Paper Details

Weather analysis has been playing its vital role in meteorology and become one of the most challengeableproblems both scientifically and technologically all over the world from the recent years. This research paper carrieshistorical weather data collected locally at South Indian textile city, Coimbatore that was analyzed for useful knowledge byapplying data mining methods. Data includes last five years’ period [2012-2017]. It had been tried to extract useful practicalknowledge of weather data on monthly based historical analysis. This Proposed research work was done using data miningtool called Weka by examining changing patterns of weather parameters which includes maximum temperature, minimumtemperature, wind speed and rainfall. After preprocessing of data and outlier analysis, improved fuzzy K-means clusteringalgorithm and Decision Tree techniques were applied. Two clusters were generated by using improved K-means Clusteringalgorithm with lowest and highest of mean parameters. The result obtained with smallest error (27%) was selected on testdata set. While for the number of rules generated of the given tree was selected with minimum error of 20%. The resultsshowed that for the given adequate set data, these techniques can be used for weather investigation and climate changestudies.

B. Murugesakumar, Dr.K.Anandakumar, Dr. A. Bharathi, “IMPROVED FUZZY K-MEANS CLUSTER ALGORITHM TO ANALYSE WEATHER DATA IN COIMBATORE REGION”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 4, Issue 11, pp. 840-846, November 2017.