Battles Lecture

Title:  The Data Show LIVE: Coast Guard Cadets and Faculty Apply Natural Language Processing to Search and Rescue Reports

Time:  Friday,  7:30 PM - 8:30 PM

Abstract:  When someone is lost at sea, the US Coast Guard coordinates a search and rescue (SAR) response. After-action reports (AARs) from these incidents may contain vital information about a person’s ability to survive. Cadets and faculty from the US Coast Guard Academy used text analysis tools, natural language processing (NLP), and other methods from machine learning to identify and analyze SAR AARs about people in the water (PIW). This experience demonstrates how faculty can expand the horizon of their research program, include students in knowledge discovery, and produce tangible results. A classification model was developed to label SAR AAR files according to the presence of a PIW. The authors and their students continue to enhance the model and apply it to other Coast Guard-related domains with text-based reports.

Bio:  Dr. Zachary Kudlak came to the U.S. Coast Guard Academy in 2017. Dr. Kudlak graduated from the University of Rhode Island with his Ph.D. in 2010, where his dissertation was in graph theory, studying edge colorings of graphs. Since then, Dr. Kudlak has been working in the field of difference equations and is particularly interested in investigating systems of difference equations with non-constant coefficients. Most recently he has branched into natural language processing research. Dr. Kudlak has taught a wide range of undergraduate mathematics courses from calculus courses to probability and simulation courses and most recently started teaching machine learning-related topics. His honors include being a 2011 Project NExT Fellow. His other interests are competitive running, hiking with his dog, and spending time with his family. LT Sherman is from Columbus, OH and is a 2015 graduate from the US Coast Guard Academy. LT Sherman has served on 3 ships with five years of sea time around the world. His military honors include Navy and Coast Guard Achievement Medals and the Meritorious Service Medal. He received his Master of Science in engineering (MSE) in Data Science from the University of Pennsylvania, and has done significant work applying machine learning (ML) methods to search and rescue datasets. Of note, he presented his work on Machine Learning-Based Priority Scoring for Search and Rescue Satellite Aided Tracking (SARSAT) at the Military Operations Research Society (MORS) Symposium in 2022 and at the World Maritime Rescue Congress, Rotterdam, Netherlands in 2023. His interests in data science include natural language processing methods, ML model comparison testing, and boosting. His other interests outside of work include running, photography, and landscaping at his home in Gales Ferry.