GA-based Feature Selection with ANFIS Approach to Breast Cancer Recurrence
نویسنده
چکیده
Automatic disease diagnosis systems are important for medical fields. These systems have been used to help doctors to make better diagnosis. Breast cancer is a very common class of cancers among women. In this paper, we focus on breast cancer recurrence problem, hybridizing two methodologies, Genetic Algorithm (GA) and Adaptive Neuro Fuzzy Inference System (ANFIS), to develop a good diagnosis system. GA has been used as a selection algorithm to find the best features, whilst ANFIS has been used as a classifier algorithm. The robustness of the proposed hybrid methodology is examined using classification accuracy, sensitivity, and specificity. The proposed hybrid algorithm has achieved accuracy of 88% for training dataset and 71% for testing. The results demonstrate the effective interpretation and point out the ability to design a good diagnosis system.
منابع مشابه
Feature selection using genetic algorithm for breast cancer diagnosis: experiment on three different datasets
Objective(s): This study addresses feature selection for breast cancer diagnosis. The present process uses a wrapper approach using GA-based on feature selection and PS-classifier. The results of experiment show that the proposed model is comparable to the other models on Wisconsin breast cancer datasets. Materials and Methods: To evaluate effectiveness of proposed feature selection method, we ...
متن کاملExtracting Predictor Variables to Construct Breast Cancer Survivability Model with Class Imbalance Problem
Application of data mining methods as a decision support system has a great benefit to predict survival of new patients. It also has a great potential for health researchers to investigate the relationship between risk factors and cancer survival. But due to the imbalanced nature of datasets associated with breast cancer survival, the accuracy of survival prognosis models is a challenging issue...
متن کاملGenetic Algorithm Based Feature Selection and Unbiased Protocol for Classification of Breast Cancer Datasets
Feature selection is an essential pre-requisite before classification and diagnosis of a cancer disease. Several studies have been done using Genetic Algorithm (GA) and machine learning techniques that aim to select the relevant features by wrapping the classification algorithm as GA fitness function. However, the performance of GA based feature selection is always focusing on a same datasets t...
متن کاملSoft Tissue Modeling Using ANFIS for Training Diagnosis of Breast Cancer in Haptic Simulator
Soft tissue modeling for the creation of a haptic simulator for training medical skills has been the focus of many attempts up to now. In soft tissue modeling the most important parameter considered is its being real-time, as well as its accuracy and sensitivity. In this paper, ANFIS approach is used to present a nonlinear model for soft tissue. The required data for training the neuro-fuzzy mo...
متن کاملFeature selection using genetic algorithm for breast cancer diagnosis: experiment on three different datasets
OBJECTIVES This study addresses feature selection for breast cancer diagnosis. The present process uses a wrapper approach using GA-based on feature selection and PS-classifier. The results of experiment show that the proposed model is comparable to the other models on Wisconsin breast cancer datasets. MATERIALS AND METHODS To evaluate effectiveness of proposed feature selection method, we em...
متن کامل