Title: Understanding and prediction of smartphone app usage
Speaker: Choonsung Shin (Postdoctrol Fellow/Carnegie Mellon University)
Time: 2012. 9. 27. 9:00 am - 10:00 am
Place: KAIST GSCT N25 #3229
It is becoming harder to find an app on one’s smart phone due to the increasing number of apps available and installed on smart phones today. This talk will present a context modeling framework for understanding and prediction of mobile app usage for smartphones. Based on the framework, we collect sensory data including app use from smartphones, to perform a comprehensive analysis of the context related to mobile app use, and build a prediction model that calculate the probability of an app in the current context. Based on this model, we developed a dynamic home screen app that presents icons for the most probable apps on the main screen of the phone and highlights the most probable one. The proposed model outperformed other strategies, and, in particular, improved prediction accuracy. We found that the dynamic home screen improved accessibility to apps on the phone, compared to the conventional static home screen in terms of accuracy, required touch input and app selection time.
Choonsung Shin received his BS degree in Computer Science from Soongsil University in 2004 and his MS and PhD degrees in Information and Communications from Gwangju Institute of Science and Technology (GIST) in 2006 and 2010. He has been with Carnegie Mellon University (CMU), where he is a Postdoctoral Fellow at Human-Computer Interaction Institute since 2010. He has researched context-aware computing, human computer interaction, mobile computing, mobile augmented reality, ubiquitous virtual reality, etc.