25 December 2019 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
An important barrier to commercialization of pattern recognition myoelectric control of prostheses is the lack of robustness to confounding factors such as electrode shift, skin impedance variations, and learning effects. To overcome this challenge, a novel supervised adaptation approach based on transfer learning (TL) with convolutional neural networks (CNNs) is proposed which requires only a short training session (a few seconds for each class) to recalibrate the system. TL is proposed as a solution to the problem of insufficient calibration data due to short training times for both classification and regression-based control schemes. This approach was validated for electrode shift of roughly 2.5cm with 13 able-bodied subjects to estimate individual and combined wrist motions. With this method, the original CNN (trained before the shift) was fine-tuned with the calibration data from after shifting. The results show that the proposed technique outperforms training a CNN from scratch (random initialization of weights) or a support vector machine (SVM) using the minimal calibration data. Moreover, it demonstrates superior performance than previous LDA and QDA-based adaptation approaches. As the outcomes confirm, the proposed CNN TL method provides a practical solution for adaptation to external factors, improving the robustness of electromyogram (EMG) pattern recognition systems.
28 April 2020 in IEEE Transactions on Circuits and Systems for Video Technology
6 July 2021 in Scientific Reports
Developing high-density electrodes for recording large ensembles of neurons provides a unique opportunity for understanding the mechanism of the neuronal circuits. Nevertheless, the change of brain tissue around chronically implanted neural electrodes usually causes spike wave-shape distortion and raises the crucial issue of spike sorting with an unstable structure. The automatic spike sorting algorithms have been developed to extract spikes from these big extracellular data. However, due to the spike wave-shape instability, there have been a lack of robust spike detection procedures and clustering to overcome the spike loss problem. Here, we develop an automatic spike sorting algorithm based on adaptive spike detection and a mixture of skew-t distributions to address these distortions and instabilities. The adaptive detection procedure applies to the detected spikes, consists of multi-point alignment and statistical filtering for removing mistakenly detected spikes. The detected spikes are clustered based on the mixture of skew-t distributions to deal with non-symmetrical clusters and spike loss problems. The proposed algorithm improves the performance of the spike sorting in both terms of precision and recall, over a broad range of signal-to-noise ratios. Furthermore, the proposed algorithm has been validated on different datasets and demonstrates a general solution to precise spike sorting, in vitro and in vivo.
11 January 2022 in IEEE Journal of Biomedical and Health Informatics
Efficient storage and transmission of electromyogram (EMG) data are important for emerging applications such as telemedicine and big data, as a vital tool for further advancement of the field. However, due to limitations in internet speed and hardware resources, transmission and storage of EMG data are challenging. As a solution, this work proposes a new method for EMG data compression using deep convolutional autoencoders (CAE). Eight-channel EMG data from 10 subjects, and high-density EMG data from 18 subjects, were investigated for compression. The CAE architecture was designed to extract an abstract data representation that is heavily compressed, but from which the salient information for classification can be effectively reconstructed. The proposed method attained efficient compression; for CR = 1600, the average PRDN (percentage RMS difference normalized) was 31.5% and the wrist motions classification accuracy (CA) reduced roughly 5%. The CAE substantially outperformed the state-of-the-art high-efficiency video coding and a well-known wavelet-thresholding compression technique. Moreover, by reducing the bit-resolution of the CAE's compressed data from 24 bits to 6 bits, an additional 4-fold compression was achieved without significant degradation of the reconstruction performance. Furthermore, the CAE's inter-subject performance was promising; e.g., for CR = 1600, the PRDN for the inter-subject case was only 2.6% less than that of the within-subject performance. The powerful EMG compression performance with remarkable reconstruction results reflects the CAEs potential as an automatic end-to-end approach with the ability to learn the complete encoding and decoding process. Furthermore, the excellent inter-subject performance demonstrates the generalizability and usability of the proposed approach.
24 May 2019 in Signal Processing