Latitude, longitude, and beyond: mining mobile objects' behavior.
PhD thesis, University of Twente.
CTIT Ph.D.-thesis series No. 15-366
Full text available as:
Official URL: http://dx.doi.org/10.3990/1.9789036538923
Rapid advancements in Micro-Electro-Mechanical Systems (MEMS), and wireless communications, have resulted in a surge in data generation. Mobility data is one of the various forms of data, which are ubiquitously collected by different location sensing devices. Extensive knowledge about the behavior of humans and wildlife is buried in raw mobility data. This knowledge can be used for realizing numerous viable applications ranging from wildlife movement analysis, to various location-based recommendation systems, urban planning, and disaster relief.
With respect to what mentioned above, in this thesis, we mainly focus on providing data analytics for understanding the behavior and interaction of mobile entities (humans and animals). To this end, the main research question to be addressed is:
How can behaviors and interactions of mobile entities be determined from mobility data acquired by (mobile) wireless sensor nodes in an accurate and efficient manner?
To answer the above-mentioned question, both application requirements and technological constraints need to be considered. On the one hand, applications requirements call for accurate data analytics to uncover hidden information about individual behavior and social interaction of mobile entities, and to deal with the uncertainties in mobility data. Technological constraints, on the other hand, require these data analytics to be efficient in terms of their energy consumption and to have low memory footprint, and processing complexity.
The contributions of this thesis are:
• Mining periodic behavior from mobility data: Periodic behaviors are prevalent for both humans and wildlife. We propose a technique for identifying periodic behaviors and extracting periodic patterns from streaming mobility data.
• Modeling mobility data: A general movement model can be used to identify frequent patterns in the mobility data using the higher-level semantic they represent. We model trajectories both deterministically and probabilistically to relate them to the paths and stay-points they represent. Our deterministic approach uses collective knowledge of trajectories (on the move) to relate trajectories to the path taken by the mobile entities. Our probabilistic approach, models trajectories (on stay points and on the move) using state-space modeling techniques.
• Mining social ties only from mobility data: We study the possibility of extracting social context from mobility data. For this purpose, we propose two information theoretic indicators to measure the correlation between visits to different places based on the purpose of visit.
• Model-based trajectory compression and adaptive sampling: We propose two techniques to use the patterns discovered by trajectory modeling to reduce data redundancy and uncertainty. Thereby, we increase the lifetime of the location acquisition devices. Our first technique is a light, online, model-based trajectory compression algorithm for decreasing the number of transmitted samples. Our second approach is a model based adaptive sampling algorithm, which increases the lifetime of the location acquisition devices by reducing both the number of samples acquired and transmitted.
Techniques developed in the thesis were evaluated using five different mobility datasets collected from both wildlife and humans. These datasets are: i) small-scale dataset collected by a wireless sensor node carried by people, ii) small-scale dataset collected from capricorns, iii) large-scale Geolife dataset from Microsoft research, iv) large-scale Mobile Data Challenge dataset from Nokia, and v) a synthetic dataset produced with a movement test sequence generator.
|Item Type:||PhD Thesis|
|Supervisors:||Havinga, P.J.M. and Skidmore, A.K.|
|Assistant Supervisors:||Meratnia, N.|
|Research Group:||EWI-PS: Pervasive Systems|
|Uncontrolled Keywords:||Data mining, mobility data analysis, Big Data, ubiquitous computing|
|Deposited On:||28 October 2015|
Export this item as:
To correct this item please ask your editor
Repository Staff Only: edit this item