Hybrid approaches to optimization and machine learning methods

Azevedo, Beatriz Flamia; Rocha, Ana Maria A.C.; Pereira, Ana I.

http://hdl.handle.net/10198/29417

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Hybrid_Approaches_to_Optimization.pdf		107.43 KB	Adobe PDF	Download

Send Feedback

Authors

Azevedo, Beatriz Flamia

Rocha, Ana Maria A.C.

Pereira, Ana I.

Abstract(s)

This paper conducts a comprehensive literature review concerning hybrid techniques that combine optimization and machine learning approaches for clustering and classification problems. The aim is to identify the potential benefits of integrating these methods to address challenges in both fields. The paper outlines optimization and machine learning methods and provides a quantitative overview of publications since 1970. Additionally, it offers a detailed review of recent advancements in the last three years. The study includes a SWOT analysis of the top ten most cited algorithms from the collected database, examining their strengths and weaknesses as well as uncovering opportunities and threats explored through hybrid approaches. Through this research, the study highlights significant findings in the realm of hybrid methods for clustering and classification, showcasing how such integrations can enhance the shortcomings of individual techniques.

Keywords

Machine learning Optimization Hybrid methods Literature review Clustering Classification

URI

http://hdl.handle.net/10198/29417

Citation

Azevedo, Beatriz Flamia; Rocha, Ana Maria A.C.; Pereira, Ana I. (2023). Hybrid approaches to optimization and machine learning methods. In 10th IEEE International Conference on Data Science and Advanced Analytics (DSAA). p. 1-2. ISBN 979-8-3503-4503-2