Abstract A decision tree classifier called Mixed Mode Database Miner (MMDBM) which is used to classify large number of datasets with large number of attributes is implemented with different types of sorting techniques (quick sort and radix sort) in both Central Processing Unit (CPU) computing and General-Purpose computing on Graphics Processing Unit (GPGPU) computing and the results are discussed. This classifier is suitable for handling large number of both numerical and categorical attributes. The MMDBM classifier has been implemented in CUDA GPUs and the code is provided. We used the parallelized algorithms of the two sorting techniques on GPU using Compute Unified Device Architecture (CUDA) parallel programming platform developed by NVIDIA corporation. In this paper, we have discussed an efficient parallel (quick sort and radix sort) sorting procedures on GPGPU computing and compared the results of GPU to the CPU computing. The main result of MMDBM is used to compare the classifier with an existing CPU computing results and GPU computing results. The GPU sorting algorithms provides quick and exact results with less handling time and offers sufficient support in real time applications.

References

[1] AI-hegami A., Pruning Based Interestingness of Mined Classification Patterns, The International Arab Journal of Information Technology, vol. 6, no. 4, pp. 336-343, 2009.

[2] Alnihoud J. and Mansi R., An Enhancement of Major Sorting Algorithms, The International Arab Journal of Information Technology, vol. 7, no. 1, pp. 55-62, 2010.

[3] Akg ek mer., A Rule Induction Algorithm for Knowledge Discovery and Classification, Turkish Journal of Electrical Engineering and Computer Science, vol. 21, no. 5, pp.1223-1241, 2013.

[4] Cederman D. and Tsigas P., GPU-Quicksort: A Practical Quicksort Algorithm for Graphics Processors, Journal of Experimental Algorithmics, vol. 14, no. 4, pp. 1-22, 2009.

[5] Chiu C., Luo G., and Yuan S., A Decision Tree using CUDA GPUs, in Proceeding of the 13th International Conference on Information Integration and Web-based Applications and Services, Ho Chi Minh, pp. 399-402, 2011.

[6] Chandra B. and Paul P., Moving Towards Efficient Decision Tree Construction, Information Sciences, vol. 179, no. 8, 1059-1069, 2009.

[7] Ganesan P., Sivakumar S., and Sundar S., A Comparative Study on MMDBM Classifier Incorporating Various Sorting Procedure, Indian Journal of Science and Technology, vol. 8, no. 9, pp. 868-874, 2015.

[8] Mehta M., Agarwal R., and Rissanen J., SLIQ: A Fast Scalable Classifier for Data Mining, in Proceeding of 5th International Conference on Extending Database Technology, Avignon, pp. 18-32, 1996.

[9] Munshi A., OpenCL: Parallel Computing on the GPU and CPU, in Proceeding of 35st International Conference and Exhibition on Computer Graphics and Interactive Techniques, California, 2008.

[10] Nasridinov A., Lee Y., and Park Y., Decision Tree Construction on GPU: Ubiquitous Parallel Computing Approach, Computing, vol. 96, no. 5, pp.403-413, 2014.

[11] Nguyen H., GPU Gems 3, Addison-Wesley Professional, 2007.

[12] Nickolls J., Buck I., and Garland M., Scalable Parallel Programming with CUDA, ACM Queue, vol. 6, no. 2, pp. 40-53, 2008.

[13] NVIDIA Corporation, CUDA Best Practices Guide, NVIDIA Corporation, 2010.

[14] NVIDIA Corporation, CUDA C Programming Guide, NVIDIA Corporation, 2014.

[15] Panchatcharam M., Sundar S., Vetrivel V., Axel Klar., and Tiwari S., GPU Computing for Meshfree Particle Method, International Journal of Numerical Analysis and Modeling, Series B, vol. 4, no.4, pp. 394-412, 2013.

[16] Pospichal P., Jaros J., and Schwarz J., Parallel Genetic Algorithm on the CUDA Architecture, in Proceeding of International Conference on Applications of Evolutionary Computation, Istanbul, pp. 442-451, 2010.

[17] Sanders J. and Kandrot E., CUDA by Example: An Introduction to General-Purpose GPU Programming, Addison-Wesley, 2011.

[18] Shafer J., Agrawal R., and Mehta M., SPRINT: A Scalable Parallel Classifier for Data Mining, in Proceeding of the 22th International Conference on Very Large Data Bases, San Antonio, pp. 962-969, 1996.

[19] Sundar S., Srikanth D., and Shanmugam M., A New Predictive Classifier for Improved Performance in Data Mining: Object Oriented Design and Implementation, in Proceeding of the International Conference on Industrial Mathematics, Bombay, pp. 491-514, 2006.

[20] Telbany M., Warda M., and Borahy M., Mining the Classification Rules for Egyptian Rice Diseases, The International Arab Journal of Information Technology, vol. 3, no. 4, pp. 303- 307, 2006. 906 The International Arab Journal of Information Technology, Vol. 14, No. 6, November 2017 Sivakumar Selvarasu obtained his Msc, Computer science from Periyar E.V.R College and M.Phil from St.Joseph's College of Bharathidasan University, India, Now he is doing Ph.D in Department of Mathematics, College of Engineering Guindy Campus, Anna University, Chennai, India. His research program focuses on Data mining and areas of interest are parallel computing (GPU), Classification and analysis, Image processing and CUDA Programming. Ganesan Periyanagounder is working as a Professor of Emeritus in the Department of Mathematics, College of Engineering Guindy Campus, Anna University, Chennai, India. He received his Ph.D degree from Indian Institute of Technology, Mumbai, India. He has more than 30 years of experience in academic and research. His areas of interest include Computational Heat Transfer, Theoretical computer science and Object Oriented programming. He has more than 82 publications in Journals and Conferences. Sundar Subbiah is working as a Professor in the Department of Mathematics, Indian Institute of Technology, Madras, Chennai, India. He received his Ph.D degree from Indian Institute of Technology, Chennai, India. He has 26 years of experience in academic and research. His areas of interest include Numerics for PDEs, Mathematical Modeling & Numerical Simulation, GPU Computing and Data mining. He has guided over 12 Ph.D students and 75 M.Tech / MSc students. He has more than 80 publications in Journals and conducted 11 International Conferences and Workshops.