Date of Award

Spring 2015

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

Program

Computing

First Advisor

Ahamed, Sheikh Iqbal

Second Advisor

Kaczmarek, Thomas

Third Advisor

Arif, Muhaammad

Abstract

As smartphones become very more popular, applications are being developed with new and innovative ways to solve problems faced in the day-to-day lives of users. One area of smartphone technology that has been developed in recent years is human activity recognition HAR. This technology uses various sensors that are built into the smartphone to sense a person's activity in real time. Applications that incorporate HAR can be used to track a person's movements and are very useful in areas such as health care. In our research, we use this type of motion sensing technology, specifically, using data collected from the accelerometer sensor. The purpose of this study is to estimate the pilgrim who may become lost on the annual pilgrimage to Hajj. The application is capable of estimating the movements of people in a crowded area, and of indicating whether or not the person is lost in a crowded area based on his/her movements as detected by the smartphone. This will be a great benefit to anyone interested in crowd management strategies, specifically regarding Hajj. In this thesis, we review related literature and research that has given us the basis for our own research. For example, we could not create this application without the use of HAR technology and without specific classification algorithms. We also detail research on lost person behavior. We looked at the typical movements a person will likely make when he/she is lost and used these movements to indicate lost person behavior. We then describe the creation of the application, all of its components, and the testing process. Finally, we discuss the results of our trials and plans for future work.

Download
COinS