Multi-channel EMG Signals Research Articles

Automatic Detection of Outliers in Multi-Channel EMG Signals Using MFCC and SVM

The automatic detection of noisy channels in surface Electromyogram (sEMG) signals, at the time of recording, is very critical in making a noise-free EMG dataset. If an EMG signal contaminated by high-level noise is recorded, then it will be useless and can’t be used for any healthcare application. In this research work, a new machine learning-based paradigm is proposed to automate the detection of low-level and high-level noises occurring in different channels of high density and multi-channel sEMG signals. A modified version of mel frequency cepstral coefficients (mMFCC) is proposed for the extraction of features from sEMG channels along with other statistical parameters i-e complexity coefficient, hurst exponent, and root mean square. Several state-of-the-art classifiers such as Support Vector Machine (SVM), Ensemble Bagged Trees, Ensemble Subspace Discriminant, and Logistic Regression are used to automatically identify an EMG channel either bad or good based on these extracted features. Comparison-based analyses of these classifiers have also been considered based on total classification accuracy, prediction speed (observations/sec), and processing time. The proposed method is tested on 320 simulated EMG channels as well as 640 experimental EMG channels. SVM is used as our main classifier for the detection of noisy channels which gives a total classification accuracy of 99.4% for simulated EMG channels whereas accuracy of 98.9% is achieved for experimental EMG channels.

Detection of active segments of lower limbs EMG signal based on time-domain variance combined with short-term energy

Using EMG signal to realize gesture recognition is a technical difficulty in the application of EMG signal. In order to solve this problem and ensure the accuracy and timeliness of action classification and recognition, it is proposed to use time-domain variance combined with short-term energy to set a double threshold algorithm to detect effective activity segments. Based on the short-term energy and the zero-crossing rate, the minimum energy threshold and the frame window data variance value are designed. Then the original signal is processed by frame length and frameshift, and the complete signal data is divided into several small Windows. Finally, the effective activity segment is intercepted after comparing the upper and lower limits of the time-domain feature extraction variance with the set threshold. The experimental results show that the algorithm is effective in realizing the detection and interception of the start and end points of actions when processing single-channel or multi-channel EMG signals.

Performance Analysis of Various Supervised Classifiers for Predicting Preterm Delivery using Multi-channel Uterine EMG Signals

Performance Analysis of Various Supervised Classifiers for Predicting Preterm Delivery using Multi-channel Uterine EMG Signals

Hand recognition in gaming

Hand motion acknowledgment gives a savvy and characteristic method for human PC collaboration (HCI). It has applications running from customer hardware to control of therapeutic recovery (for example cell phone). So as to recognize hand motions, different sorts of detecting methods are used to get signals for example acknowledgment. Increasing speed base and electromyogram-based strategies are two research branches in the field of hand signal example acknowledgment. Quickening based (ACC-based) motion control is typically contemplated as a valuable connection methodology. It is appropriate to recognize perceptible, bigger scale signals with various hand directions of lower arm developments. With ACC-based strategies some unobtrusive finger or hand development might be overlooked while electromyogram-based (EMG-based) motion acknowledgment systems use multi-channel EMG signals which contain rich data about hand motions of different size scales. Because of certain issues natural in the EMG estimations, including the distinguishableness and reproducibility of estimation, the size of discriminable hand signal set is as yet restricted to 4-8 classes. So as to understand a characteristic and powerful signal based HCI framework, the determination of info hand motions that are well discriminable from one another is of essential significance. Thinking about the integral highlights of ACC-and EMG-estimations, we accept that their mix will expand the quantity of discriminable hand, wrist and lower arm signals and the precision of the acknowledgment framework. This paper depicts In IP Gaming we are proposing a framework wherein without utilizing sensors and Devices, we are recognizing the hand and signal with Simple Web camera and playing out the Image Processing system in which utilizing those motion, we can play game on reassure. In Image Process Gaming, the movements are identified through a web camera. These pictures are then passed for the picture handling. The procedures utilized for picture handling are hand motion identification, edge recognition, thresholding, form location. Utilizing OpenCV, which gives a library accumulation of capacities for various picture handling systems, these info pictures can be prepared and relating key strokes will be created. As of late, PC vision improvement has extraordinary headways and our everyday life undertakings are fragmented without utilizing PCs. The real info gadgets like Keyboard and mouse are accustomed to communicating with PCs. Among the different communication systems utilization of hands as an information is an appealing technique for building up regular Human Computer Interaction. By utilizing Hand motions client can convey more data in less Timespan. So for improving the interface among clients and PCs human PCs collaboration (HCI) innovation has incredible use.

