Abstract
Dimension reduction or feature selection is thought to be the backbone of big data applications in order to improve performance. Many scholars have shifted their attention in recent years to data science and analysis for real-time applications using big data integration. It takes a long time for humans to interact with big data. As a result, while handling high workload in a distributed system, it is necessary to make feature selection elastic and scalable. In this study, a survey of alternative optimizing techniques for feature selection are presented, as well as an analytical result analysis of their limits. This study contributes to the development of a method for improving the efficiency of feature selection in big complicated data sets.
Highlights
Categorization is an important job in data mining and machine learning that divides every example in a data collection into various groups based on the information provided by its attributes
Multi-objective optimization issues [3] are a type of optimization problem that arises in real-world applications and has many competing goals
The Pareto technique is used to develop a compromise solution that can be shown in the form of a Pareto optimal front (POF) end if the intended solutions and performance measurements are separate
Summary
Categorization is an important job in data mining and machine learning that divides every example in a data collection into various groups based on the information provided by its attributes. The findings of published efforts in the area of enhancement suggested solving a problem using swarm intelligence and evolutionary approaches, that began as static optimization and reveal a pseudo environments-based technique that can resolve and enhance an integrated multi issue to decrease or improve the outcome features. Multi-objective optimization issues [3] are a type of optimization problem that arises in real-world applications and has many competing goals. The implementation of feature selection as a multi-objective optimization process can bring certain benefits whether the classification approach is supervised or unsupervised. A multi-objective optimization strategy that sufficiently combines classifiers performance and attribute quantity provides a reasonable formulation of this problem. Problems with many goals are referred to as multi-objective optimization (MOO). The multi-objective evolutionary algorithm is a stochastic optimization technique (MOEA).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Indian Journal of Artificial Intelligence and Neural Networking
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
