Influence of Different Feature Selection Methods on EMG Pattern Recognition

Zhang, Anyuan; Li, Qi; Gao, Ning; Wang, Liang; Wu, Yan

doi:10.1109/icma.2019.8816640

Cited by 8 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can be accomplished by selecting a feature set that maximally differentiates the intended output classes [1]. The basic building block of organization schemes and crucial towards recognition of gesture commands is the abstraction of particular structures after the EMG data [2]. However, with a block dispensation still model like AR archetypal, it is challenging to extract feature parameters exactly due to the nonstationary of the EMG signal.…”

Section: Introductionmentioning

confidence: 99%

Feature Selection Approaches on Emg Design Based on Artifi-Cial Intelligence Techniques

2023

IRJMETS

View full text Add to dashboard Cite

The process of feature extraction is crucial for electromyography (EMG) pattern recognition. Redundancy of characteristics is caused by high-dimensional EMG feature vector. In order to classify the EMG signal pattern, a classifier must perform more computations, which increases computation time and lowers classification accuracy. To reduce feature redundancy, many studies adopted the feature selection method. The focus of this work is on how two alternative feature selection techniques-SFS and PSO-affect the detection of EMG patterns. To assess the various effects of various feature selection methodologies on EMG pattern identification, we suggested three different approaches. Support vector machine (SVM) combined with none feature selection method, SVM combined with SFS (SFSSVM), and SVM combined with PSO (PSOSVM) are the three options. To classify 11 arm movements, we employed SVM, SFSSVM, and PSOSVM, respectively. We explored the various effects of various feature selection strategies on EMG pattern identification by comparing the classification accuracy and calculation times of the three methods. The outcomes demonstrated that the PSOSVM performed better than SVM and SFSSVM.

show abstract

Section: Introductionmentioning

confidence: 99%

Feature Selection Approaches on Emg Design Based on Artifi-Cial Intelligence Techniques

2023

IRJMETS

View full text Add to dashboard Cite

show abstract

“…Olsson et al 21 classified a high number of movements by defining them as combinations of fundamental ones, each recognized by a binary CNN in a multi-label classification. Zhang et al 22 tested Particle Swarm Optimization (PSO) and Sequential Forward Selection (SFS) methods for the feature selection on the EMG SVM classifier. According to Wang et al 23 modeled EMG signal assuming additive noise, the Root Difference of Squares (RDS) represents EMG best and has a Gaussian Distribution.…”

Section: Introductionmentioning

confidence: 99%

“…22 Turn the screw with stick grasping screwdriver (8)23 Cut something (holding a knife with ''index finger extension'' (4))…”

mentioning

confidence: 99%

Window length insensitive real-time EMG hand gesture classification using entropy calculated from globally parsed histograms

Algüner

Ergezer

2023

Measurement and Control

View full text Add to dashboard Cite

Electromyography (EMG) signal classification is vital to diagnose musculoskeletal abnormalities and control devices by motion intention detection. Machine learning assists both areas by classifying conditions or motion intentions. This paper proposes a novel window length insensitive EMG classification method utilizing the Entropy feature. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. Additionally, the entropy feature can classify feature vectors of different sliding window lengths without including them in the training data. Many kinds of entropy feature succeeded in electroencephalography (EEG) and electrocardiography (ECG) classification research. However, to the best of our knowledge, the Entropy Feature proposed by Shannon stays untested for EMG classification to this day. All the machine learning models are tested on datasets NinaPro DB5 and the newly collected SingleMyo. As an initial analysis to test the entropy feature, classic Machine Learning (ML) models are trained on the NinaPro DB5 dataset. This stage showed that except for the K Nearest Neighbor (kNN) with high inference time, Support Vector Machines (SVM) gave the best validation accuracy. Later, SVM models trained with feature vectors created by 1 s (200 samples) sliding windows are tested on feature vectors created by 250 ms (50 samples) to 1500 ms (300 samples) sliding windows. This experiment resulted in slight accuracy differences through changing window length, indicating that the Entropy feature is insensitive to this parameter. Lastly, Locally Parsed Histogram (LPH), typical in standard entropy functions, makes learning hard for ML methods. Globally Parsed Histogram (GPH) was proposed, and classification accuracy increased from 60.35% to 89.06% while window length insensitivity is preserved. This study shows that Shannon’s entropy is a compelling feature with low window length sensitivity for EMG hand gesture classification. The effect of the GPH approach against an easy-to-make mistake LPH is shown. A real-time classification algorithm for the entropy features is tested on the newly created SingleMyo dataset.

show abstract

“…They showed that, with only a decrease of 0.9% in accuracy from 94.0 to 93.1%, they could reduce the number of sensors necessary by 54%. Other meta-heuristics were used in EMG feature selection as well ( Phinyomark and Scheme, 2018 ), such as particle swarm optimization ( Purushothaman and Vikas, 2018 ; Too et al, 2019 ; Zhang et al, 2019 ; Bakiya et al, 2020 ) and ant colony optimization ( Purushothaman and Vikas, 2018 ). Many other meta-heuristics exist which are suited for feature selection in general, such as tabu search and simulated annealing ( Diao and Shen, 2015 ).…”

Section: Introductionmentioning

confidence: 99%

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

et al. 2021

View full text Add to dashboard Cite

Choosing the right features is important to optimize lower limb pattern recognition, such as in prosthetic control. EMG signals are noisy in nature, which makes it more challenging to extract useful information. Many features are used in the literature, which raises the question which features are most suited for use in lower limb myoelectric control. Therefore, it is important to find combinations of best performing features. One way to achieve this is by using a genetic algorithm, a meta-heuristic capable of searching vast feature spaces. The goal of this research is to demonstrate the capabilities of a genetic algorithm and come up with a feature set that has a better performance than the state-of-the-art feature set. In this study, we collected a dataset containing ten able-bodied subjects who performed various gait-related activities while measuring EMG and kinematics. The genetic algorithm selected features based on the performance on the training partition of this dataset. The selected feature sets were evaluated on the remaining test set and on the online benchmark dataset ENABL3S, against a state-of-the-art feature set. The results show that a feature set based on the selected features of a genetic algorithm outperforms the state-of-the-art set. The overall error decreased up to 0.54% and the transitional error by 2.44%, which represent a relative decrease in overall errors up to 11.6% and transitional errors up to 14.1%, although these results were not significant. This study showed that a genetic algorithm is capable of searching a large feature space and that systematic feature selection shows promising results for lower limb myoelectric control.

show abstract

Influence of Different Feature Selection Methods on EMG Pattern Recognition

Cited by 8 publications

References 18 publications

Feature Selection Approaches on Emg Design Based on Artifi-Cial Intelligence Techniques

Feature Selection Approaches on Emg Design Based on Artifi-Cial Intelligence Techniques

Window length insensitive real-time EMG hand gesture classification using entropy calculated from globally parsed histograms

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

Contact Info

Product

Resources

About