Class Level Feature Depth Measure Based Fuzzy Cluster Model for Efficient Disease Prediction using Data mining
B.V. Baiju1, D. John Aravindhar2

1Mr.B.V. Baiju, Department of Information Technology, Hindustan Institute of Technology and Science, Chennai (Tamil Nadu), India.
2Dr. D. John Aravindhar, Department of Computer Science and Engineering, Hindustan Institute of Technology and Science, Chennai (Tamil Nadu), India.

Manuscript received on 18 April 2019 | Revised Manuscript received on 25 April 2019 | Manuscript published on 30 April 2019 | PP: 1596-1600 | Volume-8 Issue-4, April 2019 | Retrieval Number: D6719048419/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The data mining approaches in disease prediction has been well studied. Number of approaches has been discussed towards the prediction of diseases. The methods suffer with poor disease prediction accuracy. A novel class level feature depth (CLFD) measure based disease prediction algorithm is proposed to improve the performance in disease prediction. The input data is preprocessed to eliminate noisy records. The noise removed data set has been used to extract various features of data set. With the Extracted features, the method estimates CLFD measure on various classes or clusters using the fuzzy rule available. The class of the data point is diagnosed on the basis of the CLDF measure. Similarly, the disease prediction is performed by computing Class Level Disease Depth (CLDD) measure towards various classes of data points. The method produces high performance in disease prediction and reduces the false classification ratio with less time complexity.
Keywords: Data Mining, Disease Prediction, Fuzzy Logic, Clustering, CLFS, CLDD.

Scope of the Article: Data Mining