Extraction of Factors Related to Transportations and Destinations by Decision Trees for Personal Whereabouts Modeling

It has become possible to record the data of a visited place automatically, using a smartphone's GPS. The smartphone can visualize where a user visits and present the traveling route. In this study, we propose a personal whereabouts model for living pattern analysis, utilizing the smartphone's GPS. The proposed model aims to extract personal living patterns effectively. To this propose, it is important to analyze those factors related to location and environment. A decision tree based method is used to extract these factors for the location-based personal data analysis. We finally discuss the experiment design and our observations based on personal data collected from mobile environments.

[1]  Didier Stricker,et al.  Personalized mobile physical activity recognition , 2013, ISWC '13.

[2]  Timothy Baldwin,et al.  Japanese SemCor: A Sense-tagged Corpus of Japanese , 2012 .

[3]  Qun Jin,et al.  Cyber-Enabled Well-Being Oriented Daily Living Support Based on Personal Data Analysis , 2020, IEEE Transactions on Emerging Topics in Computing.

[4]  Jianhua Ma,et al.  A Context-Aware Scheduling Mechanism for Smartphone-Based Personal Data Collection from Multiple Wearable Devices , 2016, 2016 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData).

[5]  Qun Jin,et al.  A Framework of Personal Data Analytics for Well-Being Oriented Life Support , 2016 .

[6]  J. Ross Quinlan,et al.  Improved Use of Continuous Attributes in C4.5 , 1996, J. Artif. Intell. Res..

[7]  Pinar Senkul,et al.  Personalized time-aware outdoor activity recommendation system , 2016, SAC.

[8]  Roberto Trasarti,et al.  TOSCA: two-steps clustering algorithm for personal locations detection , 2015, SIGSPATIAL/GIS.

[9]  Masanobu Abe,et al.  A Life Log Collecting System Supported by Smartphone to Model Higher-Level Human Behaviors , 2012, 2012 Sixth International Conference on Complex, Intelligent, and Software Intensive Systems.

[10]  Juha Pärkkä,et al.  Personalization Algorithm for Real-Time Activity Recognition Using PDA, Wireless Motion Bands, and Binary Decision Tree , 2010, IEEE Transactions on Information Technology in Biomedicine.