Research Projects
Empath
Introduction
Depression is a major health issue that affects over 21 million American men and women each year. Depression often goes unrecognized and untreated, and even once treatment begins it is often difficult to measure its effectiveness. This poses particular challenges for the diagnosis and treatment of depression, particularly for those who avoid visiting a doctor or therapist due to social stigmas or a lack of energy. Currently, depression diagnosis is often based on subjective screening questionnaires or structured clinical interviews that rely on timely in-person visits as well as accurate recollections by the patient. This makes early detection of depression symptoms exceedingly difficult among this population. Yet early detection and treatment of this debilitating disorder has been shown to improve patient outcomes considerably. Along with depression's detrimental affect on mood, it can lead to other associated problems because of reduced social interactions, decrease in personal hygiene, increased alcohol use, and neglect of medications for current medical conditions. Assessment and treatment are often hampered by a lack of objective data to corroborate patients' retroactive self-reports about their current functioning; hence an objective symptom-monitoring tool could complement subject self-report measurement and enhance diagnostic accuracy.
Caregiver Interface
We developed a web interface that is designed especially for caregivers such as therapists, nurses, and doctors. At the main screen, the caregiver is presented a list of attending patients with an overall depression risk-factor. When a patient is selection, a summary of the basic behavioral factors: sleeping quality, social isolation, PHQ-9 score, weight, movement levels and speech analysis are presented in a column graph. Each factor is represented on a scale of 1-5 representing low to high risk. When a factor is selected, a new presentation of the data appears explaining the subcomponents that made up the factor score. The data is presented with a time-series plot or table however appropriate.
Demo Presentation
Robert F. Dickerson, Timothy Hnat, Enamul Hoque, and John A. Stankovic. "Demonstration of Sleep Monitoring and Caregiver Displays for Depression Monitoring". Wireless Health 2011
Download the PosterStreamfeeds
Introduction
The MetroNet project will consist of sensors deployed in the storefront windows of downtown Charlottesville. The sensors will count people as they pass by a store or walk into a store, in order to provide empirical data to the shopkeepers about the effects of advertising, window displays, weather, etc. on pedestrian business.
The goal of MetroNet is to provide an exercise in data sharing; if the shopkeepers are willing to share data, it could be used by pedestrians to see the popularity of a particular concert, by other shopkeepers to calibrate their own data, by city planners to estimate the effects of vehicular traffic on the downtown mall, by real estate customers to estimate the value of individual properties, etc. The key to MetroNet will be to provide the framework necessary to (i) provide incentives to shopkeepers for data sharing (ii) make it easy for shopkeepers to share data, and (iii) provide privacy mechanisms for sharing only aspects of the data.
Stream Aggregation
StreamLab is an experimental interface which allows users to read sensor streams, perform stream operations on them, and publish the results as new sensors on the Microsoft SenseMap interface.
Demo Presentation
Robert F. Dickerson, Jiakang Lu, Jingyuan Li, Billy Chantree, Jian Lu, John A. Stankovic, Kamin Whitehouse. MetroNet: Case Study for Collaborative Data Sharing on the World Wide Web. The Seventh International Conference on Information Processing in Sensor Networks, 2007 (IPSN '07).