Academics
follow us
Feedback

Ramisetty Kavya

Ph.D. Topic

Decision Support Systems for Health Informatics

Research Area

Artificial Intelligence & Decision Theory

Ph.D. Supervisor

Dr. Jabez Christopher    

Co. Supervisor

Prof. Spandan Bhattacharya

LinkedIn Profile

https://www.linkedin.com/in/kavya-ramisetty-509298104/

Research Course

PhD

Research Type

Full Time

Research Year

Aug, 2019 - Aug 2023

Ph.D. Status

Completed

DAC Members

Prof. Chittaranjan Hota & Dr. Venkatakrishnan Ramaswamy

Kavya's research works intend to analyse and model the cognitive aspects of decision-makers during decision-making under uncertainty. It also includes studies on different uncertainty theories, descriptive decision-making models and decision theories to aid decision-makers with interpretable knowledge and reasoning about possible combinations of decision alternatives. The outcomes of her works were used to design and develop clinical decision support systems for assisting junior clinicians at health care centres and hospitals. She is currently a Staff Engineer at Western Digital.
inf sciences

An uncertainty measure for Dempster-Shafer theory

Dempster Shafer (DS) theory, an extension of probability theory, is widely used for modeling uncertainty in information. It is based on the concept of basic probability assignment. Each basic probability value has a corresponding belief interval. These intervals offer a practical and understandable way to quantify uncertainty. Therefore this research article proposes an uncertainty measure (𝐻𝑘) which satisfies most of the mathematical properties, and a generic set of four behavioral requirements.
app intel

Interpretable systems for decision-making

This research article presents a Decision Support System based on descriptive decision-making model which provides interpretable knowledge about the decision space. The system uses fuzzy logic concepts to compute belief values (mass values), and multi-criteria decision-making methods, instead of Demster Shafer combination rule, to assign fusion probabilities. The approaches and outcomes of this work can be used to develop explainable decision support systems for various applications.