scholarly journals Classification of Walking Environments Using Deep Learning Approach Based on Surface EMG Sensors Only

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4204
Author(s):  
Pankwon Kim ◽  
Jinkyu Lee ◽  
Choongsoo S. Shin
Keyword(s):  
Muscle Activation ◽  
Lower Extremities ◽  
Surface Emg ◽  
High Accuracy ◽  
Triceps Surae ◽  
Assistive Device ◽  
Artificial Neural Network Ann ◽  
Walking Environment ◽  
Semg Signals

Classification of terrain is a vital component in giving suitable control to a walking assistive device for the various walking conditions. Although surface electromyography (sEMG) signals have been combined with inputs from other sensors to detect walking intention, no study has yet classified walking environments using sEMG only. Therefore, the purpose of this study is to classify the current walking environment based on the entire sEMG profile gathered from selected muscles in the lower extremities. The muscle activations of selected muscles in the lower extremities were measured in 27 participants while they walked over flat-ground, upstairs, downstairs, uphill, and downhill. An artificial neural network (ANN) was employed to classify these walking environments using the entire sEMG profile recorded for all muscles during the stance phase. The result shows that the ANN was able to classify the current walking environment with high accuracy of 96.3% when using activation from all muscles. When muscle activation from flexor/extensor groups in the knee, ankle, and metatarsophalangeal joints were used individually to classify the environment, the triceps surae muscle activation showed the highest classification accuracy of 88.9%. In conclusion, a current walking environment was classified with high accuracy using an ANN based on only sEMG signals.

Development of a Surface EMG-Based Control System for Controlling Assistive Devices

2020 ◽  
pp. 765-785
Author(s):  
Uvanesh K. ◽  
Suraj Kumar Nayak ◽  
Biswajeet Champaty ◽  
Goutam Thakur ◽  
Biswajit Mohapatra ◽  
...  
Keyword(s):  
Control System ◽  
Wavelet Transforms ◽  
High Efficiency ◽  
Surface Emg ◽  
Assistive Device ◽  
Discrete Wavelet ◽  
Motor Disability ◽  
Robotic Vehicle ◽  
The Time Domain ◽  
Semg Signals

The current study discusses about the development of an EMG based wireless control system for the patients suffering from high-level motor disability. Surface EMG (sEMG) signals were processed in the time domain and using discrete wavelet transforms (DWT). The statistical features of the signals (sEMG, envelope of the squared sEMG and wavelet processed sEMG) were determined and analyzed. The analysis of the features suggested that the features of the envelope of the squared sEMG signals were sufficient to be used for high-efficiency classification and control signal generation. A hall-effect sensor based switching mechanism was introduced for controlling the duration of the activation of the device. The control signals were wirelessly transmitted to the assistive device (robotic vehicle). The training and the subsequent use of the developed control system were easy.

scholarly journals Concurrent surface electromyography and force myography classification during times of prosthetic socket shift and user fatigue

2017 ◽  
Vol 4 ◽  
pp. 205566831770873 ◽  
Author(s):  
Joe Sanford ◽  
Rita Patterson ◽  
Dan O Popa
Keyword(s):  
Surface Electromyography ◽  
Muscle Activation ◽  
Surface Emg ◽  
Training Data ◽  
Control Input ◽  
Prosthetic Devices ◽  
Prosthetic Socket ◽  
User Fatigue ◽  
Force Myography

Objective Surface electromyography has been a long-standing source of signals for control of powered prosthetic devices. By contrast, force myography is a more recent alternative to surface electromyography that has the potential to enhance reliability and avoid operational challenges of surface electromyography during use. In this paper, we report on experiments conducted to assess improvements in classification of surface electromyography signals through the addition of collocated force myography consisting of piezo-resistive sensors. Methods Force sensors detect intrasocket pressure changes upon muscle activation due to changes in muscle volume during activities of daily living. A heterogeneous sensor configuration with four surface electromyography–force myography pairs was investigated as a control input for a powered upper limb prosthetic. Training of two different multilevel neural perceptron networks was employed during classification and trained on data gathered during experiments simulating socket shift and muscle fatigue. Results Results indicate that intrasocket pressure data used in conjunction with surface EMG data can improve classification of human intent and control of a powered prosthetic device compared to traditional, surface electromyography only systems. Significance Additional sensors lead to significantly better signal classification during times of user fatigue, poor socket fit, as well as radial and ulnar wrist deviation. Results from experimentally obtained training data sets are presented.

