CLASSIFICATION OF SOFTWARE CONTROL ARCHITECTURES FOR A POWERED PROSTHESIS THROUGH CONVENTIONAL GAIT ANALYSIS USING MACHINE LEARNING APPLICATIONS

The powered prosthesis for people with transtibial amputation offers the opportunity to more appropriately restore gait functionality with benefits, such as powered plantar flexion. In particular, various software control architectures provide unique capabilities for regulating the powered prosthesis during gait. One highly novel approach applies the winding filament hypothesis, which enables an advanced modeling of muscle characteristics, such as through introducing the attributes of titin into the muscle model. The objective of the research is to contrast the conventional control architecture of the BiOM-powered prosthesis compared with the winding filament hypothesis control architecture through machine learning classification. Four machine learning algorithms are applied through the Waikato Environment for Knowledge Analysis (WEKA): J48 decision tree, [Formula: see text]-nearest neighbors, logistic regression, and the support vector machine. The feature set is derived from the force signal acquired from a force plate, which is a conventional gait analysis system. The feature set applied five attributes representing temporal and kinetic aspects of the stance phase of gait. The [Formula: see text]-nearest neighbors algorithm achieves the best machine learning classification accuracy of 95%. The preliminary research establishes the foundation for more sophisticated endeavors respective of the powered prosthesis, such as determining the appropriateness of modifying the software control architecture to best accommodate the progressive lifestyle evolutions and adaptations of the person with amputation.

IMPLEMENTATION OF A SMARTPHONE WIRELESS GYROSCOPE PLATFORM WITH MACHINE LEARNING FOR CLASSIFYING DISPARITY OF A HEMIPLEGIC PATELLAR TENDON REFLEX PAIR

The patellar tendon reflex response provides fundamental means of assessing a subject’s neurological health. Dysfunction regarding the characteristics of the reflex response may warrant the escalation to more advanced diagnostic techniques. Current strategies involve the manual elicitation of the patellar tendon reflex by a highly skilled clinician with subsequent interpretation according to an ordinal scale. The reliability of the ordinal scale approach is a topic of contention. Highly skilled clinicians have been in disagreement regarding even the observation of asymmetric reflex pairs. An alternative strategy incorporated the ubiquitous smartphone with a software application to function as a wireless gyroscope platform for quantifying the reflex response. Each gyroscope signal recording of the reflex response can be conveyed wirelessly through Internet connectivity as an email attachment. The reflex response is evoked through a potential energy impact pendulum that enables prescribed targeting and potential energy level. The smartphone functioning as a wireless gyroscope platform reveals an observationally representative gyroscope signal of the reflex response. Three notably distinguishable attributes of the reflex response are incorporated into a feature set for machine learning: maximum angular rate of rotation, minimum angular rate of rotation, and time disparity between maximum and minimum angular rate of rotation. Four machine learning platforms such as the J48 decision tree, K-nearest neighbors, logistic regression, and support vector machine, were applied to the patellar tendon reflex response feature set incorporating a hemiplegic patellar tendon reflex pair. The J48 decision tree attained 98% classification accuracy, and the K-nearest neighbors, logistic regression, and support vector machine achieved perfect classification accuracy for distinguishing between a hemiplegic affected leg and unaffected leg patellar tendon reflex pair. The research findings reveal the potential of machine learning for enabling advanced diagnostic acuity respective of the gyroscope signal of the patellar tendon reflex response.

ADVANCES REGARDING POWERED PROSTHESIS FOR TRANSTIBIAL AMPUTATION

The necessity for developing advanced prostheses are apparent in light of projections that the forecast for the number of people enduring amputation will double by the year 2050. The transtibial powered prosthesis that enables positive mechanical work about the ankle during the powered plantar flexion aspect of stance phase constitutes a paradigm shift in available transtibial prostheses. The objective of the review is to advocate the state of the art regarding the transtibial powered prosthesis. The historic origins of the prosthesis and motivations for amputation are clarified. The phases of gait and the compensatory mechanisms and asymmetries inherent with passive transtibial prostheses are described. The three general classes of transtibial prosthesis (passive, energy storage and return and powered prostheses) are defined. Subsystems that are integral to the powered prosthesis are explained, such as the series elastic actuator and control architecture. Gait analysis systems and their role for the test and evaluation of energy storage and return and powered prostheses are demonstrated. Future advanced concepts; such as the integration of titin into novel muscle models that account for force enhancement and force depression including their implications for cutting edge bio-inspired actuators are elucidated. The review accounts for the evolution of the prosthetic device with regards to the scope of transtibial amputation and assesses the current state-of-the-art.

Implementation of a smartphone as a wireless gyroscope application for the quantification of reflex response

The patellar tendon reflex constitutes a fundamental aspect of the conventional neurological evaluation. Dysfunctional characteristics of the reflex response can augment the diagnostic acuity of a clinician for subsequent referral to more advanced medical resources. The capacity to quantify the reflex response while alleviating the growing strain on specialized medical resources is a topic of interest. The quantification of the tendon reflex response has been successfully demonstrated with considerable accuracy and consistency through using a potential energy impact pendulum attached to a reflex hammer for evoking the tendon reflex with a smartphone, such as an iPhone, application representing a wireless accelerometer platform to quantify reflex response. Another sensor integrated into the smartphone, such as an iPhone, is the gyroscope, which measures rate of angular rotation. A smartphone application enables wireless transmission through Internet connectivity of the gyroscope signal recording of the reflex response as an email attachment. The smartphone wireless gyroscope application demonstrates considerable accuracy and consistency for the quantification of the tendon reflex response.

