Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

E ŞAHiN, NN Arslan, D Özdemir - Neural Computing and Applications, 2024 - Springer
Deep learning models have revolutionized numerous fields, yet their decision-making
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

H Xu, W Zheng, Y Zhang, D Zhao, L Wang… - Nature …, 2023 - nature.com
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 …

Explainable and robust deep forests for EMG-force modeling

X Jiang, K Nazarpour, C Dai - IEEE Journal of Biomedical and …, 2023 - ieeexplore.ieee.org
Machine and deep learning techniques have received increasing attentions in estimating
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

P Kang, J Li, S Jiang, PB Shull - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Multimodal sensor fusion can improve the performance of human–machine interfaces
(HMIs). However, increased sensing modalities and sensor count often cause excess …

One-shot random forest model calibration for hand gesture decoding

X Jiang, C Ma, K Nazarpour - Journal of Neural Engineering, 2024 - iopscience.iop.org
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 …

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 …

Understandable time frame-based biosignal processing

H Rafiei, MR Akbarzadeh-T - Biomedical Signal Processing and Control, 2025 - Elsevier
The explainability of biological time series poses considerable challenges regarding signal
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 …

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 …

EMGCipher: Decoding Electromyography for Upper-limb Gesture Classification with Explainable AI for Resource Optimization

H Lee, M Jiang, Q Zhao - … of the IEEE Engineering in Medicine …, 2024 - ieeexplore.ieee.org
Assistive limb devices often employ surface electromyography (sEMG) and deep learning
(DL) models for gesture classification. While DL models effectively classify diverse upper …