Our lab is using clinical notes to phenotype COVID patient outcomes. The aim is to better understand the sequela of COVID-19 from clinical notes.
The question we ask is whether online echo-chambers on social media networks enhance the anxiety and depression of individuals during the COVID19 outbreak. More specifically we want to measure the intensity of the communication about COVID-19 within the echo-chamber of individuals on Twitter and investigate the impact on their subsequent tweets in terms of the level of anxiety and signs of depressive language in their Tweets. We measure echo-chambers by the number of users in the social network that tweeted about COVID-19. We build on an extensive dataset of Twitter users for whom we have identified a large number of demographic and geographic variables (such as the gender, age, ethnicity, location by state, political affiliation) as well as their social network.
Many of the cryptocurrency transactions have involved fraudulent activities including ponzi schemes, ransomware as well money-laundering. The objective is to use Graph Machine Learning methods to identify the miscreants on Bitcoin and Etherium Networks. There are many challenges including the amount of data in 100s of Gigabytes, creation and scalability of algorithms.
Orienting to a novel event is a rapid shift in attention to a change in one’s surroundings that appears to be a fundamental biological mechanism for survival and essentially functions as a “what is it” detector. Orienting appears to play a central role in human learning and development, as it facilitates adaptation to an ever-changing environment. Thus, orienting can be viewed as an allocational mechanism in which attention sifts through the complex multi-sensory world and selects relevant stimuli for further processing. The selection of stimuli for further processing has implications for what will be encoded into memories and how strong those memory traces will be. The ability to differentiate between relevant and irrelevant input, to inhibit the processing of irrelevant stimuli, and to sustain attention requires control, and inhibitory processes that improve with age.
We aim to augment recovery in spinal cord (SC) injured patients. Electrical stimulation of the SC can facilitate recovery, but the mechanisms are not yet understood. One knowledge gap lies in the exact pathways that are recruited by stimulation. To close this gap, we have tested the effects of SC stimulation in people undergoing clinically indicated surgery. By testing the distribution and size of muscle responses to SC stimulation, we can infer which circuits are activated. We are also examining how SC injury changes those responses. We propose to use Bayesian methods to understand the interaction between muscle responses to stimulation and the MRI indicated pattern of damage. The project will involve construction of models linking multiple data modalities that predict muscle activity, followed by the modification of these models to account for patterns of damage. Construction of such models would enable a deeper understanding of SC stimulation leading to more effective stimulation paradigms.
Our goal is to use deep learning networks to understand which neurons in the brain encode fine motor movements in mice. We collected large datasets entailing calcium imaging data of active neurons and high-resolution videos when mice perform motor tasks. We want to use recent advances in deep learning to (1) estimate the poses of mouse body parts at a high spatiotemporal resolution (2) extract behaviorally-relevant information and (3) align them with neural activity data. Behavioral video analysis is made possible by transfer learning, the ability to take a network that was trained on a task with a large supervised dataset and utilize it on a small supervised dataset. This has been used e.g. in a human pose–estimation algorithm called DeeperCut. Recently, such algorithms were tailored for use in the laboratory in a Python-based toolbox known as DeepLabCut, providing a tool for high-throughput behavioral video analysis.
42% of New York City greenhouse gas emissions result from on-site fossil fuel combustion in residential and commercial buildings; space heating is, by far, the majority contributor. Both New York State and NYC have policies to dramatically reduce emissions that will require a transformation in the way buildings are heated, including major efforts in existing buildings. This transition is inextricably linked to existing energy equity issues that we believe significantly overlap across NYC (and elsewhere). These include unreliable heating in the winter, susceptibility to extreme heat (an increasing occurrence with climate change) and struggles to afford energy needs. Various known data sources for NYC are available, though they are disparate and have not been analyzed holistically. Further, we believe there are potential engineering and policy solutions to these challenges. In this project, the DSI scholar will access (and search for where not yet known to qSEL researchers) relevant data sets, analyze those data sets to identify communities exposed to all or a subset of these issues, and assist qSEL researchers in developing models to evaluate possible solutions. The project has the possibility of extending through Summer 2020, subject to fundraising efforts and the success of the Spring 2020 project.
