NLR, MLP, SVM, and LDA: a comparative analysis on EMG data from people with trans-radial amputation.

BACKGROUND: Currently, the typically adopted hand prosthesis surface electromyography (sEMG) control strategies do not provide the users with a natural control feeling and do not exploit all the potential of commercially available multi-fingered hand prostheses. Pattern recognition and machine learning techniques applied to sEMG can be effective for a natural control based on the residual muscles contraction of amputated people corresponding to phantom limb movements. As the researches has reached an advanced grade accuracy, these algorithms have been proved and the embedding is necessary for the realization of prosthetic devices. The aim of this work is to provide engineering tools and indications on how to choose the most suitable classifier, and its specific internal settings for an embedded control of multigrip hand prostheses. METHODS: By means of an innovative statistical analysis, we compare 4 different classifiers: Nonlinear Logistic Regression, Multi-Layer Perceptron, Support Vector Machine and Linear Discriminant Analysis, which was considered as ground truth. Experimental tests have been performed on sEMG data collected from 30 people with trans-radial amputation, in which the algorithms were evaluated for both performance and computational burden, then the statistical analysis has been based on the Wilcoxon Signed-Rank test and statistical significance was considered at p < 0.05. RESULTS: The comparative analysis among NLR, MLP and SVM shows that, for either classification performance and for the number of classification parameters, SVM attains the highest values followed by MLP, and then by NLR. However, using as unique constraint to evaluate the maximum acceptable complexity of each classifier one of the typically available memory of a high performance microcontroller, the comparison pointed out that for people with trans-radial amputation the algorithm that produces the best compromise is NLR closely followed by MLP. This result was also confirmed by the comparison with LDA with time domain features, which provided not significant differences of performance and computational burden between NLR and LDA. CONCLUSIONS: The proposed analysis would provide innovative engineering tools and indications on how to choose the most suitable classifier based on the application and the desired results for prostheses control.

EMG and ENG-envelope pattern recognition for prosthetic hand control.

BACKGROUND: This paper proposes a new approach for neural control of hand prostheses, grounded on pattern recognition applied to the envelope of neural signals (eENG). NEW METHOD: The ENG envelope was computed by taking into account the amplitude and the occurrence of the spike in the neural recording. A pattern recognition algorithm applied on muscular signals was defined as a reference and a comparative analysis with traditionally adopted Spike Sorting Algorithms (SSA) for neural signals has been carried out. Method validation was divided in two parts: firstly, neural signals recorded from one amputee subject through intraneural electrodes were offline analyzed to discriminate between the two performed gestures; secondly, algorithm performance decay with the increase of the number of classes was studied through synthetic data. RESULTS: An accuracy of 98.26% with real data was reached with the pattern recognition applied to eENG. SSA reached an accuracy of 70%. Increasing the number of classes worsens the accuracy of this algorithm. Additionally, computational time for the pattern recognition applied to eENG is very low (32.6 µs for each sample in the data window analyzed). COMPARISON WITH EXISTING METHOD: The eENG was proved to be more reliable in decoding the user intention than the SSA algorithm and it is computationally efficient. CONCLUSIONS: It was demonstrated that it is possible to apply the well-known techniques of EMG pattern recognition to a conveniently processed neural signal and can pave the way to the application of neural gesture decoding in upper limb prosthetics.