The REACH OUT study is a multi-institutional collaboration funded by the Health Effects Institute to determine if populations who have been chronically exposed to higher levels of air pollution are at greater risk of severe COVID-19 outcomes. This is a paid position which will provide students with the opportunity to use analytic approaches on public health and environmental data. The selected student will work as part of a research team to analyze publicly available COVID-related and environmental data from the New York City Department of Health. They will also integrate findings with those from harmonized electronic health records and conduct simulations to assess the potential for selection bias in study populations. All analyses will be performed using R/R Studio. Students will be expected to create shareable and commented code as part of this work. Students will also create visualizations to communicate study results in publications and presentations.

Continue reading

We research techniques for improving safety of pedestrians, traffic flow, and smart streetscape applications. We aim to accomplish precise localization and tracking of objects by utilizing infrastructure-installed multimodal sensors such as cameras and lidars to provide a global view of the behavior of smart city traffic participants. We rely significantly on traffic intersections which are particularly suitable locations for the deployment of computing, communications, and AI-based services for smart cities of the future. The abundance of data to be collected and processed, in combination with privacy and security concerns, motivates the use of machine learning and deep learning processing, and to deploy the edge-computing paradigm which aligns well with physical intersections in metropolises.

Continue reading

Type 1 diabetes (T1D) is a chronic autoimmune disease that requires patients to need lifelong insulin therapy. Diabetes technology (insulin pumps and continuous glucose monitors (CGM)) have been shown to reduce the risk of high and low blood sugars and thus reduce long term diabetes complications. Hybrid closed-loop (HCL) insulin pumps integrate CGM technology to automatically adjust insulin delivery from the pump, with the goal of improved blood sugar and better quality of life for the patient. There are two commonly used HCL systems in our diabetes center: the t:slim x2 with Control IQ (TS) and the Omnipod 5 (O5).

Continue reading

Vehicle routing has been extensively studied in optimization problems. With the advance of AI and big data, this project aims to solve vehicle routing problems (VRP) using reinforcement learning.

Continue reading

In this project, we aim to develop GCN-based GAN models to predict spatio-temporal evolution using open human mobility datasets – SafeGraph (https://www.safegraph.com/).

Continue reading

Decoding behavioral signifiers for the brain state of vigilance can have far reaching implications for understanding the neural basis for actions and identifying disease. We are using high resolution video recordings of mice as they navigate a maze but have access to very few pre-determined behavioral signifiers. Several recent publications implemented computer vision to extract a variety of previously unreachable aspects of behavioral analysis, including animal pose estimation and distinguishable internal states. These descriptions allowed for the identification and characterization of dynamics, which then revealed an unprecedented richness to the behaviors that determine decision making. Applying such computational approaches mice during exploration and in the context of behaviors that have been validated to measure choice and memory can reveal dimensions of behavior that predict or even determine psychological constructs like vigilance. We are also obtaining neural signal data, which can be aligned with the behavioral signifiers. DSI scholars would use pose estimation analysis to evaluate behavioral signifiers for choice and memory and relate it to our real time concurrent measures of neural activity and transmitter release. The students would also have opportunity to examine the effect of disease models known to impair performance on our maze task on any identified signifier.

Continue reading

Neurodevelopmental disorders (NDDs) comprise of a group of disorders associated with abnormal brain development. Rare genetic variants have been shown to play a key role in their development, especially in those NDDs which are severe in nature. During the last decade, genetic testing has emerged as an important etiological diagnostic test for NDDs with a considerable impact on disease management and treatment. Yet, current genetic testing has a diagnostic rate of ~ 50%. Due to technical limitations in modern next-generation sequencing techniques, these techniques fail to asses a large part of the genome (2/3rd), missing critical regions which may have clinical significance. New methods now have emerged that can assess these regions better, can access repetitive regions and identify complex structural genomic events with more accuracy. This project will employ and integrate novel genomic technologies, including optical genome mapping and long read sequencing, to perform a comprehensive investigation of the human genome in parent-child trios which remained genetically unsolved after standard genomic approaches.

Continue reading