Search

This study delves into decoding hand gestures using surface electromyography (EMG) signals collected via a precision Myo-armband sensor, leveraging machine learning algorithms. The research entails rigorous data preprocessing to extract features and labels from raw EMG data. Following partitioning into training and testing sets, four traditional machine learning models are scrutinized for their efficacy in classifying finger movements across seven distinct gestures. The analysis includes meticulous parameter optimization and five-fold cross-validation to evaluate model performance. Among the models assessed, the Random Forest emerges as the top performer, consistently delivering superior precision, recall, and F1-score values across gesture classes, with ROC-AUC scores surpassing 99%. These findings underscore the Random Forest model as the optimal classifier for our EMG dataset, promising significant advancements in healthcare rehabilitation engineering and enhancing human–computer interaction technologies. [ABSTRACT FROM AUTHOR]

This study explores the development and pilot testing of an exergame designed for the rehabilitation of individuals with upper limb deficits. While traditional physiotherapy is effective, it often fails to fully engage patients due to its repetitive nature. This research integrates a novel exergame into physiotherapy regimens, aiming to enhance patient motivation through a gaming experience that complements conventional sessions. The exergame is structured around a narrative-driven adventure, with exercises embedded in gameplay that mirror adjustable physiotherapy routines. It utilizes the Myo armband, a wearable electromyography device, to capture muscle activity and movement. The system, part of a web-based platform, is easily deployable in various settings, including home environments. Comprehensive evaluations with health professionals and neurological patients indicate that the exergame significantly improves patient engagement. This study not only demonstrates the potential of exergames in enhancing traditional therapy but also underscores the importance of patient-centered therapeutic tools. [ABSTRACT FROM AUTHOR]

This work presents a semi-supervised multilayer neural network (MLNN) with an Autoencoder to develop a classification model for recognizing hand gestures from electromyographic (EMG) signals. Using a Myo armband equipped with eight non-invasive surface-mounted biosensors, raw surface EMG (sEMG) sensor data were captured corresponding to five hand gestures: Fist, Open hand, Wave in, Wave out, and Double tap. The sensor collected data underwent preprocessing, feature extraction, label assignment, and dataset organization for classification tasks. The model implementation, validation, and testing demonstrated its efficacy after incorporating synthetic sEMG data generated by an Autoencoder. In comparison to the state-of-the-art techniques from the literature, the proposed model exhibited strong performance, achieving accuracy of 99.68%, 100%, and 99.26% during training, validation, and testing, respectively. Comparatively, the proposed MLNN with Autoencoder model outperformed a K-Nearest Neighbors model established for comparative evaluation.

This study explores the development and pilot testing of an exergame designed for the rehabilitation of individuals with upper limb deficits. While traditional physiotherapy is effective, it often fails to fully engage patients due to its repetitive nature. This research integrates a novel exergame into physiotherapy regimens, aiming to enhance patient motivation through a gaming experience that complements conventional sessions. The exergame is structured around a narrative-driven adventure, with exercises embedded in gameplay that mirror adjustable physiotherapy routines. It utilizes the Myo armband, a wearable electromyography device, to capture muscle activity and movement. The system, part of a web-based platform, is easily deployable in various settings, including home environments. Comprehensive evaluations with health professionals and neurological patients indicate that the exergame significantly improves patient engagement. This study not only demonstrates the potential of exergames in enhancing traditional therapy but also underscores the importance of patient-centered therapeutic tools.

This study delves into decoding hand gestures using surface electromyography (EMG) signals collected via a precision Myo-armband sensor, leveraging machine learning algorithms. The research entails rigorous data preprocessing to extract features and labels from raw EMG data. Following partitioning into training and testing sets, four traditional machine learning models are scrutinized for their efficacy in classifying finger movements across seven distinct gestures. The analysis includes meticulous parameter optimization and five-fold cross-validation to evaluate model performance. Among the models assessed, the Random Forest emerges as the top performer, consistently delivering superior precision, recall, and F1-score values across gesture classes, with ROC-AUC scores surpassing 99%. These findings underscore the Random Forest model as the optimal classifier for our EMG dataset, promising significant advancements in healthcare rehabilitation engineering and enhancing human–computer interaction technologies.

