Diagnosing breast cancer with an improved artificial immune recognition system

Breast cancer is the top cancer in women worldwide. Scientists are looking for early detection strategies which remain the cornerstone of breast cancer control. Consequently, there is a need to develop an expert system that helps medical professionals to accurately diagnose this disease. Artificial immune recognition system (AIRS) has been used successfully for diagnosing various diseases. However, little effort has been undertaken to improve its classification accuracy. To increase the classification accuracy, this study introduces a new hybrid system that incorporates support vector machine, fuzzy logic, and real tournament selection mechanism intoAIRS. TheWisconsin Breast Cancer data set was used as the benchmark data set; it is available through the machine learning repository of the University of California at Irvine. The classification performance was measured through tenfold cross-validation, student’s t test, sensitivity Communicated by V. Loia. B Mahmoud Reza Saybani [email protected] B Shahaboddin Shamshirband [email protected] 1 Department of Information Systems, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kula Lumpur, Malaysia 2 Department of Computer Networks, Markaz-e Elmi Karbordi Bandar Abbas 1, University of Applied Science, Bandar Abbas, Iran 3 Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia 4 Department of Automation and Applied Informatics, Aurel Vlaicu University of Arad, 310130 Arad, Romania and specificity. With an accuracy of 100%, the proposed method was able to classify breast cancer dataset successfully.