Optimization of neural network using cuckoo search for the classification of diabetes

• Main Authors: Abubakar, Adamu, Shuib, Liyana, Chiroma, Haruna
• Format: Article
• Language: English; English
• Published: American Scientific Publishers 2015
• Subjects: Q350 Information theory
• Online Access: http://irep.iium.edu.my/51917/1/12CTN12-4713-NEWNewNew.pdf; http://irep.iium.edu.my/51917/7/51917-Optimization%20of%20neural%20network%20using%20cuckoo%20search%20for%20the%20classification%20of%20diabetes_SCOPUS.pdf; http://irep.iium.edu.my/51917/; http://www.ingentaconnect.com/contentone/asp/jctn/2015/00000012/00000012/art00109
• Institution: Universiti Islam Antarabangsa Malaysia

Available records show that over 80% of the patient suffering from diabetes die from heart or blood diseases. Total cure for the diabetes is currently not available. In this paper, we proposed diabetes classifier based on the cuckoo search algorithm (CS) and Neural Network (NN). The weights and bias of the NN was trained using the CS to deviate from being stuck in local minima. The high dimension of the features in our dataset triggered the study to extract the critical features using principal component analysis. The extracted features were used to built a classifier based on the NN and the CS for classifying potential diabetes patients. The propose diabetes classifier performance was compared to the classifiers built based on artificial bee colony and genetic algorithm. Simulation results show that the proposed approach converges faster to the optimum solution than the comparative classifiers. Comparative study of the approach proposed and previous methods, further proved the effectiveness of our method. The classifier has provided promising classification result in the classifying of potential diabetic patients. The classifier have the capability of automatically diagnosing possible diabetic patients. This can be of help to the physicians in taken decision about the status of a diabetic patient