analytic unit.
EEG brain networks are built after being pre-processed to the EEG signals of collection:During specific implementation, brain is filtered out using trapper
Hz noise in electric signal, is eliminated the eye electricity artefact in EEG signals using template matching method, is removed using bandpass filtering method
Motion artifacts in EEG signals;EEG data is obtained based on pretreated EEG signals, the electrode lead of EEG data is determined
Justice is the node of EEG brain networks, and the coherence factor calculated based on EEG data between electrode pair is defined as to the side of EEG brain networks
Complete structure EEG brain networks;Wherein, coherence factor is two fingers for leading linear relationship between EEG signal portrayed at a certain frequency
Mark, is a kind of method of common analysis nervous activity synchronism;Coherence factor height means that two lead synchronism god between EEG signal
Through shaking, i.e., the function degree of integration between neuron pool is high, and low coherence factor means the function separation between neuron pool
Degree is high;Consider that two lead EEG signal x (t) and y (t), the coherence factor between them is expressed as:
Wherein, wherein Pxy(f) it is the mutual spectral function of x (t) and y (t), Pxx(f) and Pyy(f) it is respectively x (t) and y (t)
Power spectrum function;Coherence factor 0<Cxy(f)<1, work as Cxy(f)=0 when, represent there is no line between x (t) and y (t) at frequency f
Property correlation;Work as Cxy(f)=1 when, represent at frequency f between x (t) and y (t) there are one-to-one relation, and phase responsibility
Number is bigger, represents that the two lead coherences based on EEG signals are stronger;In the equal of coherence factor of the present embodiment between 8-15Hz
It is worth the side as network, selects this frequency range to be because alpha the and beta rhythm and pace of moving things of task state EEG data is considered in notice
Play an important role with cognitive function is improved;
According to the side of EEG brain networks and node structure weighted network calculate node degree, and use support vector machine classifier
Classification is carried out to attention state with node degree feature and determines whether notice high concentration state, if so, then sending starting row
Instruction is walked, travel commands are wirelessly transmitted to wheelchair by ICP/IP protocol, wheelchair realizes walking;If it is not, then continue to gather brain
Electric signal;
According to the side of EEG brain networks and node structure weighted network calculate node degree, and use support vector machine classifier
Realization specific as follows of classifying is carried out to attention state with node degree feature:Task state EEG data is referenced to all leads again
Average signal, to mitigate the influence of reference electrode effect;First 5 seconds in 3 minutes task state EEG datas are removed, and will be remaining
Data length be divided into 35 sections, be 5 seconds per segment length, then non-attention, attention task 1 and pay attention to the EEG numbers that are gathered of task 2
According to including 140 sections respectively, to the EEG data section that each was split, the coherence factor between 19 leads is calculated, generates one 19
× 19 connection matrix;Since every a bit of EEG data can calculate a connection matrix, every subject is at each
140 connection matrix can be obtained in business state, finally calculate the average value of this 140 connection matrix, the flat of subject is represented with W
It is all connected with matrix, the matrix element w in wherein WijRepresent the average coherence coefficient (brain of structure of the network node (electrode) between i and j
Functional network is weighted network, in network is weighted, weight wijThe bonding strength between network node i and j is not only reacted, instead
The difference of bonding strength and capacity between node, therefore the effective means that can be analyzed as a kind of network attribute are answered);N is made to represent
Whole sets of node of brain network, the average function bonding strength of network are defined as the equal of the bonding strength between all nodes pair
Value;The degree of nodes i is defined as:ki=∑j∈Nwij, it is equal to all side bonding strengths being connected in network with the node
Summation, take the node degree of brain network as feature to classify to attention with non-attention state;Using support vector machines
Carrying out pattern recognition classifier, (support vector machine classification method is based on Statistical Learning Theory and structural risk minimization, uses
The capacity of class interval Schistosomiasis control machine, so that Structural risk minization, is solving small sample, the knowledge of non-linear and high dimensional pattern
Many peculiar advantages are shown in other problem), in embodiment, by using LibSVM tool boxes, linear kernel function is selected, then
Final accuracy is obtained using ten folding cross validations;The average node degree paid attention at each lead with non-attention state is calculated,
As shown in figure 4, in addition to 14 leads (P3), pay attention to and non-attention state all there are conspicuousness (P at other leads<0.05), and
The average nodal angle value of attention state is below non-attention state, and the variance of attention state is also below non-attention state;With node
Degree is characterized to paying attention to classifying with non-attention state, and the average correct classification rate finally drawn in 10 subjects is
