Performance of Hybrid Radial Basis Function network: Adaptive Fuzzy K-Means versus Moving k-Means Clustering as centre positioning algorithms on cervical cell precancerous stage classification

摘要: Cervical cancer been known to be the cause of many deaths each year. Screening tests, such as Pap smear test used for detection precancerous stage are able avoid occurrence cervical cancer. However, does have some disappointing disadvantages fact that it has less effective slide preparation and also is laden with human error. Therefore, a computer-aided diagnosis system introduced solution problem. Recently, artificial neural networks widely implemented i.e. classify into normal abnormal cells. In this recent study, network architecture Hybrid Radial Basis Function (HRBF) Adaptive Fuzzy K-Means Clustering (AFKM) asa centre positioning algorithm diagnose Four extracted features cell input data networks, which size nucleus cytoplasm its grey level. Cells from normal, Low-grade Squamous Intraepithelial Lesion (LSIL) High-grade (HSIL) categories training well testing data. The fed randomly via 5-folds cross validation techniques. performance compared HRBF Moving algorithm. proposed produces better accuracy, sensitivity specificity illustrates promising capability improvement.