Graduation Semester and Year

2011

Language

English

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Computer Science

Department

Computer Science and Engineering

First Advisor

Heng Huang

Abstract

Human-Centered computing defines a field of study in which computational processes affect the human being, either through ubiquitous and pervasive use of devices or any effect that improves the human condition. Human-Centered Computing applications face serious challenges in the handling of data collection, modeling, and analysis. Traditionally, the analysis of different aspects of human well-being derives from a variety of non-interrelated methods which has made it difficult to correlate and compare the different experimental findings for an accurate assessment of the contributing factors.This dissertation describes new algorithms that enable more accurate and efficient multimodal data analysis of Human-Centered computing applications in order to improve decision-making in healthcare. In particular, this work provides a theoretical framework for multimodal and inter-related data analysis and demonstrates the theory in different cases where the purpose is to (a) monitor the health condition of the human subject, and (b) to improve the quality of life through the understanding of a subject's behaviors.Our computational framework can efficiently analyze and interpret data of different modalities coming from the same human subjects. Emphasis is put on the evaluation of feature selection and classification techniques and their use for heterogeneous data fusion in order to improve the accuracy of the obtained results. Our experimental results show that the same basic methods can be used to analyze data regarding both the physiological and behavioral properties of a human subject, and to correlate the different findings into more meaningful and reliable information.

Disciplines

Computer Sciences | Physical Sciences and Mathematics

Comments

Degree granted by The University of Texas at Arlington

Download

Share

COinS