The population of the United States is aging. Based on the latest predictions by the Administration of Aging (AoA), by 2020 there will be approximately 55 million people in the US aged 65 or older, which is almost double its value in 1990. A recent study by CDC found out that among older adults, falls are the leading cause of both fatal and non-fatal injuries. As mobile and personal health devices gain in popularity, increasing amounts of data is collected via their embedded sensors such as heart rate monitors and accelerometers. In this presentation, hear how artificial intelligence and machine learning can be used to detect falls by analyzing real data obtained from digital wireless wristbands used in healthcare facilities. In addition to detecting falls, the same information can be used to recognize different forms of human motion to ultimately create a better predictor of fall possibility. Results show a significant improvement in motion recognition rate where the overall accuracy over seven selected activity classes is greater than 90% compared to the most recent literate at 54%.
Speaker: Dr. Ismail Uysal, Associate Professor, University of South Florida