International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064

Downloads: 106 | Views: 192

Research Paper | Computer Science & Engineering | India | Volume 5 Issue 2, February 2016

An Improved Mining of Biomedical Data from Web Documents Using Clustering

Nikita Gupta [3] | Gunjan Pahuja

Abstract: Now a days web is the main source of information in every field. Web is also expanding exponentially day by day. To get the relevant information is very time consuming and is not a very easy task. Mainly users go for the various search engines to search any information. But sometimes search engines are not able to give the useful results as most of the web documents are present in unstructured manner. Data mining is extraction of information from large database. Text mining uses the many techniques of data mining. In web, biomedical documents are also increasing at a very fast pace but most of them are unstructured text. These documents can be very helpful in diagnostics, treatment and prevention of any disease. There are we millions of documents on internet about a specific term so to obtain a relevant document is very difficult. The goal of this is to apply text mining techniques to retrieve useful biomedical web documents. Here a more efficient mechanism is proposed which uses the optimised K-means clustering algorithm where it can group the similar documents in one place. This approach will help the user to get all the relevant biomedical documents at one place. On comparing our approach with the original k-means algorithm and found that our algorithm on an average giving 99.06 % F-measure.

Keywords: Data Mining, Biomedical Data, Clustering, K-means

Edition: Volume 5 Issue 2, February 2016,

Pages: 1396 - 1400

How to Download this Article?

Type Your Valid Email Address below to Receive the Article PDF Link

Verification Code will appear in 2 Seconds ... Wait