Electromyography (EMG) is a measure of electrical activity generated by the contraction of muscles. Non-invasive surface EMG (sEMG)-based pattern recognition methods have shown the potential for upper limb prosthesis control. However, it is still insufficient for natural control. Recent advancements in deep learning have shown tremendous progress in biosignal processing. Multiple architectures have been proposed yielding high accuracies (>95%) for offline analysis, yet the delay caused due to optimization of the system remains a challenge for its real-time application. From this arises a need for optimized deep learning architecture based on fine-tuned hyper-parameters. Although the chance of achieving convergence is random, however, it is important to observe that the performance gain made is significant enough to justify extra computation. In this study, the convolutional neural network (CNN) was implemented to decode hand gestures from the sEMG data recorded from 18 subjects to investigate the effect of hyper-parameters on each hand gesture. Results showed that the learning rate set to either 0.0001 or 0.001 with 80-100 epochs significantly outperformed (p < 0.05) other considerations. In addition, it was observed that regardless of network configuration some motions (close hand, flex hand, extend the hand and fine grip) performed better (83.7% ± 13.5%, 71.2% ± 20.2%, 82.6% ± 13.9% and 74.6% ± 15%, respectively) throughout the course of study. So, a robust and stable myoelectric control can be designed on the basis of the best performing hand motions. With improved recognition and uniform gain in performance, the deep learning-based approach has the potential to be a more robust alternative to traditional machine learning algorithms.
Pattern recognition (PR) algorithms have shown promising results for upper limb myoelectric control (MEC). Several studies have explored the efficacy of different pre and post processing techniques in implementing PR-based MECs. This paper explores the effect of segmentation type (disjoint and overlap) and segment size on the performance of PR-based MEC, for multiple datasets recorded with different recording devices. Two PR-based methods; linear discriminant analysis (LDA) and support vector machine (SVM) are used to classify hand gestures. Optimum values of segment size, step size and segmentation type were considered as performance measure for a robust MEC. Statistical analysis showed that optimum values of segment size for disjoint segmentation are between 250ms and 300ms for both LDA and SVM. For overlap segmentation, best results have been observed in the range of 250ms-300ms for LDA and 275ms-300ms for SVM. For both classifiers the step size of 20% achieved highest mean classification accuracy (MCA) on all datasets for overlap segmentation. Overall, there is no significant difference in MCA of disjoint and overlap segmentation for LDA (P-value = 0.15) but differ significantly in the case of SVM (P-value < 0.05). For disjoint segmentation, MCA of LDA is 88.68% and for SVM, it is 77.83%. Statistical analysis showed that LDA outperformed SVM for disjoint segmentation (P-value < 0.05). For overlap segmentation, MCA of LDA is 89.86% and for SVM, it is 89.16%, showing that statistically, there is no significant difference between MCA of both classifiers for overlap segmentation (P-value = 0.45). The indicated values of segment size and overlap size can be used to achieve better performance results, without increasing delay time, for a robust PR-based MEC system.
