Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier.

One of the modern trends in the design of human-machine interfaces (HMI) is to involve the so called spiking neuron networks (SNNs) in signal processing. The SNNs can be trained by simple and efficient biologically inspired algorithms. In particular, we have shown that sensory neurons in the input layer of SNNs can simultaneously encode the input signal based both on the spiking frequency rate and on varying the latency in generating spikes. In the case of such mixed temporal-rate coding, the SNN should implement learning working properly for both types of coding. Based on this, we investigate how a single neuron can be trained with pure rate and temporal patterns, and then build a universal SNN that is trained using mixed coding. In particular, we study Hebbian and competitive learning in SNN in the context of temporal and rate coding problems. We show that the use of Hebbian learning through pair-based and triplet-based spike timing-dependent plasticity (STDP) rule is accomplishable for temporal coding, but not for rate coding. Synaptic competition inducing depression of poorly used synapses is required to ensure a neural selectivity in the rate coding. This kind of competition can be implemented by the so-called forgetting function that is dependent on neuron activity. We show that coherent use of the triplet-based STDP and synaptic competition with the forgetting function is sufficient for the rate coding. Next, we propose a SNN capable of classifying electromyographical (EMG) patterns using an unsupervised learning procedure. The neuron competition achieved via lateral inhibition ensures the "winner takes all" principle among classifier neurons. The SNN also provides gradual output response dependent on muscular contraction strength. Furthermore, we modify the SNN to implement a supervised learning method based on stimulation of the target classifier neuron synchronously with the network input. In a problem of discrimination of three EMG patterns, the SNN with supervised learning shows median accuracy 99.5% that is close to the result demonstrated by multi-layer perceptron learned by back propagation of an error algorithm.

Classification complexity in myoelectric pattern recognition.

BACKGROUND: Limb prosthetics, exoskeletons, and neurorehabilitation devices can be intuitively controlled using myoelectric pattern recognition (MPR) to decode the subject's intended movement. In conventional MPR, descriptive electromyography (EMG) features representing the intended movement are fed into a classification algorithm. The separability of the different movements in the feature space significantly affects the classification complexity. Classification complexity estimating algorithms (CCEAs) were studied in this work in order to improve feature selection, predict MPR performance, and inform on faulty data acquisition. METHODS: CCEAs such as nearest neighbor separability (NNS), purity, repeatability index (RI), and separability index (SI) were evaluated based on their correlation with classification accuracy, as well as on their suitability to produce highly performing EMG feature sets. SI was evaluated using Mahalanobis distance, Bhattacharyya distance, Hellinger distance, Kullback-Leibler divergence, and a modified version of Mahalanobis distance. Three commonly used classifiers in MPR were used to compute classification accuracy (linear discriminant analysis (LDA), multi-layer perceptron (MLP), and support vector machine (SVM)). The algorithms and analytic graphical user interfaces produced in this work are freely available in BioPatRec. RESULTS: NNS and SI were found to be highly correlated with classification accuracy (correlations up to 0.98 for both algorithms) and capable of yielding highly descriptive feature sets. Additionally, the experiments revealed how the level of correlation between the inputs of the classifiers influences classification accuracy, and emphasizes the classifiers' sensitivity to such redundancy. CONCLUSIONS: This study deepens the understanding of the classification complexity in prediction of motor volition based on myoelectric information. It also provides researchers with tools to analyze myoelectric recordings in order to improve classification performance.

Prospective validation study of Cernea classification for predicting EMG alterations of the external branch of the superior laryngeal nerve.

PURPOSES: Cernea classification is applied to describe the external branch of the superior laryngeal nerve (EBSLN). Using intraoperative neural monitoring we evaluated whether or not this classification is useful for predicting which EBSLN subtype has an increased risk of injury. METHODS: An analysis of 400 EBSLN. The identification of EBSLN was achieved with both cricothyroid muscle twitch and the glottis evoked electromyography response. We defined S1 initial EBSLN stimulation at identification and S2 final nerve stimulation achieved in the most cranial aspect of the nerve exposed above the area of surgical dissection after superior artery ligation. RESULTS: The mean S1 amplitude acquired was 259+/67 (180-421), 321 +/79 (192-391), 371 +/38 (200-551) µV, respectively, for type 1, 2A, 2B (p = 0.08). The S1 and S2 amplitudes were similar in type 1 (p = 0.3). The S1 and S2 determinations changed significantly in type 2A and 2B (p = 0.04 and 0.03). EBSLN which demonstrated a >25 % decreased amplitude in S2 increased significantly from Type 1 (4.9 %) to Type 2A (11.2 %) and 2B (18 %) (p = 0.01). None of type 1, 2.8 % type 2A and 3 % type 2B showed a loss of EBSLN conductivity. The latency determinations did not vary significantly for any parameter compared. CONCLUSIONS: The Cernea classification was, therefore, found to predict the risk of EBSLN stress. We identified amplitude differences between S1 and S2 determinations in type 2A and 2B, thus confirming that surgical dissection in these subtypes is, therefore, extremely difficult to perform.

