kHealth - Knowledge-enabled Healthcare is a platform which integrates data from passive and active sensing (including both machine and human sensors) with background knowledge from domain ontologies, semantic reasoning, and mobile computing environments to help people make decisions to improve health, fitness, and wellbeing. kHealth utilizes technology from Semantic Sensor Web, Semantic Perception, and Intelligence at the Interface to enable advanced healthcare applications. Currently we are developing an app with OSU to reduce preventable hospital readmissions of patients with Acute Decompensated Heart Failure.

Researchers: Cory Henson, Pramod Anantharam, Sujan Perera, Amit Sheth, Krishnaprasad Thirunarayan

PREDOSE (Jan 2011 - July 2011)

PREDOSE aims to develop a mechanism to automate 'qualitative coding' in social research by automatically extracting triples from web data, particularly web forum posts. The goal of such triple extraction is to provide a framework that can be exploited to study user knowledge, attitudes and behaviors as it relates to non-medical use of pharmaceutical opiods (e.g. OxyContin, buprenorphine etc). Interesting areas include 1) Social Network analysis, intended to determine information diffusion patterns and 2) Spatial-Temporal-Thematic analysis, intended to determine trends within the community regarding usage, distribution, of method of administration of pharmaceutical opioids (including Suboxone and Subutex, which are buprenorphine products).

Researchers: Delroy Cameron, Lu Chen, Gary A. Smith, Sujan Perera, Amit Sheth

Undergraduate Research

The goal of this project is to identify suspicious stock market transactions by mimicking the concepts of human immune system.