Gait Monitoring System Based On Plantar Pressure In Evaluating The Degrees Of Apoplexy Strephenopodia

Stroke patients often suffer from strephenopodia because of high muscle tension or muscle spasms.During rehabilitation training,this phenomenon is easy to damage the joints of the foot,which seriously affect their walking ability and rehabilitation.Studies have shown that timely diagnosis and correction of strephenopodia can help patients improve their walking function.The evaluation of the degree of strephenopodia is the basis for treatment and correction of strephenopodia.Therefore,the automatic detection of the degree of strephenopodia has played an important role in clinical applications and research.At present,existing strephenopodia detection methods,including traditional clinical gait analysis,gait video analysis and plantar pressure systems.There are some disadvantages:traditional clinical analysis relies on the clinical experience of professional rehabilitation doctors,and the huge demand for specialist doctors is a big challenge;Gait video analysis requires complex operations,and the general equipment is relatively expensive and difficult to popularize;The results obtained by the existing plantar pressure applications are relatively vague,and they are generally only used to identify the presence of strephenopodia.It cannot obtain clear and subtle changes in the angle of strephenopodia.In response to the above problems,this paper proposes a method for detecting strephenopodia angle based on plantar pressure signals,and builds a strephenopodia detection platform based on pressure signals and experimental verification.The main research work and contributions of this paper are as follows:First,the gait analysis treadmill system collects and processes the plantar pressure signals of the healthy person’s simulated strephenopodia patients,and uses the machine learning regression algorithm to establish a regression model to realize the strephenopodia angle detection.The results show that the three machine learning regression algorithms show good reliability and accuracy for the detection of strephenopodia angle [determination coefficient(R2)≥ 0.80],among which,Gaussian process regression(Gaussian process regression,GPR)achieved excellent detection performance in healthy participants,with an average determination coefficient(R2)of 0.93 and an average root-mean-square error(RMSE)of 0.67,compared to predecessors’ monitoring studies distinguished the degree of foot varus more finely and also had higher accuracy,which proved the feasibility of the method of detecting the angle of foot varus based on plantar pressure signals.Then,on the premise that the high-precision treadmill verified that the plantar pressure signal can correctly predict the angle of strephenopodia,and in order to reduce the detection cost and improve the convenience,we designed and established an insole-type gait monitoring system based on plantar pressure,And collected the plantar pressure signals of both healthy people and stroke strephenopodia patients and processed the signal,and used the machine learning regression algorithm to detect the degree of strephenopodia.The results show that the use of Gaussian process regression to achieve very good detection performance,with an average accuracy of 98.0%.This result proves the reliability of the pressure insole system to detect foot varus and has potential clinical application value.