Journal Articles

Permanent URI for this collection

Articles. Typically the realization of research papers reporting original research findings published in a journal issue. (URI: http://purl.org/coar/resource_type/c_6501) Item types include:

  • editorial
  • journal article
    • corrigendum
    • data paper
    • research article
    • review article
    • software paper
  • letter to the editor

Browse

Recent Submissions

Now showing 1 - 20 of 153
  • Item
    Essential requirements for the governance and management of data trusts, data repositories, and other data collaborations
    (Swansea University, 2023-09-20) Paprica, P. Alison; Crichlow, Monique; Curtis Maillet, Donna; Kesselring, Sarah; Pow, Conrad; Scarnecchia, Thomas P.; Schull, Michael J.; Cartagena, Rosario G.; Cumyn, Annabelle; Dostmohammad, Salman; Elliston, Keith O.; Griever, Michelle; Hawn Nelson, Amy; Hill, Sean L.; Isaranuwatcha, Wanrudee; Loukipoudis, Evgueni; McDonald, James Ted; McLaughlin, John R.; Rabinowitz, Alan; Razak, Fahad; Verhulst, Stefaan G.; Verma, Amol A.; Victor, J. Charles; Young, Andrew; Yu, Joanna; McGrail, Kimberlyn
    Introduction Around the world, many organisations are working on ways to increase the use, sharing, and reuse of person-level data for research, evaluation, planning, and innovation while ensuring that data are secure and privacy is protected. As a contribution to broader efforts to improve data governance and management, in 2020 members of our team published 12 minimum specification essential requirements (min specs) to provide practical guidance for organisations establishing or operating data trusts and other forms of data infrastructure. Approach and Aims We convened an international team, consisting mostly of participants from Canada and the United States of America, to test and refine the original 12 min specs. Twenty-three (23) data-focused organisations and initiatives recorded the various ways they address the min specs. Sub-teams analysed the results, used the findings to make improvements to the min specs, and identified materials to support organisations/initiatives in addressing the min specs. Results Analyses and discussion led to an updated set of 15 min specs covering five categories: one min spec for Legal, five for Governance, four for Management, two for Data Users, and three for Stakeholder & Public Engagement. Multiple changes were made to make the min specs language more technically complete and precise. The updated set of 15 min specs has been integrated into a Canadian national standard that, to our knowledge, is the first to include requirements for public engagement and Indigenous Data Sovereignty. Conclusions The testing and refinement of the min specs led to significant additions and improvements. The min specs helped the 23 organisations/initiatives involved in this project communicate and compare how they achieve responsible and trustworthy data governance and management. By extension, the min specs, and the Canadian national standard based on them, are likely to be useful for other data-focused organisations and initiatives.
  • Item
    Double Disparity of Sexual Minority Status and Rurality in Cardiometabolic Hospitalization Risk: A Secondary Analysis Using Linked Population-Based Data
    (MDPI, 2023-10-30) Gupta, Neeru; Cookson, Samuel R.
    Studies have shown separately that sexual minority populations generally experience poorer chronic health outcomes compared with those who identify as heterosexual, as do rural populations compared with urban dwellers. This Canadian national observational study explored healthcare patterns at the little-understood intersections of lesbian, gay, or bisexual (LGB) identity with residence in rural and remote communities, beyond chronic disease status. The secondary analysis applied logistic regressions on multiple linked datasets from representative health surveys, administrative hospital records, and a geocoded index of community remoteness to examine differences in the risk of potentially avoidable cardiometabolic-related hospitalization among adults of working age. Among those with an underlying cardiometabolic condition and residing in more rural and remote communities, a significantly higher hospitalization risk was found for LGB-identified persons compared with their heterosexual peers (odds ratio: 4.2; 95% confidence interval: 1.5–11.7), adjusting for sociodemographic characteristics, behavioral risk factors, and primary healthcare access. In models stratified by sex, the association remained significant among gay and bisexual men (5.6; CI: 1.3–24.4) but not among lesbian and bisexual women (3.5; CI: 0.9–13.6). More research is needed leveraging linkable datasets to better understand the complex and multiplicative influences of sexual minority status and rurality on cardiometabolic health to inform equity-enhancing preventive healthcare interventions.
