HSL Seminar: Safa Jabri, Univ of Michigan + Björn Lütjens et al, HSL(12p, 11/3, 33-206)

Two talks for the price of one! (also via Zoom link: https://mit.zoom.us/j/96531308383)


Towards Personalized Rehabilitation Interventions: Wearables for Balance Assessment & Training

Safa Jabri, University of Michigan

Abstract— Balance deficits due to aging and neurological/sensory disorders have substantial physical, emotional, and monetary costs. Appropriately designed balance rehabilitation programs are effective in creating new & strengthening existing sensorimotor pathways and enhancing postural control, however, access to personalized training with physical therapists remains a challenge. In this talk, I will be sharing a few of the research projects led by the Sienko Research Group to investigate the use of wearable sensors and machine learning methods to capture, evaluate and provide feedback on human performance in the context of balance rehabilitation. This work represents some of the first and necessary steps in achieving the long-term goal of creating personalized, optimized, and automated balance training technologies to complement, supplement and increase access to clinic-quality care.


Machine Learning for Making Local Climate Projections More Accessible

Ana Mata-Payerro, Björn Lütjens, David Dao, Lea Hadzic, Lucas Czech, Matthew Kearney, Thomas Huber (MIT)

Abstract—Decision-makers in industry are grappling with climate change and ask for local climate risk analyses. Local analyses, however, are largely inaccessible, because climate datasets can be unorganized and the size of petabytes. Further, running Earth system models at the local scale suffers from the curse of dimensionality. This will be an overview talk about how machine learning can alleviate this issue. We will talk about collecting local data of reforestation projects, trustworthy climate emulators, and finally visualizing climate information.