Abstract Background Muscle strength and dexterity impairments are common among patients with multiple sclerosis (MS) producing limitations in activities of daily living related to the upper limb (UL). This study aimed to evaluate the effectiveness of serious games specifically developed for the MYO Armband® capture sensor in improving forearm and wrist mobility, UL muscle strength, dexterity, fatigue, functionality, quality of life, satisfaction, adverse effects and compliance. Methods A double-blinded (allocation concealment was performed by a blinded investigator and by blinding for assessors) randomised controlled trial was conducted. The sample was randomised into two groups: an experimental group that received treatment based on UL serious games designed by the research team and controlled by the MYO Armband® gesture capture sensor, along with conventional rehabilitation and a control group that received the same conventional rehabilitation for the UL. Both groups received two 60-min sessions per week over an eight-week period. Wrist range of motion (goniometry), grip muscle strength (Jamar® dynamometer), coordination and gross UL dexterity (Box and Block Test), fatigue (Fatigue Severity Scale), functionality (ABILHAND), quality of life (Multiple Sclerosis Impact Scale-29), adverse effects (Simulator Sickness Questionnaire, SSQ), perceived workload (NASA-Task load index), satisfaction (Client Satisfaction Questionnaire-8 (CSQ-8), Satisfaction with Technology Scale, System Usability Scale (SUS) and QUEST 2.0) and compliance (attendance) were assessed in both groups pre-treatment, post-treatment and during a follow-up period of 2 weeks without receiving any treatment. Results Significant differences were observed in the experimental group compared to the control group in the assessment of forearm supination (p = .004) and grip strength (p = .004). Adverse effects were minimal (SSQ: 7/100 points) and perceived workload was low (NASA-Task Load Index: 25/100 points) in the experimental group. The MYO Armband® technology proved to be useful for the participants (SUS: 80.66/100) and the satisfaction scales received high scores (QUEST 2.0: 59.4/70 points; Satisfaction with Technology: 84.36/100 points). There were significant differences between the groups in terms of attendance percentage (p = .029). Conclusions An experimental protocol using MYO Armband®-based serious games designed for UL rehabilitation showed improvements in active wrist range of motion and handgrip strength in patients with MS, with high satisfaction, minimal adverse effects and workload and excellent compliance. Trial registration number: This randomised controlled trial has been registered at ClinicalTrials.gov Identifier: NCT04171908.

Nowadays, surface electromyography (sEMG) is evolving as a technology for hand gesture recognition. Detailed studies have revealed the capacity of EMG signals to access detailed information, particularly in the classification of hand gestures. Indeed, this advancement emerges as an interesting element in refining the recognition and interpretation of sign languages and exploring deeper into the phonology of signed languages. Aligned with this advancement and the need for a reliable and mobile sign language recognition system, we introduce a specialized sEMG dataset, acquired using the Myo armband. This device is adept at capturing recordings at frequencies of up to 200 Hz. The dataset focuses on the 28 letters of the Arabic alphabet and 10 digits using hand gestures, with each gesture captured into 400 frames. This considerable collection of 18,716 samples was achieved with the cooperation of three contributors, providing a varied and comprehensive range of gestural data.

Background: Muscle strength and dexterity impairments are common among patients with multiple sclerosis (MS) producing limitations in activities of daily living related to the upper limb (UL). This study aimed to evaluate the effectiveness of serious games specifically developed for the MYO Armband® capture sensor in improving forearm and wrist mobility, UL muscle strength, dexterity, fatigue, functionality, quality of life, satisfaction, adverse effects and compliance. Methods: A double-blinded (allocation concealment was performed by a blinded investigator and by blinding for assessors) randomised controlled trial was conducted. The sample was randomised into two groups: an experimental group that received treatment based on UL serious games designed by the research team and controlled by the MYO Armband® gesture capture sensor, along with conventional rehabilitation and a control group that received the same conventional rehabilitation for the UL. Both groups received two 60-min sessions per week over an eight-week period. Wrist range of motion (goniometry), grip muscle strength (Jamar® dynamometer), coordination and gross UL dexterity (Box and Block Test), fatigue (Fatigue Severity Scale), functionality (ABILHAND), quality of life (Multiple Sclerosis Impact Scale-29), adverse effects (Simulator Sickness Questionnaire, SSQ), perceived workload (NASA-Task load index), satisfaction (Client Satisfaction Questionnaire-8 (CSQ-8), Satisfaction with Technology Scale, System Usability Scale (SUS) and QUEST 2.0) and compliance (attendance) were assessed in both groups pre-treatment, post-treatment and during a follow-up period of 2 weeks without receiving any treatment. Results: Significant differences were observed in the experimental group compared to the control group in the assessment of forearm supination (p =.004) and grip strength (p =.004). Adverse effects were minimal (SSQ: 7/100 points) and perceived workload was low (NASA-Task Load Index: 25/100 points) in the experimental group. The MYO Armband® technology proved to be useful for the participants (SUS: 80.66/100) and the satisfaction scales received high scores (QUEST 2.0: 59.4/70 points; Satisfaction with Technology: 84.36/100 points). There were significant differences between the groups in terms of attendance percentage (p =.029). Conclusions: An experimental protocol using MYO Armband®-based serious games designed for UL rehabilitation showed improvements in active wrist range of motion and handgrip strength in patients with MS, with high satisfaction, minimal adverse effects and workload and excellent compliance. Trial registration number: This randomised controlled trial has been registered at ClinicalTrials.gov Identifier: NCT04171908. [ABSTRACT FROM AUTHOR]

