Effective Feature Set Selection and Centroid Classifier Algorithm for Web Services Discovery

Venkatachalam K, Karthikeyan NK


Text preprocessing and document classification plays a vital role in web services discovery. Nearest centroid classifiers were mostly employed in high-dimensional application including genomics. Feature selection is a major problem in all classifiers and in this paper we propose to use an effective feature selection procedure followed by web services discovery through Centroid classifier algorithm. The task here in this problem statement is to effectively assign a document to one or more classes. Besides being simple and robust, the centroid classifier s not effectively used for document classification due to the computational complexity and larger memory requirements. We address these problems through dimensionality reduction and effective feature set selection before training and testing the classifier. Our preliminary experimentation and results shows that the proposed method outperforms other algorithms mentioned in the literature including K-Nearest neighbors, Naive Bayes classifier and Support Vector Machines.


Document processing, Centroid classifier, Ontology alignment, Semantic web, KNN algorithm, Web service annotation.

Full Text:


DOI: http://doi.org/10.11591/ijeecs.v5.i2.pp441-450


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

shopify stats IJEECS visitor statistics