Fractal analysis of stride interval time series is a useful tool in human gait research which cou... more Fractal analysis of stride interval time series is a useful tool in human gait research which could be used as a marker for gait adaptability, gait disorder, and fall risk among patients with movement disorders. This study is designed to systematically and comprehensively investigate two practical aspects of fractal analysis which significantly affect the outcome: the series length and the parameters used in the algorithm. The Hurst exponent, scaling exponent, and/or fractal dimension are computed from both simulated and experimental data using three fractal methods, namely detrended fluctuation analysis, box-counting dimension, and Higuchi's fractal dimension. The advantages and drawbacks of each method are discussed, in terms of biases and variability. The results demonstrate that a careful selection of fractal analysis methods and their parameters is required, which is dependent on the aim of study (either analyzing differences between experimental groups or estimating an accurate determination of fractal features). A set of guidelines for the selection of the fractal methods and the length of stride interval time series is provided, along with the optimal parameters for a robust implementation for each method.
The success of biological signal pattern recognition depends crucially on the selection of releva... more The success of biological signal pattern recognition depends crucially on the selection of relevant features. Across signal and imaging modalities, a large number of features have been proposed, leading to feature redundancy and the need for optimal feature set identification. A further complication is that, due to the inherent biological variability, even the same classification problem on different datasets can display variations in the respective optimal sets, casting doubts on the generalizability of relevant features. Here, we approach this problem by leveraging topological tools to create charts of features spaces. These charts highlight feature sub-groups that encode similar information (and their respective similarities) allowing for a principled and interpretable choice of features for classification and analysis. Using multiple electromyographic (EMG) datasets as a case study, we use this feature chart to identify functional groups among 58 state-of-the-art EMG features, and to show that they generalize across three different forearm EMG datasets obtained from able-bodied subjects during hand and finger contractions. We find that these groups describe meaningful non-redundant information, succinctly recapitulating information about different regions of feature space. We then recommend representative features from each group based on maximum class separability, robustness and minimum complexity.
Recent investigations into the use of real-time, pattern recognition based myoelectric control sy... more Recent investigations into the use of real-time, pattern recognition based myoelectric control systems have shown excellent results in terms of classification accuracy and limb controllability under clinical supervision. Longer term, continuous use appears to be subject to deterioration in classification accuracy and usability due to factors including electrode displacement, electrode/skin interface impedance, and user variability. In this work, a simple filtering strategy for improved robustness to external noise is introduced. Recorded signals are digitally filtered to remove noise vulnerable frequencies while retaining discriminatory myoelectric information for classification.
In many pattern recognition applications, confidence scores are used to extract more information ... more In many pattern recognition applications, confidence scores are used to extract more information than discrete class membership alone, yet they have not traditionally been leveraged in myoelectric control. In this work, the confidence scores of eight common classification schemes were examined. Their role in rejecting inadvertent motions is investigated, and the tradeoffs observed in the design of rejection capable control schemes are demonstrated. It is shown that the distribution of confidences can varying greatly between classifiers, even when classification performance is similar. As a specific example, an ensemble of support vector machines in a one against one configuration (SVM1vs1) outperforms the previously reported LDAR myoelectric pattern recognition rejection scheme in terms of accuracy-rejection curves (ARC) and false acceptance/rejection (FAR) curves.
If citing, it is advised that you check and use the publisher's definitive version for pagination... more If citing, it is advised that you check and use the publisher's definitive version for pagination, volume/issue, and date of publication details. And where the final published version is provided on the Research Portal, if citing you are again advised to check the publisher's website for any subsequent corrections.
