Welcome!

I am a PhD student in the Industrial and Systems Engineering Department at the University of Wisconsin-Madison, specializing in Human Factors. My research centers on the application of machine learning tools to solve problems associated with driving impairment. I also work on "Big Data" problems in driving, text mining of accident databases, and investigate ways to measure and model Trust. Prior to attending UW-Madison I worked in the Humans and Automations Lab at MIT, where I conducted research on models of supervisory control of Unmanned Vehicles.

Recent News

Human Factors Publication: A paper I co-authored with John Lee and Mahtab Ghazizadeh, entitled Text Mining to Decipher Free-Response Consumer Complaints: Insights From the NHTSA Vehicle Owner's Complaint Database, has been accepted for publication in Human Factors: The Journal of the Human Factors and Ergonomics Society. The paper describes the benefits of unsupervised learning for understanding free response databases and explores the relationships between google searches, manufacturer recalls, and consumer complaints. The paper is available online at Sage Publications.

Human Factors Publication: A paper I co-authored with John Lee, Chris Schwarz, and Tim Brown, entitled Steering in a random forest: Ensemble learning based detection of drowsiness related lane departures, has been accepted for publication in Human Factors: The Journal of the Human Factors and Ergonomics Society. The paper describes driver drowsiness detection in the context of basic supervised machine learning and presents an algorithm which uses an ensemble classifier to predict drowsiness-related lane departures from steering input. The paper will be available online at SAGE publications and in print.

Transportation Research Board 93rd Annual Meeting: A conference proceedings paper I wrote entitled, "Impairment as a hidden state: How Hidden Markov Models improve drowsiness detection and may differentiate between distraction, drowsiness, and alcohol impairment," has been accepted for presentation at the 93rd Annual Meeting of the Transportation Research Board (TRB) The work was co-authored with John Lee, Chris Schwarz, and Tim Brown. It describes the advantages of temporal models for the detection of driver drowsiness and presents model architectures for detecting and differentiating drowsiness, distraction, and alcohol impairment. Please e-mail me for more details!