Data Mining and Mobility Data Warehousing

------------------------------------------♦----------------------------------------- INTRODUCTION

The knowledge of phenomenon related to movement not only of people and vehicles but also of animals and other moving objects – has always been a key concerns in many areas of scientific study or social analysis. Many applications track the movement of mobile objects, using location- gaining technologies such as Global Positioning System (GPS), Global System for Mobile Communications (GSM) etc., and it can be symbolized as sequences of time stamped locations. [7,8] TD consists of movements of objects, which record their position as it evolves over time, the concept of indecision appears in various ways; data vagueness due to sampling and/or measurement errors, indecision in querying and answering, uncertainty by purpose during pre-processing for preserving secrecy, and so on. Although indecision is inherent in TD, to the best of our knowledge there is no related work in the database literature that studies its consequence in the knowledge discovery process [8].

Moving objects are objects that change their location and/or shape over time. Moving objects are classified into 2 main categories moving points (e.g. cars, buses, planes, mobile users, etc.), and moving regions (e.g. hurricanes, forests fires, etc.). Being designed to deal with new data, moving objects databases required new techniques that were lately investigated in several research works. Modeling moving objects was one of those issues. Modeling moving objects was introduced in [1- 4] where discrete, continuous, and constraint models were presented. Also, indexing of moving objects is still considered a crucial research direction. Inspired by the importance of spatial data warehouses, several research works studied this area. In [5] the authors proposed a method to perform a selective materialization based on the relative access frequency of the sets of mergeable spatial regions, that is, the sets of mergeable spatial regions should be pre-computed before accessed. In [6] the authors classified the spatial data warehouses’ dimensions in to 3 categories: descriptive, temporal, and spatial.

Incremental’ means changes in the accessible database i.e. placing of new data into the database or removal of existing data from the database. This is sometimes called ‘% of delta change in the database’. This is a significant issue now a day. Because at present most of the databases are dynamic in nature. So, we need to develop some new data mining algorithms which can grip the dynamic feature of the database resourcefully and effectively. The objective of incremental data mining algorithms is to reduce the scanning and calculation attempt for newly added records. Here we get better the competence of newly added record updating problem. These are the few prime factors that cause to apply the incremental Mining [9-10].

In this paper we found that the moving object congregation prototype represents an incident that involves enabling the prediction of anomalies in traffic system, congregation of moving objects. Effectively and efficiently discovering the specific congregation pattern turns to be a lingering challenging issue since the large number of moving objects generates a large quantity of trajectory data.

Available online at www.ignited.in Page 2

[1] B. X. O. Wolfson, S. Chamberlain, and L. Jiang, "Moving objects databases: issues and solutions," in Proc. Int. Conf. on Statistical and Scientific Database Management, 1998, pp. 111–122. [2] R. H. G. M. Erwig, M. Schneider, and M. Vazirgiannis, "Spatio-temporal data types: an approach to modeling and querying moving objects in databases," GeoInformatica, vol. 3, pp. 269-296, 1999. [3] O. W. A. P. Sistla, S. Chamberlain, and S. Dao, "Modeling and querying moving objects," in Proc. Int. Conf. on Data Engineering, 1997, pp. 422–432. [4] R. H. G. Martin Erwig, Markus Schneider, Michalis Vazirgiannis, "Abstract and Discrete Modeling of Spatio-Temporal Data Types.," in Proceedings of the 6th ACM international symposium on Advances in geographic information systems, New York, USA, 1998, pp. 131-136. [5] N. S. Jiawei Han, and Krzysztof Koperski, "Selective materialization: An efficient method for spatial data cube construction," in PAKDD ’98: Proceedings of the Second Pacific-Asia Conference on Research and Development in Knowledge Discovery and Data Mining, London, UK, 1998, pp. 144– 158. [6] T. M. Y. Bedard, and J. Han, "Fundamentals of spatial data warehousing for geographic knowledge discovery," in Geographic Data Mining and Knowledge Discovery, 2001, pp. 53–73. [7] Ajaya Kumar Akasapu, Lokesh Kumar Sharma, G. Ramakrishna in Volume 9– No.5, November 2010, “Efficient Trajectory Pattern Mining for both Sparse and Dense Dataset”, International Journal of Computer Applications (0975 – 8887). [8] Applications Volume-9 –No. 5. Jae-Gil Lee, Jiawei Han & Kyu-Young Whang” Trajectory Clustering: A Partition-and-Group Framework in University of Illinois at Urbana-Champaign KAIST Sonal Athavale1 Neelabh Sao2 “Data Mining on Moving Object Trajectories” IJCSET |April 2012| Vol 2, Issue 4,1040-1042 [9] Data Mining concepts and techniques by Jiawei Han and Micheline Kamber, Morgan Kaufmann (publisher) from chapter-7 ‘Cluster analysis’, ISBN: 978-1-55860-901-3, 2006. [10] Dunham, M.H., Data Mining: Introductory And Advanced Topics, New Jersey: Prentice Hall, ISBN-13: 9780130888921. 2003.