A Framework for Data Mining Visualization using Cluster Analysis: An Experimental Study on HIV-AIDS Datasets

• Main Authors: Syahrul Nizam, Junaini, Huspi, S.H, Mat, A.R, Noor Alamshah, Bolhassan
• Format: Conference or Workshop Item
• Language: English
• Published: Proceedings of the International Conference on Man-Machine Systems (ICoMMS 2006), 15-16 September 2006, Langkawi, Malaysia 2006
• Subjects: T Technology (General)
• Online Access: http://ir.unimas.my/id/eprint/1188/1/ICOMMS-169%2BFINAL%2B-%2BIRIS.pdf; http://ir.unimas.my/id/eprint/1188/
• Institution: Universiti Malaysia Sarawak

With a need for rational selection of a highly needed bio-informatics-related data, a technique to select, process and visualize the data is crucial. Through visualization, certain hidden form of knowledge can be achieved. Visual data exploration is really useful when little is known about the data and the exploration goals are vague. In this paper we present the method to be developed and implemented in a system prototype that will be able to produce an interactive visualization. The objective of this paper is twofold. First, we would like to investigate which visual data mining technique is the most effective for conveying and understanding bioactivity-related data visualization. Second, to explore new techniques to present and visualize the data as well as to validate the techniques by creating prototype of visualization tools to display and analysis the data. We develop a new framework using clustering technique for visualization and model the data. The dataset that will be used in our study is a subset of a particular AIDS dataset. For this study, 1000 molecules will be tested and analyzed. This paper explains an ongoing project.