Date of Award

Fall 2019

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computing

First Advisor

Ahamed, Sheikh Iqbal

Second Advisor

Love, Richard R.

Third Advisor

Kawsar, Ferdaus Ahmed

Abstract

In the United States, falls are one of the leading causes of fatal and non-fatal injuries for people of all ages. Current clinical methods to assess fall risk are impractical, and often do not use individuals’ actual performance. With current technological advances, and the Internet of Things (IoT), the tools are available to create a digital system that can take into account an individual’s actual performance in making a fall risk assessment. A digital insole based sensory computing system can collect and analyze human gait patterns to develop a fall risk assessment platform with great accuracy.The presented research considers current clinical methods and describes a computerized self-service platform that successfully addresses different gait variables and metrics critical to accurate fall risk assessment. The system incorporates a shoe insole with pressure sensors, and an accelerometer. Collected foot data are transferred to an analytics visualization platform. A wide range of gait pattern recognition metrics, and gait data analyses features are then displayed on the platform enabling specific fall risk assessment.

COinS