Paper Title
Visual Data Mining With Pixel Oriented and Parallel Co-Ordinate Techniques on Medical Data

Abstract
Visual data mining as a sculpture and discipline of testing significant discernments out of enormous capacities of data that are inexplicable in another way requires consistent visual data representations. In contrast, traditional data mining techniques are not suitable to process these enormous volumes of data. On the other hand Visual data mining procedures have proven to be of more significance in investigative data analysis and they also have a high potential for mining large datasets. Particularly, biological data have been increasing ecologist are stepping up their determinations in appreciative the biological processes that trigger sickness pathways in the medical contexts. In this paper we evaluate the cancer patient data under visual data mining two popular techniques which are pixel oriented and parallel co-ordinate techniques and the performance is also presents as a graphs below. And also make comparison between two techniques in handling of data and accuracy of results. Data mining is the procedure of finding possibly important examples, affiliations, patterns, arrangements and conditions in information. Key business samples incorporate site access examination for enhancements in e-trade promoting, misrepresentation recognition, screening and examination, retail site or item investigation, and client division. Information mining systems can find data that numerous conventional business investigation and measurable strategies neglect to convey. Furthermore, the use of information mining methods further endeavors the estimation of information distribution center by changing over costly volumes of information into important resources for future strategic and vital business improvement. Administration data frameworks ought to give propelled abilities that give the client the ability to ask more modern and applicable inquiries. It engages the right individuals by giving the particular data they require. Numerous learning revelation applications, for example, on-line administrations and internet applications, require precise mining data from information that progressions all the time. In such a situation, successive or intermittent upgrades may change the status of a few standards found before. More data ought to be gathered amid.