Ehsan Hoque (academic)

Ehsan Hoque is an American computer scientist and academic. He is a Professor in the Computer Science Department at the University of Rochester in New York.

Hoque is most known for his work in the field of artificial intelligence, particularly in utilizing AI methods to augment and enhance human capabilities. His work revolves around affective computing, speech processing, and computer vision.

Education
Hoque completed his Bachelor of Science in Computer Engineering from Penn State University in 2004, and then obtained a master's degree in Electrical and Computer Engineering from the University of Memphis in 2007. Later, he completed his Ph.D. in Media Arts and Sciences from the Massachusetts Institute of Technology in 2013, where the MIT Museum highlighted his Ph.D. thesis as one of the most unconventional inventions of MIT. In 2017, he received Alumni Achievement Award from Penn State University.

Career
Hoque began his academic career in 2013 by joining the University of Rochester as an assistant professor in the Computer Science Department, becoming associate professor in 2020.

Hoque served as the Interim Director of the Goergen Institute for Data Science at the University of Rochester between 2018 and 2019, and held the Assaro-Biggar family fellowship from 2016 to 2019. As of 2023, he serves as a board member of the National Academies Health Sciences Policy.

Research
Hoque holds a patent for the concept of utilizing a computer as a conversational mentor, which was introduced in 2012 and later integrated by Microsoft as "Speaker Coach" in PowerPoint. In 2019, along with colleagues, he helped establish the Morris K. Udall Center of Excellence in Parkinson's Disease Research by the National Institute of Neurological Disorders and Strokes (NINDS) at the University of Rochester. He has authored numerous publications spanning the areas of Artificial Intelligence, human-centered computing, and medicine, including articles in peer-reviewed journals.

Social skills training
Hoque has worked in developing computational techniques to enable social skills training. In 2012, he developed an Automated Conversation Helper that utilized a 3D virtual character to act as an interviewer during a job interview. It offered immediate feedback on the participant's nonverbal behavior by employing advanced technology to detect facial expressions, analyze speech patterns and respond in real-time with synthesized speech and behavior. In related research, his work concluded that automated technologies, specifically those that analyze nonverbal communication and provide feedback, such as My Automated Conversation coacH (MACH), offer a personalized approach to enhancing human social interaction and have the potential to be utilized for both practical and therapeutic purposes. He and his students have expanded the research to develop Live Interactive Social Skills Assistant (LISSA) and Standardized Online Patient for Healthcare Interaction Education (SOPHIE). LISSA provides real-time feedback on smiling, eye contact, body movement and volume in real-time and has been validated to help individuals with Autism Spectrum Disorder. SOPHIE has been designed to train doctors to have more empathy and be explicit with information while dealing with final-stage cancer patients.

Affective computing
Hoque has worked on developing techniques, technologies, and theories, to improve the capacity to accurately recognize, interpret, and respond to human nonverbal cues. He demonstrated that those techniques have implications in health AI. He and his students have developed Parkinson's Analysis with Remote-Kinetic tasks (PARK)—a webcam-based system enabling neurological care to be available anytime, anywhere. The system allows remote participants to perform a set of UPDRS test using a webcam and a microphone and receive a screening for Parkinson's disease, and have the severity of their tremors being automatically measured.

Awards and honors

 * 2014, 2016, 2020 – Google Faculty Research Award
 * 2016 – MIT Top 35 Innovators under 35 (TR 35)
 * 2017 – Pennsylvania State University Alumni Achievement Award
 * 2017 – 10 Scientists to Watch (the SN 10) by Science News
 * 2018 – NSF CAREER Award, National Science Foundation
 * 2019 – Early Career Award for Scientists and Engineers, Army Research Office
 * 2020 – Emerging Leaders in Health and Medicine by the National Academy of Medicine
 * 2022 – ACM Distinguished Member
 * 2023 – ACM UbiComp 10-Year Impact Award

Personal
Hoque is a triathlete and finished an Ironman Triathlon in 2022 at Maryland and at Lake Placid in 2023.

Selected articles

 * Hoque, M. E., McDuff, D. J., & Picard, R. W. (2012). Exploring temporal patterns in classifying frustrated and delighted smiles. IEEE Transactions on Affective Computing, 3(3), 323–334.
 * Hoque, M., Courgeon, M., Martin, J. C., Mutlu, B., & Picard, R. W. (2013, September). Mach: My automated conversation coach. In Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing (pp. 697–706).
 * Baten, R. A., Aslin, R. N., Ghoshal, G., & Hoque, E. (2022). Novel idea generation in social networks is optimized by exposure to a “Goldilocks” level of idea-variability. PNAS Nexus, 1(5), pgac255.
 * Islam, M.S., Rahman, W., Abdelkader, A., Lee, S., Yang, P.T., Purks, J.L,  Adams, J.L., Schneider, R.B., Dorsey, E.R.,  and Hoque, E. (2023),  Using AI to Measure Parkinson's Disease Severity at Home, Nature Digital Medicine 2023.