Capability to track the mobility pattern of children and elders can enable many useful applications. Assisted GPS (AGPS) and Wi-Fi can be used to precisely calculate the location of a person, but AGPS consumes a lot of power and Wi-Fi coverage is often spotty. On the other hand, Cell ID offers ubiquitous coverage in most inhabited environments, low power consumption, but has the disadvantage of lower accuracy. This paper introduces an energy-efficient cellular and AGPS/Wi-Fi tracking system based on the construction of a mobility map from a person's historical location data. A location map consists of a set of crucial locations (CL), personal common locations (PCL), and routes. CL is a point that terminates several routes and PCL is a place where the person spends a lot of time in. The tracking process is divided into four parts: data collection, offline data processing, online tracking, and path reconstruction. With the use of the mobility map, AGPS fixes can be significantly reduced and a more accurate recognition of the person's location can be provided during the tracking phase.
[1]
Thad Starner,et al.
Using GPS to learn significant locations and predict movement across multiple users
,
2003,
Personal and Ubiquitous Computing.
[2]
Sajal K. Das,et al.
LeZi-update: an information-theoretic approach to track mobile users in PCS networks
,
1999,
MobiCom.
[3]
Albert Kai-sun Wong,et al.
An AGPS-based elderly tracking system
,
2009,
2009 First International Conference on Ubiquitous and Future Networks.
[4]
Mung Chiang,et al.
Energy Efficient Assisted GPS Measurement and Path Reconstruction for People Tracking
,
2010,
2010 IEEE Global Telecommunications Conference GLOBECOM 2010.
[5]
Roger S. Cheng,et al.
An Energy-Efficient Elderly Tracking Algorithm
,
2011,
2011 IEEE International Conference on Communications (ICC).
[6]
Naranker Dulay,et al.
TRAcME: Temporal Activity Recognition Using Mobile Phone Data
,
2008,
2008 IEEE/IFIP International Conference on Embedded and Ubiquitous Computing.