Purpose: For an in-depth analysis of the learning benefits that a stereoscopic view presents during endoscopic training, surgeons required a custom surgical evaluation system enabling simulator independent evaluation of endoscopic skills. Automated surgical skill assessment is in dire need since supervised training sessions and video analysis of recorded endoscope data are very time-consuming. This paper presents a first step towards a multimodal training evaluation system, which is not restricted to certain training setups and fixed evaluation metrics. Methods: With our system we performed data fusion of motion and muscle-action measurements during multiple endoscopic exercises. The exercises were performed by medical experts with different surgical skill levels, using either two or three-dimensional endoscopic imaging. Based on the multi-modal measurements, training features were calculated and their significance assessed by distance and variance analysis. Finally, the features were used automatic classification of the used endoscope modes. Results: During the study, 324 datasets from 12 participating volunteers were recorded, consisting of spatial information from the participants' joint and right forearm electromyographic information. Feature significance analysis showed distinctive significance differences, with amplitude-related muscle information and velocity information from hand and wrist being among the most significant ones. The analyzed and generated classification models exceeded a correct prediction rate of used endoscope type accuracy rate of 90%. Conclusion: The results support the validity of our setup and feature calculation, while their analysis shows significant distinctions and can be used to identify the used endoscopic view mode, something not apparent when analyzing time tables of each exercise attempt. The presented work is therefore a first step toward future developments, with which multivariate feature vectors can be classified automatically in real-time to evaluate endoscopic training and track learning progress. [ABSTRACT FROM AUTHOR]

This study investigates the performance of the Support Vector Machine (SVM) to classify non-real-time and real-time EMG signals. The study also compares training performance using personalized and generalized data from all subjects. Thus, an idea about the data sets to be used in the training of the real-time classification model has been put forward. In addition, real-time classification results were obtained for ten days, and it was observed how training oneself would affect the classification results. EMG data were acquired for 7 hand gestures from 8 healthy subjects to create the data set: fist, fingers spread, wave-in, wave-out, pronation, supination, and rest. Subjects repeated each gesture 30 times. The Myo armband with 8 dry surface electrodes was used for data acquisition. 14 features of the EMG signals have been extracted and non-real-time classification has been made for each feature; the highest accuracy of 96.38% was obtained using root mean square (RMS) and integrated EMG features. Three (3) kernel functions of SVM were tested in non-real-time classification and the highest accuracy was obtained with Cubic SVM using 3rd order polynomial. For this reason, Cubic SVM was used for real-time classification using the features that gave the best results in non-real-time classification. A subject repeated the gestures and real-time classification was performed. The highest accuracy of 99.05% was obtained with the mean absolute value (MAV) feature. The real-time classification was undertaken on eight subjects using the MAV feature's best performance with an average accuracy of 95.83% using the personalized data set and 91.79% using the generalized data set. The greatest accuracy is obtained by training the classifier with the subject's own data. Thus, it can be said that EMG signals are personal, just like fingerprints and retina. In addition, as a result, the tests repeated for 10 days showed the repeatability of the activation of the relevant muscle set and the training takes place and how this can be applied to those who will use prosthetic hands to obtain certain gestures. • Reliable real-time classification of EMG data achieved using SVM algorithm and one feature. • Performance using individual and generalized EMG data compared. • Training on individual data determined to give significant better accuracy • Participants observed to train to repeat activation of relevant muscles. [ABSTRACT FROM AUTHOR]

Background: The ability to perform activities of daily living (ADL) is essential to preserving functional independence and quality of life. In recent years, rehabilitation strategies based on new technologies, such as MYO Armband®, have been implemented to improve dexterity in people with upper limb impairment. Over the last few years, many studies have been published focusing on the accuracy of the MYO Armband® to capture electromyographic and inertial data, as well as the clinical effects of using it as a rehabilitation tool in people with loss of upper limb function. Nevertheless, to our knowledge, there has been no systematic review of this subject. Methods: A systematically comprehensive literature search was conducted in order to identify original studies that answered the PICO question (patient/population, intervention, comparison, and outcome): What is the accuracy level and the clinical effects of the MYO Armband® in people with motor impairment of the upper limb compared with other assessment techniques or interventions or no intervention whatsoever? The following data sources were used: Pubmed, Scopus, Web of Science, ScienceDirect, Physiotherapy Evidence Database, and the Cochrane Library. After identifying the eligible articles, a cross-search of their references was also completed for additional studies. The following data were extracted from the papers: study design, disease or condition, intervention, sample, dosage, outcome measures or data collection procedure and data analysis and results. The authors independently collected these data following the CONSORT 2010 statement when possible, and eventually reached a consensus on the extracted data, resolving disagreements through discussion. To assess the methodological quality of papers included, the tool for the critical appraisal of epidemiological cross-sectional studies was used, since only case series studies were identified after the search. Additionally, the articles were classified according to the levels of evidence and grades of recommendation for diagnosis studies established by the Oxford Center for Evidence-Based Medicine. Also, The Cochrane Handbook for Systematic Reviews of Interventions was used by two independent reviewers to assess risk of bias, assessing the six different domains. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) was followed to carry out this review. Results: 10 articles with a total 180 participants were included in the review. The characteristics of included studies, sample and intervention characteristics, outcome measures, the accuracy of the system and effects of the interventions and the assessment of methodological quality of the studies and risk of bias are shown. Conclusions: Therapy with the MYO Armband® has shown clinical changes in range of motion, dexterity, performance, functionality and satisfaction. It has also proven to be an accurate system to capture signals from the forearm muscles in people with motor impairment of the upper limb. However, further research should be conducted using bigger samples, well-defined protocols, comparing with control groups or comparing with other assessment or therapeutic tools, since the studies published so far present a high risk of bias and low level of evidence and grade of recommendation. [ABSTRACT FROM AUTHOR]

