摘要：The past decades have brought many remarkable researches in diagnosis of disease. The interpretation of the problems in medicine is a significant and tedious task. The detection of heart problem from various factors or symptoms is an issue which is not free from false presumptions often accompanied by unpredictable effects. Thus the effort to utilize knowledge and experience of numerous specialists and clinical data of patients collected earlier to facilitate the interpretation process is considered as a valuable asset. This paper introduces an efficient approach to predict heart stroke risk levels from the heart problem dataset by using machine learning technique. Earlier researchers have used k-means based mafia algorithm and the accuracy was 74%. When modifying the algorithm with fuzzy c-means, the accuracy is increased to 89%. There is a 15% improvement while comparing to the earlier algorithm..
其他摘要：The past decades have brought many remarkable researches in diagnosis of disease. The interpretation of the problems in medicine is a significant and tedious task. The detection of heart problem from various factors or symptoms is an issue which is not free from false presumptions often accompanied by unpredictable effects. Thus the effort to utilize knowledge and experience of numerousspecialists and clinical data of patients collected earlier to facilitate the interpretation process is considered as avaluable asset. This paper introduces anefficient approach to predict heart strokerisk levels from the heart problem dataset by using machine learning technique. Earlier researchers have used k-meansbased mafia algorithm and the accuracy was 74%. When modifying the algorithm with fuzzy c-means, the accuracy is increased to 89%. There is a 15% improvement while comparing to the earlier algorithm.
关键词：Machine learnin;Heart Problem;Fuzzy C-means;Apriori Algorithm and ID3 Algorithm
