Identification and removal of contaminants in sEMG recordings through a methodology based on Fuzzy Inference and Actor-Critic Reinforcement learning

Tosin, Maurício Cagliari; Balbinot, Alexandre

doi:10.1016/j.eswa.2022.117772

Cited by 11 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al, 2019 [19], Maurício Cagliari Tosin et. Al, 2022 [33], Mahsa Barfi et. Al, 2022 [34], and Ravi Suppiah et.…”

Section: Recent Development Of Emg Control Methodsmentioning

confidence: 99%

Analysis of ANN and Fuzzy Logic Dynamic Modelling to Control the Wrist Exoskeleton

Karis,

Kasdirin,

Abas

et al. 2023

Journal of Robotics and Control

View full text Add to dashboard Cite

Human intention has long been a primary emphasis in the field of electromyography (EMG) research. This being considered, the movement of the exoskeleton hand can be accurately predicted based on the user's preferences. The EMG is a nonlinear signal formed by muscle contractions as the human hand moves and easily captured noise signal from its surroundings. Due to this fact, this study aims to estimate wrist desired velocity based on EMG signals using ANN and FL mapping methods. The output was derived using EMG signals and wrist position were directly proportional to control wrist desired velocity. Ten male subjects, ranging in age from 21 to 40, supplied EMG signal data set used for estimating the output in single and double muscles experiments. To validate the performance, a physical model of an exoskeleton hand was created using Sim-mechanics program tool. The ANN used Levenberg training method with 1 hidden layer and 10 neurons, while FL used a triangular membership function to represent muscles contraction signals amplitude at different MVC levels for each wrist position. As a result, PID was substituted to compensate fluctuation of mapping outputs, resulting in a smoother signal reading while improving the estimation of wrist desired velocity performance. As a conclusion, ANN compensates for complex nonlinear input to estimate output, but it works best with large data sets. FL allowed designers to design rules based on their knowledge, but the system will struggle due to the large number of inputs. Based on the results achieved, FL was able to show a distinct separation of wrist desired velocity hand movement when compared to ANN for similar testing datasets due to the decision making based on rules setting setup by the designer.

show abstract

“…al, 2019 [19], Maurício Cagliari Tosin et. Al, 2022 [33], Mahsa Barfi et. Al, 2022 [34], and Ravi Suppiah et.…”

Section: Recent Development Of Emg Control Methodsmentioning

confidence: 99%

Analysis of ANN and Fuzzy Logic Dynamic Modelling to Control the Wrist Exoskeleton

Karis,

Kasdirin,

Abas

et al. 2023

Journal of Robotics and Control

View full text Add to dashboard Cite

show abstract

“…Therefore, it is collected using the BIOPAC MP150 DAQ setup. However, while collecting the signal for MOA, a series of 50-60 taps are done in the proximity of the electrodeattached muscle in one minute [29]. To retain only the signal containing MOA, the obtained signal is filtered beyond 35 Hz using a low pass filter with a cutoff frequency of 35 Hz.…”

Section: Datasetmentioning

confidence: 99%

“…However, their values may be insignificant from the perspective of the goal. Procedures to compute these physical parameters are referred from [29], [32].…”

Section: ) Observationsmentioning

confidence: 99%

“…In all these studies, implementing RL to those problems requires formulating the problem as a Markov decision process (MDP). In [29], M.C. Tosin et al formulated noise removal as an MDP and dynamically filtered four different types of noise introduced at different intervals of a signal.…”

Section: Introductionmentioning

confidence: 99%

“…The fuzzy logic-based rewarding strategy requires an inference table, which can only be determined by an expert. However, in [29], the authors deduced a heatmap-based fuzzy inference table before the learning process. This heatmap table guides the output of the fuzzy system, which is then used to generate a reward.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

supDQN: Supervised Rewarding Strategy Driven Deep Q-Network for sEMG Signal Decontamination

Jena,

Gehlot,

Kumar

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The presence of muscles throughout the active parts of the body, such as the upper and lower limbs, makes electromyography-based human-machine interaction prevalent. However, muscle signals are stochastic and noisy, with noises being both regular and irregular. Irregular noises due to movements or electrical switching require dynamic filtering. Conventionally, filters are stacked, which unnecessarily trims and delays the signal. This study introduces a decontamination technique involving a supervised rewarding strategy to drive a deep Q-network-based agent (supDQN). It applies one of three filters to decontaminate a 1 sec long surface electromyography signal, which is dynamically contaminated. A machine learning agent identifies whether the signal after filtering is clean or noisy, generating a reward accordingly. The identification accuracy is enhanced by using a local interpretable model-agnostic explanation. The deep Q-network is guided by this reward to select the filter optimally while decontaminating a signal. The proposed filtering strategy is tested on four noise levels (-5 dB, -1 dB, +1 dB, +5 dB). supDQN filters the signal desirably when the signal-tonoise ratio (SNR) is between -5 dB to +1 dB but filters less desirably at high SNR (+5 dB). A normalized root mean square (Ω) is formulated to depict the difference of the filtered signal from the ground truth. This is used to compare supDQN and conventional methods, including wavelet denoising with debauchies and symlet wavelet, high-order low-pass filter, notch filter, and high-pass filter. The proposed filtering strategy gives an average Ω value of 1.1974, which is lower than that of the conventional filters.

show abstract

Artificial intelligence on biomedical signals: technologies, applications, and future directions

Lee,

Park,

Kim

et al. 2024

Med-X

View full text Add to dashboard Cite

Integrating artificial intelligence (AI) into biomedical signal analysis represents a significant breakthrough in enhanced precision and efficiency of disease diagnostics and therapeutics. From traditional computational models to advanced machine learning algorithms, AI technologies have improved signal processing by efficiently handling complexity and interpreting intricate datasets. Understanding physiological data, which requires highly trained professionals, is now more accessible; in regions with limited access, AI tools expand healthcare accessibility by providing high-level diagnostic insights, ultimately improving health outcomes. This review explores various AI methodologies, including supervised, unsupervised, and reinforcement learning, and examines their synergy for biomedical signal analysis and future directions in medical science. By capturing a comprehensive overview of the current state and prospects of AI-driven healthcare, this paper highlights the transformative potential of AI in analyzing biomedical signals. Graphical Abstract

show abstract

Identification and removal of contaminants in sEMG recordings through a methodology based on Fuzzy Inference and Actor-Critic Reinforcement learning

Cited by 11 publications

References 39 publications

Analysis of ANN and Fuzzy Logic Dynamic Modelling to Control the Wrist Exoskeleton

Analysis of ANN and Fuzzy Logic Dynamic Modelling to Control the Wrist Exoskeleton

supDQN: Supervised Rewarding Strategy Driven Deep Q-Network for sEMG Signal Decontamination

Artificial intelligence on biomedical signals: technologies, applications, and future directions

Contact Info

Product

Resources

About