84.1%;(correct situation of classifying is:Attention state is divided into attention state, non-attention state is divided into non-attention state and is;Classification is wrong
By mistake situation be:Attention state is divided into non-attention state, non-attention state, which is divided into, pays attention to state for classification error, classification accuracy rate=
Classify correct sample number/(correct sample number+classification error sample number of classifying));Structure can be achieved in the accuracy for improving classification
Build EEG brains network to classify to attention state with node diagnostic, judge whether high concentration is so as to improve brain electric control for notice
Accuracy;
Under walking mode, Motor preparation current potential, ERD features and the Alpha prosodic features of the EEG signals of collection are extracted, is made
The Alpha rhythm and pace of moving things energy of EEG signals after pretreatment is calculated with AR Power estimations method, eeg data calculates window a length of 2 seconds, and window is every
It is secondary to slide 1 second;Motor preparation current potential is extracted using Empirical mode decomposition, a length of 2 seconds of data window, window slides 1 second every time;Make
ERD is extracted with cospace type method, a length of 2 seconds of data window, window slides 1 second every time;If detect and left upper extremity motion intention
Relevant Motor preparation current potential and ERD, then send left-hand rotation instruction;If detect and the relevant Motor preparation of right upper extremity motion intention
Current potential and ERD, then send right-hand rotation instruction;If fail to detect with any upper extremity exercise be intended to relevant Motor preparation current potential and
ERD, then send straight trip instruction;Similarly, the instruction that will turn left, and turn right and keep straight on is wirelessly transmitted to wheelchair by ICP/IP protocol, takes turns
Chair is realized, turns right and keep straight on;If Alpha rhythm and pace of moving things energy continues to exceed the threshold value 3 seconds of setting, send and stop walking and refer to
Order, the situation of change of the Alpha rhythm and pace of moving things when threshold value is according to every patient's eye closing rest are set, and will stop travel commands
Wheelchair is wirelessly transmitted to by ICP/IP protocol, wheelchair, which is realized, stops walking, if it is not, then skip to detection Motor preparation current potential and
Continue to realize at ERD and either turn right or keep straight on.The present invention is by building EEG networks, with node diagnostic to attention state
Classify, improve the accuracy of classification, whether notice is concentrated into the switch as controling wheelchair walking, and transport by detecting
Dynamic readiness potential and ERD features, avoid the interference of time domain, solve and only analyze local brain area in the prior art, cause brain telecommunications
Number processing is inaccurate so that the control accuracy of wheelchair is poor, motion intention corresponds to current potential and is disturbed influence causes the reality of wheelchair control
The problem of when property is poor, has reached the effect of the precision and real-time that improve wheelchair control.
Claims (7)
- A kind of 1. method for controlling intelligent wheelchair based on human brain motion intention, it is characterised in that:Include the following steps:Step 1:EEG brain networks are built by the EEG signals of collection;Step 2:Classified according to the node diagnostic of EEG brain networks to attention state, judge whether tested object is in notice Collected state, if so, starting wheelchair walking mode, and skips to step 3;If it is not, then skip to step 1;Step 3:Motor preparation current potential, ERD features and the eye closing prosodic feature of the EEG signals of collection are extracted, it is left according to its generation Turn, turn right, keep straight on and stop straight trip instruction controling wheelchair.
- A kind of 2. method for controlling intelligent wheelchair based on human brain motion intention according to claim 1, it is characterised in that:Institute Step 1 is stated to include the following steps:Step 1.1:After gathering EEG signals using electrode cap, Hz noise is removed using trapper to EEG signals, uses mould Plate matching method eliminates eye electricity artefact, and pretreated EEG signals are obtained after removing motion artifacts using bandpass filter;Step 1.2:EEG data is obtained based on pretreated EEG signals, the electrode lead of EEG data is defined as EEG brains Structure is completed on the node of network, the side that the coherence factor calculated based on EEG data between electrode pair is defined as to EEG brain networks EEG brain networks.
- A kind of 3. method for controlling intelligent wheelchair based on human brain motion intention according to claim 2, it is characterised in that:Institute Step 2 is stated to include the following steps:Step 2.1:According to the side of EEG brain networks and node structure weighted network calculate node degree, and using support vector machines point Class device carries out attention state with node degree feature classification and judges whether to be in notice high concentration state, if so, then skipping to Step 2.2;If it is not, then skip to step 1;Step 2.2:Generate travel commands and send to wheelchair, wheelchair and skip to step 3 after starting walking mode.
