Multimodal deep learning network based hand ADLs tasks classification for prosthetics control

Deep learning for processing electromyographic signals: A taxonomy-based survey

“…In-fact, only few of the herein reviewed papers consider data augmentation. In particular the authors of three articles augmented the EMG sig-nals by adding Gaussian noise to the original set of signals and modulating the signal to noise ratio [14,219,183]. Only one paper dealing with high-density EMG electrodes proposes a random shift of the training images by one pixel in four directions to improve the system robustness respect to electrode array positioning [68].…”

“…After a careful review of all papers within this class, CNNs revealed to be the most commonly used networks, followed by AEs, RNNs, and DBNs (see Figure 5). According to the increasing popularity of CNNs in several research fields due to their proven high performance, several authors proposed classifiers based on CNNs only [14,155,94,183,174,18,199,161,163,171,7,64,120,22,180,192,13,213,68,56,52,70,140], or on both CNNs-RNNs [81,200,198,191], or on CNN-AE [219]. Some authors have alternatively developed multi-class classifiers entirely based on deep AEs [222,110,128,164,163,3], RNNs [175,98,181] or DBNs [170,169].…”