Time-Based Location Prediction Technique for Wireless Cellular Networks
In this paper, we are introducing a time-based location prediction technique for wireless cellular networks. This technique is based on a two dimensional sequence mining algorithm. We have taken concepts of data partitioning methods and modified SPADE algorithm (Sequential PAttern Discovery using Equivalence classes), which has been implemented over a mining model known as mining mobile sequential patterns, and called Dynamic MobileSPADE algorithm. This algorithm mines for mobile sequential patterns based on dynamic-length item sets. In mining for mobile sequential patterns in a mobile environment, we use base stations ID data from a dataset constructed by the reality mining project at the MIT. Experiments were conducted to study and evaluate the performance of the proposed techniques. The experimental results show that the proposed technique is promising and it can be used effectively to predict future locations of mobile users with high accuracy using the generated mobile sequential patterns.
- 1.Nguyen SN, Orlowska ME (2006) A further study in the data partitioning approach for frequent itemsets mining. In: 17th Australasian database conference, Hobart, Australia, pp 31–36Google Scholar
- 2.Savasere A, Omiecinski E, Navathe S (1995) An efficient algorithm for mining association rules in large databases. In: Proceedings of the 21st very large databases conference, Zurich, Switzerland, pp 432–444Google Scholar
- 3.Zaki M (2001) SPADE: an efficient algorithm for mining frequent sequences. Mach Learn J 42(1/2):31–60Google Scholar
- 4.Eagle N, Pentland A (2006) Reality mining: sensing complex social systems. Pers Ubiquitous Comput 10(4):255–268Google Scholar