- A kind of 4. method for controlling intelligent wheelchair based on human brain motion intention according to claim 3, it is characterised in that:Institute Step 3 is stated to include the following steps:Step 3.1:By pretreated EEG signals using AR Power estimations method extraction eye closing prosodic feature, empirical modal point is used Solution extracts Motor preparation current potential, and ERD is extracted using cospace type method;Step 3.2:If detecting the relevant Motor preparation current potential of left upper extremity motion intention and ERD based on step 3.1, generation is left Turn instruction;If detecting the relevant Motor preparation current potential of right upper extremity motion intention and ERD, generation, which is turned right, to be instructed;If do not detect To Motor preparation current potential and ERD, then generation straight trip instruction;Control instruction is sent to wheelchair by ICP/IP protocol and realizes wheelchair Left-hand rotation, right-hand rotation and straight trip;Step 3.3:Whether the energy for judging eye closing prosodic feature based on 3.2 exceedes threshold value, if exceeding, generation stops walking and refers to Make and sent by ICP/IP protocol to wheelchair control wheelchair and stop walking, continue to detect if not exceeded, then skipping to step 3.2.
- A kind of 5. method for controlling intelligent wheelchair based on human brain motion intention according to claim 4, it is characterised in that:Institute Stating eye closing prosodic feature includes Alpha prosodic features.
- A kind of 6. intelligent wheelchair control system based on human brain motion intention, it is characterised in that:Including collection amplifying unit, wirelessly Transmission unit, analytic unit and intelligent wheel chair, whereinAmplifying unit is gathered, for amplifying after providing electrode cap collection EEG signals by amplifier and being converted to digital signal;Wireless transmission unit, for EEG signals to be sent to analytic unit and send control instruction to wheelchair;Analytic unit, judges whether notice is concentrated for building EEG networks according to the EEG signals of collection, walks into wheelchair Extraction eye closing prosodic feature, Motor preparation current potential and ERD after pattern, the corresponding walking of generation, left-hand rotation, right-hand rotation, stopping walking referring to Order;Intelligent wheel chair, completes walking for receiving order-driven motor, turns left, turns right, keeps straight on and stop walking.
- A kind of 7. intelligent wheelchair control system based on human brain motion intention according to claim 6, it is characterised in that:Institute Stating wireless transmission unit includes blue tooth interface and wireless router.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711184676.0A CN107981997B (en) | 2017-11-23 | 2017-11-23 | A kind of method for controlling intelligent wheelchair and system based on human brain motion intention |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711184676.0A CN107981997B (en) | 2017-11-23 | 2017-11-23 | A kind of method for controlling intelligent wheelchair and system based on human brain motion intention |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107981997A true CN107981997A (en) | 2018-05-04 |
CN107981997B CN107981997B (en) | 2019-11-29 |
Family
ID=62032683
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711184676.0A Active CN107981997B (en) | 2017-11-23 | 2017-11-23 | A kind of method for controlling intelligent wheelchair and system based on human brain motion intention |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107981997B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110931123A (en) * | 2019-12-06 | 2020-03-27 | 深圳市德力凯医疗设备股份有限公司 | Matrix brain network and construction method thereof |
CN111134974A (en) * | 2019-12-09 | 2020-05-12 | 西安交通大学 | Wheelchair robot system based on augmented reality and multi-mode biological signals |
CN112869743A (en) * | 2021-01-15 | 2021-06-01 | 北京理工大学 | Exercise initiation intention neural analysis method considering cognitive distraction |
CN113228138A (en) * | 2018-12-27 | 2021-08-06 | 株式会社村田制作所 | Cognitive ability detection device and cognitive ability detection system |
CN114327048A (en) * | 2021-12-07 | 2022-04-12 | 重庆邮电大学 | Mechanical arm control method and system based on electroencephalogram signals and electro-oculogram signals |