Muscle fiber conduction velocity of the vastus medilais and lateralis muscle after eccentric exercise induced-muscle damage

Change in muscle fiber conduction velocity (MFCV) has been reported after eccentric exercise induces muscle fiber damage, most likely due to a change in membrane permeability of the injured fiber. The extent of damage to the muscle fiber depends on the morphological and architectural characteristics of the muscle fibers. Morphological and architectural characteristics of the VMO muscle fibers are different from VL muscle. Thus, it is expected that eccentric exercise of quadriceps muscle results in a non-uniform fiber damage within the VMO and VL muscle and, as a consequence, non-uniform changes in membrane excitability and conduction velocity. The aim of the study was to investigate MFCV of the VMO and VL muscles before and 24 h after eccentric exercise. Multichannel surface EMG signals were concurrently recorded from the right VMO and VL muscles of 15 healthy men during sustained isometric contractions at 50% of the maximal force. Maximal voluntary force significantly reduced after eccentric exercise with respect to the pre-exercise condition (P < 0.0001). MFCV decreased over time during the sustained contractions at faster rates when assessed 24 h after exercise (VMO = −26.1; VL = −20.1) with respect to the pre-exercise condition (VMO = −9.1; VL = −13.7, P < 0.0001). Moreover, VMO showed a greater rate of reduction in MFCV over sustained contraction (26.1 ± 10.7%) in comparison with VL muscle (20.1 ± 8.5%, P < 0.025) 24 h after eccentric exercise. The result indicates that eccentric exercise contributes to a larger reduction in MFCV within the VMO muscle as compared to the VL muscle. This may abolish the ability of VMO to counteract the lateral pull of the VL muscle during knee extension, thereby leaving the knee complex more vulnerable to injury.

Robust estimation of average twitch contraction forces of populations of motor units in humans

The characteristics of motor unit force twitch profiles provide important information for the understanding of the muscle force generation. The twitch force is commonly estimated with the spike-triggered averaging technique, which, despite the many limitations, has been important for clarifying central issues in force generation. In this study, we propose a new technique for the estimation of the average twitch profile of populations of motor units with uniform contractile properties. The method encompasses a model-based deconvolution of the force signal using the identified discharge times of a population of motor units. The proposed technique was validated using simulations and tested on signals recorded during voluntary activation. The results of the simulations showed that the proposed method provides accurate estimates (relative error <25%) of the main parameters of the average twitch force when the number of identified motor units is between 5% and 15% of the total number of active motor units. It is discussed that current detection and decomposition methods of multi-channel surface EMG signals allow decoding this relative sample of the active motor unit pool. However, even when this condition is not met, our results show that the estimates provided by the new method are anyway always superior to those obtained by the spike triggered average approach, especially for high motor unit synchronization levels and when a relatively small number of triggers is available. In conclusion, we present a new method that overcome the main limitations of the spike-triggered average for the study of contractile properties of individual motor units. The method provides a new reliable tool for the investigation of the determinants of muscle force.

Decomposition of Multi-Channel Intramuscular EMG Signals by Cyclostationary-Based Blind Source Separation.

We propose a novel decomposition method for electromyographic signals based on blind source separation. Using the cyclostationary properties of motor unit action potential trains (MUAPt), it is shown that the MUAPt can be decomposed by joint diagonalization of the cyclic spatial correlation matrix of the observations. After modeling the source signals, we provide the proof of orthogonality of the sources and of their delayed versions in a cyclostationary context. We tested the proposed method on simulated signals and showed that it can decompose up to six sources with a probability of correct detection and classification >95%, using only eight recording sites. Moreover, we tested the method on experimental multi-channel signals recorded with thin-film intramuscular electrodes, with a total of 32 recording sites. The rate of agreement of the decomposed MUAPt with those obtained by an expert using a validated tool for decomposition was >93%.