This research presents work on control of a prosthetic arm using surface electromyography (sEMG) signals acquired from triceps and biceps of fifteen healthy and four amputated subjects. Myo armband was used to acquire sEMG signals corresponding to four different arm motions: elbow extension, elbow flexion, wrist pronation, and wrist supination. Ten time-domain features were extracted and considered for classification to recognize the four-arm motions. These features and their various combinations were used to train four different classifiers, in both offline and real-time settings. It was found that the combination of signal mean and waveform length as a feature and k-nearest neighbors as classifier performed significantly better (p < 0.05) than all other combinations in both offline and real-time settings. The offline accuracies of 95.8% and 68.1% and real-time accuracies of 91.9% and 60.1% were obtained for healthy and amputated subjects, respectively. Results obtained using the presented scheme successfully demonstrate that using suitable features and classifier, classification accuracies can be significantly improved for transhumeral prosthesis, thereby, providing better, wearable and non-invasive control of prostheses using sEMG signals. [ABSTRACT FROM AUTHOR]

Bu çalışma kapsamında insansız bir kara aracının kişinin el ve parmak hareketleri ile uzaktan kontrolü gerçekleştirilmiştir. Beyinden kol kaslarına iletilen ve kişinin el hareketlerini gerçekleştirmesini sağlayan Elektromiyografi (EMG) sinyalleri, kişinin koluna giydiği sekiz EMG sensör içeren bileklik vasıtası ile gerçek zamanlı olarak alınmıştır. Raspberry pi 3 gömülü sistem kartı üzerinde geliştirilen sinyal işleme, öznitelik çıkarımı ve sınıflandırma algoritmaları kullanılarak anlamlandırılmıştır. Başka bir deyişle el hareketin örüntüsü (el kapama, parmak açma, serçe parmak temas, bilek dışa bükme, vs.) ile EMG sinyal grubu arasındaki ilişkiler tanımlanmıştır. Anlamlandırılan her bir el hareketi araç için bir hareketi kontrol komutu (el kapama: araç ileri, parmak açma: araç dur, serçe parmağa temas: sola dönüş, bilek dışa bükme: sağa dönüş, vs.) olarak kullanılmıştır. Böylece insan – mobil araç etkileşim ağı kurulmuştur. Kurulan insan- mobil araç etkileşim ağı sayesinde el hareketleri ile mobil aracın gerçek zamanlı hareket kontrolü ortalama % 92 başarı ile gerçekleştirilmiştir.

In this brief, an enhanced robotic learning interface has been investigated using Beetle Antennae Search (BAS) and Extreme Learning Machine (ELM). The initial values of learning weights and bias of the network have significant effect on the performance of the ELM, hence, BAS algorithm was employed to optimize the initial values of learning weights and bias. Kinect v2 camera sensor was applied to obtain the endpoint’s position of the upper limb, MYO armband was used to measure the corresponding joint angle values. Those aforementioned data formed the dataset to be trained by ELM and after training the ELM model was able to generate angle values by only giving position as input without a need to carry out kinematic calculations. The proposed method has been validated by conducting series of experimental studies on a KUKA iiwa robot. [ABSTRACT FROM AUTHOR]

The aim of this study was to develop a badminton teaching system using the wearable technology for improving badminton teaching and learning. This system can provide the similarity scores automatically by comparing a student's movement and strength while playing badminton with a well-trained expert model. A quasi-experiment was conducted for eight weeks to evaluate the effectiveness of the developed system. A paired-sample t-test was analyzed to evaluate whether there is a significant difference between the pretest and posttest for the experimental group (EG) and the control group (CG) respectively. Also, an independent sample t test was utilized to compare the posttests between EG and CG. The results show that the badminton teaching system developed in this study could enhance the learning effectiveness of novice badminton learners. The results not only show that applying wearable technology, the Myo armband, can benefit learners' badminton training, but also can demonstrate the importance of providing instant and adaptive feedback in motor skill learning. [ABSTRACT FROM AUTHOR]

