Movement intention detection from SEMG signals using time-domain features and discriminant analysis classifiers

2018 ◽  
Author(s):  
S. Herle
Keyword(s):  
Discriminant Analysis ◽  
Time Domain ◽  
Movement Intention ◽  
Semg Signals

Continuous Estimation Prediction of Knee Joint Angles Using Fusion of Electromyographic and Inertial Sensors for Active Transfemoral Leg Prostheses

2018 ◽  
Vol 10 (02) ◽  
pp. 1840008
Author(s):  
Alberto López-Delis ◽  
Cristiano J. Miosso ◽  
João L. A. Carvalho ◽  
Adson F. da Rocha ◽  
Geovany A. Borges
Keyword(s):  
Knee Joint ◽  
Joint Angle ◽  
Inertial Sensors ◽  
Sagittal Plane ◽  
Joint Angles ◽  
Knee Joint Angle ◽  
Improved Performance ◽  
Continuous Estimation ◽  
Movement Intention ◽  
Semg Signals

Information extracted from the surface electromyographic (sEMG) signals can allow for the detection of movement intention in transfemoral prostheses. The sEMG can help estimate the angle between the femur and the tibia in the sagittal plane. However, algorithms based exclusively on sEMG information can lead to inaccurate results. Data captured by inertial-sensors can improve this estimate. We propose three myoelectric algorithms that extract data from sEMG and inertial sensors using Kalman-filters. The proposed fusion-based algorithms showed improved performance compared to methods based exclusively on sEMG data, generating improvements in the accuracy of knee joint angle estimation and reducing estimation artifacts.

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

2020 ◽  
Vol 10 (2) ◽  
pp. 541 ◽  
Author(s):  
Qingqing Li ◽  
Penghui Dong ◽  
Jun Zheng
Keyword(s):  
Time Domain ◽  
User Authentication ◽  
Total Error ◽  
Surface Emg ◽  
Sensitive Data ◽  
Total Error Rate ◽  
Shoulder Surfing ◽  
Promising Solution ◽  
One Class Classifier ◽  
Semg Signals

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.

scholarly journals Human Gait Recognition Based on Multiple Feature Combination and Parameter Optimization Algorithms

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Farong Gao ◽  
Taixing Tian ◽  
Ting Yao ◽  
Qizhong Zhang
Keyword(s):  
Frequency Domain ◽  
Time Domain ◽  
Gait Recognition ◽  
Fuzzy Entropy ◽  
Human Gait ◽  
Function Parameter ◽  
Svm Classifier ◽  
Feature Combination ◽  
Multiple Feature ◽  
Semg Signals

Accuracy is a key index of human gait recognition. In this paper, we propose an improved gait recognition algorithm, which combines multiple feature combination and artificial bee colony for optimizing the support vector machine (ABC-SVM). Firstly, considering the complexity characteristics of surface electromyography (sEMG) signals, four types of features are extracted from the denoised sEMG signals, including the time-domain features of integral of absolute value (IAV), variance (VAR), and number of zero-crossing (ZC) points, frequency-domain features of mean power frequency (MPF) and median frequency (MF), and wavelet features and fuzzy entropy features. Secondly, the classifiers of SVM, linear discriminant analysis (LDA), and extreme learning machine (ELM) are employed to recognize the gait with obtained features, including singe-class features, multiple combination features, and optimized features of dimension reduction by principal component analysis (PCA). Thirdly, the penalty coefficient and kernel function parameter of the SVM classifier are optimized by the ABC algorithm, and the influence of different features and classifiers on the recognition results is studied. Finally, the feature samples selected to construct the SVM classifier are trained and recognized. Results show that the classification performance of the ABC-SVM classifier is significantly better than that of the nonoptimized SVM classifier, and the average recognition rate is increased by 3.18%. In addition, the combined feature samples (time-domain, frequency-domain, wavelet, and fuzzy entropy features) not only improve the gait classification accuracy but also enhance the recognition stability.