Kinematical and EMG-classifications of a fencing attack.

8 expert fencers were studied with a 3-dimensional motion analysis system. Each subject performed 10 flèche attacks toward a standardized target. Surface electromyography signals (EMG) were recorded of the deltoid pars clavicularis, infraspinatus and triceps brachii caput laterale muscles of the weapon arm. The recorded EMGs were averaged using EMG wavelet-transformation software. 4 phases were defined based on the arm kinematics and used to classify fencers into 2 groups. A first group of 4 fencers showed an early maximal elbow extension (Early MEE) whereas the second group presented a late maximal elbow extension (Late MEE). 2 EMG-classifications were based on this kinematical classification, one in the time-domain and the other in the frequency-domain by using the spherical classification. The time-domain EMG-classification showed a significantly ( P=0.03) higher normalized deltoid intensity for the Early MEE group (91 ± 18%) than the Late MEE group (36 ± 13%) in the attack phase. The spherical classification revealed that the activity of all the muscles was significantly classified (recognition rate 75%, P=0.04) between the 2 groups. This study of EMG and kinematics of the weapon upper limb in fencing proposes several classifications, which implies a relationship between kinematic strategies, muscular activations and fencing success.

Mean power frequency during speech in myalgia patients.

The purpose of this study was to clarify a difference of mean power frequency (MPF) during speech between control and myalgia patients groups. The control group consisted of 20 asymptomatic volunteers and the myalgia patients group consisted of 19 patients. A bilateral electromyogram (EMG) of masseter muscles during speech movement was recorded using surface electrodes, and the EMG data were stored and analysed with a computer-based EMG analyzer. The MPF during the entire duration of EMG burst during speech was compared between the control and myalgia group. The average (SD) MPFs during speech in the myalgia and control groups were 214.06 (17.23) and 183.39 (22.35) Hz, respectively, significantly higher in the former (P < 0.001). In myalgia patients, firing rates or recruitment of motor units innervated by high threshold motoneurons might decrease and lead to a higher MPF. The result suggests the possibility that muscle pain, that is a subjective experience, could be evaluated by objective data that is calculated from electromyographic activities which is recorded during speech.

A Subject-Transfer Framework Based on Single-Trial EMG Analysis Using Convolutional Neural Networks.

In recent years, electromyography (EMG)-based practical myoelectric interfaces have been developed to improve the quality of daily life for people with physical disabilities. With these interfaces, it is very important to decode a user's movement intention, to properly control the external devices. However, improving the performance of these interfaces is difficult due to the high variations in the EMG signal patterns caused by intra-user variability. Therefore, this paper proposes a novel subject-transfer framework for decoding hand movements, which is robust in terms of intra-user variability. In the proposed framework, supportive convolutional neural network (CNN) classifiers, which are pre-trained using the EMG data of several subjects, are selected and fine-tuned for the target subject via single-trial analysis. Then, the target subject's hand movements are classified by voting the outputs of the supportive CNN classifiers. The feasibility of the proposed framework is validated with NinaPro databases 2 and 3, which comprise 49 hand movements of 40 healthy and 11 amputee subjects, respectively. The experimental results indicate that, when compared to the self-decoding framework, which uses only the target subject's data, the proposed framework can successfully decode hand movements with improved performance in both healthy and amputee subjects. From the experimental results, the proposed subject-transfer framework can be seen to represent a useful tool for EMG-based practical myoelectric interfaces controlling external devices.

An LDA-Based Approach for Real-Time Simultaneous Classification of Movements Using Surface Electromyography.

