Date of Award
Master of Science
Electrical and Computer Engr
Aaron L. Robinson
Data is the key for developing algorithms that can infer the causes of agitation in mentally-ill individuals. Unfortunately, appropriate datasets are not readily available due to issues such as confidentiality breach and privacy invasion. This thesis addresses three problems.First, we identify a number of publicly-available datasets that are functions of actions and emotions of mentally-ill individuals. These include datasets of physiological signals, training videos and commercial movies.Second, we synthesize change in body-weight as a function of actions and emotions by extending a well-known model. The extended model is evaluated with respect to change in diet, physical activity and stress, using data reported in the literature. The evaluation results show promise.Third, we propose an efficient way to store several physiological signals with different sampling frequencies. Instead of storing every sample of each signal, a linear interpolation-based approach synchronizes the signals at the desired sampling rate as and when needed.
dissertation or thesis originally submitted to the local University of Memphis Electronic Theses & dissertation (ETD) Repository.
Koirala, Dewashish, "Data collection, body-weight generation and efficient storage of physiological data" (2017). Electronic Theses and Dissertations. 1781.