B. Hudgins - Academia.edu (original) (raw)

Papers by B. Hudgins

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society Volume 13: 1991

ABSTRACT

SPIE Proceedings, 1994

Bend enhanced fiber (BEF) sensors are curvature-measuring optical analogs of elongation- measurin... more Bend enhanced fiber (BEF) sensors are curvature-measuring optical analogs of elongation- measuring resistance strain gauges. They are made by treating optical fibers to have an optically absorptive zone along a thin axial stripe a few millimeters long. Light transmission through the fiber past this zone then becomes a robust function of curvature, three orders of magnitude more sensitive to bending

Medical & Biological Engineering & Computing, 1994

and the loading period was 0.775. The areas which are easily measured by the ASKER hardness meter... more and the loading period was 0.775. The areas which are easily measured by the ASKER hardness meter are selected. However, the coefficient of correlation was smaller than that in the above-mentioned muscle tonus measurement, because an unnatural pose of the body is needed to hold the measured area horizontally. The larger scatter (error of 11-6%) of the ASKER value also resulted from the difficulty in keeping the measured area horizontal.

Proceedings of the First Joint BMES/EMBS Conference. 1999 IEEE Engineering in Medicine and Biology 21st Annual Conference and the 1999 Annual Fall Meeting of the Biomedical Engineering Society (Cat. No.99CH37015)

ABSTRACT A new technique to extract more control information from the myoelectric signal (MES) is... more ABSTRACT A new technique to extract more control information from the myoelectric signal (MES) is introduced. The technique is based on the correlation of the MES obtained from a linear array of surface electrodes. The goal is to develop a continuous classifier of the MES to be used for myoelectric control

− A Gaussian mixture model (GMM) based classification scheme is proposed in this paper to perform... more − A Gaussian mixture model (GMM) based classification scheme is proposed in this paper to perform multiple limb motion discrimination using continuous myoelectric signals (MES) from limb muscles. The system is optimized with respect to the feature set, classifier and post-end processing of the decisions through comprehensive experimentation. The experiments examine the effects of various feature sets including the time-domain (TD) features and the autoregressive (AR) features with root mean square value (RMS), and the effect of the majority vote (MV) in post-processing on the classification performance. The averaged GMM classification performance is compared with that of three other motion techniques (a linear discriminant analysis (LDA), a linear perceptron (LP) neural network and a multilayer perceptron (MLP) neural network). The Gaussian mixture motion model achieves 96.91% classification accuracy using a combination of AR with RMS and TD (AR+RMS+TD) feature set for a six class p...

Technology and Disability, 2003

This work represents an ongoing investigation of dexterous and natural control of upper extremity... more This work represents an ongoing investigation of dexterous and natural control of upper extremity prostheses using the myoelectric signal. The scheme described within uses pattern recognition to process four channels of myoelectric signal, with the task of discriminating six classes of limb movement. The method does not require segmentation of the myoelectric signal data, allowing a continuous stream of class decisions to be delivered to a prosthetic device. Due to the fact that the classifier learns the muscle activation patterns for each desired class for each individual, a natural control actuation results. The continuous decision stream allows complex sequences of manipulation involving multiple joints to be performed without interruption. The continuous classifier is optimized with respect to the feature set and classifier used, and post-processing of the decisions to eliminate spurious errors.

2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015

Muscle synergies have been proposed as a way for the central nervous system (CNS) to simplify the... more Muscle synergies have been proposed as a way for the central nervous system (CNS) to simplify the generation of motor commands and they have been shown to explain a large portion of the variation in the muscle patterns across a variety of conditions. However, whether human subjects are able to control prostheses proportionally with a small set of synergies has not been tested directly. Here we investigated if muscle synergies can be used to identify different wrist and hand motions. We recorded electromyographic (EMG) activity from eight arm muscles while the subjects exerted seven different intensity levels during the motions when performing seven classes of hand and wrist motion. From these data we extracted the muscle synergies and classified the tasks associated to each contraction intensity profile by linear discriminant analysis (LDA). We compared the performance obtained using muscle synergies with the performance of using the mean absolute values (MAV) as a feature. Also, the consistency of extracted muscle synergies was studied across intensity variations. While the synergies showed relative consistency particularly across closer intensity levels, average classification results generated with the synergies were less accurate than MAVs. These results indicate that although the performance of muscle synergies was very close to MAVs, they do not provide additional information for task identification across different exerted intensity levels.

Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

This paper introduces the use of Gaussian mixture models (GMM) for discriminating multiple classe... more This paper introduces the use of Gaussian mixture models (GMM) for discriminating multiple classes of limb motions using continuous myoelectric signals (MES). The purpose of this work is to investigate an optimum configuration of a GMM-based limb motion classification scheme. For this effort, a complete experimental evaluation of the Gaussian mixture motion model is conducted on a 12-subject database. The experiments examine algorithmic issues of the GMM including the model order selection and variance limiting. The final classification performance of this GMM system has been compared with that of three other classifiers (a linear discriminant analysis (LDA), a linear perceptron neural network (LP) and a multilayer perceptron (MLP) neural network) . The Gaussian mixture motion model attains 96.3% classification accuracy using four channel MES for distinguishing six limb motions and is shown to outperform the other motion modeling techniques on an identical six limb motion task.

Journal of Microcomputer Applications, 1995

ABSTRACT This paper describes the design and development of an eight-channel ambulatory monitor f... more ABSTRACT This paper describes the design and development of an eight-channel ambulatory monitor for use in ergonomic and rehabilitation studies. This portable, battery operated instrument is capable of recording various physiological and biomechanical parameters during the course of a working shift. By incorporating a digital signal processor within the instrument, sophisticated on-line processing is possible. The processed data is stored in a removable non-volatile memory module which can be interrogated by a PC type machine. Evaluation of the instrument in a laboratory setting has been performed to verify operation. In addition, clinical trials are presently underway in a hospital environment as part of an injury prevention program targeted towards nurses. It is proposed that this instrument can be used to determine compliance with such programs after the initial training phase and give some indication as to whether refresher courses are warranted.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1998

An accurate and computationally efficient means of classifying myoelectric signal (MES) patterns ... more An accurate and computationally efficient means of classifying myoelectric signal (MES) patterns has been the subject of considerable research effort in recent years. Effective feature extraction is crucial to reliable classification and, in the quest to improve the accuracy of transient MES pattern classification, many forms of signal representation have been suggested. It is shown that feature sets based upon

IEEE Transactions on Biomedical Engineering, 1984

Techniques for the estimation of skeletal muscle fiber conduction velocity are of considerable in... more Techniques for the estimation of skeletal muscle fiber conduction velocity are of considerable interest. These techniques use, in general, some form of cross correlation or zero-crossing analysis. Cross correlation is a straightforward method of conduction velocity estimation, however, it is difficult to realize low-cost real-time processors. Polarity correlation offers a method which preserves the advantages of cross correlation and satisfies the speed-cost constraint. This paper describes the algorithm for implementation of a polarity cofrelator instrument using a microprocessor. The instrument is tested with deterministic and stochastic signals and used to estimate the conduction velocity of biceps brachii fibers of ten normal subjects. The performance of the instrument is compared to the zero-crossing technique described by Lynn. This technique was later used by Naeije and Zorn [2], Parker [3], and Nishizono et al. [4] in an attempt to find a reliable and noninvasive estimate. The cross correlation function estimate requires a substantial amount of numerical computation and hence there is a tradeoff between speed and cost. Realtime low-cost estimation of conduction velocity via the cross correlation function is not feasible with present technology. An alternative technique proposed by Lynn [5] achieves continuous real-time velocity estimation through the use of digital bandpass filtering and zero-crossing detection coded on a PDP-11 minicomputer. Masuda et al. [6] modified Lynn's technique using a gradient threshold zero-crossing method. This approach does not require an analog-to-digital converter or digital filtering. However, both of these techniques suffer from Manuscript

