• Pranita Paradkar
• Sapna Choudhry

Automated disease detection from human body parameters has been a topic of medical research for more than a decade now. Many researchers have proposed various techniques for performing this task, but most of the proposed approaches work under certain disease conditions, and there are very few techniques which produce accurate results for multiple diseases. In the proposed approach, we are detecting 4 diseases and using a hybrid of support vector machine (SVM), k-Nearest Neighbour (kNN) and Naive Bayes classifiers in order to evaluate the diseases from input human body parameters. The evaluation results show more than 15% improvement in classification accuracy when compared to kNN and Naive Bayes classifiers individually. The proposed system can be extended for any number of diseases.

disease detection, kNN, SVM, Naive Bayes, hybrid, multiple diseases

"Improving the Accuracy of Multiple Disease Detection System Using Novel Hybrid Classifier", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 7, page no.862-867, July-2018, Available :http://www.jetir.org/papers/JETIR1807139.pdf

"Improving the Accuracy of Multiple Disease Detection System Using Novel Hybrid Classifier", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 7, page no. pp862-867, July-2018, Available at : http://www.jetir.org/papers/JETIR1807139.pdf