With recent advancements in wearable sensors, wireless communication and embedded computing techn... more With recent advancements in wearable sensors, wireless communication and embedded computing technologies, wearable EMG armbands are now commercially available and accessible to most laboratories. Due to the embedded system constraints, however, these armbands typically sample EMG signals at a lower frequency (e.g. 200 Hz for the Myo armband) than professional versions. It remains unclear whether existing EMG feature extraction methods, which have largely been developed based on EMG signals sampled at the Nyquist rate (generally 1000 Hz) or above, are still effective for use with these emerging lower-frequency systems. In this study, we investigate the effects of sampling rate (low: 200 Hz vs. high: 1000 Hz) on performance in classifying eight classes of hand motion in 20 able-bodied subjects for eleven commonly used time-domain features. The effect of within- and between-day variation on the performance of EMG features was also investigated. The results show that classification accuracies drop significantly with the lower sampling rate for all of the evaluated features, when using either a support vector machine or a linear discriminant analysis classifier. Furthermore, the within-class variability increased significantly with reduced sampling rate, although the level of inter-session repeatability was not affected. In comparing the performance of single features, waveform length outperformed the others for both high- and low-sampling rates. The optimal feature sets found using sequential forward selection for the two sampling rates, however, were found to be different. These results suggest that feature selection results for myoelectric control, previously determined using EMG data sampled at 1000 Hz, may not directly apply to this new generation of low-sampling rate wearable EMG sensors.
IEEE Transactions on Neural Systems and Rehabilitation Engineering, Feb 1, 2020
An important barrier to commercialization of pattern recognition myoelectric control of prosthese... more 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.
bioRxiv (Cold Spring Harbor Laboratory), Feb 6, 2018
Myoelectric prosthetic devices are commonly used to help upper limb amputees perform activities o... more Myoelectric prosthetic devices are commonly used to help upper limb amputees perform activities of daily living, however amputees still lack the sensory feedback required to facilitate reliable and precise control. Augmented feedback may play an important role in affecting both short-term performance, through real-time regulation, and long-term performance, through the development of stronger internal models. In this work, we investigate the potential tradeoff between controllers that enable better short-term performance and those that provide sufficient feedback to develop a strong internal model. We hypothesize that augmented feedback may be used to mitigate this tradeoff, ultimately improving both short and long-term control. We used psychometric measures to assess the internal model developed while using a filtered myoelectric controller with augmented audio feedback, imitating classification-based control but with augmented regression-based feedback. In addition, we evaluated the short-term performance using a multi degree-of-freedom constrained-time target acquisition task. Results obtained from 24 able-bodied subjects show that an augmented feedback control strategy using audio cues enables the development of a stronger internal model than the filtered control with filtered feedback, and significantly better path efficiency than both raw and filtered control strategies. These results suggest that the use of augmented feedback control strategies may improve both short-term and long-term performance. Recent advances in material design, micromachining, and the understanding of human neuromuscular systems have enabled the development of lightweight prosthetic devices that can be used to help amputees perform activities of daily living. One approach to controlling these devices is to use myoelectric signals sensed from contractions of the amputee's remnant or congenitally different muscles 1. Researchers have developed many signal processing techniques 2 , feature extraction methods 3-5 , and control strategies 6 to enhance the performance of this approach. Despite these advancements in the field of myoelectric prostheses, many amputees still abandon their devices out of frustration 7 , due in part to insufficient precision in the control of prosthesis movements and a lack of adequate sensory feedback 8,9. Although invasive feedback, such as stimulation of sensory peripheral nerves 10 , has the potential to elicit close-to-natural tactile sensations, many prosthesis users prefer non-invasive feedback methods that do not require surgical intervention 11. With this preference in mind, researchers have proposed using non-invasive sensory substitution methods to provide sensory information to prostheses users either through different sensory channels or using different modalities 12. Vibro-tactile 13 , mechano-tactile 14 , electrotactile 15-17 , skin stretch 18 , and auditory 19 are just some of the techniques that have been developed and used to provide prosthesis users with feedback. Although some studies (e.g. 14,20,21) have shown that sensory feedback improves performance, others (c.f. 14) have concluded that sensory feedback had no effect on performance. This lack of consensus arises, at least in part, because of an unclear understanding of how the incorporation of feedback relates to performance. The role of feedback for real-time regulation and in improving human understanding of the control system and the task being performed is still unclear. Researchers have hypothesized that the human central nervous system implements control by estimating the current state of the musculoskeletal system and updating this estimate
This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Background and Objective: Non-invasive multichannel Electroencephalography (EEG) recordings provi... more 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.