Classification of Surface Electromyogram Signals Acquired from the Forearm of a Healthy Volunteer

2016 ◽  
pp. 315-333
Author(s):  
Uvanesh K. ◽  
Suraj Kumar Nayak ◽  
Biswajeet Champaty ◽  
Goutam Thakur ◽  
Biswajit Mohapatra ◽  
...  
Keyword(s):  
Neural Network ◽  
Surface Emg ◽  
Acquisition System ◽  
Discrete Wavelet ◽  
Signal Acquisition ◽  
Semg Signal ◽  
Emg Signal ◽  
Flexor Carpi Ulnaris ◽  
Artificial Neural Network Ann

Surface EMG (sEMG) signals from the palmaris longus, flexor carpi radialis and flexor carpi ulnaris muscles were recorded using an in-house developed EMG signal acquisition system. The bandwidth of the acquisition system was 1500 Hz. The extracted sEMG signal was processed using Discrete Wavelet Transform (DWT). The features of the extracted and the wavelet processed signals were determined and were used for probable classification using Artificial Neural Network (ANN). A classification efficiency of more than 90% was achieved using ANN classifiers. The results suggested that the sEMG may be successfully used for designing efficient control system.

Development of a Surface EMG-Based Control System for Controlling Assistive Devices

2016 ◽  
pp. 335-355
Author(s):  
Uvanesh K. ◽  
Suraj Kumar Nayak ◽  
Biswajeet Champaty ◽  
Goutam Thakur ◽  
Biswajit Mohapatra ◽  
...  
Keyword(s):  
Control System ◽  
Wavelet Transforms ◽  
High Efficiency ◽  
Surface Emg ◽  
Assistive Device ◽  
Discrete Wavelet ◽  
Motor Disability ◽  
Robotic Vehicle ◽  
The Time Domain ◽  
Semg Signals

The current study discusses about the development of an EMG based wireless control system for the patients suffering from high-level motor disability. Surface EMG (sEMG) signals were processed in the time domain and using discrete wavelet transforms (DWT). The statistical features of the signals (sEMG, envelope of the squared sEMG and wavelet processed sEMG) were determined and analyzed. The analysis of the features suggested that the features of the envelope of the squared sEMG signals were sufficient to be used for high-efficiency classification and control signal generation. A hall-effect sensor based switching mechanism was introduced for controlling the duration of the activation of the device. The control signals were wirelessly transmitted to the assistive device (robotic vehicle). The training and the subsequent use of the developed control system were easy.

scholarly journals Ictal quantitative surface electromyography correlates with postictal EEG suppression

Neurology ◽  
2020 ◽  
Vol 94 (24) ◽  
pp. e2567-e2576 ◽  
Author(s):  
Anca A. Arbune ◽  
Isa Conradsen ◽  
Damon P. Cardenas ◽  
Luke E. Whitmire ◽  
Shannon R. Voyles ◽  
...  
Keyword(s):  
Muscle Activation ◽  
Silent Period ◽  
Deltoid Muscle ◽  
Surface Emg ◽  
Stepwise Multiple Regression ◽  
Unexpected Death ◽  
Increased Risk ◽  
Convulsive Seizures

ObjectiveTo test the hypothesis that neurophysiologic biomarkers of muscle activation during convulsive seizures reveal seizure severity and to determine whether automatically computed surface EMG parameters during seizures can predict postictal generalized EEG suppression (PGES), indicating increased risk for sudden unexpected death in epilepsy. Wearable EMG devices have been clinically validated for automated detection of generalized tonic-clonic seizures. Our goal was to use quantitative EMG measurements for seizure characterization and risk assessment.MethodsQuantitative parameters were computed from surface EMGs recorded during convulsive seizures from deltoid and brachial biceps muscles in patients admitted to long-term video-EEG monitoring. Parameters evaluated were the durations of the seizure phases (tonic, clonic), durations of the clonic bursts and silent periods, and the dynamics of their evolution (slope). We compared them with the duration of the PGES.ResultsWe found significant correlations between quantitative surface EMG parameters and the duration of PGES (p < 0.001). Stepwise multiple regression analysis identified as independent predictors in deltoid muscle the duration of the clonic phase and in biceps muscle the duration of the tonic-clonic phases, the average silent period, and the slopes of the silent period and clonic bursts. The surface EMG-based algorithm identified seizures at increased risk (PGES ≥20 seconds) with an accuracy of 85%.ConclusionsIctal quantitative surface EMG parameters correlate with PGES and may identify seizures at high risk.Classification of evidenceThis study provides Class II evidence that during convulsive seizures, surface EMG parameters are associated with prolonged postictal generalized EEG suppression.

