COMPARATIVE ANALYSIS OF THYROID DISEASE USING FUZZY C AND K MEANS ALGORITHMS

Abstract

Data mining is a process which involves sorting large data sets and spots patterns and relationships which will help solve problems through data analysis. Data mining techniques plus tools enable big enterprises to forecast future coming trends and is then able to make better decisions make more-informed business decisions hence this study. Thyroid disease is a medical problem that occurs when one’s thyroid fails to produce enough hormones. This disease is known to affect everyone of all ages and all genders.in order to identify these disorders are detected by blood tests are taken, and are however difficult to analyze because of the vast amounts of blood samples of data to be forecasted. because of this barrier this study allows us to compare two algorithms to determine the best in results output enabling us to have a quick reaction to these disorders. Thyroid diseases have become the most common especially amongst African in the African continent with continent with 68- 72%population affected while 4-6% affected yearly are women between the age of 18-25. The causes of thyroid diseases are different which further leads to different types of thyroid diseases and resulting disorders from just the popular known goiter to a cancerous goiter. The diseases are further classified into two the normal thyroid and the abnormal thyroid. This paper will be of comparison analysis of thyroid diseases using the unsupervised algorithms k means and fuzzy c in the African continent. In addition, the imagining in medical systems for thyroid diseases has a lot of research today. Effects caused by thyroid diseases are known to be uncomfortable and when managed well they may result positively. Hence when it is a simple goiter is can be cured naturally, but when it becomes cancerous then it may result in diseases like myxema coma. In order to cure this the measures like k means or fuzzy c keywords cluster, fuzzy, kmeans, Africa, thyroid, diseases