Abstract
Feature redundancy minimization is a noticeable topic in today’s research world. Almost in every case of machine learning algorithm, feature selection (FS) creates a great necessity to ensure a good level of classification problem. So, in case of feature selection algorithms, the characteristics to reduce the redundant feature as well as selecting the relevant feature or ranking of the features is equally important. But the problem is most of the FS method are focused on either feature subset selection or feature ranking. As a result, the existence of redundant feature in data is still a problem. So, this paper is going to perform a systematic literature review and Bibliometric analysis on Feature redundancy minimization problem. This review was conducted using three database and articles were retrieved through PRISMA framework. Finally, a tool named “VOSviewer” was used to perform the bibliometric analysis over the collected articles. The outcome of this review showed that, filter approached redundancy minimization-based FS related research work is very little in number. This research work also addresses the commonly used algorithm in FS method.
Publisher
The Association of Professional Researchers and Academicians
Reference7 articles.
1. Ab Hamid, T. M. T., Sallehuddin, R., Yunos, Z. M., & Ali, A. (2021). Ensemble based filter feature selection with harmonize particle swarm optimization and support vector machine for optimal cancer classification. Machine Learning with Applications, 5, 100054. doi: 10.1016/j.mlwa.2021.100054.
2. Albort-Morant, G., Leal-Millán, A. & Cepeda-Carrión, G. (2016) ‘The antecedents of green innovation performance: A model of learning and capabilities’, Journal of Business Research, 69(11), pp. 4912–4917. doi: 10.1016/j.jbusres.2016.04.052.
3. Cao, P., Liu, X., Zhang, J., Zhao, D., Huang, M., & Zaiane, O. (2017). ℓ2, 1 norm regularized multi-kernel based joint nonlinear feature selection and over-sampling for imbalanced data classification. Neurocomputing, 234, 38-57. doi: 10.1016/j.neucom.2016.12.036.
4. Damgacioglu, H., Celik, N. & Celik, E. (2018) ‘MR2: A two-stage feature selection algorithm in high-throughput methylation data for max-relevance and min-redundancy’, IISE Annual Conference and Expo 2018, pp. 1169–1174.
5. Guo, Y., Hu, M., Tsang, E. C., Chen, D., & Xu, W. (2022). Feature selection based on min-redundancy and max-consistency. Advances in Computational Intelligence, 2, 1-11. doi: 10.1007/s43674-021-00021-9.