Intelligent decision support system of swine flu prediction using novel case classification algorithm. Issue 1 (9th December 2014)

• Record Type: Journal Article
• Authors: Biswas, Saroj K.; Sinha, Nidul; Baruah, Barnana; Purkayastha, Biswajit
• Is Part Of: International journal of knowledge engineering and data mining. Volume 3:Issue 1(2014)
• Page Start: 1
• Page End: 19
• Publication Date: 2014-12-09
• Subjects: CBR -- case–based reasoning -- intelligent DSS -- decision support systems -- feature selection -- cross–validation -- nearest neighbour -- swine flu prediction -- case classification -- feature weighting -- case representation -- similarity; Knowledge representation (Information theory) -- Periodicals; Data mining -- Periodicals; 006.305
• Languages: English
• ISSNs: 1755-2087

Abstract

Case Based Reasoning (CBR) is a powerful problem–solving method that could be effectively used in medical science. But for the success of CBR, reasonable evaluation of case similarity is one of the key technologies. In order to solve feature weighting problem in case similarity a weighted nearest neighbour (w–NN) is considered based on inductive learning for swine flu prediction. Finally based on w–NN and extensibility in similarity, a novel case classification algorithm is proposed for swine flu prediction. The novel case classification algorithm exploits knowledge about hidden patterns and relationships from a huge collection of healthcare industrial data which is not properly mined and not put to the optimum use. Comparison of the proposed model is also done with an earlier proposed model and from the empirical results it is found that our model is very promising because it produces 85.6% accurate result that is superior to the earlier model.