Main Article Content


Drug analysis is important for recommendation disease oriented treatment. In recent days drug combination is improperly suggest to patients without knowing the disease factor. Due to non-relation drug patterns the patients are inse4cure to affect side effects.  In most researchers implementing machine learning concepts based on big data analytics using different algorithms like, decision tree, random forest, and logical process. But in recognition to identify the relation is failed because of improper feature analysis and classifier value results inaccuracy. To resolve this problem we propose an efficient feature selection based on optimized decision tree model and implemented with support vector machine to classify the drug relation to make effective recognition class for patients. Initially the preprocessing was carried to normalize the dataset to reduce the Nosie. Then drug margin impact rate is estimated to find the relational margins. Then feature selection was done by decision and tree and classification was carried out by SVM. The classifier produce higher result in precision, recall rate, f-measure with low false measure. This proposed system achieves high performance compared to other systems.

Article Details

How to Cite
E.Loganathan, M.Prakash, & G.Sivakumar. (2023). Enhanced Drug Recognition based on Decision tree optimized Support vector machine for disease related recommendation. International Journal of Intellectual Advancements and Research in Engineering Computations, 11(2), 1–9. Retrieved from