Opportunistic Discovery of Personal Places Using Multi-Source Sensor Data

Abstract

Modern smartphones and wearables are able to continuously collect significant amounts of sensor data, where such data can be helpful to study a user's mobility or social interaction patterns, but also to deliver various services based on a user's presence at different places during certain times of the day. Therefore, it is important to accurately identify personal places of interest (POIs), such as a user's workplace or home. Such places are usually determined using segmentation of location traces, but frequent gaps in the data (i.e., missing location readings) can result in a large number of small and incomplete segments that should actually be grouped together into a single large segment. This paper presents a segmentation approach that utilizes a user's personal data obtained from multiple sensor sources and devices such as the battery recharge behavior (measured on smartphones), step counts, and sleep patterns (measured by wearables), to opportunistically fill gaps in the user's location traces. Using the data from a mobile crowd sensing study of more than 450 users over a 2-year period, we show that our approach is able to generate fewer, but more complete segments compared to the state of the art.

Smart Bracelet System for Temperature Monitoring and Movement Tracking Analysis

“…Gu et al used sensor data and Wi-Fi technology to continuously monitor sleep patterns [7]. Vhaduri et al proposed a method that uses data collected by smartphones and sensors to opportunistically fill gaps in user location traces [8].…”

Deriving College Students’ Phone Call Patterns to Improve Student Life

“…With an unprecedented expansion of smartphone sensing technology, researchers have begun capturing various types of automated sensor data uninterruptedly and seamlessly using smartphones and fitness trackers. Such datasets have then been used to assess students' health and wellbeing [32] and academic performance [33] to offer awareness for better management of student life and improve their quality of life. A group of researchers studied mobile phone data to analyze the activities of users to predict future changes in their activities [34].…”

“…While the main focus of this work was to develop a firewall for incoming calls and reminder apps based on routine phone calls behaviors, this work did not investigate how students' communication behaviors change over the years. Another group of scientists analyzed the correlation between activity, mood, mental wellbeing, and sleep with educational outcomes via a 10-week long study on 48 graduate and undergraduate students utilizing surveys and automated cell phone data [33]. Similarly, others investigated the relationship between students' perceived happiness and mobility and attempted to predict changes in satisfaction using physiological signals, changes in location, and phone usage data along with subjective survey responses collected from a 1-month study on 68 undergraduate students [35].…”

“…• Places of interest (POIs) are the places where people either spend a significant amount of their day or visit frequently [33], [38], [39]. For example, for an on-campus freshmen cohort, POIs can be dormitories (DM), classrooms/buildings (CL), dining halls and other food courts (DI), athletic facilities (AL), as well as other indoor (OI) and outdoor places (OD) [40].…”

“…The NetHealth mobile crowdsensing (MCS) study [33], [34], [38], [40], [45]- [57] began at the University of Notre Dame in 2015 with over 400 on-campus freshmen (average age of 17 years and 11 months with a standard deviation of 11 months) to investigate the impacts of "always-on connectivity" on the health habits, emotional wellness, and social ties of college students over multiple semesters. All procedures were fully approved by Notre Dame's Institutional Review Board (IRB) before distribution.…”