Humanity thrives along major rivers – this is as true now as it was ages ago. Our dependence on rivers for agriculture and electricity, as well as the need to control its flow because of our proximity, has resulted in dramatic changes to the nature of the rivers. What were once great perennial rivers are now mere trickles during the summer months. This puts the livelihood of many people, especially poor farmers, in jeopardy. How can we monitor and document changes to the flow through rivers over time? Since river gauge measurements are rare or non-existent, any way in which we can use freely available satellite imagery (Landsat, Sentinel) to determine the changes in flow patterns of rivers over time would be extremely useful. One such tool is Rivamap – it uses OpenCV to analyze satellite imagery to extract information about rivers, especially for large rivers. What about smaller ones – it does not seem to work as well. In this project, the student(s) will have to develop machine-learning based methods (or extend the capabilities of Rivamap) to study satellite images to extract information about the path and dimensions of rivers of different flow rates and flow patterns. Comparison with ground-truth data will be needed.

Continue reading

The PHIA project is a multi-country population-based HIV Impact Assessment survey which has interviewed and tested for HIV over 450,000 people of all ages in Africa. We are also currently conducting a second round of surveys in many countries, and hope to use best practices in big data management to generate a combined dataset across all countries. We want to combine this data with environmental, mobility and social media data and then use machine learning to identify trends in HIV incidence, treatment disruption and risk factors. We would also be interested in looking at other ways to use environmental data to predict potential zoonotic outbreaks.

Continue reading

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.

Continue reading

This project builds on a novel cellular model of human aging (Sturm et al. Epigenomics 2019) where we can investigate trajectories of multiple molecular features of aging over long time periods. The underlying multi-omic dataset includes epigenomic (DNA methylation), proteomic (protein abundance), bioenergetics (mitochondrial respiration), telomere length, and various secreted factors. A major challenge for the DSI Fellow will be to integrate the multi-omic dataset to capture dynamic signatures of mitochondrial dysfunction and cellular aging, working collaboratively with other scientists. The existing project is expected to result in one or more publications. Possibility to continue work for pay over the summer.

Continue reading

Advances in data collection technologies in neuroscience has resulted in a deluge of high-quality data that needs to be analyzed, and presented to the experimentalist in a meaningful way. Usually the “data analysis and visualization”-pipeline is built from scratch for each new experiment resulting in a significant amount of code duplication and wasted effort in rebuilding the analysis tools. There is a growing need for a unified system to automate much of the repetitive tasks and aid biologists in understanding their data more efficiently.

Continue reading

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.

Continue reading

Research on: (i) COSMOS cloud connected vehicles, (ii) Monitoring of traffic intersections, using bird’s eye cameras, supported by ultra-low latency computational/communications hubs; (iii) Simultaneous video-based tracking of cars and pedestrians, and prediction of movement based on long-term observations of the intersection; (iv) Real-time computational processing, using deep learning, utilizing GPUs, in support of COSMOS applications; (v) Sub-10ms latency communication between all vehicles and the edge cloud computational/communication hub, to be used in support of autonomous vehicle navigation. The research is performed using the pilot node of project COSMOS infrastructure.

Continue reading