Loading Events

« All Events

BE/PICS Joint Seminar: Uma Balakrishnan and Kunal Poorey, Sandia National Laboratories

July 18

These talks will be held jointly, with each talk 30 minutes each (1 hour total). Final time and location TBC.

Talk 1: “Optimizing Anomaly Detection for GenAI based Digital Twins of Wearable Data” (Uma Balakrishnan)

In this presentation, we introduce a methodology that utilizes both real and synthetic datasets (digital twins) to address the uncertainties associated with anomaly detection thresholds in health data from wearables. By integrating state-of-the-art wearables using generative AI, and sophisticated anomaly detection techniques, our approach offers a precise and comprehensive understanding of potential health issues, significantly reducing the false negative rate. Enhancing real datasets with generative AI-based digital twins increases population size and achieves strong concordance in uncertainty analysis with results obtained from real data alone. This robust concordance is consistent even when applied to small village populations, showcasing the scalability and reliability of our generative algorithm. Validating synthetic users (digital twins) by comparing their statistical signatures with real datasets confirms the effectiveness of our approach. Our methodology promises to revolutionize healthcare data collection and address privacy concerns by providing a more comprehensive and reliable health assessment tool for early detection of biothreats or pandemics. Moreover, we have developed a versatile anomaly detection method based on the fourth-order moments of physiological parameters, applicable to a wide range of datasets and compatible with various healthcare data sources, including wearables. Our goal is to empower individuals and healthcare systems with advanced tools for real-time anomaly detection and enhanced health assessment, paving the way for improved public health outcomes.

Talk 2: “AI-aided Computational Methods to Overcome Challenges in Biology and Engineering” (Kunal Poorey)

Abstract coming soon.

Uma Balakrishnan, Ph.D. and Kunal Poorey, Ph.D.

Sandia National Laboratories

Dr. Uma Balakrishnan has a wealth of experience with over 30+ published journal articles and a portfolio of more than 20+ conference presentations and invited talks. Her contributions span various domains, including inventing a higher-order numerical scheme for hydraulic stimulation at Halliburton, which led to a patent application for enhanced convergence accuracy, targeted drug delivery, instabilities of free surface flows and multiphase flows, spin coating and enhanced geothermal systems. Currently at Sandia National Laboratories, she actively engages in cutting-edge research, delving into credibility of scientific machine learning, dimensionality reduction, turbulence closures, transfer learning and the development of anomaly detection systems for pandemic outbreaks.

Kunal Poorey is a seasoned computational biologist and data scientist with over 15 years of experience in bioinformatics and applied data science. He holds a Ph.D. in Biochemistry and Molecular Genetics from the University of Virginia. Currently, he serves as a Senior Member of R&D Staff at Sandia National Laboratories, specializing in GenAI, AI/ML, functional genomics, and metagenomics. Kunal has led multiple LDRD projects, developing advanced machine learning tools for biosecurity, pandemic prediction, and antibiotic resistance characterization. He also leads machine learning tasks for the DOE BETO DISCOVR project, pioneering methods for early detection of crop failure biomarkers. His work extends to creating predictive tools for material and chemical discovery, notably contributing to the NA-115 Accelerated Material Discovery initiative. Kunal’s expertise in omics data analysis has resulted in numerous high-profile publications and presentations. Additionally, he has developed novel bioinformatics tools for CRISPR guide optimization and parallel computing. As a mentor, Kunal has guided many interns, post-doctoral researchers, and technical staff, showcasing his commitment to fostering the next generation of scientists.


July 18
Event Category:
Event Tags:


View Organizer Website