Journal Articles

Permanent URI for this collection

https://unbscholar.lib.unb.ca/handle/1882/12771

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

Now showing 1 - 20 of 33

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.
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.
A Multi-Variate Approach to Predicting Myoelectric Control Usability
(Institute of Electrical and Electronics Engineers, 2021) Nawfel, Jena L.; Englehart, Kevin B.; Scheme, Erik J.
Pattern recognition techniques leveraging the use of electromyography signals have become a popular approach to provide intuitive control of myoelectric devices. Performance of these control interfaces is commonly quantified using offline classification accuracy, despite studies having shown that this metric is a poor indicator of usability. Researchers have identified alternative offline metrics that better correlate with online performance; however, the relationship has yet to be fully defined in the literature. This has necessitated the continued trial-and-error-style online testing of algorithms developed using offline approaches. To bridge this information divide, we conducted an exploratory study where thirty-two different metrics from the offline training data were extracted. A correlation analysis and an ordinary least squares regression were implemented to investigate the relationship between the offline metrics and six aspects online use. The results indicate that the current offline standard, classification accuracy, is a poor indicator of usability and that other metrics may hold predictive power. The metrics identified in this work also may constitute more representative evaluation criteria when designing and reporting new control schemes. Furthermore, linear combinations of offline training metrics generate substantially more accurate predictions than using individual metrics. We found that the offline metric feature efficiency generated the best predictions for the usability metric throughput. A combination of two offline metrics (mean semi-principal axes and mean absolute value) significantly outperformed feature efficiency alone, with a 166% increase in the predicted R 2 value (i.e., VEcv). These findings suggest that combinations of metrics could provide a more robust framework for predicting usability.
A Multiday Evaluation of Real-Time Intramuscular EMG Usability with ANN
(MDPI, 2020) Waris, Asim; ur Rehman, Muhammad Zia; Niazi, Imran Khan; Jochumsen, Mads; Englehart, Kevin; Jensen, Winnie; Haavik, Heidi; Kamavuako, Ernest Nlandu
Recent developments in implantable technology, such as high-density recordings, wireless transmission of signals to a prosthetic hand, may pave the way for intramuscular electromyography (iEMG)-based myoelectric control in the future. This study aimed to investigate the real-time control performance of iEMG over time. A novel protocol was developed to quantify the robustness of the real-time performance parameters. Intramuscular wires were used to record EMG signals, which were kept inside the muscles for five consecutive days. Tests were performed on multiple days using Fitts’ law. Throughput, completion rate, path efficiency and overshoot were evaluated as performance metrics using three train/test strategies. Each train/test scheme was categorized on the basis of data quantity and the time difference between training and testing data. An artificial neural network (ANN) classifier was trained and tested on (i) data from the same day (WDT), (ii) data collected from the previous day and tested on present-day (BDT) and (iii) trained on all previous days including the present day and tested on present-day (CDT). It was found that the completion rate (91.6 ± 3.6%) of CDT was significantly better (p < 0.01) than BDT (74.02 ± 5.8%) and WDT (88.16 ± 3.6%). For BDT, on average, the first session of each day was significantly better (p < 0.01) than the second and third sessions for completion rate (77.9 ± 14.0%) and path efficiency (88.9 ± 16.9%). Subjects demonstrated the ability to achieve targets successfully with wire electrodes. Results also suggest that time variations in the iEMG signal can be catered by concatenating the data over several days. This scheme can be helpful in attaining stable and robust performance.
A proportional control scheme for high density force myography
(IOP Publishing, 2018-08) Belyea, Alexander T.; Englehart, Kevin B.; Scheme, Erik J.
