Search

Despite decades of research and development of pattern recognition approaches, the clinical usability of myoelectriccontrolled prostheses is still limited. One of the main issues is the high inter-subject variability that necessitates long and frequent user-specific training. Cross-user models present an opportunity to improve clinical viability of myoelectric control systems by leveraging existing data to shorten training. However, due to the difficulty of obtaining large sets of data from amputee populations, data from intact-limbed subjects are often supplemented when building cross-user models; which may not translate well to clinical usability. In this preliminary study, the differences between intact-limbed and amputee cross-user electromyography (EMG) patterns were examined. Previously collected EMG data from 20 intact limbed and 10 amputee subjects for different wrist, finger, and grasping gestures were analysed. Results using unsupervised clustering showed that amputees were consistently grouped into a different cluster than intact-limbed subjects and that additional clustering into more subgroups found larger differences between amputees than able-bodied subjects. Furthermore, a simple linear classifier was able to discriminate between able-bodied and amputee subjects using EMG from multiple gestures with 90% accuracy. These results suggest that using able-bodied subject data alone may be insufficient to capture the necessary inter-subject variance when designing cross-user myoelectric control systems for prosthesis control., Comment: Submitted to MEC 2020 (Myoelectric Control) Conference

Recent human computer-interaction (HCI) studies using electromyography (EMG) and inertial measurement units (IMUs) for upper-limb gesture recognition have claimed that inertial measurements alone result in higher classification accuracy than EMG. In biomedical research such as in prosthesis control, however, EMG remains the gold standard for providing gesture specific information, exceeding the performance of IMUs alone. This study, therefore, presents a preliminary investigation of these conflicting claims between these converging research fields. Previous claims from both fields were verified within this study using publicly available datasets. The conflicting claims were found to stem from differences in terminology and experimental design. Specifically, HCI studies were found to exploit positional variation to increase separation between similar hand gestures. Conversely, in clinical applications such as prosthetics, position invariant gestures are preferred.This work therefore suggests that future studies explicitly outline experimental approaches to better differentiate between gesture recognition approaches., Comment: Submitted to 2020 MEC (Myoelectric Control) conference

Surface electromyography (sEMG) provides an intuitive and non-invasive interface from which to control machines. However, preserving the myoelectric control system's performance over multiple days is challenging, due to the transient nature of the signals obtained with this recording technique. In practice, if the system is to remain usable, a time-consuming and periodic recalibration is necessary. In the case where the sEMG interface is employed every few days, the user might need to do this recalibration before every use. Thus, severely limiting the practicality of such a control method. Consequently, this paper proposes tackling the especially challenging task of unsupervised adaptation of sEMG signals, when multiple days have elapsed between each recording, by introducing Self-Calibrating Asynchronous Domain Adversarial Neural Network (SCADANN). SCADANN is compared with two state-of-the-art self-calibrating algorithms developed specifically for deep learning within the context of EMG-based gesture recognition and three state-of-the-art domain adversarial algorithms. The comparison is made both on an offline and a dynamic dataset (20 participants per dataset), using two different deep network architectures with two different input modalities (temporal-spatial descriptors and spectrograms). Overall, SCADANN is shown to substantially and systematically improves classification performances over no recalibration and obtains the highest average accuracy for all tested cases across all methods., Comment: 12 pages + 2 pages appendices. The last three authors shared senior authorship

Within the field of electromyography-based (EMG) gesture recognition, disparities exist between the offline accuracy reported in the literature and the real-time usability of a classifier. This gap mainly stems from two factors: 1) The absence of a controller, making the data collected dissimilar to actual control. 2) The difficulty of including the four main dynamic factors (gesture intensity, limb position, electrode shift, and transient changes in the signal), as including their permutations drastically increases the amount of data to be recorded. Contrarily, online datasets are limited to the exact EMG-based controller used to record them, necessitating the recording of a new dataset for each control method or variant to be tested. Consequently, this paper proposes a new type of dataset to serve as an intermediate between offline and online datasets, by recording the data using a real-time experimental protocol. The protocol, performed in virtual reality, includes the four main dynamic factors and uses an EMG-independent controller to guide movements. This EMG-independent feedback ensures that the user is in-the-loop during recording, while enabling the resulting dynamic dataset to be used as an EMG-based benchmark. The dataset is comprised of 20 able-bodied participants completing three to four sessions over a period of 14 to 21 days. The ability of the dynamic dataset to serve as a benchmark is leveraged to evaluate the impact of different recalibration techniques for long-term (across-day) gesture recognition, including a novel algorithm, named TADANN. TADANN consistently and significantly (p<0.05) outperforms using fine-tuning as the recalibration technique., Comment: 10 Pages. The last three authors shared senior authorship

The research in myoelectric control systems primarily focuses on extracting discriminative representations from the electromyographic (EMG) signal by designing handcrafted features. Recently, deep learning techniques have been applied to the challenging task of EMG-based gesture recognition. The adoption of these techniques slowly shifts the focus from feature engineering to feature learning. However, the black-box nature of deep learning makes it hard to understand the type of information learned by the network and how it relates to handcrafted features. Additionally, due to the high variability in EMG recordings between participants, deep features tend to generalize poorly across subjects using standard training methods. Consequently, this work introduces a new multi-domain learning algorithm, named ADANN, which significantly enhances (p=0.00004) inter-subject classification accuracy by an average of 19.40% compared to standard training. Using ADANN-generated features, the main contribution of this work is to provide the first topological data analysis of EMG-based gesture recognition for the characterisation of the information encoded within a deep network, using handcrafted features as landmarks. This analysis reveals that handcrafted features and the learned features (in the earlier layers) both try to discriminate between all gestures, but do not encode the same information to do so. Furthermore, using convolutional network visualization techniques reveal that learned features tend to ignore the most activated channel during gesture contraction, which is in stark contrast with the prevalence of handcrafted features designed to capture amplitude information. Overall, this work paves the way for hybrid feature sets by providing a clear guideline of complementary information encoded within learned and handcrafted features., Comment: The first two authors shared first authorship. The last three authors shared senior authorship. 32 pages

Varieties of noises are major problem in recognition of Electromyography (EMG) signal. Hence, methods to remove noise become most significant in EMG signal analysis. White Gaussian noise (WGN) is used to represent interference in this paper. Generally, WGN is difficult to be removed using typical filtering and solutions to remove WGN are limited. In addition, noise removal is an important step before performing feature extraction, which is used in EMG-based recognition. This research is aimed to present a novel feature that tolerate with WGN. As a result, noise removal algorithm is not needed. Two novel mean and median frequencies (MMNF and MMDF) are presented for robust feature extraction. Sixteen existing features and two novelties are evaluated in a noisy environment. WGN with various signal-to-noise ratios (SNRs), i.e. 20-0 dB, was added to the original EMG signal. The results showed that MMNF performed very well especially in weak EMG signal compared with others. The error of MMNF in weak EMG signal with very high noise, 0 dB SNR, is about 5-10 percent and closed by MMDF and Histogram, whereas the error of other features is more than 20 percent. While in strong EMG signal, the error of MMNF is better than those from other features. Moreover, the combination of MMNF, Histrogram of EMG and Willison amplitude is used as feature vector in classification task. The experimental result shows the better recognition result in noisy environment than other success feature candidates. From the above results demonstrate that MMNF can be used for new robust feature extraction.