CN110251148A - A kind of robot assisted rehabilitation control method based on fuzzy Emotion identification - Google Patents
A kind of robot assisted rehabilitation control method based on fuzzy Emotion identification Download PDFInfo
- Publication number
- CN110251148A CN110251148A CN201910488811.3A CN201910488811A CN110251148A CN 110251148 A CN110251148 A CN 110251148A CN 201910488811 A CN201910488811 A CN 201910488811A CN 110251148 A CN110251148 A CN 110251148A
- Authority
- CN
- China
- Prior art keywords
- training
- patient
- rehabilitation
- fuzzy
- emotion identification
- 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
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- 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
-
- 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
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Evolutionary Computation (AREA)
- Developmental Disabilities (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Child & Adolescent Psychology (AREA)
- Mathematical Physics (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Cardiology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The robot assisted rehabilitation control method based on fuzzy Emotion identification that present invention discloses a kind of, method includes the following steps: S1: utilizing the electrocardio and skin electric signal of biosensor acquisition patient, data prediction is carried out, characteristic value related with patient mood is obtained;S2: the characteristic value that the S1 step obtains is filtered out into physiological signal essential signature sets using mRMR algorithm, obtains the real-time emotion state of patient;S3: carrying out fuzzy reasoning to feature set, carries out Emotion identification to the training object in rehabilitation training using Emotion identification method;S4: according to obtained feedback result controlled training rhythm, when recognizing passive mood, rehabilitation training difficulty is adjusted.The technical solution has used the training method of robot assisted, and robotics is melted into medical science of recovery therapy, simplifies the heavy training process of the Traditional Rehabilitation treatment of paralytic and improves therapeutic effect.
Description
Technical field
The robot assisted rehabilitation control method based on fuzzy Emotion identification that the present invention relates to a kind of, it is auxiliary to can be used for robot
Help medical science of recovery therapy technical field.
Background technique
Hemiplegia caused by cerebral apoplexy causes limbs of patient dyskinesia even to be paralysed, and the course of disease is long, restores slowly, to cause
Many patients lose self care ability, cause enormous impact to patient and its family members.Society and family need to spend a large amount of
These patients are treated and looked after to time with money, causes the tremendous increase of social cost.Therefore, in order to restore patient's itself
Limb function improves basic operational capability, while discharging more social resources, eases off the pressure, researchers have always searched for
The rehabilitation therapy method of effect.Introductory song reports the clinicing aspect of early stage nervous system rehabilitation, mainly there is massage, massages, acupuncture and moxibustion therapy
And facilitated technique.With the progress of social medical level, the reasons such as the variation of diseases range, medical model is changed.Mesh
It is preceding mainly using prevention, health care and rehabilitation as major way.Therefore, after stroke rehabilitation, effective rehabilitation training, which can be improved, to be controlled
Therapeutic effect.The stability for consolidating the physical condition of patient is of great significance for the rehabilitation of patient.
Traditional Rehabilitation treatment relies on physiatrician itself professional quality.The mood of patient in the training process also phase not to the utmost
Together.In rehabilitation training, the treatment personnel to lack experience cannot timely and accurately perceive the subjective emotion of patient, also can not essence
Rehabilitation training intensity is adjusted quasi-ly, some, which even result in patient for treatment and generate, is weary of and resists.This is for patients with cerebral apoplexy
Rehabilitation is totally unfavorable.
Summary of the invention
The object of the invention is to propose a kind of based on fuzzy mood to solve the above-mentioned problems in the prior art
The robot assisted rehabilitation control method of identification.
The purpose of the invention will be achieved through the following technical solutions:, and a kind of robot based on fuzzy Emotion identification is auxiliary
Rehabilitation control method is helped, method includes the following steps:
S1: using the electrocardio and skin electric signal of biosensor acquisition patient, data prediction is carried out, is obtained and patient's feelings
The related characteristic value of thread;
S2: the characteristic value that the S1 step obtains is filtered out into physiological signal essential signature sets using mRMR algorithm, is obtained
The real-time emotion state of patient;
S3: carrying out fuzzy reasoning to feature set, carries out feelings to the training object in rehabilitation training using Emotion identification method
Thread identification;Obtain emotional state of the patient in training.
S4: according to the obtained feedback result controlled training rhythm of emotional state of the patient in training in S3 step,
When recognizing passive mood, rehabilitation training difficulty is adjusted.
Preferably, in the S1 step,
Physiological signal feature extraction includes the following steps:
S11: it is pre-processed with electrocardio and skin electric signal of the normalized method to collected patient;Patient is obtained to exist
Physiological signal in training mood is analyzed for emotional state.