  • Item
    Comparison of socio-economic determinants of COVID-19 testing and positivity in Canada: A multi-provincial analysis
    (PLOS, 2023-08-23) Antonova, Lilia; Somayaji, Chandy; Cameron, Jillian; Sirski, Monica; Sundaram, Maria E.; McDonald, James Ted; Mishra, Sharmistha; Kwong, Jeffrey C.; Katz, Alan; Baral, Stefan; Caulley, Lisa; Calzavara, Andrew; Corsten, Martin; Johnson-Obaseki, Stephanie
    The effects of the COVID-19 pandemic have been more pronounced for socially disadvantaged populations. We sought to determine how access to SARS-CoV-2 testing and the likelihood of testing positive for COVID-19 were associated with demographic factors, socioeconomic status (SES) and social determinants of health (SDH) in three Canadian provinces.
  • Item
    Novel wearable HD-EMG sensor with shift-robust gesture recognition using deep learning
    (IEEE, 2023-09-11) Chamberland, Félix; Buteau, Étienne; Tam, Simon; Campbell, Evan; Mortazavi, Ali; Scheme, Erik; Fortier, Paul; Boukadoum, Mounir; Campeau-Lecours, Alexandre; Gosselin, Benoit
    In this work, we present a hardware-software solution to improve the robustness of hand gesture recognition to confounding factors in myoelectric control. The solution includes a novel, full-circumference, flexible, 64-channel high-density electromyography (HD-EMG) sensor called EMaGer. The stretchable, wearable sensor adapts to different forearm sizes while maintaining uniform electrode density around the limb. Leveraging this uniformity, we propose novel array barrel-shifting data augmentation (ABSDA) approach used with a convolutional neural network (CNN), and an anti-aliased CNN (AA-CNN), that provides shift invariance around the limb for improved classification robustness to electrode movement, forearm orientation, and inter-session variability. Signals are sampled from a 4×16 HD-EMG array of electrodes at a frequency of 1 kHz and 16-bit resolution. Using data from 12 non-amputated participants, the approach is tested in response to sensor rotation, forearm rotation, and inter-session scenarios. The proposed ABSDA-CNN method improves inter-session accuracy by 25.67% on average across users for 6 gesture classes compared to conventional CNN classification. A comparison with other devices shows that this benefit is enabled by the unique design of the EMaGer array. The AA-CNN yields improvements of up to 63.05% accuracy over non-augmented methods when tested with electrode displacements ranging from −45 ∘ to +45 ∘ around the limb. Overall, this article demonstrates the benefits of co-designing sensor systems, processing methods, and inference algorithms to leverage synergistic and interdependent properties to solve state-of-the-art problems.
  • Item
    Analyzing the impact of class transitions on the design of pattern recognition-based myoelectric control schemes
    (Elsevier, 2022-01) Raghu, Shriram Tallam Puranam; MacIsaac, Dawn T.; Scheme, Erik J.
    Despite continued efforts to improve classification accuracy, it has been reported that offline accuracy is a poor indicator of the usability of pattern recognition-based myoelectric control. One potential source of this disparity is the existence of transitions between contraction classes that happen during regular use and are reported to be problematic for pattern recognition systems. Nevertheless, these transitions are often ignored or undefined during both the training and testing processes. In this work, we propose a set of metrics for analyzing the transitions that occur during the voluntary changes between contraction classes during continuous control. These metrics quantify the common types of errors that occur during transitions and compare them to existing metrics that apply only to the steady-state portions of the data. We then use these metrics to analyze transition characteristics of 6 commonly used classifiers on a novel dataset that includes continuous transitions between all combinations of seven different contraction classes. Results show that a linear discriminant classifier consistently outperforms other conventional classifiers during both transitions and steady-state conditions, despite having an almost identical offline performance. Results also show that, although offline training metrics correlate with steady-state performance, they do not correlate with transition performance. These insights suggest that the proposed set of metrics could provide a shift in perspective on the way pattern recognition systems are evaluated and provide a more representative picture of a classifier’s performance, potentially narrowing the gap between offline performance and online usability.
