A Wrapper feature selection based frequent pattern classification framework for high dimensional microarray datasets
International Journal of Drug Delivery Technology · 18.06.2026 · 16 (55s)
DOI: 10.25258/ijddt.16.55s.99 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 18.06.2026. Verfasst von Araja Raja Gopalaa und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Microarray feature ranking and classification is one of the major challenge to scientific and biomedical researchers due to its high dimensional feature space and limited number of samples. Each microarray contains a large numbers of identical DNA molecules which are used to identify a specific gene related disease. Feature transformation, feature ranking and data classification are the essential techniques which are used to classify the high dimensional data with high true positive rate. Feature transformation is the process of normalizing the feature values within the bounded range. Feature transformation helps to improve the feature ranking process in high dimensional feature space. Most of the traditional feature transformation approaches such as log transformation, min-max normalization etc. are independent of data distribution and outliers. Traditional K-means based feature ranking approaches such as information gain, ANOVA, t-test, Signal-to-noise ratio (SNR) are not applicable to wrapper based feature selection approach. Wrapper based feature selection approach is applied on the high dimensional feature space to find and extract the subset of highly correlated features using ensemble classification accuracy. In this paper, a novel filter based wrapper feature selection method and data classification approach are proposed on high dimensional microarray datasets using MapReduce framework. In this model, a kernel based max-min data transformation method is used to normalize the entire microarray data for feature space partitions. Hybrid correlation based clustering method is used to partition the feature space into k-correlated features. Selected kcorrelated features are used in proposed wrapper feature selection approach for data classification. Finally, a comparative analysis is performed on the different microarray datasets to study the true positive rate, error rate and runtime of the proposed model and the traditional models.
Zitieren
APA
Gopalaa, A. R., & Prasadb, M. K. (2026). A Wrapper feature selection based frequent pattern classification framework for high dimensional microarray datasets. International Journal of Drug Delivery Technology, 16(55s). https://doi.org/10.25258/ijddt.16.55s.99
Vancouver
Gopalaa AR, Prasadb MK. A Wrapper feature selection based frequent pattern classification framework for high dimensional microarray datasets. International Journal of Drug Delivery Technology. 2026;16(55s). doi:10.25258/ijddt.16.55s.99
BibTeX
@article{Gopalaa2026,
author = {Gopalaa, Araja Raja and Prasadb, M.H.M. Krishna},
title = {A Wrapper feature selection based frequent pattern classification framework for high dimensional microarray datasets},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {55s},
doi = {10.25258/ijddt.16.55s.99}
}
EUVIMED