Myoelectric control has been used predominantly in the field of prosthetics, but is an increasing... more Myoelectric control has been used predominantly in the field of prosthetics, but is an increasingly promising hands-free input modality for emerging consumer markets such as mixed reality. Developing robust machine learning-enabled EMG control systems, however, has historically required substantial domain expertise. This has presented a significant barrier to entry for researchers, impeded progress in EMG-based interaction design, and contributed to the perception that such systems lack the robustness and intuitiveness required for real-world use. To overcome these challenges, we present LibEMG, an open-source Python library for performing offline EMG analyses and developing online EMG-based interactions. By abstracting the challenges and nuances surrounding myoelectric control, including hardware interfacing, data acquisition, feature extraction/selection, classification, post-processing, and evaluation, we eliminate many of the significant barriers limiting the exploration of this technology. Combining expertise from the prosthetics and human-computer interaction communities into a shared library, extensive examples, and documentation, we provide researchers with an accessible tool to accelerate research and improve reproducibility in myoelectric control. In doing so, we aim to facilitate the exploration of this technology, particularly outside prosthesis control, to unlock its potential as a widely applicable hands-free input modality.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
The increasing stress on the global healthcare system driven by the rise of chronic disease and a... more The increasing stress on the global healthcare system driven by the rise of chronic disease and an aging population is necessitating an emphasis on proactive health monitoring and self-management. Potential exists in the wave of emerging wearable devices and the internet of things (IoT) to support a movement towards the decentralization of healthcare. In particular, mobility impairments caused by injury or chronic disease are a major source of concern in the aging population. Individuals with mobility impairments often rely on assistive devices, such as canes or walkers to increase safety and stability. Given the prevalence of assistive devices among these users, instrumenting and connecting assistive technologies could be an effective means of unobtrusive activity monitoring. In this work we present an affordable hybrid sensorized cane, capable of measuring loading, mobility and stability information. The proposed system, which is nearly indistinguishable from a traditional cane, collects these data and then wirelessly transmits them to a mobile device for cloud storage and analysis. A multi-sensor fusion algorithm was used to segment valid gait cycles and identify various temporal gait events. Based on preliminary results, it is believed that the proposed system will be able to identify a variety of gait perturbations, potentially offering future applications in early diagnosis and the management of chronic conditions.
Information extracted from signals recorded from multi-channel surface myoelectric signal (MES) r... more Information extracted from signals recorded from multi-channel surface myoelectric signal (MES) recording sites can be used as inputs to control systems for powered prostheses. For small, closely spaced muscles, such as the muscles in the forearm, the detected MES often contains contributions from more than one muscle; the contribution from each specific muscle being modified by a tissue filter between the muscle and the detection points. In this work, the measured raw MES signals are rotated by class specific rotation matrices to spatially decorrelate the measured data prior to feature extraction. This tunes the pattern recognition classifier to better discriminate the test motions. Using this preprocessing step, MES analysis windows may be cut from 256 ms to 128 ms without affecting the classification accuracy.
Signatures have long been considered to be one of the most accepted and practical means of user v... more Signatures have long been considered to be one of the most accepted and practical means of user verification, despite being vulnerable to skilled forgers. In contrast, EEG signals have more recently been shown to be more difficult to replicate, and to provide better biometric information in response to known a
IEEE Transactions on Biomedical Engineering, Feb 1, 2014
The evolution of deep learning techniques has been transformative as they have allowed complex ma... more 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.