Background: The ability to perform activities of daily living (ADL) is essential to preserving functional independence and quality of life. In recent years, rehabilitation strategies based on new technologies, such as MYO Armband®, have been implemented to improve dexterity in people with upper limb impairment. Over the last few years, many studies have been published focusing on the accuracy of the MYO Armband® to capture electromyographic and inertial data, as well as the clinical effects of using it as a rehabilitation tool in people with loss of upper limb function. Nevertheless, to our knowledge, there has been no systematic review of this subject. Methods: A systematically comprehensive literature search was conducted in order to identify original studies that answered the PICO question (patient/population, intervention, comparison, and outcome): What is the accuracy level and the clinical effects of the MYO Armband® in people with motor impairment of the upper limb compared with other assessment techniques or interventions or no intervention whatsoever? The following data sources were used: Pubmed, Scopus, Web of Science, ScienceDirect, Physiotherapy Evidence Database, and the Cochrane Library. After identifying the eligible articles, a cross-search of their references was also completed for additional studies. The following data were extracted from the papers: study design, disease or condition, intervention, sample, dosage, outcome measures or data collection procedure and data analysis and results. The authors independently collected these data following the CONSORT 2010 statement when possible, and eventually reached a consensus on the extracted data, resolving disagreements through discussion. To assess the methodological quality of papers included, the tool for the critical appraisal of epidemiological cross-sectional studies was used, since only case series studies were identified after the search. Additionally, the articles were classified according to the levels of evidence and grades of recommendation for diagnosis studies established by the Oxford Center for Evidence-Based Medicine. Also, The Cochrane Handbook for Systematic Reviews of Interventions was used by two independent reviewers to assess risk of bias, assessing the six different domains. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) was followed to carry out this review. Results: 10 articles with a total 180 participants were included in the review. The characteristics of included studies, sample and intervention characteristics, outcome measures, the accuracy of the system and effects of the interventions and the assessment of methodological quality of the studies and risk of bias are shown. Conclusions: Therapy with the MYO Armband® has shown clinical changes in range of motion, dexterity, performance, functionality and satisfaction. It has also proven to be an accurate system to capture signals from the forearm muscles in people with motor impairment of the upper limb. However, further research should be conducted using bigger samples, well-defined protocols, comparing with control groups or comparing with other assessment or therapeutic tools, since the studies published so far present a high risk of bias and low level of evidence and grade of recommendation.

The applications of wearable sensors in daily life are increasing day by day. The wearable sensor technologies provide a wide range of knowledge that can be utilized by human gesture/action systems. Although the electromyography (EMG) sensors, which are one of the most simple and effective wearable sensors, are usually employed in especially medical diagnosis, it holds a great amount of information (e.g., activity descriptors) regarding human activities. This study aims to evaluate the applicability of EMG signals in action recognition by identifying the relevant features of EMG signals alongside their commonly used properties. These (relevant) features are categorized into general basic statistical variables in time/frequency/aLBP/uniform aLBP domains, special statistical features in time and frequency domains, AR coefficients, and features in the wavelet domain. In order to evaluate and validate the applicability of EMG signal, a set of features is extracted from a wide range of datasets established by the authors of this paper in a way of describing distinct human actions (total of 132 distinct features). The study determines the dominant features for human action recognition systems by proposing a new wearable sensor-based methodology that exploits feature selection algorithms. Hence, the determination of the relevancy order of the features is one of the significant outcomes of this study. The results figure out that the most relevant ones are the metrics that detect fluctuations, i.e., a higher amount of entropy, belonging to the signal. [ABSTRACT FROM AUTHOR]

In this study, we present a transfer learning method for gesture classification via an inductive and supervised transductive approach with an electromyographic dataset gathered via the Myo armband. A ternary gesture classification problem is presented by states of 'thumbs up', 'thumbs down', and 'relax' in order to communicate in the affirmative or negative in a non-verbal fashion to a machine. Of the nine statistical learning paradigms benchmarked over 10-fold cross validation (with three methods of feature selection), an ensemble of Random Forest and Support Vector Machine through voting achieves the best score of 91.74% with a rule-based feature selection method. When new subjects are considered, this machine learning approach fails to generalise new data, and thus the processes of Inductive and Supervised Transductive Transfer Learning are introduced with a short calibration exercise (15 s). Failure of generalisation shows that 5 s of data per-class is the strongest for classification (versus one through seven seconds) with only an accuracy of 55%, but when a short 5 s per class calibration task is introduced via the suggested transfer method, a Random Forest can then classify unseen data from the calibrated subject at an accuracy of around 97%, outperforming the 83% accuracy boasted by the proprietary Myo system. Finally, a preliminary application is presented through social interaction with a humanoid Pepper robot, where the use of our approach and a most-common-class metaclassifier achieves 100% accuracy for all trials of a '20 Questions' game. [ABSTRACT FROM AUTHOR]