  • Item
    A linearly extendible multi-artifact removal approach for improved upper extremity EEG-based motor imagery decoding
    (IOP Publishing Ltd, 2021) Asogbon, Mojisola Grace; Samuel, Oluwarotimi Williams; Li, Xiangxin; Nsugbe, Ejay; Scheme, Erik; Li, Guanglin
    Background and Objective: Non-invasive multichannel Electroencephalography (EEG) recordings provide an alternative source of neural information from which motor imagery (MI) patterns associated with limb movement intent can be decoded for use as control inputs for rehabilitation robots. The presence of multiple inherent dynamic artifacts in EEG signals, however, poses processing challenges for brain-computer interface (BCI) systems. A large proportion of the existing EEG signal preprocessing methods focus on isolating single artifact per time from an ensemble of EEG trials and require calibration and/or reference electrodes, resulting in increased complexity of their application to MI-EEG controlled rehabilitation devices in practical settings. Also, a few existing multi-artifacts removal methods though explored in other domains, they have rarely been investigated in the space of MI-EEG signals for multiple artifacts cancellation in a simultaneous manner. Approach: Building on the premise of previous works, this study propose a semi-automatic EEG preprocessing method that combines Generalized Eigenvalue Decomposition driven by low-rank approximation and a Multi-channel Wiener Filter (GEVD-MWF) that employs a learning technique for simultaneous elimination of multiple artifacts from MI-EEG signals. The proposed method is applied to remove multiple artifacts from 64-channel EEG signals recorded from transhumeral amputees while they performed distinct classes of upper limb MI tasks before decoding their movement intent using a selection of features and machine learning algorithms. Main Results: Experimental results show that the proposed GEVD-MWF method yields significant improvements in MI decoding accuracies, in the range of 13.23%-41.21% compared to four existing popular artifact removal algorithms. Further investigation revealed that the GEVD-MWF approach enabled accuracies in the range of 90.44% - 99.67% using "single trial" EEG recordings, which could eliminate the need to record and process large ensembles of EEG trials as commonly required in some existing approaches. Additionally, using a variant of the sequential forward floating selection algorithm, a subset of 9 channels was used to obtain a decoding accuracy of 93.73%±1.58%. Significance: Given its improved performance, reduced data requirements, and feasibility with few channels, the proposed GEVD-MWF could potentially spur the development of effective real-time control strategies for multi-degree of freedom EEG-based miniaturized rehabilitation robotic interfaces.
  • Item
    Myoelectric control with fixed convolution-based time-domain feature extraction: exploring the spatio–temporal interaction
    (IEEE, 2022-02-24) Khushaba, Rami N.; Al-Timemy, Ali H.; Samuel, Oluwarotimi Williams; Scheme, Erik J.
    The role of feature extraction in electromyogram (EMG) based pattern recognition has recently been emphasized with several publications promoting deep learning (DL) solutions that outperform traditional methods. It has been shown that the ability of DL models to extract temporal, spatial, and spatio–temporal information provides significant enhancements to the performance and generalizability of myoelectric control. Despite these advancements, it can be argued that DL models are computationally very expensive, requiring long training times, increased training data, and high computational resources, yielding solutions that may not yet be feasible for clinical translation given the available technology. The aim of this paper is, therefore, to leverage the benefits of spatio–temporal DL concepts into a computationally feasible and accurate traditional feature extraction method. Specifically, the proposed novel method extracts a set of well-known time-domain features into a matrix representation, convolves them with predetermined fixed filters, and temporally evolves the resulting features over a short and long-term basis to extract the EMG temporal dynamics. The proposed method, based on Fixed Spatio–Temporal Convolutions, offers significant reductions in the computational costs, while demonstrating a solution that can compete with, and even outperform, recent DL models. Experimental tests were performed on sparse-and high-density EMG (HD-EMG) signals databases, across a total of 44 subjects performing a maximum of 53 movements. Despite the simplification compared to deep approaches, our results show that the proposed solution significantly reduces the classification error rates by 3% to 10% in comparison to recent DL models, while being efficient for real-time implementations.
  • Item
    Automation of the Timed-Up-and-Go test using a conventional video camera
    (IEEE, 2019-08-09) Savoie, Patrick; Cameron, James A. D.; Kaye, Mary E.; Scheme, Erik J.
