Projects

Quotes Projects

"Engineering problems are under-defined, there are many solutions, good, bad and indifferent. The art is to arrive at a good solution. This is a creative activity, involving imagination, intuition and deliberate choice. "
- Michio Kaku

Projects

/node/310
Facial expression analysis
Thursday, July 20, 2017 - 12:17
face
, expression analysis

The face conveys information about a person’s age, sex, background, and identity, what they are feeling, or thinking. Facial expression provides cues about emotion, intention, alertness, pain, personality, regulates interpersonal behavior, and communicates psychiatric and biomedical status among other functions. Not surprisingly, the face has been of keen interest to behavioral scientists.

The Human Sensing Lab develops real-time automatic systems for...

/node/328
A Wearable System for Home-Monitoring Parkinson's Disease
Monday, January 19, 2015 - 19:52
Parkinson's
, wearable technology

Parkinson’s Disease (PD) affects 7-10 million people worldwide. There is no cure – medication can only provide symptomatic relief – and costs associated with PD, including treatment, social security payments, and lost income from inabilty to work, is estimated to be nearly $25 billion per year in the United States alone.

We aim to lower costs by building a wearable system consisting of low-cost accelerometers to detect and quantitatively assess the...

/node/329
ECG based physiological event prediction
Friday, January 16, 2015 - 21:34
ECG
, fatigue
, cardiac arrest

ECG based physiological event prediction is a project centered around the use of machine learning to detect and predict physiological events on a macro scale, from ECG readings. Objectives of this project are twofold. Initially, developing algorithms to predict a future cardiac arrest event from a live stream of ECG data. Next, detect and predict stress and fatigue from a live stream ECG data.

These algorithms will be trained in a weakly supervised...

Past projects

http://www.ri.cmu.edu/projects/project_601.html
Multimodal Diaries

Summarization of daily activity from multimodal data (audio, video, body sensors and computer monitoring).

http://www.f-zhou.com/ta.html
Temporal Alignment of Human Behavior

Temporal alignment of two or more subjects recorded from heterogeneous sensors is a challenging problem. This project develops statistical techniques for spatio-temporal alignment of multidimensional time series.

http://www.f-zhou.com/tc.html
Temporal Segmentation of Human Behavior

Temporal Segmentation of Human Motion & Temporal Segmentation of Facial Behavior.

http://www.ri.cmu.edu/projects/project_631.html
Deception Detection

Learning facial indicators of deception.

http://www.ri.cmu.edu/projects/project_600.html
Hot Flash Detection

Machine learning algorithms to detect hot flashes in women using physiological measures.

http://www.ri.cmu.edu/projects/project_599.html
Forecasting the Anterior Cruciate Ligament Rupture Patterns

Use of machine learning techniques to predict the injury pattern of the Anterior Cruciate Ligament (ACL) using non-invasive methods.

http://www.ri.cmu.edu/projects/project_524.html
Camera Assisted Meeting Event Observer

We are developing the Camera Assisted Meeting Event Observer (CAMEO) - a sensory system designed to provide an electronic agent with physical awareness of the real world.

http://www.ri.cmu.edu/projects/project_632.html
Intelligent Diabetes Assistant

We are working to create an intelligent assistant to help patients and clinicians work together to manage diabetes at a personal and social level. This project uses machine learning to predict the effect that patient specific behaviors have on blood glucose.

http://www.ri.cmu.edu/projects/project_606.html
Indoor People Localization

Tracking multiple people in indoor environments with the connectivity of Bluetooth devices.

http://www.ri.cmu.edu/projects/project_585.html
Reflective Agents with Distributed Adaptive Reasoning

The focus of the RADAR project is to build a cognitive assistant that embodies machine learning technology that is able to function without requiring expert tuning or specially trained users.