CN114366101A (en) * | 2021-12-31 | 2022-04-19 | 西安臻泰智能科技有限公司 | Motor imagery electroencephalogram signal classification method, device, equipment and storage medium |
CN114652532A (en) * | 2022-02-21 | 2022-06-24 | 华南理工大学 | Multifunctional brain-controlled wheelchair system based on SSVEP and attention detection |
CN115590695A (en) * | 2022-10-08 | 2023-01-13 | 华南脑控(广东)智能科技有限公司(Cn) | Wheelchair control system based on electro-oculogram and face recognition |
CN115886841A (en) * | 2022-08-26 | 2023-04-04 | 华中科技大学 | Steady-state vision-evoked electroencephalogram dynamic initial classification method based on brain region linkage |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203149771U (en) * | 2013-03-26 | 2013-08-21 | 无锡商业职业技术学院 | A fatigue driving caution system |
AU2013101211A4 (en) * | 2013-09-11 | 2013-10-10 | Huang, Xu PROF | A novel two-stage multi-criteria evaluation for internal attack in WSN |
CN103349595A (en) * | 2013-07-16 | 2013-10-16 | 杭州电子科技大学 | Intelligent brain-computer interface wheelchair based on multi-mode hierarchical control |
CN104050394A (en) * | 2014-07-04 | 2014-09-17 | 北京师范大学 | Modeling method and topological attribute analytical method for group brain network |
CN104360730A (en) * | 2014-08-19 | 2015-02-18 | 西安交通大学 | Man-machine interaction method supported by multi-modal non-implanted brain-computer interface technology |
KR20150021810A (en) * | 2013-08-21 | 2015-03-03 | 주식회사 케이티 | Method and apparatus of determining user's attention |
CN107024987A (en) * | 2017-03-20 | 2017-08-08 | 南京邮电大学 | A kind of real-time human brain Test of attention and training system based on EEG |
CN107037883A (en) * | 2017-04-13 | 2017-08-11 | 安徽大学 | A kind of mixing brain machine interface system and method based on Mental imagery |
-
2017
- 2017-11-23 CN CN201711184676.0A patent/CN107981997B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203149771U (en) * | 2013-03-26 | 2013-08-21 | 无锡商业职业技术学院 | A fatigue driving caution system |
CN103349595A (en) * | 2013-07-16 | 2013-10-16 | 杭州电子科技大学 | Intelligent brain-computer interface wheelchair based on multi-mode hierarchical control |
KR20150021810A (en) * | 2013-08-21 | 2015-03-03 | 주식회사 케이티 | Method and apparatus of determining user's attention |
AU2013101211A4 (en) * | 2013-09-11 | 2013-10-10 | Huang, Xu PROF | A novel two-stage multi-criteria evaluation for internal attack in WSN |
CN104050394A (en) * | 2014-07-04 | 2014-09-17 | 北京师范大学 | Modeling method and topological attribute analytical method for group brain network |
CN104360730A (en) * | 2014-08-19 | 2015-02-18 | 西安交通大学 | Man-machine interaction method supported by multi-modal non-implanted brain-computer interface technology |
CN107024987A (en) * | 2017-03-20 | 2017-08-08 | 南京邮电大学 | A kind of real-time human brain Test of attention and training system based on EEG |
CN107037883A (en) * | 2017-04-13 | 2017-08-11 | 安徽大学 | A kind of mixing brain machine interface system and method based on Mental imagery |
Non-Patent Citations (2)
Title |
---|
戴冷湜: ""脑电信号的特征提取与分析方法研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
李世杰: ""基于SSVEP信号的在线BCI关键技术研究"", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113228138A (en) * | 2018-12-27 | 2021-08-06 | 株式会社村田制作所 | Cognitive ability detection device and cognitive ability detection system |
CN110931123B (en) * | 2019-12-06 | 2024-01-05 | 深圳市德力凯医疗设备股份有限公司 | Matrix type brain network and construction method thereof |
CN110931123A (en) * | 2019-12-06 | 2020-03-27 | 深圳市德力凯医疗设备股份有限公司 | Matrix brain network and construction method thereof |
CN111134974A (en) * | 2019-12-09 | 2020-05-12 | 西安交通大学 | Wheelchair robot system based on augmented reality and multi-mode biological signals |
CN111134974B (en) * | 2019-12-09 | 2021-04-20 | 西安交通大学 | Wheelchair robot system based on augmented reality and multi-mode biological signals |
CN112869743A (en) * | 2021-01-15 | 2021-06-01 | 北京理工大学 | Exercise initiation intention neural analysis method considering cognitive distraction |
CN112869743B (en) * | 2021-01-15 | 2021-10-22 | 北京理工大学 | Exercise initiation intention neural analysis method considering cognitive distraction |
CN114327048A (en) * | 2021-12-07 | 2022-04-12 | 重庆邮电大学 | Mechanical arm control method and system based on electroencephalogram signals and electro-oculogram signals |