    The Timed-Up-and-Go (TUG) test is a simple clinical tool commonly used to quickly assess the mobility of patients. Researchers have endeavored to automate the test using sensors or motion tracking systems to improve its accuracy and to extract more resolved information about its sub-phases. While some approaches have shown promise, they often require the donning of sensors or the use of specialized hardware, such as the now discontinued Microsoft Kinect, which combines video information with depth sensors (RGBD). In this work, we leverage recent advances in computer vision to automate the TUG test using a regular RGB video camera without the need for custom hardware or additional depth sensors. Thirty healthy participants were recorded using a Kinect V2 and a standard video feed while performing multiple trials of 3 and 1.5 meter versions of the TUG test. A Mask Regional Convolutional Neural Net (R-CNN) algorithm and a Deep Multitask Architecture for Human Sensing (DMHS) were then used together to extract global 3D poses of the participants. The timing of transitions between the six key movement phases of the TUG test were then extracted using heuristic features extracted from the time series of these 3D poses. The proposed video-based vTUG system yielded the same error as the standard Kinect-based system for all six key transitions points, and average errors of less than 0.15 seconds from a multi-observer hand labeled ground truth. This work describes a novel method of video-based automation of the TUG test using a single standard camera, removing the need for specialized equipment and facilitating the extraction of additional meaningful information for clinical use.
  • Item
    Evaluation of myoelectric control learning using multi-session game-based training
    (IEEE, 2018-07-12) Tabor, Aaron; Bateman, Scott; Scheme, Erik
    While training is critical for ensuring initial success as well as continued adoption of a myoelectric powered prosthesis, relatively little is known about the amount of training that is necessary. In previous studies, participants have completed only a small number of sessions, leaving doubt about whether the findings necessarily generalize to a longer-term clinical training program. Furthermore, a heavy emphasis has been placed on a functional prosthesis use when assessing the effectiveness of myoelectric training. Although well-motivated, this all-inclusive approach may obscure more subtle improvements made in underlying muscle control that could lead to tangible benefits. In this paper, a deeper exploration of the effects of myoelectric training was performed by following the progress of 30 participants as they completed a series of ten 30-min training sessions over multiple days. The progress was assessed using a newly developed set of metrics that was specifically designed to quantify the aspects of muscle control that are foundational to the strong myoelectric prosthesis use. It was determined that, while myoelectric training can lead to improvements in muscle control, these improvements may take longer than previously considered, even occurring after improvements in the training game itself. These results suggest the need to reconsider how and when transfer from training activities is assessed.
  • Item
    A symmetrical component feature extraction method for fault detection in induction machines
    (IEEE, 2019-09) St-Onge, Xavier F.; Cameron, James; Saleh, Saleh; Scheme, Erik J.
    Induction motors (IMs) are among the fully developed electromechanical technologies that are still in use today. Over the course of the last century, their structure, control, and operation have been undergone through several stages of development. Among stages of development, the automated control and continuous monitoring of IMs has benefited from the emergence of modern artificial intelligence (AI) methods. IM automation schemes have demonstrated the ability to provide machine fault detection and diagnosis (FDD) function. AI-based FDD methods in IMs have employed frequency-domain, time-frequency, and time-domain analyses as the basis of their feature extraction schemes. A promising feature extraction scheme is one that uses symmetrical components (SCs) in time-domain FDD systems. Current SC-based approaches, however, are limited in their generalizability to different fault classes, may require detailed machine models, and can suffer from computational limitations. In this paper, an improved feature extraction method that uses SCs for a pattern recognition based FDD scheme for three-phase (3φ) IMs will be presented. This novel feature extraction method will be implemented and verified experimentally to demonstrate high classification performance, increased generalizability, and low computational cost.