Early diagnosis of lung cancer greatly improves the likelihood of survival and remission, but lim... more Early diagnosis of lung cancer greatly improves the likelihood of survival and remission, but limitations in existing technologies like low-dose computed tomography have prevented the implementation of widespread screening programs. Breath-based solutions that seek disease biomarkers in exhaled volatile organic compound (VOC) profiles show promise as affordable, accessible and non-invasive alternatives to traditional imaging. In this pilot work, we present a lung cancer detection framework using cavity ring-down spectroscopy (CRDS), an effective and practical laser absorption spectroscopy technique that has the ability to advance breath screening into clinical reality. The main aims of this work were to (1) test the utility of infrared CRDS breath profiles for discriminating non-small cell lung cancer (NSCLC) patients from controls, (2) compare models with VOCs as predictors to those with patterns from the CRDS spectra (breathprints) as predictors, and (3) present a robust approach for identifying relevant disease biomarkers. First, based on a proposed learning curve technique that estimated the limits of a model’s performance at multiple sample sizes (10–158), the CRDS-based models developed in this work were found to achieve classification performance comparable or superior to like mass spectroscopy and sensor-based systems. Second, using 158 collected samples (62 NSCLC subjects and 96 controls), the accuracy range for the VOC-based model was 65.19%–85.44% (51.61%–66.13% sensitivity and 73.96%–97.92% specificity), depending on the employed cross-validation technique. The model based on breathprint predictors generally performed better, with accuracy ranging from 71.52%–86.08% (58.06%–82.26% sensitivity and 80.21%–88.54% specificity). Lastly, using a protocol based on consensus feature selection, three VOCs (isopropanol, dimethyl sulfide, and butyric acid) and two breathprint features (from a local binary pattern transformation of the spectra) were identified as possible NSCLC biomarkers. This research demonstrates the potential of infrared CRDS breath profiles and the developed early-stage classification techniques for lung cancer biomarker detection and screening.
IEEE Journal of Biomedical and Health Informatics, 2022
Efficient storage and transmission of electromyogram (EMG) data are important for emerging applic... more 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 CAEs compressed data from 24 bits to 6 bits, an additional 4-fold compression was achieved without significant degradation of the reconstruction performance. Furthermore, the CAEs 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.
Increases in the rates of chronic disease and an aging population have created a demand for new f... more Increases in the rates of chronic disease and an aging population have created a demand for new forms of preventative care and proactive health monitoring technologies. While senior populations may be hesitant to adopt wearable technologies, the ability to retrofit assistive devices already in use by the individuals may provide a major stepping stone for increased adoption rates and monitoring abilities. Design of such systems often exhibit challenges with respect to sensor selection, placement, and consequently, reliability and usability of the system in real-world environments. As part of a growing line of smart assistive devices, this work presents a proposed design for a multi-sensor walker with pilot data collected and tested in a real-world environment, including outdoors. Preliminary analysis of results demonstrates the ability to determine levels of activity and environments, important factors related to health and wellness and risk of falls.
Fractal analysis of stride interval time series is a useful tool in human gait research which cou... more Fractal analysis of stride interval time series is a useful tool in human gait research which could be used as a marker for gait adaptability, gait disorder, and fall risk among patients with movement disorders. This study is designed to systematically and comprehensively investigate two practical aspects of fractal analysis which significantly affect the outcome: the series length and the parameters used in the algorithm. The Hurst exponent, scaling exponent, and/or fractal dimension are computed from both simulated and experimental data using three fractal methods, namely detrended fluctuation analysis, box-counting dimension, and Higuchi's fractal dimension. The advantages and drawbacks of each method are discussed, in terms of biases and variability. The results demonstrate that a careful selection of fractal analysis methods and their parameters is required, which is dependent on the aim of study (either analyzing differences between experimental groups or estimating an accurate determination of fractal features). A set of guidelines for the selection of the fractal methods and the length of stride interval time series is provided, along with the optimal parameters for a robust implementation for each method.
The success of biological signal pattern recognition depends crucially on the selection of releva... more The success of biological signal pattern recognition depends crucially on the selection of relevant features. Across signal and imaging modalities, a large number of features have been proposed, leading to feature redundancy and the need for optimal feature set identification. A further complication is that, due to the inherent biological variability, even the same classification problem on different datasets can display variations in the respective optimal sets, casting doubts on the generalizability of relevant features. Here, we approach this problem by leveraging topological tools to create charts of features spaces. These charts highlight feature sub-groups that encode similar information (and their respective similarities) allowing for a principled and interpretable choice of features for classification and analysis. Using multiple electromyographic (EMG) datasets as a case study, we use this feature chart to identify functional groups among 58 state-of-the-art EMG features, and to show that they generalize across three different forearm EMG datasets obtained from able-bodied subjects during hand and finger contractions. We find that these groups describe meaningful non-redundant information, succinctly recapitulating information about different regions of feature space. We then recommend representative features from each group based on maximum class separability, robustness and minimum complexity.