Objective. Force myography (FMG) has been shown to be a potentially higher accuracy alternative to electromyography for pattern recognition based prosthetic control. Classification accuracy, however, is just one factor that affects the usability of a control system. Others, like the ability to start and stop, to coordinate dynamic movements, and to control the velocity of the device through some proportional control scheme can be of equal importance. To impart effective fine control using FMG-based pattern recognition, it is important that a method of controlling the velocity of each motion be developed. Methods. In this work force myography data were collected from 14 able bodied participants and one amputee participant as they performed a set of wrist and hand motions. The offline proportional control performance of a standard mean signal amplitude approach and a proposed regression-based alternative was compared. The impact of providing feedback during training, as well as the use of constrained or unconstrained hand and wrist contractions, were also evaluated. Results. It is shown that the commonly used mean of rectified channel amplitudes approach commonly employed with electromyography does not translate to force myography. The proposed class-based regression proportional control approach is shown significantly outperform this standard approach (ρ < 0.001), yielding a R2 correlation coefficients of 0.837 and 0.830 for constrained and unconstrained forearm contractions, respectively for able bodied participants. No significant difference (ρ = 0.693) was found in R2 performance when feedback was provided during training or not. The amputee subject achieved a classification accuracy of 83.4% ± 3.47% demonstrating the ability to distinguish contractions well with FMG. In proportional control the amputee participant achieved an R2 of of 0.375 for regression based proportional control during unconstrained contractions. This is lower than the unconstrained case for able-bodied subjects for this particular amputee, possibly due to difficultly in visualizing contraction level modulation without feedback. This may be remedied in the use of a prosthetic limb that would provide real-time feedback in the form of device speed. Conclusion. A novel class-specific regression-based approach is proposed for multi-class control is described and shown to provide an effective means of providing FMG-based proportional control.
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.
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.
An analytical method reduces noise bias in motor adaptation analysis
(Nature Research, 2021) Blustein, Daniel H.; Shehata, Ahmed W.; Kuylenstierna, Erin S.; Englehart, Kevin B.; Sensinger, Jonathon W.
When a person makes a movement, a motor error is typically observed that then drives motor planning corrections on subsequent movements. This error correction, quantified as a trial-by-trial adaptation rate, provides insight into how the nervous system is operating, particularly regarding how much confidence a person places in different sources of information such as sensory feedback or motor command reproducibility. Traditional analysis has required carefully controlled laboratory conditions such as the application of perturbations or error clamping, limiting the usefulness of motor analysis in clinical and everyday environments. Here we focus on error adaptation during unperturbed and naturalistic movements. With increasing motor noise, we show that the conventional estimation of trial-by-trial adaptation increases, a counterintuitive finding that is the consequence of systematic bias in the estimate due to noise masking the learner’s intention. We present an analytic solution relying on stochastic signal processing to reduce this effect of noise, producing an estimate of motor adaptation with reduced bias. The result is an improved estimate of trial-by-trial adaptation in a human learner compared to conventional methods. We demonstrate the effectiveness of the new method in analyzing simulated and empirical movement data under different noise conditions.
An Extra Low-mass Harmonic Radar Transponder for Insect Tracking Applications
(IEEE, 2023-06-05) Ala, Ramin; Rouse, Chris D.; Colpitts, Bruce G.
The design, construction, and performance of a harmonic radar transponder with a total mass of less than 500 μg is presented. The transponder is intended for insect tracking applications and consists of very fine wire and a small Schottky diode. It is designed for fundamental and harmonic frequencies of 10 GHz and 20 GHz, respectively. Compared to existing harmonic radar transponders, this transponder is easy to construct because the loop inductor can be implemented with a simple bend in the dipole conductor without degrading performance. Through careful design optimization, the conversion loss of the transponder is not impacted by the measures taken to minimize its mass. The expected harmonic power versus the transmitted power is estimated based on the link analysis between the transmitter and receiver of the radar, with the link analysis itself being performed via calculation, harmonic balance simulation, and full-wave simulation. The link analysis simulation predicted a received power of -66.4 dBm for a transmitted power of +22 dBm and a range of 2.4 m. The measured received power level at the harmonic frequency, obtained from the broadside of the transponder in an anechoic test chamber, is approximately -70 dBm, which agrees well with the link analysis. Simulated and measured transponder radiation patterns are also compared and show good agreement. Low-mass transponders such as this enable tracking of smaller insects without reducing their lifespan or compromising their ability to fly at natural altitudes and ranges.