  • Item
    A survey on neuromarketing using EEG signals
    (IEEE, 2021-03-12) Khurana, Vaishali; Gahalawat, Monika; Kumar, Pradeep; Roy, Partha Pratim; Dogra, Debi Prosad; Scheme, Erik; Soleymani, Mohammad
    Neuromarketing is the application of neuroscience to the understanding of consumer preferences toward products and services. As such, it studies the neural activity associated with preference and purchase intent. Neuromarketing is considered an emerging area of research, driven in part by the approximately 400 billion dollars spent annually on advertisement and promotion. Given the size of this market, even a slight improvement in performance can have an immense impact. Traditional approaches to marketing consider a posteriori user feedback in the form of questionnaires, product ratings, or review comments, but these approaches do not fully capture or explain the real-time decision-making process of consumers. Various physiological measurement techniques have been proposed to facilitate the recording of this crucial aspect of the decision-making process, including brain imaging techniques [functional magnetic resonance imaging (fMRI), electroencephalography (EEG), steady state topography (SST)], and various biometric sensors. The use of EEG in neuromarketing is especially promising. EEG detects the sequential changes of brain activity, without appreciable time delay, needed to assess both the unconscious reaction and sensory reaction of the customer. Several types of EEG devices are now available in the market, each with its own advantages and disadvantages. Researchers have conducted experiments using many of these devices, across different age groups and different categories of products. Because of the deep insights that can be gained, the field of neuromarketing research is carefully monitored by consumer and research protection groups to ensure that subjects are properly protected. This article surveys a range of considerations for EEG-based neuromarketing strategies, including the types of information that can be gathered, how marketing stimuli are presented to consumers, how such strategies may affect the consumer in terms of appeal and memory, machine learning techniques applied in the field, and the variety of challenges faced, including ethics, in this emerging field.
  • Item
    On the usability of intramuscular EMG for prosthetic control: A Fitts’ Law approach
    (Elsevier, 2014-10) Kamavuako, Ernest N.; Scheme, Erik J.; Kevin B., Englehart
    Previous studies on intramuscular EMG based control used offline data analysis. The current study investigates the usability of intramuscular EMG in two degree-of-freedom using a Fitts’ Law approach by combining classification and proportional control to perform a task, with real time feedback of user performance. Nine able-bodied subjects participated in the study. Intramuscular and surface EMG signals were recorded concurrently from the right forearm. Five performance metrics (Throughput, Path efficiency, Average Speed, Overshoot and Completion Rate) were used for quantification of usability. Intramuscular EMG based control performed significantly better than surface EMG for Path Efficiency (80.5 ± 2.4% vs. 71.5 ± 3.8%, P = 0.004) and Overshoot (22.0 ± 3.0% vs. 45.1 ± 6.6%, P = 0.01). No difference was found between Throughput and Completion Rate. However the Average Speed was significantly higher for surface (51.8 ± 5.5%) than for intramuscular EMG (35.7 ± 2.7%). The results obtained in this study imply that intramuscular EMG has great potential as control source for advanced myoelectric prosthetic devices.
  • Item
    Combined surface and intramuscular EMG for improved real-time myoelectric control performance
    (Elsevier, 2014-03) Kamavuako, Ernest N.; Scheme, Erik J.; Englehart, Kevin B.
    The four main functions that are available in current clinical prostheses (e.g. Otto Bock DMC Plus®) are power grasp, hand open, wrist pronation and wrist supination. Improving the control of these two DoFs is therefore of great clinical and commercial interest. This study investigates whether control performance can be improved by targeting wrist rotator muscles by means of intramuscular EMG. Nine able-bodied subjects were evaluated using offline metrics and during a real-time control task. Two intramuscular (targeted) and four surface EMG channels were recorded concurrently from the right forearm. The control was derived either from the four surface sources or by combining two surface channels combined with two intramuscular channels located in the pronator and supinator muscles (combined EMG). Five metrics (Throughput, Path efficiency, Average Speed, Overshoot and Completion Rate) were used to quantify real-time performance. A significant improvement of 20% in Throughput was obtained with combined EMG (0.90 ± 0.12 bit/s) compared to surface EMG alone (0.75 ± 0.10 bit/s). Furthermore, combined EMG performed significantly better than surface EMG in terms of Overshoot, Path Efficiency and offline classification error. No significant difference was found for Completion Rate and Average Speed. The results obtained in this study imply that targeting muscles that are involved in the rotation of the forearm could improve the performance of myoelectric control systems that include both wrist rotation and opening/closing of a terminal device. Keywords: Fitts’ Law test, targeted EMG, pattern recognition, intramuscular EMG, real-time control, wrist rotator
  • Item
    Sponsorship in focus: a typology of sponsorship contexts and research agenda
    (Emerald, 2021-03-08) Lin, Hsin-Chen; Bruning, Patrick F.