S12: totally 40 spies such as respective mean value, standard deviation, first-order difference mean value are extracted from patient's electrocardio and skin electric signal
Value indicative is as feature set.
Preferably, in the S2 step, 10 physiological signal critical eigenvalue compositions is filtered out using mRMR algorithm and are closed
Key feature set.
Preferably, in the S2 step, mRMR algorithm includes the following steps
S21: the mutual information I (X, Y) between every kind of physiological characteristic parameter X, Y and target emotion C is defined;
S22: input patient data set;
S23: the correlation under every kind of data set between characteristic parameter and target emotion is calculated;
S24: redundancy analysis;
S25: the mutual information sequence between physiological characteristic parameter and target emotion;
S26: it chooses and maximum character subset is contributed to feature extraction.:
Preferably, in the S3 step, Emotion identification is carried out using Fuzzy Pattern Recognition Method.
Preferably, in the S4 step, phase one is changed using training difficulty shift design and patients target's emotional state
The robot assisted rehabilitation training switch controller of cause, it is difficult to training of the obtained Emotion identification result to the rehabilitation training
Degree is adjusted.When recognizing passive mood, rehabilitation training difficulty is adjusted to improve the enthusiasm of patient.
The invention adopts the above technical scheme compared with prior art, have following technical effect that this method using electrocardio,
Skin electric signal judges that target locating emotional state and intelligently adjusts trained difficulty in the training process, to reach optimum training shape
State.
1, robotics is melted into medical science of recovery therapy, simplifies the biography of paralytic by the training method for having used robot assisted
The heavy training process of system rehabilitation simultaneously improves therapeutic effect.
2, the robot assisted rehabilitation control method based on fuzzy Emotion identification pays close attention to the mood of user in training, can
Timely adjustment training difficulty after obtaining patients ' psychological physiological data in real time and analyzing, so that it remains optimistic positive shape
State, readily available better rehabilitation effect.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of robot assisted rehabilitation control method based on fuzzy Emotion identification of the invention.
Fig. 2 is electrocardiosignal figure of the invention.
Fig. 3 is breath signal figure of the invention.
Fig. 4 is mRMR Feature Selection algorithm flow chart of the invention.
Fig. 5 is fuzzy controller input/output state figure of the invention.
Fig. 6 is discrimination column display figure of the invention.
Specific embodiment
The purpose of the present invention, advantage and feature, by by the non-limitative illustration of preferred embodiment below carry out diagram and
It explains.These embodiments are only the prominent examples using technical solution of the present invention, it is all take equivalent replacement or equivalent transformation and
The technical solution of formation, all falls within the scope of protection of present invention.
The robot assisted rehabilitation control method based on fuzzy Emotion identification that present invention discloses a kind of, as shown in Figure 1, root
According to preferred embodiment of the invention, a kind of robot assisted rehabilitation control method based on fuzzy Emotion identification, with rehabilitation machine
" positive " and " passiveness " caused by target Ipsilateral is dbjective state, specific implementation packet in people's auxiliary mark rehabilitation training
Include following steps:
Electrocardio and skin electric signal in S1 step, acquisition rehabilitation training under patients target's mood, carry out data and locate in advance
Reason;
S2 step, feature extraction simultaneously filter out physiological signal essential signature sets using mRMR algorithm;
S3 step carries out fuzzy reasoning to feature set, using fuzzy pattern Emotion identification method to the instruction in rehabilitation training
Practice object and carries out Emotion identification;
S4 step, according to obtained feedback result controlled training rhythm, when recognizing passive mood, adjust rehabilitation
Training difficulty.
In S1 step, by design electrocardio and skin electric signal fatigue state measurement experiment, to obtain patient in training process
Electrocardio and skin electric signal under target emotion.
In S2 step, electrocardio and skin electric signal mood physiological responses signature analysis the following steps are included:
(1) the characteristic values conducts such as respective mean value, standard deviation, first-order difference mean value are extracted from patient's electrocardio and skin electric signal
Feature set.
(2) mRMR maximal correlation minimal redundancy algorithm is used, goes out to react what dbjective state changed from mathematics angle analysis
Electrocardio and skin electric signal important feature and combinations thereof.
In S3 step, using Fuzzy Pattern Recognition Method design object emotional state judgment models.
In S4 step, consistent robot assisted is changed with patients target's emotional state using training difficulty shift design
Rehabilitation training switch controller.
With reference to the accompanying drawing shown in 1, the specific implementation example of above steps is described in detail.
