Affiliations: Department of Computer Science, University of
Colorado, Boulder, CO, USA
Note: [] Corresponding author: Junho Ahn, Department of Computer Science,
University of Colorado, Boulder, CO 80309, USA. Tel.: +1 303 492 0914; Fax: +1
303 492 2844; E-mail: [email protected]
Abstract: Mobile phones have become widely used for obtaining help in
emergencies, such as accidents, crimes, or health emergencies. The smartphone
is an essential device that can record emergency situations, which can be used
for clues or evidence, or as an alert system in such situations. In this paper,
we focus on mobile-based identification of potentially unusual, or abnormal
events, occurring in a mobile user's daily behavior patterns. For purposes of
this research, we have classified events as "unusual" for a mobile user when an
event is an infrequently occurring one from the user's normal behavior patterns
– all of which are collected and recorded on a user's mobile phone. We
build a general unusual event classification model to be automated on the
smartphone for use by any mobile phone users. To classify both normal and
unusual events, we analyzed the activity, location, and audio sensor data
collected from 20 mobile phone users to identify these users' personalized
normal daily behavior patterns and any unusual events occurring in their daily
activity. We used binary fusion classification algorithms on the subjects'
recorded experimental data and ultimately identified the most accurately
performing fusion algorithm for unusual event detection.
Keywords: Unusual event, mobile, pattern, classification, fusion, personal
