Diabetes Diagnosis from Big Data using Fuzzy-Neural Chaotic Tree

Today, diabetes is considered an important disease in the world. The statistics show that this disease is developing worldwide. For this reason, smart and automated systems are considered as a challenge in the medical world. The methods available in computer science meet this need. To date, various methods have been proposed to diagnose and predict diabetes, but there are some errors that researchers are seeking to resolve. Data mining is used as a technical science in identifying and extracting new knowledge of data. In this research, a new method has been developed for categorizing diabetic data, which consists of three parts: the first part is the preprocessing, in which data normalization operations are performed, then the extraction and selection of attributes. Finally, classification operations is done based on the principles of data mining. The classification results can be used to predict diabetes in different individuals. The use of criteria such as sensitivity, specificity, accuracy is used to evaluate the results. The proposed approach is based on the combination of fuzzy-neural in chaotic mode along with K-means tree. The results indicate that the proposed method is more suitable than the previous methods.

کلیدواژه ها:

Diabetes Detection ، Data Mining ، Fuzzy-Neural ، Chaos Theory ، K-means Tree