Search ETDs:
Goal-seeking Decision Support System to Empower Personal Wellness Management
Chippa, Mukesh K

2016, Doctor of Philosophy, University of Akron, Computer Engineering.
Obesity has reached epidemic proportions globally, with
more than one billion adults overweight with at least three
hundred million of them clinically obese; this is a major
contributor to the global burden of chronic disease and
disability. This can also be associated with the rising health
care costs; in the USA more than 75\% of health care costs
relate to chronic conditions such as Diabetes and Hypertension.
While there are various technological advancements in
fitness tracking devices such as Fitbit, and many employers
offer wellness programs, such programs and devices have
not been able to create societal scale transformations in
the life style of the users.

The challenge in keeping healthy people healthy and helping
them to be intrinsically motivated to manage their own health is
at the focus for this investigation on Personal Wellness
Management. In this dissertation, this problem is presented
as a decision making under uncertainty where the participant
takes an action at discrete time steps and the outcome of the
action is uncertain. The main focus is to formulate the decision
making problem in the Goal-seeking framework. To evaluate
this formulation, the problem was also formulated in two classical
sequential decision-making frameworks --- Markov Decision
Process and Partially Observable Markov Decision Process.
The sequential decision-making frameworks allow us to compute
optimal policies to guide the participants' choice of actions. One
of the major challenges in formulating the wellness management
problem in these frameworks is the need for clinically validated
data. While it is unrealistic to find such experimentally validated
data, it is also not clear that the models in fact capture all the
inconstraints that are necessary to make the optimal solutions
effective for the participant. The Goal-seeking framework offers
an alternative approach that does not require explicit modeling
of the participant or the environment.
This dissertation presents a software system that is designed in
the Goal-seeking framework. The architecture of the system is
extensible. A modular subsystem that is useful to visualize exercise
performance data that are gathered from a Kinect camera is
described.
Shivakumar Sastry, Dr (Advisor)
Nghi Tran, Dr (Committee Member)
Igor Tsukerman, Dr (Committee Member)
William Schneider IV, Dr (Committee Member)
Victor Pinheiro, Dr (Committee Member)
120 p.

Recommended Citations

Hide/Show APA Citation

Chippa, M. (2016). Goal-seeking Decision Support System to Empower Personal Wellness Management. (Electronic Thesis or Dissertation). Retrieved from https://etd.ohiolink.edu/

Hide/Show MLA Citation

Chippa, Mukesh. "Goal-seeking Decision Support System to Empower Personal Wellness Management." Electronic Thesis or Dissertation. University of Akron, 2016. OhioLINK Electronic Theses and Dissertations Center. 16 Dec 2017.

Hide/Show Chicago Citation

Chippa, Mukesh "Goal-seeking Decision Support System to Empower Personal Wellness Management." Electronic Thesis or Dissertation. University of Akron, 2016. https://etd.ohiolink.edu/

Files

ChippaM.dis (final).pdf (1.96 MB) View|Download