    Purpose – Sponsorship has become an important marketing activity. However, research on the topic treats the sponsorship context, characterized according to the type of sponsored property and the social role of these properties, as a stable characteristic or as a dichotomous characteristic within empirical studies. Therefore, we outline a multi-level typology of the different types of sponsorship contexts to account for traditional types of sponsorship as well as emerging themes such as online sponsorship. We then propose an agenda for future research. Design/methodology/approach – We conduct a general review of the sponsorship literature to synthesise established sponsorship types with newly emerging themes to develop a multi-level typology of sponsorship contexts and a research agenda. Findings – Our conceptual analysis revealed a typology of sponsorship contexts that captures both general and specific types of sport sponsorship, prosocial cause sponsorship, culture and community sponsorship, and media and programming content sponsorship. Research limitations/implications – Our typology provides an organizing framework for future research focusing on different sponsorship contexts. However, the emergent categories still require further empirical testing. Therefore, we develop a set of questions to guide future research on the topic. Practical implications – Our typology outlines the different sponsorship contexts that should be considered by organizations that engage in sponsorship-linked marketing. Originality/value – This paper provides a multi-level categorization of sponsorship contexts that integrates both traditional categories and newly emerging categories to better inform future research on situational differences in sponsorship. Keywords: Sponsorship Context; Sponsorship Property; Sponsee; Cause Marketing; Sports Marketing
  • Item
    Gauge theory on noncommutative Riemannian principal bundles
    (Springer, 2021-10-11) Ćaćić, Branimir; Mesland, Bram
    We present a new, general approach to gauge theory on principal G-spectral triples, where G is a compact connected Lie group. We introduce a notion of vertical Riemannian geometry for G-C∗-algebras and prove that the resulting noncommutative orbitwise family of Kostant’s cubic Dirac operators defines a natural unbounded K K G-cycle in the case of a principal G-action. Then, we introduce a notion of principal G-spectral triple and prove, in particular, that any such spectral triple admits a canonical factorisation in unbounded K K G-theory with respect to such a cycle: up to a remainder, the total geometry is the twisting of the basic geometry by a noncommutative superconnection encoding the vertical geometry and underlying principal connection. Using these notions, we formulate an approach to gauge theory that explicitly generalises the classical case up to a groupoid cocycle and is compatible in general with this factorisation; in the unital case, it correctly yields a real affine space of noncommutative principal connections with affine gauge action. Our definitions cover all locally compact classical principal G-bundles and are compatible with θ-deformation; in particular, they cover the θ-deformed quaternionic Hopf fibration C∞(S7 θ ) ← C∞(S4 θ ) as a noncommutative principal SU(2)-bundle.
  • Item
    Problem Uncertainty, Institutional Insularity, and Modes of Learning in Canadian Provincial Hydraulic Fracturing Regulation
    (Wiley, 2020-09-28) Millar, Heather
    This study uses policy learning frameworks to explain variation in processes of hydraulic fracturing regulatory development in Canadian provinces. Using a cross-case comparison of British Columbia and Nova Scotia, the article demonstrates that differences in problem uncertainty and institutional insularity in each province determined modes of technical, social, and political learning in each province. In British Columbia elected officials framed LNG as a safe, clean energy source generating economic benefits. These frames made it difficult for anti-fracking advocates to increase the salience of environmental risks and scientific uncertainty. Low problem uncertainty and high institutional insularity fostered processes of technical learning within the BC Oil and Gas Commission focused on single-issue regulations. In Nova Scotia, an external review provided an ad hoc institutional venue through which environmental advocates, residents, and experts could increase the salience of scientific uncertainty and dread environmental risks. These conditions fostered collective processes of social learning among anti-fracking advocates and political learning among elected officials, resulting in a ban.
  • Item
    Surface Versus Untargeted Intramuscular EMG Based Classification of Simultaneous and Dynamically Changing Movements
    (Institute of Electrical and Electronics Engineers, 2013) Kamavuako, Ernest Nlandu; Rosenvang, Jakob Celander; Horup, Ronnie; Jensen, Winnie; Farina, Dario; Englehart, Kevin B.