CN114327048B (en) * | 2021-12-07 | 2024-04-19 | 山东华数信息技术股份有限公司 | Mechanical arm control method and system based on electroencephalogram signals and electrooculogram signals |
CN114366101B (en) * | 2021-12-31 | 2024-05-03 | 西安臻泰智能科技有限公司 | Motor imagery electroencephalogram signal classification method, device, equipment and storage medium |
CN114366101A (en) * | 2021-12-31 | 2022-04-19 | 西安臻泰智能科技有限公司 | Motor imagery electroencephalogram signal classification method, device, equipment and storage medium |
CN114652532B (en) * | 2022-02-21 | 2023-07-18 | 华南理工大学 | Multifunctional brain-controlled wheelchair system based on SSVEP and attention detection |
CN114652532A (en) * | 2022-02-21 | 2022-06-24 | 华南理工大学 | Multifunctional brain-controlled wheelchair system based on SSVEP and attention detection |
CN115886841A (en) * | 2022-08-26 | 2023-04-04 | 华中科技大学 | Steady-state vision-evoked electroencephalogram dynamic initial classification method based on brain region linkage |
CN115886841B (en) * | 2022-08-26 | 2024-09-17 | 华中科技大学 | Steady state vision induced electroencephalogram initial classification method based on brain region linkage |
CN115590695A (en) * | 2022-10-08 | 2023-01-13 | 华南脑控(广东)智能科技有限公司(Cn) | Wheelchair control system based on electro-oculogram and face recognition |
CN115590695B (en) * | 2022-10-08 | 2024-06-14 | 华南脑控(广东)智能科技有限公司 | Wheelchair control system based on electrooculogram and face recognition |
Also Published As
Publication number | Publication date |
---|---|
CN107981997B (en) | 2019-11-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107981997B (en) | A kind of method for controlling intelligent wheelchair and system based on human brain motion intention | |
CN108236464B (en) | Feature extraction method based on electroencephalogram signals and detection extraction system thereof | |
Townsend et al. | Continuous EEG classification during motor imagery-simulation of an asynchronous BCI | |
Pfurtscheller et al. | 15 years of BCI research at Graz University of Technology: current projects | |
Leeb et al. | Multimodal fusion of muscle and brain signals for a hybrid-BCI | |
CN102184019B (en) | Method for audio-visual combined stimulation of brain-computer interface based on covert attention | |
CN104548347A (en) | Pure idea nerve muscle electrical stimulation control and nerve function evaluation system | |
CN107037883A (en) | A kind of mixing brain machine interface system and method based on Mental imagery | |
CN110495893B (en) | System and method for multi-level dynamic fusion recognition of continuous brain and muscle electricity of motor intention | |
CN104382595A (en) | Upper limb rehabilitation system and method based on myoelectric signal and virtual reality interaction technology | |
EP2111156A1 (en) | A system and method for processing brain signals in a bci system | |
CN102722727A (en) | Electroencephalogram feature extracting method based on brain function network adjacent matrix decomposition | |
CN101711709A (en) | Method for controlling electrically powered artificial hands by utilizing electro-coulogram and electroencephalogram information | |
WO2020118797A1 (en) | Prosthesis control method, apparatus, system and device, and storage medium | |
CN103699226A (en) | Tri-modal serial brain-computer interface method based on multi-information fusion | |
CN104978035A (en) | Brain computer interface system evoking P300 based on somatosensory electrical stimulation and implementation method thereof | |
RU2738197C2 (en) | System and method of generating control commands based on operator bioelectric data | |
Gupta et al. | Detecting eye movements in EEG for controlling devices | |
Wang et al. | An approach of one-vs-rest filter bank common spatial pattern and spiking neural networks for multiple motor imagery decoding | |
Awan et al. | Effective classification of EEG signals using K-nearest neighbor algorithm | |
CN104571504A (en) | Online brain-machine interface method based on imaginary movement | |
CN114298089A (en) | Multi-mode strength training assisting method and system | |
CN114557708A (en) | Device and method for detecting somatosensory stimulation consciousness based on electroencephalogram dual-feature fusion | |
CN113064493A (en) | Electroencephalogram signal-based unmanned aerial vehicle emergency detection method and system | |
CN106843509B (en) | Brain-computer interface 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 |