Feature extraction of the first difference of EMG time series for EMG pattern recognition

Phinyomark, Angkoon; Quaine, Franck; Charbonnier, Sylvie; Servière, Christine; Tarpin-Bernard, Franck; Laurillau, Yann

doi:10.1016/j.cmpb.2014.06.013

Cited by 108 publications

(34 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are three types of features that can be extracted from sEMG signals: time domain features, frequency domain features, and time-frequency domain features [28]. In our study, we concentrated on using features extracted from the time domain, which are widely used in studies and practices due to their low computational complexity compared with frequency domain and time-frequency domain features and performance in low-noise environments [29][30][31][32]. We selected the following 11 time domain features in this study.…”

Section: Semg Feature Extractionmentioning

confidence: 99%

Enhancing the Security of Pattern Unlock with Surface EMG-Based Biometrics

Dong

Zheng

2020

Applied Sciences

View full text Add to dashboard Cite

Pattern unlock is a popular screen unlock scheme that protects the sensitive data and information stored in mobile devices from unauthorized access. However, it is also susceptible to various attacks, including guessing attacks, shoulder surfing attacks, smudge attacks, and side-channel attacks, which can achieve a high success rate in breaking the patterns. In this paper, we propose a new two-factor screen unlock scheme that incorporates surface electromyography (sEMG)-based biometrics with patterns for user authentication. sEMG signals are unique biometric traits suitable for person identification, which can greatly improve the security of pattern unlock. During a screen unlock session, sEMG signals are recorded when the user draws the pattern on the device screen. Time-domain features extracted from the recorded sEMG signals are then used as the input of a one-class classifier to identify the user is legitimate or not. We conducted an experiment involving 10 subjects to test the effectiveness of the proposed scheme. It is shown that the adopted time-domain sEMG features and one-class classifiers achieve good authentication performance in terms of the F 1 score and Half of Total Error Rate (HTER). The results demonstrate that the proposed scheme is a promising solution to enhance the security of pattern unlock.

show abstract

Section: Semg Feature Extractionmentioning

confidence: 99%

Enhancing the Security of Pattern Unlock with Surface EMG-Based Biometrics

Dong

Zheng

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Twenty-seven features of four types (time-domain, frequency-domain, time-and frequency-domain, and nonlinear dynamic features) were calculated. The ten time-domain features included mean absolute value, mean absolute value slope, Willison amplitude, variance (VAR), zero crossing, slope sign change, waveform length (WL), root mean square, autoregressive coefficients (AR), and autoregressive coefficients from the first difference of EMG (FDAR) [6,[13][14][15]. The two frequency-domain features were median frequency and mean power frequency [16][17][18].…”

Section: Feature Set Computation and Reductionmentioning

confidence: 99%

“…Many empirical studies have been conducted that investigate different types of classifiers using various features computed from sEMG signals. For real-time, close-range, and convenient controlling, a variety of classification approaches, such as the support vector machine (SVM), neural networks (NNs), and quadratic discriminant analysis (QDA), have been applied to estimate the motion intent from the sEMG signals * Correspondence: kanjm@bjfu.edu.cn [4][5][6]. Among the various types of classifiers, however, the SVM is considered to have a better performance than other approaches such as decision trees, neural networks, and model-based reasoning approaches [7].…”

Section: Introductionmentioning

confidence: 99%

Classification of surface electromyogram signals based on directed acyclic graphs and support vector machines

Hu¹,

Kan²,

Li³

2018

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper presents a novel classification approach for surface electromyogram (sEMG) signals. The proposed classification approach involves two steps: (1) feature extraction from an sEMG, in which a 7-dimensional feature vector is extracted from 27 types of features of the sEMG by linear discriminant analysis (LDA), and (2) a novel classifier, DAGSVMerr, based on a directed acyclic graph (DAG) and support vector machine (SVM), in which a separability measure function based on erroneous recognition rates (ERRs) is defined to determine the initial operation list. The proposed approach takes advantage of the feedback idea to improve the performance of the classification. The experimental results show that the proposed approach has a better performance than traditional methods, and it achieves an average classification accuracy rate of 99.4% ± 1.3% with an error rate of 0.6%. Correct classification rates of the proposed approach are very high, and the approach can be utilized to recognize gesture instructions by analyzing sEMG signals in gesture equipment control studies.

show abstract

“…Phinyomark et al [9] performed feature extraction from 1 st difference of sEMG time series and concluded that the accuracy was higher as compare to features extracted from original signals. Omari et al [10] extracted different features from a four channel-sEMG signal and analyzed them using LDA, quadratic discriminant analysis, and kNN.…”

mentioning

confidence: 99%

MLPNN and kNN Based Classification of sEMG Signal for Myoelectric Control of Upper Limb Prosthesis

Negi¹,

Kumar²,

Mishra³

2017

Proceedings of the Second International Conference on Research in Intelligent and Computing in Engineering

View full text Add to dashboard Cite

AbstractiAnalysis of sEMG signal has been an emerging field for the myoelectric control of upper limb prosthesis. The objective of present work is to obtain the performance measures like accuracy, sensitivity, specificity and positive predictivity using MLMNN with back propagation algorithm. Using MLMNN classifier, an average classification accuracy of 93.71% was achieved over ten subjects for the combination of [MAV1, WL, AAC, ZC, and WAMM] features. Next the classification accuracy is obtained with kNN classifier for ky 3, 5, and 7. The results showed that average classification accuracy of 93.06% is achieved using kNN and it is better than MLMNN in terms of time and simplicity.

show abstract

Feature extraction of the first difference of EMG time series for EMG pattern recognition

Cited by 108 publications

References 37 publications

Enhancing the Security of Pattern Unlock with Surface EMG-Based Biometrics

Enhancing the Security of Pattern Unlock with Surface EMG-Based Biometrics

Classification of surface electromyogram signals based on directed acyclic graphs and support vector machines

MLPNN and kNN Based Classification of sEMG Signal for Myoelectric Control of Upper Limb Prosthesis

Contact Info

Product

Resources

About