Henry Griffith

Contactless on-bed activity sensing using first-reflection echolocation

A novel system capable of detecting on-bed activity during sleep using first-reflection ultrasonic echolocation is described herein. As is employed in many existing solutions, such activity detection may be utilized in the assessment of sleep quality. Compared to current approaches using either wearable devices or sensors collocated on the surface of the bed, the proposed architecture greatly enhances convenience for the end-user by providing minimal disruptions to his or her standard sleep routine. A series of experiments were conducted in order to investigate the capacity of the system to detect activity during sleep. System performance was benchmarked against both a wrist-worn accelerometer as well as a smartphone application placed adjacent to the subject on the bed. Analysis demonstrates a statistically significant correlation between features computed from the systems output and the filtered activity data produced by the application, with maximum p values on the order of 10-3. Comparison with activity estimates formulated from the wrist-worn accelerometer output suggests stronger agreement, as indicated by increased correlation coefficient values.

Towards Reduced Latency in Saccade Landing Position Prediction Using Velocity Profile Methods

Saccade landing position prediction algorithms are a promising approach for improving the performance of gaze-contingent rendering systems. Amongst the various techniques considered in the literature, velocity profile methods operate by first fitting a window of velocity data obtained at the initiation of the saccadic event to a model profile known to resemble the empirical dynamics of the gaze trajectory. The research described herein proposes an alternative approach to velocity profile-based prediction aimed at reducing latency. Namely, third-order statistical features computed during a finite window at the saccade onset are mapped to the duration and characteristic parameters of the previously proposed scaled Gaussian profile function using a linear support vector machine regression model using an offline fitting process over the entire saccade duration. Prediction performance is investigated for a variety of window sizes for a data set consisting of 9,109 horizontal saccades of a minimum mandated data quality induced by a 30-degree step stimulus. An RMS saccade amplitude prediction error of 1.5169° is observed for window durations of one-quarter of the saccade duration using the newly proposed method. Moreover, the method is demonstrated to reduce prediction execution time by three orders of magnitude versus techniques mandating online fitting.

Home-based upper extremity rehabilitation support using a contactless ultrasonic sensor

Home-based rehabilitation protocols have been shown to improve outcomes amongst individuals with limited upper-extremity (UE) functionality. While approaches employing both video conferencing technologies and gaming platforms have been successfully demonstrated for such applications, concerns regarding patient privacy and technological complexity may limit further adoption. As an alternative solution for assessing adherence to prescribed UE rehabilitation protocols, the Echolocation Activity Detector, a linear array of first-reflection ultrasonic distance sensors, is proposed herein. To demonstrate its utility for home-based rehabilitation, a controlled experiment exploring the ability of the system to distinguish between various parameters of UE motion, including motion plane, range, and speed, was conducted for five participants. Activity classification is accomplished using a quadratic support vector machine classifier using time-domain features which exploit the known geometric relationships between the patient and the device, along with the ideal kinematics of the activities of interest. Average classification accuracy for the five classes of UE motion considered herein exceeds 91%.

Office activity classification using first-reflection ultrasonic echolocation

Excessive sedentary time poses considerable health risks for individuals predominately engaged in desk-bound work. To empower interventions aimed at addressing this problem, reliable technologies for continuous activity monitoring within an office environment are required. As an alternative to existing solutions, we propose the Echolocation-based Activity Detector, a contactless sensor array of four first-reflection ultrasonic distance sensors. The research described herein demonstrates the capacity of the sensor to distinguish between common activities performed at a workstation within an office environment, including sedentary sitting, typing, writing, and standing. Cubic support vector machine classifiers are developed using dispersion-related features computed from the time-series array outputs. Average classification accuracy for sedentary activities exceeds 85%, while classification accuracy for the entire activity set exceeds 80% for a controlled experiment conducted with six participants.

Towards a first-reflection ultrasonic sensor array for compensatory movement identification in stroke sufferers

The use of compensatory motion strategies amongst stroke sufferers has been well documented in the literature. While these modified movement patterns allow individuals to address functional deficits, research suggests that employing such techniques may inhibit motor skill recovery. Although detection of these movements using either wearable sensors or gaming technologies within home-based rehabilitation regiments has been demonstrated, both the physical limitations and technological preferences of the target population limit the efficacy of such solutions. The objective of this extended abstract is to demonstrate progress towards employing a contactless first-reflection ultrasonic echolocation sensor to detect compensatory movements associated with excessive trunk flexion in response to reduced upper extremity functionality. Results from preliminary experiments in which compensatory motions are induced using a motion-restricting elbow brace are described herein. Preliminary results are promising, with average classification accuracy exceeding 78%.

A wearable system for asymmetric contactless human sensing

A wearable sensor capable of detecting the presence of humans within a front-facing 90-degree sector of varying radius is demonstrated herein. The system offers extensive applicability across a variety of scenarios where detecting the parameters of human interaction, including separation distance and duration, is of value. Sensing is accomplished using an ultrasonic distance and passive infrared sensor. This design improves upon previous approaches presented in the literature by eliminating privacy concerns associated with audio and video capture, and also relaxing the requirement that both interacting individuals be in possession of dedicated hardware. A KNN classifier is developed using data obtained from a designed indoor experiment intended to demonstrate system robustness across geometries consistent with those observed in the target application. Employing a set of only three features, an overall accuracy rate of 94.2% is realized for detecting human interactions occurring within a 90-degree sector of three-foot radius.

Enhancing continuity between gender diversity interventions using hybrid social networks

Increasing gender diversity within the engineering workforce is crucial for ensuring competitive advantage in the global marketplace. Although non-systemic gender diversity interventions in engineering education report positive outcomes throughout the literature, the cumulative effect of such efforts has proven insufficient. While resource intensive mechanisms for improving coordination between offerings in order to enhance aggregate outcomes have been proposed, constrained funding environments limit the feasibility of such solutions. We have recently introduced a hybrid social networking-based framework for extending continuity between in-person programming in a work-in-progress paper. Such an approach offers the capacity to increase engagement between in-person interventions while introducing only limited marginal costs. The research described herein expands upon this effort by providing a more detailed description of the coordination effort, and also enhancing the survey pool used to examine potential barriers to participation amongst the target user population. Results from a survey of over 130 high school and college students are presented, with a particular focus on examining factors which threaten the feasibility of the proposed implementation.