Myoelectric prostheses are a viable solution for people with amputations. The challenge in implementing a usable myoelectric prosthesis lies in accurately recognizing different hand gestures. The current myoelectric devices usually implement very few hand gestures. In order to approximate a real hand functionality, a myoelectric prosthesis should implement a large number of hand and finger gestures. However, increasing number of gestures can lead to a decrease in recognition accuracy. In this work a Myo armband device is used to recognize fourteen gestures (five build in gestures of Myo armband in addition to nine new gestures). The data in this research is collected from three body-able subjects for a period of 7 seconds per gesture. The proposed method uses a pattern recognition technique based on Multi-Layer Perceptron Neural Network (MLPNN). The results show an average accuracy of 90.5% in recognizing the proposed fourteen gestures. [ABSTRACT FROM AUTHOR]

Featured Application: Results of this work could be useful in the field of hand gesture recognition based on myoelectric signal processing, which has widespread usage for robotic arms and upper limb prosthesis control. The surface electromyography signal (sEMG) is widely used for gesture characterization; its reliability is strongly connected to the features extracted from sEMG recordings. This study aimed to investigate the use of two complexity measures, i.e., fuzzy entropy (FEn) and permutation entropy (PEn) for hand gesture characterization. Fourteen upper limb movements, sorted into three sets, were collected on ten subjects and the performances of FEn and PEn for gesture descriptions were analyzed for different computational parameters. FEn and PEn were able to properly cluster the expected numbers of gestures, but computational parameters were crucial for ensuring clusters' separability and proper gesture characterization. FEn and PEn were also compared with other eighteen classical time and frequency domain features through the minimum redundancy maximum relevance algorithm and showed the best predictive importance scores in two gesture sets; they also had scores within the subset of the best five features in the remaining one. Further, the classification accuracies of four different feature sets presented remarkable increases when FEn and PEn are included as additional features. Outcomes support the use of FEn and PEn for hand gesture description when computational parameters are properly selected, and they could be useful in supporting the development of robotic arms and prostheses myoelectric control. [ABSTRACT FROM AUTHOR]

ABSTRAK Sinyal EMG merupakan salah satu sinyal yang dapat digunakan untuk memberikan perintah pada kursi roda listrik. Sinyal EMG yang digunakan diambil dari sinyal otot fleksor dan ekstensor yang berada di tangan kanan. Sinyal tersebut diambil menggunakan sensor Myo Armband. Klasifikasi sinyal EMG diambil dari pergerakan jari yang mewakili perintah gerak yaitu jari kelingking untuk bergerak maju, jari manis untuk berhenti, jari tengah untuk belok kanan dan jari telunjuk untuk belok kiri. Setiap sinyal EMG diekstraksi fitur untuk menentukan karakteristik sinyal sehingga fitur yang diperoleh adalah Average Absolute Value, Root Mean Square, Simple Integral Square, EMG Simple Variant and Integrated EMG. Kemudian fitur tersebut digunakan sebagai input dari metode klasifikasi Artificial Neural Network Backpropagation. Jumlah data latih yang digunakan adalah 800 data sedangkan data uji yang digunakan adalah 200 data. Tingkat keberhasilan proses klasifikasi ini sebesar 93%. Kata kunci: electromyogram, artificial neural network, klasifikasi sinyal, tangan kanan, Myo Armband. ABSTRACT EMG signal is one of the signals that can be used to give orders to electric wheelchairs. The EMG signal used is taken from the flexor and extensor muscle signals in the right hand. The signal is taken using the Myo Armband sensor. The EMG signal classification is taken from the movement of the finger which represents the command of motion ie the little finger to move forward, ring finger to stop, middle finger to turn right and index finger to turn left. Each EMG signal is extracted features to determine the signal characteristics so that the features obtained are Average Absolute Value, Root Mean Square, Simple Integral Square, EMG Simple Variant and Integrated EMG. Then the feature is used as input from the Backpropagation classification method. The amount of training data used is 800 data while the test data used is 200 data. The success rate of this classification process is 93%. Keywords: electromyogram, artificial neural network, signal classification, right hand, Myo Armband.