A Performance Comparison of EMG Classification Methods for Hand and Finger Motion

2014 ◽  
Author(s):  
Sungtae Shin ◽  
Reza Langari ◽  
Reza Tafreshi
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Discriminant Analysis ◽  
Dimension Reduction ◽  
Time Domain ◽  
Classification Accuracy ◽  
Human Motion ◽  
Support Vector ◽  
Classification Methods ◽  
Data Set

For recognizing human motion intent, electromyogram (EMG) based pattern recognition approaches have been studied for many years. A number of methods for classifying EMG patterns have been introduced in the literature. On the purpose of selecting the best performing method for the practical application, this paper compares EMG pattern recognition methods in terms of motion type, feature extraction, dimension reduction, and classification algorithm. Also, for more usability of this research, hand and finger EMG motion data set which had been published online was used. Time-domain, empirical mode decomposition, discrete wavelet transform, and wavelet packet transform were adopted as the feature extraction. Three cases, such as no dimension reduction, principal component analysis (PCA), and linear discriminant analysis (LDA), were compared. Six classification algorithms were also compared: naïve Bayes, k-nearest neighbor, quadratic discriminant analysis, support vector machine, multi-layer perceptron, and extreme machine learning. The performance of each case was estimated by three perspectives: classification accuracy, train time, and test (prediction) time. From the experimental results, the time-domain feature set and LDA were required for the highest classification accuracy. Fast train time and test time are dependent on the classification methods.

scholarly journals Identification of 7 Movements of the Human Hand Using sEMG - 360° on the Forearm

2021 ◽  
Author(s):  
◽  
A. Ibarra-Fuentes
Keyword(s):  
Time Domain ◽  
Index Finger ◽  
Ring Finger ◽  
Middle Finger ◽  
Svm Classifier ◽  
Human Hand ◽  
Absolute Value ◽  
The Time Domain ◽  
Flexion And Extension ◽  
Semg Signals

This document shows the identification of 7 gestures (movements) of the human hand from sEMG – 360° signals in the forearm. sEMG – 360° is the sEMG measurement through 8 channels every 45° making a total of 360°. When making a hand gesture, there will be 8 independents sEMG signals that will be used to identify the movement. The 7 gestures to identify are: relaxed hand (closed), open hand (fingers extended), flexion and extension of the little finger, the ring finger, the middle finger, the index finger and the thumb separately. 100 samples of each of the gesture were captured and 3 feature extractors were applied in the time domain (mean absolute value (MAV), root mean square value (RMS) and area vale under the curve (CUA)), then a vector support machine (SVM) classifier was applied to each extractor. The movements were identified and the percentage of accuracy in the identification was calculated for each extractor + SVM classifier. The calculation of the percentage of accuracy took into account the 8 channels for each gesture. 97.61 % accuracy was achieved in the identification of human hand gestures by applying sEMG – 360°.

Terahertz time-domain spectroscopy combined with support vector machines and partial least squares-discriminant analysis applied for the diagnosis of cervical carcinoma

2015 ◽  
Vol 7 (6) ◽  
pp. 2333-2338 ◽  
Author(s):  
Na Qi ◽  
Zhuoyong Zhang ◽  
Yuhong Xiang ◽  
Yuping Yang ◽  
Xueai Liang ◽  
...  
Keyword(s):  
Support Vector Machines ◽  
Discriminant Analysis ◽  
Least Squares ◽  
Partial Least Squares ◽  
Time Domain ◽  
Terahertz Spectroscopy ◽  
Support Vector ◽  
Terahertz Time Domain Spectroscopy ◽  
Vector Machines ◽  
Effective Diagnosis

Combined with terahertz spectroscopy, partial least squares-discriminant analysis and support vector machines could be novel and effective diagnosis methods for cervical cancer.

Sign in / Sign up

Export Citation Format

Share Document