In the S1 step, it may be preferable that tested by using electrocardio and skin electric signal mood physiological signal measurements, to obtain
The electrocardio of patients target's emotional reactions and skin electroresponse signal in training process.
Specific implementation includes following procedure:
(1) experimental duties design: constructing virtual training environment project training task based on virtual reality technology.Subject
By the bead in operation robot end's control interface according to the cube in route collision continuous renewal.And it is vertical by design
Cube renewal rate is to inducing patient actively and passive two kinds of target emotion states;
(2) it tests questionnaire design: in patient's training, being exchanged with patient, understand patient and experience in real time, and set by difficulty
Meter induces patients target's mood, acquires physiological signal.
(3) experimental data obtain: to from patient's Ipsilateral electrocardio and skin electricity data be monitored record and pretreatment;
(4) experimentation designs: being suitble to subject mood induction firstly, determining according to the virtual experimental task of previous designs
Training difficulty;Subject is acquired simultaneously in different rehabilitation training task electrocardios and skin electroresponse signal, signal graph such as Fig. 2, Fig. 3 institute
Show, abscissa is the time, ordinate represents sampled signal voltage;Finally, training terminates, according to circumstances experiment arrangement questionnaire tune
It looks into.
In the S2 step, electrocardio and skin electric signal emotive response signature analysis the following steps are included:
(1) totally 40 features such as respective mean value, standard deviation, first-order difference mean value are extracted from patient's electrocardio and skin electric signal
Value is used as feature set.
(2) mRMR maximal correlation minimal redundancy algorithm is used, goes out to react what dbjective state changed from mathematics angle analysis
Electrocardio and skin electric signal important feature and combinations thereof.Ten eigenvalue clusters are selected into optimal characteristics collection.
As shown in figure 4, mRMR Feature Selection algorithm flow includes:
(1) the mutual information I (X, Y) between every kind of physiological characteristic parameter X, Y and target emotion C is defined;
(2) patient data set is inputted;
(3) correlation under every kind of data set between characteristic parameter and target emotion is calculated;
(4) redundancy analysis;
(5) the mutual information sequence between physiological characteristic parameter and target emotion;
(6) it chooses and maximum character subset is contributed to feature extraction.
In the S3 step, Fuzzy Pattern Recognition Method design object emotional state identification module is preferentially used.
Specifically, the fuzzy logic tool box (fuzzy logic) carried using Matlab is used to construct the machine in project
Device people's recovering aid mood physiological responses identification model, as shown in Figure 5.
Specific implementation includes:
(1) input, output language variable and its Linguistic Value are determined.The every of all patients under the experiment of target emotion task
Take turns input of the physiological signal data characteristic value screening final finishing measured at table, as model.Then according to the difference of Linguistic Value
Determine subordinating degree function, type function and function parameter.
(2) the proprietary numerical value by a characteristic value under every kind of mood task carries out arrangement analysis, establishes input mould
Type range.Input uses trigonometric function form.Define the whole value range under its target emotion.
(3) input domain of each species characteristic value in different emotional training scenes is determined respectively.As shown in Figure 5.
(4) fuzzy rule is established in setting:
1)If(input1 is Emean1)and(input2 is Esdnn1)and(input3 is HRsdnn1)and
(input4 is Esdsd) and (input5 is Epnn501) and (input6 is HRV triangle index 1) and
(input7 is Smean1)and(input8 is Sdifflstd1)and(input9 is Sdifflmean1)and
(input10 is Sdiff1 dvalue1)then(output1 is mfl);
2)If(input1 is Emean2)and(input2is Esdnn2)and(input3is HRsdnn2)and
(input4 is Esdsd2) and (input5 is Epnn502) and (input6 is HRV triangle index 2) and
(input7 is Smean2)and(input8 is Sdifflstd2)and(input9 is Sdifflmean2)and
(input10 is Sdiffldvalue2)then(output1 is mf2)。
Decision Control is defined as follows by exercising supervision to patient mood state during patient carries out rehabilitation training
Rule: initial rehabilitation training mode is selected by patient, healing robot is started to work;It is normally put when detecting that patient mood is in
Loose state, system are switched to initiative rehabilitation training mode;When detecting that patient mood is in positive state, work at present mould is kept
Formula, healing robot continue working;When detecting that patient muscle is in passive states, system is switched to passive rehabilitation training mould
Formula stops after a period of time.
