Abstract Cardiac illness is the most infectious disease in the world currently for individuals of all ages. An essential necessity to anticipate heart illness correctly in a short period. Problems that are both complex and persistent are best tackled using optimization methods. The majority of applications of machine learning and clustering techniques are in the field of cardiovascular disease prediction. When making predictions, clustering makes heavy use of classification algorithms. For data preparation and cleaning, the hamming distance feature selection approach is suggested in this article for use across various heart illness datasets. In order to provide a reliable forecast of heart illness, a bio-inspired clustering model like Bilinear Fuzzy K-means Clustering (BFKC) is used with the Chaotic Drift Cuckoo Search Optimization Algorithm (CDCSOA). The findings show that BFKC-trained CDCSOA performs well, with an accuracy of 95 percent.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|