User authentication has become an essential security element that enables a wide range of applications in P2P systems for higher security and safety requirements. In previous, many researchers worked on user authentication based on certificates, passwords, and feature-based authentication (e.g. face recognition, fingerprint detection, iris recognition, voice recognition). However, authentication using those technologies may fail because this information can be easily shared among users or synthesized. Also, there are several cyber and cryptography attacks. With the progress of the latest sensor technology, wearable as Microsoft Bands, Fitbit, and Garmin has provided for more information collecting opportunities. From those above point of views, this paper presents a novel user identification system based on the bio signal analysis of arm movement (3-axis accelerometer & 3-axis gyroscope) and electromyography (EMG) signal using Myo armband as a wearable user authentication system in P2P system that identifies users based on the bio-signal of movement of a person's arm. In this study, the gesture and EMG signals are obtained from the sensor and denoised using wavelet denoising algorithm. The denoised signals are analyzed using the envelope and cepstrum analysis for extracting the potential feature vector. Finally, the feature vector is used to train and identify a user using multi-class support vector machine (MC-SVM) with different kernel function for user authentication. For validating the proposed authentication model, signals are obtained from the arm movements, i.e., directions and hand gesture data using acceleration, gyroscope and EMG sensors of several subjects. According to the experimental results, the proposed model shows satisfactory performance. To evaluate the efficiency of the proposed systems, we measure and compare its classification accuracy with state-of-the-art algorithms. And the proposed algorithm outperforms with others. [ABSTRACT FROM AUTHOR]

Introduction: The most common way of assessing surgical performance is by expert raters to view a surgical task and rate a trainee's performance. However, there is huge potential for automated skill assessment and workflow analysis using modern technology. The aim of the present study was to evaluate machine learning (ML) algorithms using the data of a Myo armband as a sensor device for skills level assessment and phase detection in laparoscopic training.Materials and Methods: Participants of three experience levels in laparoscopy performed a suturing and knot tying task on silicon models. Experts rated performance using Objective Structured Assessment of Surgical Skills (OSATS). Participants wore Myo armbands (Thalmic Labs™, Ontario, Canada) to record acceleration, angular velocity, orientation, and Euler orientation. ML algorithms (decision forest, neural networks, boosted decision tree) were compared for skill level assessment and phase detection.Results: 28 participants (8 beginner, 10 intermediate, 10 expert) were included, and 99 knots were available for analysis. A neural network regression model had the lowest mean absolute error in predicting OSATS score (3.7 ± 0.6 points, r2 = 0.03 ± 0.81; OSATS min.-max.: 4-37 points). An ensemble of binary-class neural networks yielded the highest accuracy in predicting skill level (beginners: 82.2% correctly identified, intermediate: 3.0%, experts: 79.5%) whereas standard statistical analysis failed to discriminate between skill levels. Phase detection on raw data showed the best results with a multi-class decision jungle (average 16% correctly identified), but improved to 43% average accuracy with two-class boosted decision trees after Dynamic time warping (DTW) application.Conclusion: Modern machine learning algorithms aid in interpreting complex surgical motion data, even when standard analysis fails. Dynamic time warping offers the potential to process and compare surgical motion data in order to allow automated surgical workflow detection. However, further research is needed to interpret and standardize available data and improve sensor accuracy. [ABSTRACT FROM AUTHOR]

Kalman filter has been successfully applied to fuse the motion capture data collected from Kinect sensor and a pair of MYO armbands to teleoperate a robot. A new strategy utilizing the vector approach has been developed to accomplish a specific motion capture task. The arm motion of the operator is captured by a Kinect sensor and programmed with Processing software. Two MYO armbands with the inertial measurement unit embedded are worn on the operator's arm, which is used to detect the upper arm motion of the human operator. This is utilized to recognize and to calculate the precise speed of the physical motion of the operator's arm. User Datagram Protocol is employed to send the human movement to a simulated Baxter robot arm for teleoperation. In order to obtain joint angles for human limb utilizing vector approach, RosPy and Python script programming has been utilized. A series of experiments have been conducted to test the performance of the proposed technique, which provides the basis for the teleoperation of simulated Baxter robot.

Nowadays, surface electromyography (sEMG) is evolving as a technology for hand gesture recognition. Detailed studies have revealed the capacity of EMG signals to access detailed information, particularly in the classification of hand gestures. Indeed, this advancement emerges as an interesting element in refining the recognition and interpretation of sign languages and exploring deeper into the phonology of signed languages. Aligned with this advancement and the need for a reliable and mobile sign language recognition system, we introduce a specialized sEMG dataset, acquired using the Myo armband. This device is adept at capturing recordings at frequencies of up to 200 Hz. The dataset focuses on the 28 letters of the Arabic alphabet and 10 digits using hand gestures, with each gesture captured into 400 frames. This considerable collection of 18,716 samples was achieved with the cooperation of three contributors, providing a varied and comprehensive range of gestural data., (© 2023 The Author(s).)

