Research And Design Of Intelligent Nursing Wheelchair System Based On EEG Control

At present,the number of elderly people over the age of 65 in China has reached 160 million,accounting for more than 10% of the country's total population.China has entered an age of population aging,and the problem of walking and cleaning care for the elderly has become increasingly prominent.In addition,the group of lower limbs disabled who has the problem of walking and cleaning care is urgently needed to be solved.With the development of science and technology,electric wheelchairs have improved their daily lives for groups with normal upper limb function and lower limbs disabled.It's difficult for people with physical disabilities to use traditional electric wheelchairs.Brain-Computer Interface(BCI)is a direct communication pathway between the brain and other electronic devices without the involvement of muscles and peripheral nerves.The BCI provides a new form of communication with the outside world for people with lower limb disabled.According to the above,this paper researches and develops a smart nursing wheelchair system based on EEG control.The system can help the elderly and lower limbs to solve the problem of walking and cleaning care,which has greatly established self-confidence and improved life satisfaction for them.In this paper,the research on brain-controlled intelligent nursing wheelchair system is divided into two parts: brain-controlled wheelchair and nursing monitoring.The brain-controlled wheelchair part mainly accomplishes the task of EEG signal acquisition,feature extraction,classification and identification,and issuing commands,which realizes the wheelchair forward,left turn and right turn control after the recognition of the user's motion intention.After comparing the characteristics of P300,SSVEP and MI control mode,this paper chooses MI-based BCI control mode.And imagining left/right foot movement to control wheelchair turning,or imaging two feet movement to control wheelchair forward.On the feature extraction algorithm,wavelet decomposition is used to reconstruct the signal,and the AR spectrum is used to estimate the power spectrum of the reconstructed signal and construct the wavelet energy entropy feature vector to complete the EEG signal feature extraction.On the classification and identification algorithm,the extracted feature vectors are classified and identified by Fisher classifier and SVM classifier,respectively.Finally,the SVM classifier is selected to complete the classification and identification of EEG signals.The system can be expressed as Wavelet-AR-SVM mode in EEG signal analysis and processing.The nursing monitoring part uses the PIC18F87K22 chip as the main controller.Through the HMI and cellphone APP,which realize the package processing of the user's defecation,andhelp the vulnerable group to solve the problem of handling the urine.This part mainly realizes the function of toilet lid ON/OFF,spray bar adjusting,waterway conversion,warm water cleaning,and warm air drying.The monitoring part uses CC2530 as the main controller to set up the wireless sensor network,and sends the collected vital signs of human body such as body temperature,heart rate,blood oxygen concentration and other information to the main controller to realize the monitoring of basic vital characteristics information.Family members and medical staff can also query the basic vital characteristics of users by mobile phones.In summary,the system provides a full range of services for people with mobility impairments,and improves their ability to live independently,which enhances their self-confidence and happiness index.It also provides convenience to family members and medical staff.Therefore the research of the system has important social benefits.