Myoelectric-based decoding strategies offer significant advantages in the areas of human-machine interactions because they are intuitive and require less cognitive effort from the users. However, a general drawback in using machine learning techniques for classification is that the decoder is limited to predicting only one movement at any instant and hence restricted to performing the motion in a sequential manner, whereas human motor control strategy involves simultaneous actuation of multiple degrees of freedom (DOFs) and is considered to be a natural and efficient way of performing tasks. Simultaneous decoding in the context of myoelectric-based movement control is a challenge that is being addressed recently and is increasingly popular. In this paper, we propose a novel classification strategy capable of decoding both the individual and combined movements, by collecting data from only the individual motions. Additionally, we exploit low-dimensional representation of the myoelectric signals using a supervised decomposition algorithm called linear discriminant analysis, to simplify the complexity of control and reduce computational cost. The performance of the decoding algorithm is tested in an online context for the two DOFs task comprising the hand and wrist movements. Results indicate an overall classification accuracy of 88.02% for both the individual and combined motions.

Multiday Evaluation of Techniques for EMG-Based Classification of Hand Motions.

Currently, most of the adopted myoelectric schemes for upper limb prostheses do not provide users with intuitive control. Higher accuracies have been reported using different classification algorithms but investigation on the reliability over time for these methods is very limited. In this study, we compared for the first time the longitudinal performance of selected state-of-the-art techniques for electromyography (EMG) based classification of hand motions. Experiments were conducted on ten able-bodied and six transradial amputees for seven continuous days. Linear discriminant analysis (LDA), artificial neural network (ANN), support vector machine (SVM), K-nearest neighbor (KNN), and decision trees (TREE) were compared. Comparative analysis showed that the ANN attained highest classification accuracy followed by LDA. Three-way repeated ANOVA test showed a significant difference (P < 0.001) between EMG types (surface, intramuscular, and combined), days (1-7), classifiers, and their interactions. Performance on the last day was significantly better (P < 0.05) than the first day for all classifiers and EMG types. Within-day, classification error (WCE) across all subject and days in ANN was: surface (9.12 ± 7.38%), intramuscular (11.86 ± 7.84%), and combined (6.11 ± 7.46%). The between-day analysis in a leave-one-day-out fashion showed that the ANN was the optimal classifier (surface (21.88 ± 4.14%), intramuscular (29.33 ± 2.58%), and combined (14.37 ± 3.10%). Results indicate that within day performances of classifiers may be similar but over time, it may lead to a substantially different outcome. Furthermore, training ANN on multiple days might allow capturing time-dependent variability in the EMG signals and thus minimizing the necessity for daily system recalibration.

Transfer Spectral Entropy and Application to Functional Corticomuscular Coupling.

Functional corticomuscular coupling (FCMC) with different rhythmic oscillations plays different roles in neural communication and interaction between the central nervous system and the peripheral system. Larger methods, such as coherence and Granger causality (GC), have been used to describe the frequency band characteristics in the frequency domain, but they fail to account for the inherent complexity. Considering that the transfer entropy (TE) method as an information theory has advantages in complexity and direction, we extended it and proposed a novel method named transfer spectral entropy (TSE) to explore the local frequency band characteristics between two coupling signals. To verify this, we introduced a Henon model and a neural mass model to generate the simulation signals. We then applied the proposed method to explore the FCMC by analyzing the correlation between the EEG and EMG signals during steady-state force output. Simulation results showed that the TSE method, compared with the GC method, not only described the information interaction in the local frequency band but also restrained the "false coupling." In addition, the results also revealed that the TSE method was sensitive to coupling strength but not to the data length. Further analysis of the experimental data showed that beta1 (15-25 Hz) and beta2 (25-35 Hz) bands were prominent in the FCMC for both EEG-to-EMG and EMG-to-EEG directions. In addition, the statistical analysis of the significant area indicated that the coupling in the EEG-to-EMG direction was higher at the beta1 and beta2 bands than that in the EMG-to-EEG direction, and the coupling in the EMG-to-EEG direction was higher at the gamma1 band (35-45 Hz) than that in the opposition. The FCMC results complementarily refined the previous studies that mainly focused on the beta band (15-35 Hz). The simulation and experimental data expound the effectiveness of the TSE model to describe the information interaction in the local frequency band between two time series, and this study extends the relative studies on FCMC.