With reference to the accompanying drawings and examples, a specific embodiment of the invention is described in detail:
The outpatient service of 7 vital signs stables is chosen and disease of being hospitalized in the attached Nanjing Tongren Hospital rehabilitation medicine center of certain university
Example is experimental subjects, and carries out above-mentioned experiment to it.From Physiological Psychology, target emotion can be reacted by going out with mathematics means analysis
Electrocardio and skin electric signal important feature of state change and combinations thereof.Based on the analysis results, mean value and first-order difference mean value etc. are special
Sign has more apparent statistical significance to the variation of target fatigue state.Further, there is statistical significance with obtained above
Myoelectricity mean value and the features such as first-order difference mean value as output, known based on Fuzzy Pattern Recognition Method design object emotional state
Other device, and be trained and cross validation.Fig. 6 gives the emotional state recognition result of patient, and abscissa is patient code, indulges
Coordinate is the percentage number correctly identified.The boredom discrimination of this 7 patients (R1-R7) reaches respectively as seen from Figure 6
To 85.70%, 100.00%, 57.10%, 85.70%, 71.40%, 71.40% and 85.70%.
Still there are many embodiment, all technical sides formed using equivalents or equivalent transformation by the present invention
Case is within the scope of the present invention.
Claims (6)
1. a kind of robot assisted rehabilitation control method based on fuzzy Emotion identification, it is characterised in that: this method includes following
Step:
S1: using the electrocardio and skin electric signal of biosensor acquisition patient, data prediction is carried out, obtains having with patient mood
The characteristic value of pass;
S2: the characteristic value that the S1 step obtains is filtered out into physiological signal essential signature sets using mRMR algorithm, obtains patient
Real-time emotion state;
S3: carrying out fuzzy reasoning to feature set, carries out mood knowledge to the training object in rehabilitation training using Emotion identification method
Not;Obtain emotional state of the patient in training.
S4: it according to the obtained feedback result controlled training rhythm of emotional state of the patient in training in S3 step, is identifying
When to passive mood, rehabilitation training difficulty is adjusted.
2. a kind of robot assisted rehabilitation control method based on fuzzy Emotion identification according to claim 1, feature
It is: in the S1 step,
Physiological signal feature extraction includes the following steps:
S11: it is pre-processed with electrocardio and skin electric signal of the normalized method to collected patient;Patient is obtained in training
Physiological signal in mood is analyzed for emotional state.
S12: totally 40 characteristic values such as respective mean value, standard deviation, first-order difference mean value are extracted from patient's electrocardio and skin electric signal
As feature set.
3. a kind of robot assisted rehabilitation control method based on fuzzy Emotion identification according to claim 1, feature
It is: in the S2 step, filters out 10 physiological signal critical eigenvalue composition essential signature sets using mRMR algorithm.
4. a kind of robot assisted rehabilitation control method based on fuzzy Emotion identification according to claim 3, feature
Be: in the S2 step, mRMR algorithm includes the following steps
S21: the mutual information I (X, Y) between every kind of physiological characteristic parameter X, Y and target emotion C is defined;
S22: input patient data set;
S23: the correlation under every kind of data set between characteristic parameter and target emotion is calculated;
S24: redundancy analysis;
S25: the mutual information sequence between physiological characteristic parameter and target emotion;
S26: it chooses and maximum character subset is contributed to feature extraction.
5. a kind of robot assisted rehabilitation control method based on fuzzy Emotion identification according to claim 1, feature
It is: in the S3 step, Emotion identification is carried out using Fuzzy Pattern Recognition Method.