Recent investigations into the use of real-time, pattern recognition based myoelectric control sy... more Recent investigations into the use of real-time, pattern recognition based myoelectric control systems have shown excellent results in terms of classification accuracy and limb controllability under clinical supervision. Longer term, continuous use appears to be subject to deterioration in classification accuracy and usability due to factors including electrode displacement, electrode/skin interface impedance, and user variability. In this work, a simple filtering strategy for improved robustness to external noise is introduced. Recorded signals are digitally filtered to remove noise vulnerable frequencies while retaining discriminatory myoelectric information for classification.
In many pattern recognition applications, confidence scores are used to extract more information ... more In many pattern recognition applications, confidence scores are used to extract more information than discrete class membership alone, yet they have not traditionally been leveraged in myoelectric control. In this work, the confidence scores of eight common classification schemes were examined. Their role in rejecting inadvertent motions is investigated, and the tradeoffs observed in the design of rejection capable control schemes are demonstrated. It is shown that the distribution of confidences can varying greatly between classifiers, even when classification performance is similar. As a specific example, an ensemble of support vector machines in a one against one configuration (SVM1vs1) outperforms the previously reported LDAR myoelectric pattern recognition rejection scheme in terms of accuracy-rejection curves (ARC) and false acceptance/rejection (FAR) curves.
If citing, it is advised that you check and use the publisher's definitive version for pagination... more If citing, it is advised that you check and use the publisher's definitive version for pagination, volume/issue, and date of publication details. And where the final published version is provided on the Research Portal, if citing you are again advised to check the publisher's website for any subsequent corrections.
With recent advancements in wearable sensors, wireless communication and embedded computing techn... more With recent advancements in wearable sensors, wireless communication and embedded computing technologies, wearable EMG armbands are now commercially available and accessible to most laboratories. Due to the embedded system constraints, however, these armbands typically sample EMG signals at a lower frequency (e.g. 200 Hz for the Myo armband) than professional versions. It remains unclear whether existing EMG feature extraction methods, which have largely been developed based on EMG signals sampled at the Nyquist rate (generally 1000 Hz) or above, are still effective for use with these emerging lower-frequency systems. In this study, we investigate the effects of sampling rate (low: 200 Hz vs. high: 1000 Hz) on performance in classifying eight classes of hand motion in 20 able-bodied subjects for eleven commonly used time-domain features. The effect of within- and between-day variation on the performance of EMG features was also investigated. The results show that classification accuracies drop significantly with the lower sampling rate for all of the evaluated features, when using either a support vector machine or a linear discriminant analysis classifier. Furthermore, the within-class variability increased significantly with reduced sampling rate, although the level of inter-session repeatability was not affected. In comparing the performance of single features, waveform length outperformed the others for both high- and low-sampling rates. The optimal feature sets found using sequential forward selection for the two sampling rates, however, were found to be different. These results suggest that feature selection results for myoelectric control, previously determined using EMG data sampled at 1000 Hz, may not directly apply to this new generation of low-sampling rate wearable EMG sensors.
IEEE Transactions on Neural Systems and Rehabilitation Engineering, Feb 1, 2020
An important barrier to commercialization of pattern recognition myoelectric control of prosthese... more 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.