Use of smartphones and portable media devices for quantifying human movement characteristics of gait, tendon reflex response, and Parkinson's disease hand tremor

Smartphones and portable media devices are both equipped with sensor components, such as accelerometers. A software application enables these devices to function as a robust wireless accelerometer platform. The recorded accelerometer waveform can be transmitted wireless as an e-mail attachment through connectivity to the Internet. The implication of such devices as a wireless accelerometer platform is the experimental and post-processing locations can be placed anywhere in the world. Gait was quantified by mounting a smartphone or portable media device proximal to the lateral malleolus of the ankle joint. Attributes of the gait cycle were quantified with a considerable accuracy and reliability. The patellar tendon reflex response was quantified by using the device in tandem with a potential energy impact pendulum to evoke the patellar tendon reflex. The acceleration waveform maximum acceleration feature of the reflex response displayed considerable accuracy and reliability. By mounting the smartphone or portable media device to the dorsum of the hand through a glove, Parkinson's disease hand tremor was quantified and contrasted with significance to a non-Parkinson's disease steady hand control. With the methods advocated in this chapter, any aspect of human movement may be quantified through smartphones or portable media devices and post-processed anywhere in the world. These wearable devices are anticipated to substantially impact the biomedical and healthcare industry.

WIRELESS ACCELEROMETER SYSTEM FOR QUANTIFYING DISPARITY OF HEMIPLEGIC GAIT USING THE FREQUENCY DOMAIN

The proper allocation of a therapy strategy and dosage is fundamentally associated with the quantified evaluation of gait quality. Wireless accelerometer systems for the evaluation of quantified hemiplegic gait characteristics has been successfully applied in inherently autonomous environments through the consideration of the temporal domain of the gait acceleration waveform. The frequency domain has notable potential for identifying the quantified disparity of the affected leg and unaffected leg through the application of a tandem-activated wireless accelerometer system mounted to the lateral malleolus of each lower leg through an elastic band. The quantification of disparity for hemiplegic gait via the application of wireless accelerometers was applied in an outdoor environment, while walking on a sidewalk. In addition, the wireless accelerometers were tandem activated while the subject had achieved steady-state gait status, which mitigated the need to subjectively remove starting acceleration and stopping deceleration aspects of the gait cycle. Four predominant frequencies within the 0–5 Hz bandwidth demonstrated a considerable degree of accuracy and reliability. The organization of the four predominant frequencies for both affected leg and unaffected leg were found to be disparate in a statistically significant manner, implicating a disparity of the rhythmicity respective of the affected leg in contrast to the unaffected leg in hemiplegic gait. These preliminary findings may advance gait quantification techniques, which may improve the efficacy of gait rehabilitation therapy. Enclosed are the initial test and evaluation of a tandem-activated wireless accelerometer system using the frequency domain for ascertaining a quantified disparity of hemiplegic gait.

ASSISTIVE VIBROTACTILE BIOFEEDBACK SYSTEM FOR POSTURAL CONTROL ON PERTURBED SURFACE

Postural control is an important aspect of human locomotion and stance. When inputs to the Central Nervous System (CNS), consisting of the vestibular, somatosensory, and visual senses, degrade or become dysfunctional, the postural control is affected. Biofeedback has been established as a potential intervention method to assist individuals improve postural control, by augmenting or complementing signals to the CNS. This paper presents an approach to help achieve better postural control using vibrotactile biofeedback. Tests to monitor postural control, in eyes open and eyes closed states, on a wobble board were introduced to assess the viability of the designed system in providing accurate real-time biofeedback responses. Postural control was gauged by measuring the angular displacement of perturbations experienced. Perturbations along the anterior and posterior direction are used to determine the level of provided vibrotactile biofeedback. The feedback informs subjects the severity of perturbation and direction of imbalance. Significant improvement (p-value < 0.05) in postural control while on perturbed surface was detected when the designed biofeedback system was used. The wearable system was found to be effective in improving postural control of the subjects and can be expanded for rehabilitation, conditioning, and strengthening applications dealing with human postural control.

Implementation of an iPhone wireless accelerometer application for the quantification of reflex response

The patellar tendon reflex represents an inherent aspect of the standard neurological evaluation. The features of the reflex response provide initial perspective regarding the status of the nervous system. An iPhone wireless accelerometer application integrated with a potential energy impact pendulum attached to a reflex hammer has been successfully developed, tested, and evaluated for quantifying the patellar tendon reflex. The iPhone functions as a wireless accelerometer platform. The wide coverage range of the iPhone enables the quantification of reflex response samples in rural and remote settings. The iPhone has the capacity to transmit the reflex response acceleration waveform by wireless transmission through email. Automated post-processing of the acceleration waveform provides feature extraction of the maximum acceleration of the reflex response ascertained after evoking the patellar tendon reflex. The iPhone wireless accelerometer application demonstrated the utility of the smartphone as a biomedical device, while providing accurate and consistent quantification of the reflex response.

Quantified reflex strategy using an iPod as a wireless accelerometer application

A primary aspect of a neurological evaluation is the deep tendon reflex, frequently observed through the patellar tendon reflex. The reflex response provides preliminary insight as to the status of the nervous system. A quantified reflex strategy has been developed, tested, and evaluated though the use of an iPod as a wireless accelerometer application integrated with a potential energy device to evoke the patellar tendon reflex. The iPod functions as a wireless accelerometer equipped with robust software, data storage, and the capacity to transmit the recorded accelerometer waveform of the reflex response wirelessly through email for post-processing. The primary feature of the reflex response acceleration waveform is the maximum acceleration achieved subsequent to evoking the patellar tendon reflex. The quantified reflex strategy using an iPod as a wireless accelerometer application yields accurate and consistent quantification of the reflex response.