A sEMG Classification Framework with Less Training Data.

Supervised machine learning algorithms, such as Artificial Neural Network (ANN), have been applied to surface electromyograph (sEMG) to classify user's muscular states. This paper introduces a novel framework to design a binary sEMG classifier to distinguish if the user performs a repetitive motion with a dumbbell. This framework enables to reduce the number of tasks required for collecting training data as it utilizes prior knowledge of sEMG. The performance of the proposed classifier is validated experimentally. Experimental results show that the proposed framework enables the design of a classifier which distinguishes the user's state with a 95.7% success rate. This accuracy is comparable to an accuracy of ANN classifier (99.6%), but with less training data. Under the identical training conditions, the accuracy of the proposed framework outperforms the ANN classifier whose accuracy drops to 65.6%.

Anomaly Detection of Electromyographic Signals.

In this paper, we provide a robust framework to detect anomalous electromyographic (EMG) signals and identify contamination types. As a first step for feature selection, optimally selected Lawton wavelets transform is applied. Robust principal component analysis (rPCA) is then performed on these wavelet coefficients to obtain features in a lower dimension. The rPCA based features are used for constructing a self-organizing map (SOM). Finally, hierarchical clustering is applied on the SOM that separates anomalous signals residing in the smaller clusters and breaks them into logical units for contamination identification. The proposed methodology is tested using synthetic and real world EMG signals. The synthetic EMG signals are generated using a heteroscedastic process mimicking desired experimental setups. A sub-part of these synthetic signals is introduced with anomalies. These results are followed with real EMG signals introduced with synthetic anomalies. Finally, a heterogeneous real world data set is used with known quality issues under an unsupervised setting. The framework provides recall of 90% (± 3.3) and precision of 99%(±0.4).

An ICA-EBM-Based sEMG Classifier for Recognizing Lower Limb Movements in Individuals With and Without Knee Pathology.

Surface electromyography (sEMG) data acquired during lower limb movements has the potential for investigating knee pathology. Nevertheless, a major challenge encountered with sEMG signals generated by lower limb movements is the intersubject variability, because the signals recorded from the leg or thigh muscles are contingent on the characteristics of a subject such as gait activity and muscle structure. In order to cope with this difficulty, we have designed a three-step classification scheme. First, the multichannel sEMG is decomposed into activities of the underlying sources by means of independent component analysis via entropy bound minimization. Next, a set of time-domain features, which would best discriminate various movements, are extracted from the source estimates. Finally, the feature selection is performed with the help of the Fisher score and a scree-plot-based statistical technique, prior to feeding the dimension-reduced features to the linear discriminant analysis. The investigation involves 11 healthy subjects and 11 individuals with knee pathology performing three different lower limb movements, namely, walking, sitting, and standing, which yielded an average classification accuracy of 96.1% and 86.2%, respectively. While the outcome of this study per se is very encouraging, with suitable improvement, the clinical application of such an sEMG-based pattern recognition system that distinguishes healthy and knee pathological subjects would be an attractive consequence.

Classification of Transient Myoelectric Signals for the Control of Multi-Grasp Hand Prostheses.

Understanding the neurophysiological signals underlying voluntary motor control and decoding them for controlling limb prostheses is one of the major challenges in applied neuroscience and rehabilitation engineering. While pattern recognition of continuous myoelectric (EMG) signals is arguably the most investigated approach for hand prosthesis control, its underlying assumption is poorly supported, i.e., that repeated muscular contractions produce consistent patterns of steady-state EMGs. In fact, it still remains to be shown that pattern recognition-based controllers allow natural control over multiple grasps in hand prosthesis outside well-controlled laboratory settings. Here, we propose an approach that relies on decoding the intended grasp from forearm EMG recordings associated with the onset of muscle contraction as opposed to the steady-state signals. Eight unimpaired individuals and two hand amputees performed four grasping movements with a variety of arm postures while EMG recordings subsequently processed to mimic signals picked up by conventional myoelectric sensors were obtained from their forearms and residual limbs, respectively. Off-line data analyses demonstrated the feasibility of the approach also with respect to the limb position effect. The sampling frequency and length of the classified EMG window that off-line resulted in optimal performance were applied to a controller of a research prosthesis worn by one hand amputee and proved functional in real-time when operated under realistic working conditions.