6. a kind of robot assisted rehabilitation control method based on fuzzy Emotion identification according to claim 1, feature
It is: in the S4 step, consistent robot is changed with patients target's emotional state using training difficulty shift design
Auxiliary rehabilitation exercise switch controller adjusts training difficulty of the obtained Emotion identification result to the rehabilitation training
It is whole.When recognizing passive mood, rehabilitation training difficulty is adjusted to improve the enthusiasm of patient.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910488811.3A CN110251148A (en) | 2019-06-05 | 2019-06-05 | A kind of robot assisted rehabilitation control method based on fuzzy Emotion identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910488811.3A CN110251148A (en) | 2019-06-05 | 2019-06-05 | A kind of robot assisted rehabilitation control method based on fuzzy Emotion identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110251148A true CN110251148A (en) | 2019-09-20 |
Family
ID=67916972
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910488811.3A Pending CN110251148A (en) | 2019-06-05 | 2019-06-05 | A kind of robot assisted rehabilitation control method based on fuzzy Emotion identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110251148A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110838357A (en) * | 2019-11-19 | 2020-02-25 | 上海青鸿教育科技有限公司 | Attention holographic intelligent training system based on face recognition and dynamic capture |
CN110931104A (en) * | 2019-12-10 | 2020-03-27 | 清华大学 | Upper limb rehabilitation robot intelligent training system and method based on machine learning |
CN113158973A (en) * | 2021-05-12 | 2021-07-23 | 合肥工业大学 | Driver emotion intensity measurement method based on fuzzy classification calculation |
CN114681258A (en) * | 2020-12-25 | 2022-07-01 | 深圳Tcl新技术有限公司 | Method for adaptively adjusting massage mode and massage equipment |
CN114883014A (en) * | 2022-04-07 | 2022-08-09 | 南方医科大学口腔医院 | Patient emotion feedback device and method based on biological recognition and treatment couch |
-
2019
- 2019-06-05 CN CN201910488811.3A patent/CN110251148A/en active Pending
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110838357A (en) * | 2019-11-19 | 2020-02-25 | 上海青鸿教育科技有限公司 | Attention holographic intelligent training system based on face recognition and dynamic capture |
CN110931104A (en) * | 2019-12-10 | 2020-03-27 | 清华大学 | Upper limb rehabilitation robot intelligent training system and method based on machine learning |
CN114681258A (en) * | 2020-12-25 | 2022-07-01 | 深圳Tcl新技术有限公司 | Method for adaptively adjusting massage mode and massage equipment |
CN114681258B (en) * | 2020-12-25 | 2024-04-30 | 深圳Tcl新技术有限公司 | Method for adaptively adjusting massage mode and massage equipment |
CN113158973A (en) * | 2021-05-12 | 2021-07-23 | 合肥工业大学 | Driver emotion intensity measurement method based on fuzzy classification calculation |
CN113158973B (en) * | 2021-05-12 | 2022-08-30 | 合肥工业大学 | Driver emotion intensity measurement method based on fuzzy classification calculation |
CN114883014A (en) * | 2022-04-07 | 2022-08-09 | 南方医科大学口腔医院 | Patient emotion feedback device and method based on biological recognition and treatment couch |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110251148A (en) | A kind of robot assisted rehabilitation control method based on fuzzy Emotion identification | |
CN105893780B (en) | Based on the interactive psychiatric appraisal procedure monitored with brain wave and brain blood flow of VR | |
Romero-Laiseca et al. | A low-cost lower-limb brain-machine interface triggered by pedaling motor imagery for post-stroke patients rehabilitation | |
CN102319067B (en) | Nerve feedback training instrument used for brain memory function improvement on basis of electroencephalogram | |
KR102014176B1 (en) | Brain training simulation system based on behavior modeling | |
CN104483847A (en) | Robot auxiliary recovery human-computer interaction control method based on emotion recognition and hybrid theory | |
CN109589247A (en) | It is a kind of based on brain-machine-flesh information loop assistant robot system | |
CN109925582A (en) | Bimodal brain-machine interactive movement neural feedback training device and method | |
CN105852831A (en) | Equipment based on virtual reality interaction technology and brain function real-time monitoring technology | |
CN108721048A (en) | Rehabilitation training control method, computer readable storage medium and terminal | |
CN103301002B (en) | Based on maincenter-peripheral nervous recovery training method and the system of optics Brian Imaging | |
CN109646784A (en) | Immersive VR-based insomnia disorder psychotherapy system and method | |
CN110931104A (en) | Upper limb rehabilitation robot intelligent training system and method based on machine learning | |
Bian et al. | Physiology-based affect recognition during driving in virtual environment for autism intervention. | |
CN109106346A (en) | Depressive emotion screening and regulating system | |
Li et al. | Preliminary study of online real-time control system for lower extremity exoskeletons based on EEG and sEMG fusion | |
Su et al. | Intelligent medical rehabilitation training instrument based on movement coordination | |
US20220000426A1 (en) | Multi-modal brain-computer interface based system and method | |
CN109645962A (en) | A kind of robot assisted rehabilitation man-machine collaboration training method based on fatigue perception | |
CN115067970A (en) | Rehabilitation effect evaluation method and system based on electroencephalogram and electromyogram signals | |
Yang et al. | An sEMG-Based Human-Exoskeleton Interface Fusing Convolutional Neural Networks With Hand-Crafted Features | |
Nandagopal et al. | Brainwave Sensor based Smart Home Controller for Paralysed People | |
CN114587391A (en) | Brain-computer interface-based rehabilitation training device and training method | |
Brezany et al. | Towards precision brain disorder rehabilitation | |
CN105213033B (en) | Computer closed loop rehabilitation control system based on dyskinetic sacred disease |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190920 |