Hand gestures recognition (HGR) has been considered as one of the crucial research fields of human–computer interaction (HCI). Computer vision is a very active research field in the HGR, traditional vision-based methods, which used camera and ultrasonic/optical sensor to collect the videos or images of the hand gestures shown by participants, have some limitations, such as fixed in-lab location, complex lighting conditions, and cluttered backgrounds. In order to provide new approaches, we described the development of a novel hand gesture recognition system that combined wearable armband and smart glove made by customizable pressure sensor arrays to detect sequential hand gestures. A deep learning technique long short-term memory (LSTM) algorithm had been computed to build an effective model to classify hand gestures by training and testing the collected inertial measurement unit (IMU), electromyographic (EMG), and finger and palm’s pressure data. Furthermore, we built a relatively large database of ten sequential hand gestures consisted by five dynamic gestures and five air gestures collected from ten participants. Our experimental results showed an outstanding classification performance of the proposed LSTM algorithm. These findings have promising implications for sequential hand gesture recognition and the HCI research status. [ABSTRACT FROM AUTHOR]

This research work presents the design of the electronics modules of Adam's Hand, a transradial myoelectric prosthesis based on an innovative mechanism which can actuate five three‐phalanges fingers (15 degrees of freedom) with just one motor, instead of the five/six motors conventionally used in other prosthetic devices; moreover, the prosthesis uses two servomotors to actuate the wrist movements. Adam's Hand fingertips are provided with temperature and pressure sensors, while the user myoelectric signals are acquired wirelessly by means of the Myo armband, a wearable device provided with eight electromyography electrodes, a nine‐axis inertial measurement unit, and a transmission module. These data are received through an HM‐11 BLE module, connected to Adam's Hand custom PCB, which features an Arduino Micro board. This board processes all the data and drives the actuators by means of properly chosen drivers. A Raspberry Pi 3 board manages a touchscreen display – which can be used to visualise the gathered data – and sends them to a dedicate cloud platform, so that the orthopaedic technicians who take care of Adam's Hand users can monitor them in real time, thus improving their recovery during the rehabilitation period. [ABSTRACT FROM AUTHOR]

The objective of this article is to classify the 27 gestures of the Colombian sign alphabet, by means of a classifier of artificial neural networks based on electromyographic signals. The classifier was designed in four phases: Acquisition of electromyographic signals from the eight sensors of the Myo Armband handle, extraction of characteristics of the electromyographic signals using the wavelet transform of packages, training of the neural network and validation of the classification method using the cross-validation technique. For the present study, records of electromyographic signals from 13 subjects with hearing impairment were acquired. The classifier presented an average accuracy percentage of 88.4%, very similar to other classification methods presented in the literature. The classification method can be scaled to classify, in addition to the 27 gestures, the vocabulary of the Colombian sign language. [ABSTRACT FROM AUTHOR]

The artificial hand is necessary and hopeful item for supporting disabled person who losts hand due to contingent accident in the industrial fields or military. However, most of supporting product like an artificial hand is very expensive product that is not easily accessible as well as it is hard for a person to familiar with although it support powerful functionality. In the other side, cheap model of such items does not support detailed motion of hand. It is simply an alternative to mimic the shape of hand. In fact, a number of disabled people who lose their hands may not want an artificial hands that completely replace ones hands. They merely want an artificial hands that support simple movement in the daily life. The financial part is also important factor that can not be excluded from consideration. Causing above reasons, the artificial hand supporting basic motion frequently used in the daily life with low cost is strongly required. In this paper, we propose the artificial hand with low cost and controlled by muscle movement which captured by muscle sensor. Considering the cost, we design the frame of hand with 3D printing technology. With muscle sensor, it is possible to control the fingers only by muscular movement of the forearm, thereby improving the convenience of the control. In addition, we suggest mobile application by touch interfacing in the mobile device, and also proposed the training guide web site. The proposed mobile application is used for inspection method of functional normalcy of the artificial hands. The web site is used to support confirming movement of muscle sensor and training for use of muscle control because most of people are not likely to have used muscles for a long time and may not be familiar with muscle control for the proposed artificial hands. Through simulations, we confirm that the proposed artificial hand supports several motion of hand which are frequently used in the daily life, and the suggested system is enough to support disabled person. [ABSTRACT FROM AUTHOR]

Health conditions might cause muscle weakness and immobility in some body parts; hence, physiotherapy exercises play a key role in the rehabilitation. To improve the engagement during the rehabilitation process, we therefore propose a human-computer interface (serious game) in which five wrist movements (extension, flexion, pronation, supination and neutral) are detected via two commercial sensors (Leap motion controller and Myo armband). Leap motion provides data regarding positions of user's finger phalanges through two infrared cameras, while Myo armband facilitates electromyography signal and inertial motion of user's arm through its electrodes and inertial measurement unit. The main aim of this study is to explore the performance of these sensors on wrist movement recognition in terms of accuracy, sensitivity and specificity. Eight healthy participants played 5 times a proposed game with each sensor in one session. Both sensors reported over 85% average recognition accuracy in the five wrist movements. Based on t test and Wilcoxon signed-rank test, early results show that there were significant differences between Leap motion controller and Myo armband recognitions in terms of average sensitivities on extension (p=0.0356), flexion (p=0.0356) and pronation (p=0.0440) movements, and average specificities on extension (p=0.0276) and pronation (p=0.0249) movements. [ABSTRACT FROM AUTHOR]