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.
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.
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
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.
Conservative analytical assessments of localized RF exposure from small magnetic field sources
(Institute of Electrical and Electronics Engineers (IEEE), 2024-04-18) Rouse, Chris D.
A conservative analytical framework for assessing radiofrequency (RF) exposure from small magnetic field sources near the body is presented, with an emphasis on the 3kHz to 10MHz frequency range. Worst-case exposure models are proposed and analyzed for both homogeneous and heterogeneous tissue based on source dimensions, drive current, and separation distance. Electromagnetic analysis of induced field enhancements due to tissue heterogeneity is presented. Maximum drive currents for compliance with the basic restrictions are obtained for both tissue models. In the heterogeneous case, field enhancement in thin regions of low conductivity leads to significantly lower allow- able drive levels for nerve stimulation (NS) compliance. Guidance is provided regarding how to account for such enhancements for various internal E-field calculation methods. The impact of these field enhancements on 10-g specific absorption rate (SAR) is found to be small, i.e., the homogeneous tissue assumption appears to be sufficiently conservative. A small enhancement factor may be appropriate for 1-g SAR. The benefit of assessing against the basic restrictions instead of the reference levels is also explored. This work can be leveraged by regulatory and standardization bodies to develop exemption levels for small magnetic field sources, e.g., inductive chargers, to significantly reduce compliance burdens.
Conventional analysis of trial-by-trial adaptation is biased: Empirical and theoretical support using a Bayesian estimator
(Public Library of Science, 2018-12) Blustein, Daniel; Shehata, Ahmed; Englehart, Kevin; Sensinger, Jonathon; Maurice A. Smith
Research on human motor adaptation has often focused on how people adapt to self-generated or externally-influenced errors. Trial-by-trial adaptation is a person’s response to self-generated errors. Externally-influenced errors applied as catch-trial perturbations are used to calculate a person’s perturbation adaptation rate. Although these adaptation rates are sometimes compared to one another, we show through simulation and empirical data that the two metrics are distinct. We demonstrate that the trial-by-trial adaptation rate, often calculated as a coefficient in a linear regression, is biased under typical conditions. We tested 12 able-bodied subjects moving a cursor on a screen using a computer mouse. Statistically different adaptation rates arise when sub-sets of trials from different phases of learning are analyzed from within a sequence of movement results. We propose a new approach to identify when a person’s learning has stabilized in order to identify steady-state movement trials from which to calculate a more reliable trial-by-trial adaptation rate. Using a Bayesian model of human movement, we show that this analysis approach is more consistent and provides a more confident estimate than alternative approaches. Constraining analyses to steady-state conditions will allow researchers to better decouple the multiple concurrent learning processes that occur while a person makes goal-directed movements. Streamlining this analysis may help broaden the impact of motor adaptation studies, perhaps even enhancing their clinical usefulness.
Determination of optimum threshold values for EMG time domain features; a multi-dataset investigation
(IOP Publishing, 2016) Kamavuako, Ernest Nlandu; Scheme, Erik Justin; Englehart, Kevin Brian
Objective. For over two decades, Hudgins' set of time domain features have extensively been applied for classification of hand motions. The calculation of slope sign change and zero crossing features uses a threshold to attenuate the effect of background noise. However, there is no consensus on the optimum threshold value. In this study, we investigate for the first time the effect of threshold selection on the feature space and classification accuracy using multiple datasets. Approach. In the first part, four datasets were used, and classification error (CE), separability index, scatter matrix separability criterion, and cardinality of the features were used as performance measures. In the second part, data from eight classes were collected during two separate days with two days in between from eight able-bodied subjects. The threshold for each feature was computed as a factor (R = 0:0.01:4) times the average root mean square of data during rest. For each day, we quantified CE for R = 0 (CEr0) and minimum error (CEbest). Moreover, a cross day threshold validation was applied where, for example, CE of day two (CEodt) is computed based on optimum threshold