bioRxiv (Cold Spring Harbor Laboratory), Feb 6, 2018
Myoelectric prosthetic devices are commonly used to help upper limb amputees perform activities o... more Myoelectric prosthetic devices are commonly used to help upper limb amputees perform activities of daily living, however amputees still lack the sensory feedback required to facilitate reliable and precise control. Augmented feedback may play an important role in affecting both short-term performance, through real-time regulation, and long-term performance, through the development of stronger internal models. In this work, we investigate the potential tradeoff between controllers that enable better short-term performance and those that provide sufficient feedback to develop a strong internal model. We hypothesize that augmented feedback may be used to mitigate this tradeoff, ultimately improving both short and long-term control. We used psychometric measures to assess the internal model developed while using a filtered myoelectric controller with augmented audio feedback, imitating classification-based control but with augmented regression-based feedback. In addition, we evaluated the short-term performance using a multi degree-of-freedom constrained-time target acquisition task. Results obtained from 24 able-bodied subjects show that an augmented feedback control strategy using audio cues enables the development of a stronger internal model than the filtered control with filtered feedback, and significantly better path efficiency than both raw and filtered control strategies. These results suggest that the use of augmented feedback control strategies may improve both short-term and long-term performance. Recent advances in material design, micromachining, and the understanding of human neuromuscular systems have enabled the development of lightweight prosthetic devices that can be used to help amputees perform activities of daily living. One approach to controlling these devices is to use myoelectric signals sensed from contractions of the amputee's remnant or congenitally different muscles 1. Researchers have developed many signal processing techniques 2 , feature extraction methods 3-5 , and control strategies 6 to enhance the performance of this approach. Despite these advancements in the field of myoelectric prostheses, many amputees still abandon their devices out of frustration 7 , due in part to insufficient precision in the control of prosthesis movements and a lack of adequate sensory feedback 8,9. Although invasive feedback, such as stimulation of sensory peripheral nerves 10 , has the potential to elicit close-to-natural tactile sensations, many prosthesis users prefer non-invasive feedback methods that do not require surgical intervention 11. With this preference in mind, researchers have proposed using non-invasive sensory substitution methods to provide sensory information to prostheses users either through different sensory channels or using different modalities 12. Vibro-tactile 13 , mechano-tactile 14 , electrotactile 15-17 , skin stretch 18 , and auditory 19 are just some of the techniques that have been developed and used to provide prosthesis users with feedback. Although some studies (e.g. 14,20,21) have shown that sensory feedback improves performance, others (c.f. 14) have concluded that sensory feedback had no effect on performance. This lack of consensus arises, at least in part, because of an unclear understanding of how the incorporation of feedback relates to performance. The role of feedback for real-time regulation and in improving human understanding of the control system and the task being performed is still unclear. Researchers have hypothesized that the human central nervous system implements control by estimating the current state of the musculoskeletal system and updating this estimate
This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Background and Objective: Non-invasive multichannel Electroencephalography (EEG) recordings provi... more 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.
Myoelectric control has been used predominantly in the field of prosthetics, but is an increasing... more Myoelectric control has been used predominantly in the field of prosthetics, but is an increasingly promising hands-free input modality for emerging consumer markets such as mixed reality. Developing robust machine learning-enabled EMG control systems, however, has historically required substantial domain expertise. This has presented a significant barrier to entry for researchers, impeded progress in EMG-based interaction design, and contributed to the perception that such systems lack the robustness and intuitiveness required for real-world use. To overcome these challenges, we present LibEMG, an open-source Python library for performing offline EMG analyses and developing online EMG-based interactions. By abstracting the challenges and nuances surrounding myoelectric control, including hardware interfacing, data acquisition, feature extraction/selection, classification, post-processing, and evaluation, we eliminate many of the significant barriers limiting the exploration of this technology. Combining expertise from the prosthetics and human-computer interaction communities into a shared library, extensive examples, and documentation, we provide researchers with an accessible tool to accelerate research and improve reproducibility in myoelectric control. In doing so, we aim to facilitate the exploration of this technology, particularly outside prosthesis control, to unlock its potential as a widely applicable hands-free input modality.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
The increasing stress on the global healthcare system driven by the rise of chronic disease and a... more The increasing stress on the global healthcare system driven by the rise of chronic disease and an aging population is necessitating an emphasis on proactive health monitoring and self-management. Potential exists in the wave of emerging wearable devices and the internet of things (IoT) to support a movement towards the decentralization of healthcare. In particular, mobility impairments caused by injury or chronic disease are a major source of concern in the aging population. Individuals with mobility impairments often rely on assistive devices, such as canes or walkers to increase safety and stability. Given the prevalence of assistive devices among these users, instrumenting and connecting assistive technologies could be an effective means of unobtrusive activity monitoring. In this work we present an affordable hybrid sensorized cane, capable of measuring loading, mobility and stability information. The proposed system, which is nearly indistinguishable from a traditional cane, collects these data and then wirelessly transmits them to a mobile device for cloud storage and analysis. A multi-sensor fusion algorithm was used to segment valid gait cycles and identify various temporal gait events. Based on preliminary results, it is believed that the proposed system will be able to identify a variety of gait perturbations, potentially offering future applications in early diagnosis and the management of chronic conditions.
