An Unsupervised, Fast Correlation-Based Filter for Feature Selection for Data Clustering

Pramokchon, Part; Piamsa-nga, Punpiti

doi:10.1007/978-981-4585-18-7_10

Cited by 6 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Fleuret used the conditional mutual information maximization to select feature (Pesek 2011). Bontempi and Meyer proposed a causal filter selection method, called min-Interaction Max-Relevance (Pramokchon and Piamsanga 2014). However, almost all these improved methods apply information metric to evaluate feature redundancy (i.e.)…”

Section: Feature Selectionmentioning

confidence: 98%

A novel intelligent approach for predicting atherosclerotic individuals from big data for healthcare

Priya¹,

Kumar²

2015

International Journal of Production Research

View full text Add to dashboard Cite

Atherosclerosis is a condition in human circulatory, where the arteries become narrowed and hardened due to accumulation of plaque around artery wall. The growth of the disease is slow and asymptomatic. Currently, imaging methods are applied for predicting the disease progression; however, they are deficient in the required resolution and sensitivity for detection. In this work, clinical observations and habits of individuals are considered for assorting the pathologic community. Intelligent machine learning technique, decision tree forest is used for assorting the individuals. A case study was made in this work regarding the atherosclerosis disease progression and crucial features were extracted. Optimised missing value imputation strategy, iterative principal component analysis for STULONG data-set and efficient feature subset selection method, hybrid fast correlation-based filter (FCBF) have been employed for extracting the relevant features and ignoring the redundant features. Further proceeding with the methodology, our work has outperformed with extreme overall accuracy of about 99.47% compared with other state-of-the-art machine learning techniques.

show abstract