Multi-channel intramuscular and surface EMG decomposition by convolutive blind source separation

Objective. The study of motor unit behavior has been classically performed by selective recording systems of muscle electrical activity (EMG signals) and decomposition algorithms able to discriminate between individual motor unit action potentials from multi-unit signals. In this study, we provide a general framework for the decomposition of multi-channel intramuscular and surface EMG signals and we extensively validate this approach with experimental recordings. Approach. First, we describe the conditions under which the assumptions of the convolutive blind separation model are satisfied. Second, we propose an approach of convolutive sphering of the observations followed by an iterative extraction of the sources. This approach is then validated using intramuscular signals recorded by novel multi-channel thin-film electrodes on the Abductor Digiti Minimi of the hand and Tibilias Anterior muscles, as well as on high-density surface EMG signals recorded by electrode grids on the First Dorsal Interosseous muscle. The validation was based on the comparison with the gold standard of manual decomposition (for intramuscular recordings) and on the two-source method (for comparison of intramuscular and surface EMG recordings) for the three human muscles and contraction forces of up to 90% MVC. Main results. The average number of common sources identified for the validation was 14 ± 7 (averaged across all trials and subjects and all comparisons), with a rate of agreement in their discharge timings of 92.8 ± 3.2%. The average Decomposability Index, calculated on the automatic decomposed signals, was 16.0 ± 2.2 (7.3–44.1). For comparison, the same index calculated on the manual decomposed signals was 15.0 ± 3.0 (6.3–76.6). Significance. These results show that the method provides a solid framework for the decomposition of multi-channel invasive and non-invasive EMG signals that allows the study of the behavior of a large number of concurrently active motor units.

Control of word processing environment using myoelectric signals

This paper shows how myoelectric signals (EMG) can be used to generate control signals for further use in human–machine interfaces. Our custom-built portable USB device is able to capture multi-channel highspeed surface EMG signals from muscles and its software counterpart is capable to control common PC interface including ordinary text editors such as MS Word. At the time of the study the system utilized three parallel EMG channels to control user interfaces. The interaction was based on series of 1-of-N selections which specify rows and columns in on-screen keyboards. The selection was performed by quantification of selected muscle activity of the user. The system was further tested by a disabled person who provided input during a participatory design session. Our study has demonstrated that the system and the user interface can be used for effective text input and editing also in disabled people.

Detection and Recognition of Motor Unit Action Potentials in the Multi-Channel Surface EMG Signals

The method about the detection and recognition of MUAPs was explored by using the multi-channel sEMG signals at the low contraction force. A combined detection method of continuous wavelet transform and hypothesis testing was applied for each channel sEMG signal. The comprehensive judgemental rule was implemented and utilized to analyze the motor unit firing. Then, the single channel signal which contained the candidate MUAP waveforms was derived from the average processing of multi-channel sEMG signals. With the averaged signal, the clustering algorithm was applied, and the unclassified waveforms were identified. The experimental results showed that some illusive shapes were rejected and the satisfying recognition performance could be acquired by using the averaged sEMG signals.

Geometry assessment of anal sphincter muscle based on monopolar multichannel surface EMG signals

Anatomical studies on the external anal sphincter (EAS) indicate that superficial muscle fibres are circular at low depth within the anal canal. A more complex geometry of the fibres is documented for increasing depth within the muscle and along the anal canal. Monopolar intra-anal EMG signals recorded using an array of electrodes placed in circular direction have no common mode components if the muscle fibres are circular, with constant depth within the muscle and parallel to the detection array. Thus, the presence of common mode signals may provide indications about the geometry of muscle fibres of EAS. Intra-anal EMG signals were recorded from EAS of 12 subjects using an anal probe carrying three circumferential arrays of 16 electrodes at three depths within the anal canal. Contribution of common mode components in single MUAPs was lower for MUs located superficially in the muscle (Pearson correlation coefficient: R = −0.75, p ≪ 0.001) and at a lower depth within the anal canal (non-parametric one way Kruskal–Wallis ANOVA, Χ = 17.3, p < 0.001), in line with EAS anatomy. A large contribution of common mode components was found in the interference signal, suggesting that the signal receives contributions from far, large muscles (e.g. puborectalis, glutei).

