Category: Announcements

April 3, 202512:15 PM – 1:15 PM Speaker:Ankan Bhattacharyya, Computer Science Department, University of Kentucky Where:327 McVey Hall (Virtual Speaker)(Zoom link: https://uky.zoom.us/j/82467171189) Title:System for the 2D-3D detection of bourbon barrel features-of- interest Abstract:During the bourbon aging process, where bourbon is stored in new, charred oak barrels for months or years, distilleries realize a significant amount of product wastage. Some of this loss arises from expected environmental processes (i.e. evaporation of the bourbon through the porous wood of the barrel), while a considerable portion is due to the unexpected structural failure of the barrel itself. While these events have been a part of the bourbon industry since its inception, it is only recently that distilleries have begun to investigate the properties of the barrel which may contribute to and/or lead to product…

April 3, 202512:15 PM – 1:15 PM Speaker:Barry Farmer, Center for Computational Sciences, University of Kentucky Where:327 McVey Hall (Virtual Speaker)(Zoom link: https://uky.zoom.us/j/82467171189) Title:Enhancing AI/ML Research with HPC Resources: A Practical Approach Abstract:Navigating high-performance computing (HPC) environments can be challenging for researchers seeking to access and utilize a wide range of software tools. This session introduces key services developed to simplify access to software and resources at the University of Kentucky, including the Software Discovery Service (SDS) and the Singularity Container Composer. These tools enable users to quickly locate available software and customize containerized applications to meet their specific research needs. We’ll explore how to search for software, create custom containers, and deploy Jupyter Notebooks using Open OnDemand, providing practical applications for a variety of research areas. While there will be…

March 27, 202512:15 PM – 1:15 PM Speaker:Jeff Talbert, College of Medicine, University of Kentucky Where:327 McVey Hall (Virtual Speaker)(Zoom link: https://uky.zoom.us/j/82467171189) Title:The Rapid Actionable Data for Opioid Response (RADOR-KY) Project Abstract:This presentation will focus on the development of RADOR-KY, the Rapid Actionable Data for Opioid Response in Kentucky. RADOR-KY is an integrated population-based near-real time statewide system that uses multiple data sources to monitor and respond to the ongoing opioid overdose crisis. RADOR-KY uses dashboards to visualize data sources and topics and of interest identified by stakeholders. RADOR-KY allows users to develop customizable dashboards that will allow them options to select specific measures.  Lastly, RADOR-KY will forecast opioid overdose incidents using predictive analytics and machine learning to forecast future trends.   Click here to see the complete list of speak

February 13, 202512:15 PM - 1:15 PM Speaker:Hasan Poonawala, Mechanical Engineering, University of Kentucky Where:327 McVey Hall(Zoom link: https://uky.zoom.us/j/82467171189) Title:Adding smart sensors to your data collection pipeline using deep learning on embedded computers. Abstract: Newer kinds of data collection are now possible thanks to combined advances in machine learning and embedded computing. In particular, relevant data can be autonomously extracted from sensors at the source.  This talk will discuss some examples through projects in my lab, like collecting data on seated-vs-standing behavior by individuals in their homes, with lessons learned. Click here to see the complete list of speakers.

January 30, 202511:45 AM - 12:45 PM (Temporary Timeslot) Speaker:Mahmut Gokmen, Institute for Biomedical Informatics, University of Kentucky Where:327 McVey Hall(Zoom link: https://uky.zoom.us/j/82467171189) Title:Task-Specific Adaptation of Vision Foundational Models for Coronary Artery Disease Diagnosis Abstract: This presentation will demonstrate the application of vision foundational models in detecting, grading, and understanding the real-world implications of Coronary Artery Disease. During the session, the general architecture of a foundational model will be explained, along with how it is trained using a self-supervised technique (DINO) and how it can be adapted to task-specific structures when necessary. Additionally, the current pace of advancements in foundational models and their future potential will also be discussed. Click here to see the complete list of speakers.