from day one and vice versa. Finally, we quantified the effect of the threshold when using training data from one day and test data of the other. Main results. All performance metrics generally degraded with increasing threshold values. On average, CEbest (5.26 ± 2.42%) was significantly better than CEr0 (7.51 ± 2.41%, P = 0.018), and CEodt (7.50 ± 2.50%, P = 0.021). During the two-fold validation between days, CEbest performed similar to CEr0. Interestingly, when using the threshold values optimized per subject from day one and day two respectively, on the cross-days classification, the performance decreased. Significance. We have demonstrated that threshold value has a strong impact on the feature space and that an optimum threshold can be quantified. However, this optimum threshold is highly data and subject driven and thus do not generalize well. There is a strong evidence that R = 0 provides a good trade-off between system performance and generalization. These findings are important for practical use of pattern recognition based myoelectric control.
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.
Effects of Confidence-Based Rejection on Usability and Error in Pattern Recognition-Based Myoelectric Control
(Institute of Electrical and Electronics Engineers, 2019) Robertson, Jason W.; Englehart, Kevin B.; Scheme, Erik J.
Rejection of movements based on the confidence in the classification decision has previously been demonstrated to improve the usability of pattern recognition based myoelectric control. To this point, however, the optimal rejection threshold has been determined heuristically, and it is not known how different thresholds affect the tradeoff between error mitigation and false rejections in real-time closed-loop control. To answer this question, 24 able-bodied subjects completed a real-time Fitts' law-style virtual cursor control task using a support vector machine classifier. It was found that rejection improved information throughput at all thresholds, with the best performance coming at thresholds between 0.60 and 0.75. Two fundamental types of error were defined and identified: operator error (identifiable, repeatable behaviors, directly attributable to the user), and systemic error (other errors attributable to misclassification or noise). The incidence of both operator and systemic errors were found to decrease as rejection threshold increased. Moreover, while the incidence of all error types correlated strongly with path efficiency, only systemic errors correlated strongly with throughput and trial completion rate. Interestingly, more experienced users were found to commit as many errors as novice users, despite performing better in the Fitts' task, suggesting that there is more to usability than error prevention alone. Nevertheless, these results demonstrate the usability gains possible with rejection across a range of thresholds for both novice and experienced users alike.
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.
FMG Versus EMG: A Comparison of Usability for Real-Time Pattern Recognition Based Control
(Institute of Electrical and Electronics Engineers, 2019) Belyea, Alex; Englehart, Kevin; Scheme, Erik
Objective: Force myography (FMG), which measures the surface pressure profile exerted by contracting muscles, has been proposed as an alternative to electromyography (EMG) for human-machine interfaces. Although FMG pattern recognition-based control systems have yielded higher offline classification accuracy, comparatively few works have examined the usability of FMG for real-time control. In this work, we conduct a comprehensive comparison of EMG- and FMG-based schemes using both classification and regression controllers. Methods: A total of 20 participants performed a two-degree-of-freedom Fitts' Law-style virtual target acquisition task using both FMG- and EMG-based classification and regression control schemes. Performance was evaluated based on the standard Fitts' law testing metrics throughput, path efficiency, average speed, number of timeouts, overshoot, stopping distance, and simultaneity. Results: The FMG-based classification system significantly outperformed the EMG-based classification system in both throughput (0.902 ± 0.270) versus (0.751 ± 0.309), (ρ <; 0.001) and path efficiency (87.2 ± 8.7) versus (83.2 ± 7.8), (ρ <; 0.001). Similarly, FMG-based regression significantly outperformed EMG-based regression in throughput (0.871 ± 0.2) versus (0.69 ± 0.3), (ρ <; 0.001) and path efficiency (64.8 ± 5.3) versus (58.8 ± 7.1), (ρ <; 0.001). Conclusions: The FMG-based schemes outperformed the EMG-based schemes regardless of which controller was used. This provides further evidence for FMG as a viable alternative to EMG for human-machine interfaces. Significance: This work describes a comprehensive evaluation of the online usability of FMG- and EMG-based control using both sequential classification and simultaneous regression control.

Browse

Browsing Journal Articles by Subject "Electrical and Computer Engineering"

Results Per Page

Sort Options