    The pattern recognition-based myoelectric control scheme is in the process of being implemented in clinical settings, but it has been mainly tested on sequential and steady state data. This paper investigates the ability of pattern recognition to resolve movements that are simultaneous and dynamically changing and compares the use of surface and untargeted intramuscular EMG signals for this purpose. Ten able-bodied subjects participated in the study. Both EMG types were recorded concurrently from the right forearm. The subjects were instructed to track dynamic contraction profiles using single and combined degrees of freedom in three trials. During trials one and two, the amplitude and the frequency of the profile were kept constant (nonmodulated data), and during trial three, the two parameters were modulated (modulated data). The results showed that the performance was up to 93% for nonmodulated tasks, but highly depended on the nature of the data used. Surface and untargeted intramuscular EMG had equal performance for data of similar nature (nonmodulated), but the performance of intramuscular EMG decreased, compared to surface, when tested on modulated data. However, the results of intramuscular recordings obtained in this study are promising for future use of implantable electrodes, because, besides the value added in terms of potential chronic implantation, the performance is theoretically the same as for surface EMG provided that enough information is captured in the recordings. Nevertheless, care should be taken when training the system since data obtained from selective recordings probably need more training data to generalize to new signals.
  • Item
    Do Cost Functions for Tracking Error Generalize across Tasks with Different Noise Levels?
    (Public Library of Science, 2015) Sensinger, Jonathon; Aleman-Zapata, Adrian; Englehart, Kevin; Shu-Dong Zhang
    Control of human-machine interfaces are well modeled by computational control models, which take into account the behavioral decisions people make in estimating task dynamics and state for a given control law. This control law is optimized according to a cost function, which for the sake of mathematical tractability is typically represented as a series of quadratic terms. Recent studies have found that people actually use cost functions for reaching tasks that are slightly different than a quadratic function, but it is unclear which of several cost functions best explain human behavior and if these cost functions generalize across tasks of similar nature but different scale. In this study, we used an inverse-decision-theory technique to reconstruct the cost function from empirical data collected on 24 able-bodied subjects controlling a myoelectric interface. Compared with previous studies, this experimental paradigm involved a different control source (myoelectric control, which has inherently large multiplicative noise), a different control interface (control signal was mapped to cursor velocity), and a different task (the tracking position dynamically moved on the screen throughout each trial). Several cost functions, including a linear-quadratic; an inverted Gaussian, and a power function, accurately described the behavior of subjects throughout this experiment better than a quadratic cost function or other explored candidate cost functions (p<0.05). Importantly, despite the differences in the experimental paradigm and a substantially larger scale of error, we found only one candidate cost function whose parameter was consistent with the previous studies: a power function (cost ∝ errorα) with a parameter value of α = 1.69 (1.53–1.78 interquartile range). This result suggests that a power-function is a representative function of user’s error cost over a range of noise amplitudes for pointing and tracking tasks.
  • Item
    High-density force myography: A possible alternative for upper-limb prosthetic control
    (Rehabilitation Research and Development Service, 2016) Radmand, Ashkan; Scheme, Erik; Englehart, Kevin
    Several multiple degree-of-freedom upper-limb prostheses that have the promise of highly dexterous control have recently been developed. Inadequate controllability, however, has limited adoption of these devices. Introducing more robust control methods will likely result in higher acceptance rates. This work investigates the suitability of using high-density force myography (HD-FMG) for prosthetic control. HD-FMG uses a high-density array of pressure sensors to detect changes in the pressure patterns between the residual limb and socket caused by the contraction of the forearm muscles. In this work, HD-FMG outperforms the standard electromyography (EMG)-based system in detecting different wrist and hand gestures. With the arm in a fixed, static position, eight hand and wrist motions were classified with 0.33% error using the HD-FMG technique. Comparatively, classification errors in the range of 2.2%–11.3% have been reported in the literature for multichannel EMG-based approaches. As with EMG, position variation in HD-FMG can introduce classification error, but incorporating position variation into the training protocol reduces this effect. Channel reduction was also applied to the HD-FMG technique to decrease the dimensionality of the problem as well as the size of the sensorized area. We found that with informed, symmetric channel reduction, classification error could be decreased to 0.02%.
  • 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.