A Classification Method for Myoelectric Control of Hand Prostheses Inspired by Muscle Coordination.

Dexterous upper limb myoelectric prostheses can, to some extent, restore the motor functions lost after an amputation. However, ensuring the reliability of myoelectric control is still an open challenge. In this paper, we propose a classification method that exploits the regularity in muscle activation patterns (uniform scaling) across different force levels within a given movement class. This assumption leads to a simple training procedure, using training data collected at single contraction intensity for each movement class. The proposed method was compared to the widely accepted benchmark [linear discriminant analysis (LDA) classifier] using off-line and online evaluation. The off-line classification errors obtained with the new method were either lower or higher than LDA depending upon the chosen feature set. In the online evaluation, the new classification method was operated using amplitude-EMG features and compared to the state-of-the-art LDA classifier combined with the time domain feature set. The online evaluation was performed in 11 able-bodied and one amputee subject using a set of four functional tasks mimicking daily-life activities. The tasks assessed the dexterity (e.g., switching between functions) and robustness of control (e.g., handling heavy objects). With the new classification scheme, the amputee performed better in all functional tasks, whereas the able-bodied subjects performed significantly better in three out of four functional tasks. Overall, the novel method outperformed the state-of-the-art approach (LDA) while utilizing less training data and a smaller feature set. The proposed method is, therefore, a simple but effective and robust classification scheme, convenient for online implementation and clinical use.

The effect of time on EMG classification of hand motions in able-bodied and transradial amputees.

While several studies have demonstrated the short-term performance of pattern recognition systems, long-term investigations are very limited. In this study, we investigated changes in classification performance over time. Ten able-bodied individuals and six amputees took part in this study. EMG signals were recorded concurrently from surface and intramuscular electrodes, with intramuscular electrodes kept in the muscles for seven days. Seven hand motions were evaluated daily using linear discriminant analysis and the classification error quantified within (WCE) and between (BCE) days. BCE was computed for all possible combinations between the days. For all subjects, surface sEMG (7.2 ±â€¯7.6%), iEMG (11.9 ±â€¯9.1%) and cEMG (4.6 ±â€¯4.8%) were significantly different (P < 0.001) from each other. A regression between WCE and days (1-7) was on average not significant implying that performance may be considered similar within each day. Regression between BCE and time difference (Df) in days was significant. The slope between BCE and Df (0-6) was significantly different from zero for sEMG (R2 = 89%) and iEMG (R2 = 95%) in amputees. Results indicate that performance continuously degrades as the time difference between training and testing day increases. Furthermore, for iEMG, performance in amputees was directly proportional to the size of the residual limb.

A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series.

Sleep stage classification constitutes an important preliminary exam in the diagnosis of sleep disorders. It is traditionally performed by a sleep expert who assigns to each 30 s of the signal of a sleep stage, based on the visual inspection of signals such as electroencephalograms (EEGs), electrooculograms (EOGs), electrocardiograms, and electromyograms (EMGs). We introduce here the first deep learning approach for sleep stage classification that learns end-to-end without computing spectrograms or extracting handcrafted features, that exploits all multivariate and multimodal polysomnography (PSG) signals (EEG, EMG, and EOG), and that can exploit the temporal context of each 30-s window of data. For each modality, the first layer learns linear spatial filters that exploit the array of sensors to increase the signal-to-noise ratio, and the last layer feeds the learnt representation to a softmax classifier. Our model is compared to alternative automatic approaches based on convolutional networks or decisions trees. Results obtained on 61 publicly available PSG records with up to 20 EEG channels demonstrate that our network architecture yields the state-of-the-art performance. Our study reveals a number of insights on the spatiotemporal distribution of the signal of interest: a good tradeoff for optimal classification performance measured with balanced accuracy is to use 6 EEG with 2 EOG (left and right) and 3 EMG chin channels. Also exploiting 1 min of data before and after each data segment offers the strongest improvement when a limited number of channels are available. As sleep experts, our system exploits the multivariate and multimodal nature of PSG signals in order to deliver the state-of-the-art classification performance with a small computational cost.

Design of continuous EMG classification approaches towards the control of a robotic exoskeleton in reaching movements.