P13-6 A simultaneous measurement system for MU discharge property and conduction velocity with multi-channel surface EMG signals

P13-6 A simultaneous measurement system for MU discharge property and conduction velocity with multi-channel surface EMG signals

1012 多チャンネル表面筋電図を用いた運動単位活動電位計測による反射系機能評価(OS28-1:最近の筋活動計測とその応用1)

1012 多チャンネル表面筋電図を用いた運動単位活動電位計測による反射系機能評価(OS28-1:最近の筋活動計測とその応用1)

Discharge Rate of Sternohyoid Motor Units Activated With Surface EMG Feedback

We analyzed individual motor units of the sternohyoid muscle with the aim of characterizing their minimum and maximum discharge rates and their variability in discharge during voluntary contractions. Surface EMG signals were recorded with an array of eight electrodes from the sternohyoid muscle of seven healthy men (age: 30.2+/-3.5 yr). The multichannel surface EMG signals were displayed as feedback for the subjects who identified and modulated the activity of one target motor unit in 30-s contractions during which the discharge rate was increased from minimum to maximum (ramp contraction), sustained at maximum level (sustained), or increased in brief bursts (burst). During the ramp contractions, the minimum average discharge rate over epochs of 1 s was 11.6+/-1.5 pulses per second (pps) and the maximum 57.0+/-5.7 pps (P<0.001). During the sustained contractions, the motor unit discharge rate decreased from 65.5+/-8.4 pps at the beginning to 52.9+/-7.6 pps at the end of the contraction (P<0.05). The coefficient of variation for the interspike interval during the sustained contractions was 40.2+/-9.8% and a large percentage of discharges had instantaneous rates>50 pps (52.2+/-12.5%) and>100 pps (8.0+/-1.2%), with peak values>150 pps. During the burst contractions, the instantaneous discharge rate reached average maximum values of 97.6+/-36.8 pps. The observed discharge rates and their variability are higher than those reported for limb muscles, which may be due to large synaptic input and noise received by these motor neurons.

Automatic decomposition of multichannel intramuscular EMG signals

We describe an automatic algorithm for decomposing multichannel EMG signals into their component motor unit action potential (MUAP) trains, including signals from widely separated recording sites in which MUAPs exhibit appreciable interchannel offset and jitter. The algorithm has two phases. In the clustering phase, the distinct, recurring MUAPs in each channel are identified, the ones that correspond to the same motor units are determined by their temporal relationships, and multichannel templates are computed. In the identification stage, the MUAP discharges in the signal are identified using matched filtering and superimposition resolution techniques. The algorithm looks for the MUAPs with the largest single channel components first, using matches in one channel to guide the search in other channels, and using information from the other channels to confirm or refute each identification. For validation, the algorithm was used to decompose 10 real 6-to-8-channel EMG signals containing activity from up to 25 motor units. Comparison with expert manual decomposition showed that the algorithm identified more than 75% of the total 176 MUAP trains with an accuracy greater than 95%. The algorithm is fast, robust, and shows promise to be accurate enough to be a useful tool for decomposing multichannel signals. It is freely available at http://emglab.stanford.edu.

The application of independent component analysis to the multi-channel surface electromyographic signals for separation of motor unit action potential trains: part I?measuring techniques

The purpose of this study is to examine whether or not the application of independent component analysis (ICA) is useful for separation of motor unit action potential trains (MUAPTs) from the multi-channel surface EMG (sEMG) signals. In this study, the eight-channel sEMG signals were recorded from tibialis anterior muscles during isometric dorsi-flexions at 5%, 10%, 15% and 20% maximal voluntary contraction. Recording MUAP waveforms with little time delay mounted between the channels were obtained by vertical sEMG channel arrangements to muscle fibers. The independent components estimated by FastICA were compared with the sEMG signals and the principal components calculated by principal component analysis (PCA). From our results, it was shown that FastICA could separate groups of similar MUAP waveforms of the sEMG signals separated into each independent component while PCA could not sufficiently separate the groups into the principal components. A greater reduction of interferences between different MUAP waveforms was demonstrated by the use of FastICA. Therefore, it is suggested that FastICA could provide much better discrimination of the properties of MUAPTs for sEMG signal decomposition, i.e. waveforms, discharge intervals, etc., than not only PCA but also the original sEMG signals.