Empirical Mode Decomposition (EMD) is a data-driven and fully adaptive signal decomposition technique to decompose a signal into its Intrinsic Mode Functions (IMF). EMD has attained great attention due to its capabilities to process a signal in the frequency-time domain without altering the signal into the frequency domain. EMD-based signal denoising techniques have shown great potential to denoise nonlinear and nonstationary signals without compromising the signal's characteristics. The denoising procedure comprises three steps, i.e., signal decomposition, IMF thresholding, and signal reconstruction. Thresholding is performed to assess which IMFs contain noise. In this study, Interval Thresholding (IT), Iterative Interval Thresholding (IIT), and Clear Iterative Interval Thresholding (CIIT) techniques have been explored for denoising of electromyography (EMG) signals. The effect of different thresholding operators, i.e., SOFT, HARD, and Smoothly Clipped Absolute Deviation (SCAD), on the performance of EMD-based EMG denoising techniques is also investigated. 15 EMG signals, recorded from the upper limb of 5 healthy subjects, were used to identify the best possible combination of thresholding technique and thresholding operator for denoising EMG signals. The performance of denoising techniques is assessed by calculating the Signal to Noise (SNR) ratio of the signals. The results are further evaluated using a two-way Analysis of Variance (ANOVA) statistical test. The results demonstrated that the mean SNR values yielded by the IIT thresholding technique outperform the IT thresholding technique (P-value < 0.05), but there is no significant difference in mean SNR values of IIT and CIIT techniques (P-value = 0.9951). For thresholding operators, there is no significant difference in mean SNR values of the HARD and SOFT operator (P-value = 0.0968), whereas the HARD operator outperforms SCAD (P-value < 0.05). It has also shown that the combination of IIT thresholding with SOFT operator and threshold value equal to half of the universal threshold denoise the EMG signals while preserving the original signal's characteristics. IIT-based EMD denoising technique with HARD thresholding operator yields the highest SNR, irrespective of the level of noise embedded in the signal. Whereas IIT with SOFT operator provides comparable SNR and successfully preserves the shape of EMG signals. The
Objective. Intramuscular electromyography (iEMG) signals, invasively recorded, directly from the muscles are used to diagnose various neuromuscular disorders/diseases and to control rehabilitative and assistive robotic devices. iEMG signals are potentially being used in neurology, kinesiology, rehabilitation and ergonomics, to detect/diagnose various diseases/disorders. Electromyography-based classification and analysis systems are being designed and tested for the classification of various neuromuscular disorders and to control rehabilitative and assistive robotic devices. Many studies have explored parameters such as the pre-processing, feature extraction and selection of classifiers that can affect the performance and efficacy of iEMG-based classification systems. The pre-processing stage includes the removal of any unwanted noise from the original signal and windowing of the signal. Approach. This study investigated and presented the optimum windowing configurations for robust control and better performance results of an iEMG-based analysis system based on the stationarity rate (SR) and classification accuracy. Both disjoint and overlap, windowing techniques with varying window and overlap sizes have been investigated using a machine learning-based classification algorithm called linear discriminant analysis. Main results. The optimum window size ranges are from 200–300 ms for the disjoint and 225–300 ms for the overlap windowing technique, respectively. The inferred results show that for the overlap windowing technique the optimum range of overlap size is from 10%–30% of the length of window size. The mean classification accuracy (MCA) and mean stationarity rate (MSR) were found to be lower in the disjoint windowing technique compared to overlap windowing at all investigated overlap sizes. Statistical analysis (two-way analysis of variance test) showed that the MSR and MCA of the overlap windowing technique was significantly different at overlap sizes of 10%–30% (p-values < 0.05). Significance. The presented results can be used to achieve the best possible classification results and SR for any iEMG-based real-time diagnosis, detection and control system, which can enhance the performance of the system significantly.
In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more challenging. Lesion segmentation is an initial step in CAD schemes as it leads to low error rates in quantification of the structure, boundary, and scale of the skin lesion. Subjective clinical assessment of the skin lesion segmentation results provided by current state-of-the-art deep learning segmentation techniques does not offer the required results as per the inter-observer agreement of expert dermatologists. This study proposes a novel deep learning-based, fully automated approach to skin lesion segmentation, including sophisticated pre and postprocessing approaches. We use three deep learning models, including UNet, deep residual U-Net (ResUNet), and improved ResUNet (ResUNet++). The preprocessing phase combines morphological filters with an inpainting algorithm to eliminate unnecessary hair structures from the dermoscopic images. Finally, we used test time augmentation (TTA) and conditional random field (CRF) in the postprocessing stage to improve segmentation accuracy. The proposed method was trained and evaluated on ISIC-2016 and ISIC-2017 skin lesion datasets. It achieved an average Jaccard Index of 85.96% and 80.05% for ISIC-2016 and ISIC-2017 datasets, when trained individually. When trained on combined dataset (ISIC-2016 and ISIC-2017), the proposed method achieved an average Jaccard Index of 80.73% and 90.02% on ISIC-2017 and ISIC-2016 testing datasets. The proposed methodological framework can be used to design a fully automated computer-aided skin lesion diagnostic system due to its high scalability and robustness.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.