Hybrid Model Of Frfs And Rnn

2357 Words Sep 30th, 2016 10 Pages

Hybrid intelligent systems are vital research areas for solving complex and multi-phase problems. Medical diagnostic field is characterized by several sequential and related processes. Knowledge representation of diseases is the essential goal of any medical system. The main sub-procedures are data selection, data preprocessing, data transformation, pattern/rule induction and knowledge interpretation. Figure 4 introduces the main steps of knowledge representation system.

Figure 4: Knowledge Extraction Framework

The proposed model is a fuzzy rough hybrid system for diagnosing breast cancer patients. The diagnoses system is composed of preprocessing and classification phases. The hybrid is consisted of three main sub modules. The first sub module is responsible for the selection process. It preprocesses the data sets by eliminating the irrelative attributes. The framework utilizes a fuzzy rough algorithm to handle the uncertainty nature of the medical data. The second sub module produces an intelligent classifier of the diseases. It uses the rough neural network intelligence to learn from the uncertain reduced data set. After training, the rough neural network becomes the intelligent classifier of the unseen cases to predict their medical condition of the illness. The third sub module measures the accuracy and time complexities of the intelligent classifier by the test data set. Figure 5 shows the main sub modules and their…
Open Document