scholarly journals Does feet position alter triceps surae EMG record during heel-raise exercises in leg press machine?

2020 ◽  
pp. 1-4
Author(s):  
Reginaldo S. Pereira ◽  
Jônatas B. Azevedo ◽  
Fabiano Politti ◽  
Marcos R. R. Paunksnis ◽  
Alexandre L. Evangelista ◽  
...  
Keyword(s):  
Muscle Activation ◽  
External Rotation ◽  
Surface Emg ◽  
Triceps Surae ◽  
Neutral Position ◽  
Band Pass Filter ◽  
Muscle Involvement ◽  
Pass Filter ◽  
Leg Press ◽  
Maximal Load

Background: muscle activation measured by electromyography (EMG) provides additional insight into functional differences between movements and muscle involvement. Objective: to evaluate the EMG of triceps surae during heel-raise exercise in healthy subjects performed at leg press machine with different feet positions. Methods: ten trained healthy male adults aged between 20 and 30 years voluntarily took part in the study. After biometric analyses the EMG signals were obtained using a 8-channel telemeterized surface EMG system (EMG System do Brazil, Brazil Ltda) (amplifier gain: 1000x, common rejection mode ratio >100 dB, band pass filter: 20 to 500 Hz). All data was acquired and processed using a 16-bit analog to digital converter, with a sampling frequency of 2kHz on the soleus (Sol), medial (GM) and lateral (GL) gastrocnemius muscles in both legs, in accordance with the recommendations of SENIAN. The root mean square (RMS) of the EMG amplitude was calculated to evaluate muscle activity of the three muscles. After being properly prepared for eletromyography procedures, all subjects were instructed to perform 3 sets of 5 repetitions during heel-raise exercise using the maximal load that enabled 10 repetitions on leg press 45° machine, each set being performed with one of the following feet positions: neutral (0º), internal and external rotation (both with 45° from neutral position). The tests were sequential and applied a 5-minute rest interval between sets. The order of the tests was randomized. Results: thought had been found interaction (F=0.27, P= 0.75) on RMS parameters and feet position, the values of Sol muscle were significantly (F=17.86, P= 0.003) lower compared with GL and GM muscles independently of feet position. Conclusion: The change in the feet position during the heel-rise exercise performed in the leg press does not influence the activation of the triceps surae, and the soleus is less activated than the gastrocnemius in that exercise.

Optimization of K Value in KNN Algorithm for Spam and Ham Email Classification

2020 ◽  
Vol 4 (2) ◽  
pp. 377-383
Author(s):  
Eko Laksono ◽  
Achmad Basuki ◽  
Fitra Bachtiar
Keyword(s):  
Frequency Distribution ◽  
Confusion Matrix ◽  
High Accuracy ◽  
K Value ◽  
A Value ◽  
Optimal Value ◽  
Classification Evaluation ◽  
Email Spam ◽  
Email Classification

There are many cases of email abuse that have the potential to harm others. This email abuse is commonly known as spam, which contains advertisements, phishing scams, and even malware. This study purpose to know the classification of email spam with ham using the KNN method as an effort to reduce the amount of spam. KNN can classify spam or ham in an email by checking it using a different K value approach. The results of the classification evaluation using confusion matrix resulted in the KNN method with a value of K = 1 having the highest accuracy value of 91.4%. From the results of the study, it is known that the optimization of the K value in KNN using frequency distribution clustering can produce high accuracy of 100%, while k-means clustering produces an accuracy of 99%. So based on the results of the existing accuracy values, the frequency distribution clustering and k-means clustering can be used to optimize the K-optimal value of the KNN in the classification of existing spam emails.