IEEE Transactions on Biomedical Engineering, 2006

Classification accuracy of conventional automatic speech recognition (ASR) systems can decrease d... more Classification accuracy of conventional automatic speech recognition (ASR) systems can decrease dramatically under acoustically noisy conditions. To improve classification accuracy and increase system robustness a multiexpert ASR system is implemented. In this system, acoustic speech information is supplemented with information from facial myoelectric signals (MES). A new method of combining experts, known as the plausibility method, is employed to combine an acoustic ASR expert and a MES ASR expert. The plausibility method of combining multiple experts, which is based on the mathematical framework of evidence theory, is compared to the Borda count and score-based methods of combination. Acoustic and facial MES data were collected from 5 subjects, using a 10-word vocabulary across an 18-dB range of acoustic noise. As expected the performance of an acoustic expert decreases with increasing acoustic noise; classification accuracies of the acoustic ASR expert are as low as 11.5%. The effect of noise is significantly reduced with the addition of the MES ASR expert. Classification accuracies remain above 78.8% across the 18-dB range of acoustic noise, when the plausibility method is used to combine the opinions of multiple experts. In addition, the plausibility method produced classification accuracies higher than any individual expert at all noise levels, as well as the highest classification accuracies, except at the 9-dB noise level. Using the Borda count and score-based multiexpert systems, classification accuracies are improved relative to the acoustic ASR expert but are as low as 51.5% and 59.5%, respectively.

IEEE Engineering in Medicine and Biology Magazine, 2002

A hidden Markov model based classifier is proposed in this paper to perform automatic speech reco... more A hidden Markov model based classifier is proposed in this paper to perform automatic speech recognition using myoelectric signals from the muscles of vocal articulation. The classifier's resilience to temporal variance is compared to a linear discriminant analysis classifier that was used in a pervious study. Speech recognition was performed, using five channels of myoelectric signals, on isolated words from a 10word vocabulary. Temporal variance was induced by temporally misaligning data from the test set, with respect to the training set. When compared to the LDA classifier, the hidden Markov model classifier demonstrated a markedly lower variation in classification error due to the temporal misalignment. Characteristics of the hidden Markov model MES classifier suggest that it would effectively complement a conventional acoustic speech recognizer, in a multi-modal speech recognition system.

IEEE Transactions on Biomedical Engineering, 2003

... Levi Hargrove, Erik Scheme, Kevin Englehart and Bernie Hudgins Institute of Biomedical Engine... more ... Levi Hargrove, Erik Scheme, Kevin Englehart and Bernie Hudgins Institute of Biomedical Engineering, University of New Brunswick, Fredericton, Canada. ... [4] K. Englehart, and B. Hudgins, A robust, real time control scheme for multifunction myoelectric control, IEEE Trans. ...

This work compared a novel pattern recognition based myoelectric control system to a system based... more This work compared a novel pattern recognition based myoelectric control system to a system based on conventional control and another state of the art pattern recognition system. The results showed that the proposed system provides a more usable system as assessed qualitatively and quantitatively through a modified virtual clothespin test. Furthermore, the proposed system was designed to have an intuitive clinician interface and should help facilitate the acceptance of pattern recognition based myoelectric control systems in the clinic.

Many clinically available, upper-extremity prosthetic limbs provide myoelectric control of a sing... more Many clinically available, upper-extremity prosthetic limbs provide myoelectric control of a single device, such as a hand, elbow, or wrist. Most commonly, these systems yield control information from myoelectric signal (MES) amplitude [1] or rate of change of MES [2]. Such systems have been beneficial; however, prosthetic users would no doubt find enhanced functionality and usability if they could reliably control more than a single function (or device). Seeking to address this issue, extensive work has gone into developing schemes that provide multifunction myoelectric classification with very high accuracy [3]. However, for all continuous multifunction MES classifiers, no matter how accurate and repeatable, there exists no defined threshold (classification accuracy) of acceptability. This is due, in large part, to the limited availability of prosthetic devices housing multiple electromechanical functions. Described in this paper is a recently developed MES control software tool t...