Health Data Science Brown Bag Talk – Human Activity Recognition through Wearable Sensors Dr. Xin Liu
June 11 @ 11:30 am - 1:00 pm
Human Activity Recognition through Wearable Sensors: MDM patient identification and ICU patient activity recognition
In this talk, we present two related projects that use wearable sensors and machine learning techniques for healthcare applications. Duchenne muscular-dystrophy (DMD) patients identification and intensive care unit (ICU) patient activity recognition. In the DMD case, we have built an interactive system consisting of a smartphone-based software application to collect raw data remotely using the phone’s built-in accelerometer sensor, combined with a web-based tool to aggregate, store and analyze data. We extracted the temporal/spatial gait characteristics and used classical machine learning and deep learning techniques to evaluate the gait changes associated with DMD, using both extracted features and raw data. In the ICU case, we use the data collected by two wearable sensors to identify patient movement, which is critical for recovery. We discuss the challenges, results, and future work in this talk.
Biography: Xin Liu received her Ph.D degree in electrical engineering from Purdue University in 2002. She is currently a Professor in the Computer Science Department at the University of California, Davis. Before joining UC Davis, she was a postdoctoral research associate in the Coordinated Science Laboratory at UIUC. During 2012-2014, she took a leave of absence and was a Microsoft Research Asia. Currently, her group works on machine learning algorithm development and machine learning applications. She has received the NSF Career award (2005), and the Outstanding Engineering Junior Faculty Award from the UC Davis College of Engineering (2005), and the Chancellor’s Fellowship (2011), and the ICNP best paper award (2017). She is an IEEE Fellow