Computer Vision: Climate Science, Human Posture Estimation, and Implications for Healthcare -- Speakers Thomas Vandal and Sarah Ostadabbas from Northeastern University

Date: 

Wednesday, April 18, 2018, 4:00pm to 5:00pm

Location: 

Sherman Auditorium @ BIDMC, East Campus (330 Brookline Ave, Boston MA)

Machine learning and artificial intelligence techniques are being utilized in fields across science and engineering.  This talk will invite two non-medical researchers to present how AI/ML - specifically computer vision - is used in their fields, with the goal of introducing the community to potentially new data analysis strategies.

Learning Objectives:

  1. Share techniques and successes with research methodologies that can be applied across domains.

  2. Demonstrate benefit of harnessing domain knowledge into machine learning models.

  3. Consider ability to quantify uncertainty around predictions when using ML/AI techniques.

 

Bio for Thomas Vandal:

Thomas Vandal is an Interdisciplinary PhD candidate (soon to be graduate) in the Sustainability and Data Science Lab (SDS) at Northeastern University.  He comes with multiple years of industry experience in Boston area startups, including Freebird, Affectiva, and Boston Technologies, with a strong background in computer science and mathematics. Vandal’s research develops machine learning approaches to problems in climate science, including how super-resolution methods originally developed for images can be applied to large scale climate simulations for more detailed projections and uncertainty quantification. This work has the potential to give city planners and related stakeholders the information needed for rationalized climate change adaptation.

 

Bio for Sarah Ostadabbas:

Sarah Ostadabbas is an assistant professor in the Electrical and Computer Engineering Department of Northeastern University (NEU) where she formed the Augmented Cognition Laboratory (ACLab) with the goal of enhancing human information-processing capabilities through the design of adaptive interfaces via physical, physiological, and cognitive state estimation. These interfaces are based on rigorous models adaptively parameterized using machine learning and computer vision algorithms. Prior to Northeastern, Sarah led an NSF SBIR grant to commercialize a decision-support software/interface to prevent pressure ulcers in bed-bound patients by suggesting a resource-efficient posture changing schedule, including focus on human-centric designs.  Professor Ostadabbas is the co-author of more than 40 peer-reviewed journal and conference articles, and is an inventor on two US patent applications. ​