Myoelectric control of rehabilitation devices engages active recruitment of muscles for motor task accomplishment, which has been proven to be essential in motor rehabilitation. Unfortunately, most electromyographic (EMG) activity-based controls are limited to one single degree-of-freedom (DoF), not permitting multi-joint functional tasks. On the other hand, discrete EMG-triggered approaches fail to provide continuous feedback about muscle recruitment during movement. For such purposes, myoelectric interfaces for continuous recognition of functional movements are necessary. Here we recorded EMG activity using 5 bipolar electrodes placed on the upper-arm in 8 healthy participants while they performed reaching movements in 8 different directions. A pseudo on-line system was developed to continuously predict movement intention and attempted arm direction. We evaluated two hierarchical classification approaches. Movement intention detection triggered different movement direction classifiers (4 or 8 classes) that were trained and tested over a 5-fold cross validation. We also investigated the effect of 3 different window lengths to extract EMG features on classification. We obtained classification accuracies above 70% for both hierarchical approaches. These results highlight the viability of classifying online 8 upper-arm different directions using surface EMG activity of 5 muscles and represent a first step towards an online EMG-based control for rehabilitation devices.

Study on Interaction Between Temporal and Spatial Information in Classification of EMG Signals for Myoelectric Prostheses.

Advanced forearm prosthetic devices employ classifiers to recognize different electromyography (EMG) signal patterns, in order to identify the user's intended motion gesture. The classification accuracy is one of the main determinants of real-time controllability of a prosthetic limb and hence the necessity to achieve as high an accuracy as possible. In this paper, we study the effects of the temporal and spatial information provided to the classifier on its off-line performance and analyze their inter-dependencies. EMG data associated with seven practical hand gestures were recorded from partial-hand and trans-radial amputee volunteers as well as able-bodied volunteers. An extensive investigation was conducted to study the effect of analysis window length, window overlap, and the number of electrode channels on the classification accuracy as well as their interactions. Our main discoveries are that the effect of analysis window length on classification accuracy is practically independent of the number of electrodes for all participant groups; window overlap has no direct influence on classifier performance, irrespective of the window length, number of channels, or limb condition; the type of limb deficiency and the existing channel count influence the reduction in classification error achieved by adding more number of channels; partial-hand amputees outperform trans-radial amputees, with classification accuracies of only 11.3% below values achieved by able-bodied volunteers.

Classification of EMG signals using wavelet neural network.

An accurate and computationally efficient means of classifying electromyographic (EMG) signal patterns has been the subject of considerable research effort in recent years. Quantitative analysis of EMG signals provides an important source of information for the diagnosis of neuromuscular disorders. Following the recent development of computer-aided EMG equipment, different methodologies in the time domain and frequency domain have been followed for quantitative analysis. In this study, feedforward error backpropagation artificial neural networks (FEBANN) and wavelet neural networks (WNN) based classifiers were developed and compared in relation to their accuracy in classification of EMG signals. In these methods, we used an autoregressive (AR) model of EMG signals as an input to classification system. A total of 1200 MUPs obtained from 7 normal subjects, 7 subjects suffering from myopathy and 13 subjects suffering from neurogenic disease were analyzed. The success rate for the WNN technique was 90.7% and for the FEBANN technique 88%. The comparisons between the developed classifiers were primarily based on a number of scalar performance measures pertaining to the classification. The WNN-based classifier outperformed the FEBANN counterpart. The proposed WNN classification may support expert decisions and add weight to EMG differential diagnosis.

Surface electromyography as a tool to assess the responses of car passengers to lateral accelerations: Part I. Extraction of relevant muscular activities from noisy recordings.

The aim of this paper is to develop a method to extract relevant activities from surface electromyography (SEMG) recordings under difficult experimental conditions with a poor signal to noise ratio. High amplitude artifacts, the QRS complex, low frequency noise and white noise significantly alter EMG characteristics. The CEM algorithm proved to be useful for segmentation of SEMG signals into high amplitude artifacts (HAA), phasic activity (PA) and background postural activity (BA) classes. This segmentation was performed on signal energy, with classes belonging to a chi(2) distribution. Ninety-five percent of HAA events and 96.25% of BA events were detected, and the remaining noise was then identified using AR modeling, a classification based upon the position of the coordinates of the pole of highest module. This method eliminated 91.5% of noise and misclassified only 3.3% of EMG events when applied to SEMG recorded on passengers subjected to lateral accelerations.