scholarly journals The effects of 12 weeks of static stretch training on the functional, mechanical, and architectural characteristics of the triceps surae muscle–tendon complex

2021 ◽  
Author(s):  
Stefano Longo ◽  
Emiliano Cè ◽  
Angela Valentina Bisconti ◽  
Susanna Rampichini ◽  
Christian Doria ◽  
...  
Keyword(s):  
Muscle Activation ◽  
Maximum Voluntary Contraction ◽  
Muscle Stiffness ◽  
Triceps Surae ◽  
Maximum Force ◽  
Passive Stiffness ◽  
Electromechanical Delay ◽  
Fascicle Length ◽  
Generating Capacity ◽  
Plantarflexor Muscles

Abstract Purpose We investigated the effects of 12 weeks of passive static stretching training (PST) on force-generating capacity, passive stiffness, muscle architecture of plantarflexor muscles. Methods Thirty healthy adults participated in the study. Fifteen participants (STR, 6 women, 9 men) underwent 12-week plantarflexor muscles PST [(5 × 45 s-on/15 s-off) × 2exercises] × 5times/week (duration: 2250 s/week), while 15 participants (CTRL, 6 women, 9 men) served as control (no PST). Range of motion (ROM), maximum passive resistive torque (PRTmax), triceps surae architecture [fascicle length, fascicle angle, and thickness], passive stiffness [muscle–tendon complex (MTC) and muscle stiffness], and plantarflexors maximun force-generating capacity variables (maximum voluntary contraction, maximum muscle activation, rate of torque development, electromechanical delay) were calculated Pre, at the 6th (Wk6), and the 12th week (Wk12) of the protocol in both groups. Results Compared to Pre, STR ROM increased (P < 0.05) at Wk6 (8%) and Wk12 (23%). PRTmax increased at Wk12 (30%, P < 0.05), while MTC stiffness decreased (16%, P < 0.05). Muscle stiffness decreased (P < 0.05) at Wk6 (11%) and Wk12 (16%). No changes in triceps surae architecture and plantarflexors maximum force-generating capacity variables were found in STR (P > 0.05). Percentage changes in ROM correlated with percentage changes in PRTmax (ρ = 0.62, P = 0.01) and MTC stiffness (ρ = − 0.78, P = 0.001). In CTRL, no changes (P > 0.05) occurred in any variables at any time point. Conclusion The expected long-term PST-induced changes in ROM were associated with modifications in the whole passive mechanical properties of the ankle joint, while maximum force-generating capacity characteristics were preserved. 12 weeks of PST do not seem a sufficient stimulus to induce triceps surae architectural changes.

scholarly journals A Machine Vision Approach for Bioreactor Foam Sensing

2021 ◽  
pp. 247263032110088
Author(s):  
Jonas Austerjost ◽  
Robert Söldner ◽  
Christoffer Edlund ◽  
Johan Trygg ◽  
David Pollard ◽  
...  
Keyword(s):  
Machine Learning ◽  
Machine Vision ◽  
State Of The Art ◽  
Low Cost ◽  
High Accuracy ◽  
Consumer Electronics ◽  
Learning System ◽  
Automotive Applications ◽  
Fine Grained

Machine vision is a powerful technology that has become increasingly popular and accurate during the last decade due to rapid advances in the field of machine learning. The majority of machine vision applications are currently found in consumer electronics, automotive applications, and quality control, yet the potential for bioprocessing applications is tremendous. For instance, detecting and controlling foam emergence is important for all upstream bioprocesses, but the lack of robust foam sensing often leads to batch failures from foam-outs or overaddition of antifoam agents. Here, we report a new low-cost, flexible, and reliable foam sensor concept for bioreactor applications. The concept applies convolutional neural networks (CNNs), a state-of-the-art machine learning system for image processing. The implemented method shows high accuracy for both binary foam detection (foam/no foam) and fine-grained classification of foam levels.

Classification of sEMG signals of hand gestures based on energy features

2021 ◽  
Vol 70 ◽  
pp. 102948
Author(s):  
Naveen Kumar Karnam ◽  
Anish Chand Turlapaty ◽  
Shiv Ram Dubey ◽  
Balakrishna Gokaraju
Keyword(s):  
Hand Gestures ◽  
Semg Signals
Sign in / Sign up

Export Citation Format

Share Document