1st DRAC Presentation on Feb 12th 2021 at 11 AM
Abstract:
Disaster-affected communities are increasingly becoming the source of big (crisis) data during and following major disasters. At the same time, big data have the potential to become an integral source of information for response organizations, as they can help enhance the situational awareness and facilitate faster response where is most needed. Despite such benefits, the challenges presented by big data preclude organizations from using them routinely. Manually sifting through voluminous streaming data to filter useful information in real time is inherently impossible. We study machine learning solutions to help emergency response organizations deal with the overload of relevant information, and improve situational awareness and crisis response. As an example, we have proposed a novel approach, based on convolutional neural networks and class activation mapping, to locate damage in disaster images and to quantify the degree of damage. Our proposed machine learning solutions have the potential to transform the way in which crisis response organizations operate, and, in turn, to provide better support to the victims of disasters in a timely fashion.
Biography of Speaker:
Doina Caragea, Ph.D., is a Professor at Kansas State University. Her research and teaching interests are in the areas of machine learning, data mining, data science, information retrieval and text mining, with applications to crisis informatics, security informatics, recommender systems, and bioinformatics. Her projects build upon close collaborations with social scientists, security experts and life scientists, and aim to provide practical computational approaches to address real-world challenges. Dr. Caragea received her PhD in Computer Science from Iowa State University in August 2004, and was honored with the Iowa State University Research Excellence Award for her work. She has published more than 100 refereed conference and journal articles. Her research has been supported by several NSF grants.