Browsing by Author "Ameri, Ali"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    A Deep Transfer Learning Approach to Reducing the Effect of Electrode Shift in EMG Pattern Recognition-Based Control
    (Institute of Electrical and Electronics Engineers, 2020) Ameri, Ali; Akhaee, Mohammad Ali; Scheme, Erik; Englehart, Kevin
    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.
  • Thumbnail Image
    Item
    Compression of EMG Signals Using Deep Convolutional Autoencoders
    (Institute of Electrical and Electronics Engineers, 2022) Dinashi, Kimia; Ameri, Ali; Akhaee, Mohammad Ali; Englehart, Kevin; Scheme, Erik
    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.
  • Thumbnail Image
    Item
    Real-time simultaneous myoelectric control of multiple degrees of freedom
    (University of New Brunswick, 2014) Ameri, Ali; Englehart, Kevin; Parker, Philip; Scheme, Erik
    Natural limb control during activities of daily living involves simultaneous motions of multiple degrees of freedom (DOFs) (such as feeding or grooming, which require simultaneous activation of hand, arm, and wrist in multiple directions). A strategy for simultaneous myoelectric control is to train the system with EMG as the input and the corresponding joint force or position (angle) as the target. For prosthesis control, since it is not possible to measure force/position from an absent limb, a strategy called mirrored bilateral training was proposed (with unilateral amputees) in previous work, in which force/position was recorded from the opposite limb during mirrored contractions. In this work, the effect of alternative feature sets, estimators, feature projection, and coordinate systems on estimation performance was studied with force and position based paradigms. Furthermore, a real-time control test was performed to assess the system usability. It was shown that when the EMG (and effort) levels were similar, no significant difference (p>0.1) was found between the force and position based methods in both offline and real-time control tests. A novel training paradigm for simultaneous control is described, in which users were prompted to synchronize their contractions with a moving target cursor on a computer screen. The cursor displacements were used as targets to train the estimators. The system usability was assessed with a real-time control test, and the performance was found to be equivalent (p>0.1) to that of the mirrored bilateral training. The proposed visual target based training is more practical than mirrored training because it does not require force and position sensing equipment, and can be potentially used by both unilateral and bilateral amputees. Finally, a novel application of a support vector machine (SVM) was evaluated in simultaneous myoelectric real-time control of DOFs. It was shown with able-bodied and amputee subjects that the proposed SVM based method outperformed the widely used multilayer perceptron artificial neural network (ANN) in a Fitts’ law style real-time control test. Moreover, the processing time required for training and estimation with the SVM was significantly lower than that of the ANN. This approach is shown to provide a robust and computationally efficient system for simultaneous and proportional myoelectric control.
  • Thumbnail Image
    Item
    Real-time, simultaneous myoelectric control using a convolutional neural network
    (Public Library of Science, 2018-09-13) Ameri, Ali; Akhaee, Mohammad Ali; Scheme, Erik; Englehart, Kevin; Ginestra Bianconi
    The evolution of deep learning techniques has been transformative as they have allowed complex mappings to be trained between control inputs and outputs without the need for feature engineering. In this work, a myoelectric control system based on convolutional neural networks (CNN) is proposed as a possible alternative to traditional approaches that rely on specifically designed features. This CNN-based system is validated using a real-time Fitts’ law style target acquisition test requiring single and combined wrist motions. The performance of the proposed system is then compared to that of a standard support vector machine (SVM) based myoelectric system using a set of time-domain features. Despite the prevalence and demonstrated performance of these well-known features, no significant difference (p>0.05) was found between the two methods for any of the computed control metrics. This demonstrates the potential for automated learning approaches to extract complex and rich information from stochastic biological signals. This first evaluation of the usability of a CNN in a real-time myoelectric control environment provides a basis for further exploration.
  • Thumbnail Image
    Item
    Regression convolutional neural network for improved simultaneous EMG control
    (IOP Publishing, 2019) Ameri, Ali; Ali Akhaee, Mohammad; Scheme, Erik; Englehart, Kevin
    Objective. Deep learning models can learn representations of data that extract useful information in order to perform prediction without feature engineering. In this paper, an electromyography (EMG) control scheme with a regression convolutional neural network (CNN) is proposed as a substitute of conventional regression models that use purposefully designed features. Approach. The usability of the regression CNN model is validated for the first time, using an online Fitts' law style test with both individual and simultaneous wrist motions. Results were compared to that of a support vector regression-based scheme with a group of widely used extracted features. Main results. In spite of the proven efficiency of these well-known features, the CNN-based system outperformed the support vector machine (SVM) based scheme in throughput, due to higher regression accuracies especially with high EMG amplitudes. Significance. These results indicate that the CNN model can extract underlying motor control information from EMG signals during single and multiple degree-of-freedom (DoF) tasks. The advantage of regression CNN over classification CNN (studied previously) is that it allows independent and simultaneous control of motions.