Performance Analysis of Artificial Neural Network with Decision Tree in Prediction of Diabetes Mellitus

Autor: J. K. Alhassan, B. Attah, S. Misra
Jazyk: angličtina
Rok vydání: 2015
Předmět:
DOI: 10.5281/zenodo.1107932
Popis: Human beings have the ability to make logical decisions. Although human decision - making is often optimal, it is insufficient when huge amount of data is to be classified. Medical dataset is a vital ingredient used in predicting patient's health condition. In other to have the best prediction, there calls for most suitable machine learning algorithms. This work compared the performance of Artificial Neural Network (ANN) and Decision Tree Algorithms (DTA) as regards to some performance metrics using diabetes data. WEKA software was used for the implementation of the algorithms. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were the two algorithms used for ANN, while RegTree and LADTree algorithms were the DTA models used. From the results obtained, DTA performed better than ANN. The Root Mean Squared Error (RMSE) of MLP is 0.3913 that of RBF is 0.3625, that of RepTree is 0.3174 and that of LADTree is 0.3206 respectively.
{"references":["G. Karegowda, A. S. Manjunath, and M. A. Jayaram, \"Application of\nGenetic Algorith Optimized Neural Network Connection Weighs For\nMedical Diagnosis of Pima Indians Diabetes,\" International Journal on\nSoft Computing (IJSC), Vol. 2 No. 2. 2011, pp. 10-15.","P. Saurabh, \"Mining Educational Data to Reduce Dropout Rates of\nEngineering Student\", International Journal of Information Engineering\nand Electronic Business, 2012. Downloaded from http://www.mecspress.\norg on Sept., 2014.","Y. Radhika, and M. Shashi, \"Atmoshere Temperature Prediction using\nSupport Vector Machines,\" International Journal of Computer Theory\nand Engineering, Vol. 1 No.1, 2009, pp. 55 – 57.","Z. Bobby, World Health Organization Report on Nigerian Diabetes,\nDownloaded from http://sunnewsonline.com/new/3-9m-nigeriansdiabetic-\nsays-report/ on 24th July, 2015","J. Maroco, D. Silva, M. Guerreiro, A. de Mendonça, I. Santana.\n\"Prediction of dementia patients: A comparative approach using\nparametric vs. non parametric classifiers,\" in Proc. XIX Congresso\nAnual da Sociedade Portuguesa de Estatistica, Portuguese, 2011.","Kurt, M. Ture, A.T. Kurum. \"Comparing performances of logistic\nregression, classification and regression tree, and neural networks for\npredicting coronary artery disease\". Expert Syst Appl, vol. 34, pp. 366-\n374, 2008.","Endo, T. Shibata, H. Tanaka. \"Comparison of seven algorithms to\npredict breast cancer survival\". Biomedical Soft Computing and Human\nSciences, vol. 13, pp. 11-16, 2008.","M. Ture, I Kurt, A.T. Kurum, K. Ozdamar. \"Comparing classification\ntechniques for predicting essential hypertension\". Expert Syst Appl, vol.\n29, pp. 583-588, 2005.","Morteza, M. Nakhjavani, F. Asgarani, F.L.F Carvalho, R. Karimi, A.\nEsteghamati. \"Inconsistency in albuminuria predictors in type 2\ndiabetes: A comparison between neural network and conditional logistic\nregression\". Translational Research, vol. 161, pp. 397-405, 2013.\n[10] X. Meng, Y. Huang, D. Rao, Q. Zhang, Q. Liu. \"Comparison of three\ndata mining models for predicting diabetes or preetes by risk factors\".\nKaohsiung J Med Sci, vol. 29, pp. 93-99, 2013.\n[11] M. Ture, Z. Akturk, I. Kurt, N. Dagdeviren. \"The effect of health status,\nnutrition, and some other factors on low school performance using\ninduction technique\". Trakya Univ Tip Fak Derg, vol. 23, pp. 28-38,\n2006."]}
Databáze: OpenAIRE
Externí odkaz: