Fault-Tolerant Sensor Detection of sEMG signals: Quality Analysis Using a Two-Class Support Vector Machine.

The capacity to identify the contamination in surface electromyography (sEMG) signals is necessary for applying the sEMG controlled prosthesis over time. In this paper, the method for the automatic identification of commonly occurring contaminant types in sEMG signals is evaluated. The presented approach uses two-class support vector machine (SVM) trained with clean sEMG and artificially contaminated sEMG. The contaminants considered include electrocardiogram interference, motion artefact, power line interference, amplifier saturation, and electrode displacement. The results demonstrated that the sEMG signal with the contaminants could readily be distinguished, even with increase channels degraded. The SFTD detection depends on the noise type, whether the amputee or non-amputee subjects and which channel is being analysed. This method presented a suitable solution for the detection of contaminants in the sEMG signal, being able to provide the acquired signal validation before the movement intended recognition to operate in an intelligent recognition with greater reliability.

Novel method to characterize upper-limb movements based on paraconsistent logic and myoelectric signals.

This paper presents a novel method that investigates the use of Paraconsistent Artificial Neural Network (PANN) and upper-limb electromyography signals for classification of movements, due to their intrinsic ability to deal with imprecise, inconsistent and paracomplete data. The preliminary study presents promising results in terms of processing time and accuracy. The average classification accuracy for the developed paraconsistent logic method was 76,0±9,1% for 17 distinguish movements and a classification average processing time of 14 ms per movement.

Support vectors machine classification of surface electromyography for non-invasive naturally controlled hand prostheses.

The scientific researches in human rehabilitation techniques have continually evolved to offer again the mobility and freedom lost to disability. Many systems managed by myoelectric signals intended to mimic the movement of the human arm still have results considered partial, which makes it subject of many researches. The use of Natural Interfaces Signal Processing methods makes possible to design systems capable of offering prosthesis in a more natural and intuitive way. This paper presents a study investigating the use of forearm surface electromyography (sEMG) signals for classification of specific movements of hand using 12 sEMG channels and support vector machine (SVM). The system acquired the sEMG signal using a virtual model as a visual stimulus in order to demonstrate to the volunteer the hand movements which must be replicated by them. The Root Mean Square (RMS) value feature is extracted of the signal and it serves as input data for the classification with SVM. The classification stage used three types of kernel functions (linear, polynomial, radial basis) for comparison of the results. The average accuracy reached for the classification of seventeen distinct movements of 83.7% was achieved using the SVM linear classifier, 80.8% was achieved using the SVM polynomial classifier and 85.1% was achieved using the SVM radial basis classifier.

A new crank arm based load cell, with built-in conditioning circuit and strain gages, to measure the components of the force applied by a cyclist.

This report describes the development of a force platform based on instrumented load cells with built-in conditioning circuit and strain gages to measure and acquire the components of the force that is applied to the bike crank arm during pedaling in real conditions, and save them on a SD Card. To accomplish that, a complete new crank arm 3D solid model was developed in the SolidWorks, with dimensions equivalent to a commercial crank set and compatible with a conventional road bike, but with a compartment to support all the electronics necessary to measure 3 components of the force applied to the pedal during pedaling. After that, a 6082 T6 Aluminum Crankset based on the solid model was made and instrumented with three Wheatstone bridges each. The signals were conditioned on a printed circuit board, made on SMD technology, and acquired using a microcontroller with a DAC. Static deformation analysis showed a linearity error below 0.6% for all six channels. Dynamic analysis showed a natural frequency above 136Hz. A one-factor experiment design was performed with 5 amateur cyclists. ANOVA showed that the cyclist weight causes significant variation on the force applied to the bicycle pedal and its bilateral symmetry.