Fusion of Classification with Hybrid Optimization Technique to Predict Diabetes
B.Gomathi1, R.Sujatha2, T.Padma3
1Gomathi B*, Assistant Professor, Department of Computer Science, Shri Shankarlal Sundarbai Shasun Jain College for Women, Chennai, India.
2Sujatha R, Assistant Professor, Department of Computer Science, PSG College of Arts & Science, Coimbatore, India.
3Padma T, Professor, Department of Computer Applications, Sona College of Technology, Salem, India.
Manuscript received on February 01, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 30, 2020. | PP: 927-929 | Volume-9 Issue-3, February, 2020. | Retrieval Number: C5418029320/2020©BEIESP | DOI: 10.35940/ijeat.C5418.029320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The main objective of this paper is to predict diabetes which is growing like an epidemic in India. The key focus is to envisage diabetic and normal patient using classification approach .Fusion of SVM enhanced with hybrid optimization of PSO-BAT algorithm is proposed. Classification techniques used namely Multilayer Perceptron (MLP), Sequential Minimal Optimization (SMO), Random Forest (RF) are compared with our novel approach SVM enhanced with hybrid optimization of PSO-BAT algorithm. The accuracy is increased using the combination technique. The benchmark diabetic dataset, PIMA Indian Diabetes Dataset from UCI machine learning repository is utilized for the research. To improve the efficiency more, classifiers such as Precision, Recall and f-measure is used.
Keywords: BAT, Classification, Fusion, PSO, SVM