Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning
Deep learning models have revolutionized numerous fields, yet their decision-making
processes often remain opaque, earning them the characterization of “black-box” models …
processes often remain opaque, earning them the characterization of “black-box” models …
A fully integrated, standalone stretchable device platform with in-sensor adaptive machine learning for rehabilitation
Post-surgical treatments of the human throat often require continuous monitoring of diverse
vital and muscle activities. However, wireless, continuous monitoring and analysis of these …
vital and muscle activities. However, wireless, continuous monitoring and analysis of these …
Explainable and robust deep forests for EMG-force modeling
Machine and deep learning techniques have received increasing attentions in estimating
finger forces from high-density surface electromyography (HDsEMG), especially for neural …
finger forces from high-density surface electromyography (HDsEMG), especially for neural …
Reduce system redundancy and optimize sensor disposition for EMG–IMU multimodal fusion human–machine interfaces with XAI
Multimodal sensor fusion can improve the performance of human–machine interfaces
(HMIs). However, increased sensing modalities and sensor count often cause excess …
(HMIs). However, increased sensing modalities and sensor count often cause excess …
One-shot random forest model calibration for hand gesture decoding
Objective. Most existing machine learning models for myoelectric control require a large
amount of data to learn user-specific characteristics of the electromyographic (EMG) signals …
amount of data to learn user-specific characteristics of the electromyographic (EMG) signals …
CGMV-EGR: A Multimodal Fusion Framework for Electromyographic Gesture Recognition
W Wang, Y Liu, F Song, J Lu, J Qu, J Guo, J Huang - Pattern Recognition, 2025 - Elsevier
Surface electromyography (sEMG)-based gesture recognition in virtual/augmented reality
(VR/AR) environments faces challenges such as effective multimodal fusion and individual …
(VR/AR) environments faces challenges such as effective multimodal fusion and individual …
Understandable time frame-based biosignal processing
The explainability of biological time series poses considerable challenges regarding signal
multiplicity, high volatility, nonstationarity, and noisiness in pursuit of understanding human …
multiplicity, high volatility, nonstationarity, and noisiness in pursuit of understanding human …
Practical Finite-Time Compliant Control for Horizontal Pneumatic Artificial Muscle Systems Under Force-Sensorless Reflecting
G Liu, S Diao, Z Liu, X Zhang, X **ao… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Pneumatic artificial muscle (PAM) actuators have passive compliance and vibration
absorption capabilities, adapting to high-intensity human-robot interaction movements …
absorption capabilities, adapting to high-intensity human-robot interaction movements …
Deep Learning for Electromyographic Lower-Limb Motion Signal Classification Using Residual Learning
J Sun, Y Wang, J Hou, G Li, B Sun… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Electromyographic (EMG) signals have gained popularity for controlling prostheses and
exoskeletons, particularly in the field of upper limbs for stroke patients. However, there is a …
exoskeletons, particularly in the field of upper limbs for stroke patients. However, there is a …
EMGCipher: Decoding Electromyography for Upper-limb Gesture Classification with Explainable AI for Resource Optimization
Assistive limb devices often employ surface electromyography (sEMG) and deep learning
(DL) models for gesture classification. While DL models effectively classify diverse upper …
(DL) models for gesture classification. While DL models effectively classify diverse upper …