Abstract: This work describes a system that uses electromyography (EMG) signals obtained from muscle sensors and an Artificial Neural Network (ANN) for signal classification and pattern recognition that is used to control a small unmanned aerial vehicle using specific arm movements. The main objective of this endeavor is the development of an intelligent interface that allows the user to control the flight of a drone beyond direct manual control. The sensor used were the MyoWare Muscle sensor which contains two EMG electrodes used to collect signals from the posterior (extensor) and anterior (flexor) forearm, and the bicep. The collection of the raw signals from each sensor was performed using an Arduino Uno. Data processing algorithms were developed with the purpose of classifying the signals generated by the arm’s muscles when performing specific movements, namely: flexing, resting, and motion of the arm. With these arm motions roll control of the drone was achieved. MATLAB software was utilized to condition the signals and prepare them for the classification. To generate the input vector for the ANN and perform the classification, the root mean square and the standard deviation were processed for the signals from each electrode. The neuromuscular information was trained using an ANN with a single 10 neurons hidden layer to categorize the four targets. The result of the classification shows that an accuracy of 97.5% was obtained. Afterwards, classification results are used to generate the appropriate control signals from the computer to the drone through a Wi-Fi network connection. These procedures were successfully tested, where the drone responded successfully in real time to the commanded inputs.
Abstract: The aim of this study was to remove the two principal
noises which disturb the surface electromyography signal
(Diaphragm). These signals are the electrocardiogram ECG artefact
and the power line interference artefact. The algorithm proposed
focuses on a new Lean Mean Square (LMS) Widrow adaptive
structure. These structures require a reference signal that is correlated
with the noise contaminating the signal. The noise references are
then extracted : first with a noise reference mathematically
constructed using two different cosine functions; 50Hz (the
fundamental) function and 150Hz (the first harmonic) function for
the power line interference and second with a matching pursuit
technique combined to an LMS structure for the ECG artefact
estimation. The two removal procedures are attained without the use
of supplementary electrodes. These techniques of filtering are
validated on real records of surface diaphragm electromyography
signal. The performance of the proposed methods was compared with
already conducted research results.
Abstract: Prolonged immobilization leads to significant
weakness and atrophy of the skeletal muscle and can also impair the
recovery of muscle strength following injury. Therefore, it is
important to minimize the period under immobilization and accelerate
the return to normal activity. This study examined the effects of heat
treatment and rest-inserted exercise on the muscle activity of the lower
limb during knee flexion/extension. Twelve healthy subjects were
assigned to 4 groups that included: (1) heat treatment + rest-inserted
exercise; (2) heat + continuous exercise; (3) no heat + rest-inserted
exercise; and (4) no heat + continuous exercise. Heat treatment was
applied for 15 mins prior to exercise. Continuous exercise groups
performed knee flexion/extension at 0.5 Hz for 300 cycles without rest
whereas rest-inserted exercise groups performed the same exercise but
with 2 mins rest inserted every 60 cycles of continuous exercise.
Changes in the rectus femoris and hamstring muscle activities were
assessed at 0, 1, and 2 weeks of treatment by measuring the
electromyography signals of isokinetic maximum voluntary
contraction. Significant increases in both the rectus femoris and
hamstring muscles were observed after 2 weeks of treatment only
when both heat treatment and rest-inserted exercise were performed.
These results suggest that combination of various treatment techniques,
such as heat treatment and rest-inserted exercise, may expedite the
recovery of muscle strength following immobilization.
Abstract: Electromyography (EMG) signal processing has been investigated remarkably regarding various applications such as in rehabilitation systems. Specifically, wavelet transform has served as a powerful technique to scrutinize EMG signals since wavelet transform is consistent with the nature of EMG as a non-stationary signal. In this paper, the efficiency of wavelet transform in surface EMG feature extraction is investigated from four levels of wavelet decomposition and a comparative study between different mother wavelets had been done. To recognize the best function and level of wavelet analysis, two evaluation criteria, scatter plot and RES index are recruited. Hereupon, four wavelet families, namely, Daubechies, Coiflets, Symlets and Biorthogonal are studied in wavelet decomposition stage. Consequently, the results show that only features from first and second level of wavelet decomposition yields good performance and some functions of various wavelet families can lead to an improvement in separability class of different hand movements.