Commentary

Commentary

The application of independent component analysis to the multi-channel surface electromyographic signals for separation of motor unit action potential trains: part I—measuring techniques

The purpose of this study is to examine whether or not the application of independent component analysis (ICA) is useful for separation of motor unit action potential trains (MUAPTs) from the multi-channel surface EMG (sEMG) signals. In this study, the eight-channel sEMG signals were recorded from tibialis anterior muscles during isometric dorsi-flexions at 5%, 10%, 15% and 20% maximal voluntary contraction. Recording MUAP waveforms with little time delay mounted between the channels were obtained by vertical sEMG channel arrangements to muscle fibers. The independent components estimated by FastICA were compared with the sEMG signals and the principal components calculated by principal component analysis (PCA). From our results, it was shown that FastICA could separate groups of similar MUAP waveforms of the sEMG signals separated into each independent component while PCA could not sufficiently separate the groups into the principal components. A greater reduction of interferences between different MUAP waveforms was demonstrated by the use of FastICA. Therefore, it is suggested that FastICA could provide much better discrimination of the properties of MUAPTs for sEMG signal decomposition, i.e. waveforms, discharge intervals, etc., than not only PCA but also the original sEMG signals.

Multichannel Surface EMG for the Non-Invasive Assessment of the Anal Sphincter Muscle

Background/Aims: This work focuses on recording, processing and interpretation of multichannel surface EMG detected from the external anal sphincter muscle. The aim is to describe the information that can be extracted from signals recorded with such a technique. Methods: The recording of many signals from different locations on a muscle allows the extraction of additional information on muscle physiology and anatomy with respect to that obtained by classic bipolar recordings. Multichannel EMG methods have been recently developed for the assessment of the external anal sphincter. An anal probe was used in this study to record signals at different depths within the anal canal during contractions at different effort levels. The plug is 150 mm in length and 14 mm in diameter, holding a circumferential array of 16 equally spaced silver bar electrodes, located at a distance of 20 mm from the probe tip and aligned with the probe axis. Results: Information about localization of the innervation zone, fiber length, EMG amplitude, muscle fiber conduction velocity and single motor unit analysis can be obtained from the signals recorded with the circumferential array by means of innovative signal processing techniques. Conclusions: The type of information extracted from multichannel surface EMG signals cannot be obtained with other currently available techniques. The technological innovation described in this work is promising for a further insight into the investigation of pelvic floor pathologies and rehabilitation treatments.

A new method for the extraction and classification of single motor unit action potentials from surface EMG signals

It has been shown that multi-channel surface EMG allows assessment of anatomical and physiological single motor unit (MU) properties. To get this information, the action potentials of single MUs should be extracted from the interference EMG signals. This study describes an automatic system for the detection and classification of MU action potentials from multi-channel surface EMG signals. The methods for the identification and extraction of action potentials from the raw signals and for their clustering into the MUs to which they belong are described. The segmentation phase is based on the matched Continuous Wavelet Transform (CWT) while the classification is performed by a multi-channel neural network that is a modified version of the multi-channel Adaptive Resonance Theory networks. The neural network can adapt to slow changes in the shape of the MU action potentials. The method does not require any interaction of the operator. The technique proposed was validated on simulated signals, at different levels of force, generated by a structure based surface EMG model. The MUs identified from the simulated signals covered almost the entire recruitment curve. Thus, the proposed algorithm was able to identify a MU sample representative of the muscle. Results on experimental signals recorded from different muscles and conditions are reported, showing the possibility of investigating anatomical and physiological properties of the detected MUs in a variety of practical cases. The main limitation of the approach is that complete firing patterns can be obtained only in specific cases due to MU action potential superpositions.