Information extracted from signals recorded from multi-channel surface myoelectric signal (MES) r... more Information extracted from signals recorded from multi-channel surface myoelectric signal (MES) recording sites can be used as inputs to control systems for powered prostheses. For small, closely spaced muscles, such as the muscles in the forearm, the detected MES often contains contributions from more than one muscle; the contribution from each specific muscle being modified by a tissue filter between the muscle and the detection points. In this work, the measured raw MES signals are rotated by class specific rotation matrices to spatially decorrelate the measured data prior to feature extraction. This tunes the pattern recognition classifier to better discriminate the test motions. Using this preprocessing step, MES analysis windows may be cut from 256 ms to 128 ms without affecting the classification accuracy.
Signatures have long been considered to be one of the most accepted and practical means of user v... more Signatures have long been considered to be one of the most accepted and practical means of user verification, despite being vulnerable to skilled forgers. In contrast, EEG signals have more recently been shown to be more difficult to replicate, and to provide better biometric information in response to known a
IEEE Transactions on Biomedical Engineering, Feb 1, 2014
The evolution of deep learning techniques has been transformative as they have allowed complex ma... more 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.
Early diagnosis of lung cancer greatly improves the likelihood of survival and remission, but lim... more Early diagnosis of lung cancer greatly improves the likelihood of survival and remission, but limitations in existing technologies like low-dose computed tomography have prevented the implementation of widespread screening programs. Breath-based solutions that seek disease biomarkers in exhaled volatile organic compound (VOC) profiles show promise as affordable, accessible and non-invasive alternatives to traditional imaging. In this pilot work, we present a lung cancer detection framework using cavity ring-down spectroscopy (CRDS), an effective and practical laser absorption spectroscopy technique that has the ability to advance breath screening into clinical reality. The main aims of this work were to (1) test the utility of infrared CRDS breath profiles for discriminating non-small cell lung cancer (NSCLC) patients from controls, (2) compare models with VOCs as predictors to those with patterns from the CRDS spectra (breathprints) as predictors, and (3) present a robust approach for identifying relevant disease biomarkers. First, based on a proposed learning curve technique that estimated the limits of a model’s performance at multiple sample sizes (10–158), the CRDS-based models developed in this work were found to achieve classification performance comparable or superior to like mass spectroscopy and sensor-based systems. Second, using 158 collected samples (62 NSCLC subjects and 96 controls), the accuracy range for the VOC-based model was 65.19%–85.44% (51.61%–66.13% sensitivity and 73.96%–97.92% specificity), depending on the employed cross-validation technique. The model based on breathprint predictors generally performed better, with accuracy ranging from 71.52%–86.08% (58.06%–82.26% sensitivity and 80.21%–88.54% specificity). Lastly, using a protocol based on consensus feature selection, three VOCs (isopropanol, dimethyl sulfide, and butyric acid) and two breathprint features (from a local binary pattern transformation of the spectra) were identified as possible NSCLC biomarkers. This research demonstrates the potential of infrared CRDS breath profiles and the developed early-stage classification techniques for lung cancer biomarker detection and screening.
IEEE Journal of Biomedical and Health Informatics, 2022
Efficient storage and transmission of electromyogram (EMG) data are important for emerging applic... more 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 CAEs compressed data from 24 bits to 6 bits, an additional 4-fold compression was achieved without significant degradation of the reconstruction performance. Furthermore, the CAEs 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.
Increases in the rates of chronic disease and an aging population have created a demand for new f... more Increases in the rates of chronic disease and an aging population have created a demand for new forms of preventative care and proactive health monitoring technologies. While senior populations may be hesitant to adopt wearable technologies, the ability to retrofit assistive devices already in use by the individuals may provide a major stepping stone for increased adoption rates and monitoring abilities. Design of such systems often exhibit challenges with respect to sensor selection, placement, and consequently, reliability and usability of the system in real-world environments. As part of a growing line of smart assistive devices, this work presents a proposed design for a multi-sensor walker with pilot data collected and tested in a real-world environment, including outdoors. Preliminary analysis of results demonstrates the ability to determine levels of activity and environments, important factors related to health and wellness and risk of falls.
Uploads
Papers by Erik Scheme