@article{Hakizimana_Cheruiyot_Kimani_Nyararai_2017, title={A Hybrid Based Classification and Regression Model for Predicting Diseases Outbreak in Datasets}, volume={27}, url={https://ijcjournal.org/index.php/InternationalJournalOfComputer/article/view/1061}, abstractNote={<p>Nowadays, it has been noted that using the application of data mining techniques for predicting the outbreak of the disease has been permitted in the health institutions which have relative opportunities for conducting the treatment of diseases. The main target of this paper is to develop a hybrid based classification and regression model for diseases outbreak prediction in datasets. In this view, the mixture of FT, Random Forest, Naïve Bayes Multinomial, SMO, IB1, Simple Logistic and Bayesian Logistic Regression are applied to develop this hybrid model. Accordingly, in hybrid model from this paper there is a core achievements of getting an enhancement as the results described from experiments for combination of more than one Algorithms or methods classifier models discovered that some Algorithms  can boost or enhance others through hybrid so that  they become more strong significant basing on the accuracy of 100% as output results from hybrid training  and  with the  accuracy of 75% as output results  from hybrid evaluation and based on other  metrics measurement described on tables 4.1,4.2 and figures 4.1,4.2.</p>}, number={1}, journal={International Journal of Computer (IJC)}, author={Hakizimana, Leopord and Cheruiyot, Prof. Wilson Kipruto and Kimani, Prof. Stephen and Nyararai, Mlambo}, year={2017}, month={Sep.}, pages={69–83} }