The Places of Our Lives: Visiting Patterns and Automatic Labeling from Longitudinal Smartphone Data

Abstract

Abstract-The location tracking functionality of modern mobile devices provides unprecedented opportunity to the understanding of individual mobility in daily life. Instead of studying raw geographic coordinates, we are interested in understanding human mobility patterns based on sequences of place visits which encode, at a coarse resolution, most daily activities. This paper presents a study on place characterization in people's everyday life based on data recorded continuously by smartphones. First, we study human mobility from sequences of place visits, including visiting patterns on different place categories. Second, we address the problem of automatic place labeling from smartphone data without using any geo-location information. Our study on a large-scale data collected from 114 smartphone users over 18 months confirms many intuitions, and also reveals findings regarding both regularly and novelty trends in visiting patterns. Considering the problem of place labeling with 10 place categories, we show that frequently visited places can be recognized reliably (over 80%) while it is much more challenging to recognize infrequent places.

Big Sensed Data Meets Deep Learning for Smarter Health Care in Smart Cities

“…On the other hand, the majority of the data collected by multimedia sensors (e.g., pictures, video feeds, sounds, etc.) are not properly labelled [37].…”

Urban Analysis and Smart Communities: An Approach to the Use of Technology in Everyday Mobility

“…Also, passive data collection methods, like detailed phone call records provided by mobile telephone companies, are likely to be used [52], [41].…”

“…These spatiotemporal data collection systems are useful for human mobility analysis, granting more efficiency and response capacity in urban policies. Moreover, contrary to other mobility data collection methods, geolocation is cheaper, provides samples with more information, updates more frequently, and has more spatial and temporal coverage, due to these reasons, a large number of researches have focused on the impact of mobile devices in human mobility patterns [41], [50], [52], [53], [54]. Table II summarizes some methods used for data analysis through geolocation mobile devices.…”

“…An example of this can be an Apple fan publishing geotagged messages when shopping at an Apple Inc store. Besides LBSNs, there are location integrated services in social networks equally useful for mobility data analysis [52], [59], [60]. Data gathered from LBSN can be captured permanently using different positioning tools as mobile phones, wireless network devices, and GPS devices.…”

“…The paper is based on the data continuously recorded by smartphones. In first place, human mobility is studied from the sequences of places visited; and secondly, automatic geotagging problem is addressed from smartphone data without the use of any geolocation information [52].…”