Blood Cancer Recognition Based on Discriminant Gene Expressions: A Comparative Analysis of Optimized Machine Learning Algorithms

Sakib, Shadman; Tanzeem, Abyaz Kader; Tasawar, Ihtyaz Kader; Shorna, Fatema; Siddique, Md. Abu Bakr; Alam, Saadia Binte

doi:10.1109/iemcon53756.2021.9623210

Cited by 7 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim of this process is to combine the previously retained solutions to find interesting aspects (peaks and thresholds) of several solutions in new individuals [51]. The crossover operator is implemented as a uniform crossover, which means that all genes between two random sites on a chromosome are swapped between two genotypes representing parents for the two resulting new genotypes.…”

Section: (Iii) Crossovermentioning

confidence: 99%

A Review of Genetic Algorithm: Operations and Applications

Faizatulhaida Md Isa,

Wan Nor Munirah Ariffin,

Muhammad Shahar Jusoh

et al. 2024

ARASET

View full text Add to dashboard Cite

This article presents a review of the Genetic Algorithm (GA), a prominent optimization technique inspired by natural selection and genetics. In the context of rapidly evolving computational methodologies, GA have gained considerable attention for their efficacy in solving complex optimization problems across various domains. The background highlights the growing significance of optimization techniques in addressing real-world challenges. However, the inherent complexity and diversity of problems necessitate versatile approaches like GA. The problem statement underscores the need to explore the underlying operations and applications of GA to provide a nuanced understanding of their capabilities and limitations. The objectives of this review encompass delving into the fundamental genetic operators, such as selection, crossover, and mutation, while examining their role in maintaining diversity and converging toward optimal solutions. Methodology-wise, a systematic analysis of existing literature is undertaken to distil key insights and trends in GA applications. The main findings show the adaptability of GA in tackling problems spanning engineering, economics, bioinformatics, and beyond. By facilitating the discovery of optimal or near-optimal solutions within large solution spaces, GA proves its mettle in scenarios where traditional methods fall short. The conclusion underscores the enduring relevance of GA in the optimization landscape, emphasizing their potential to remain a pivotal tool for addressing intricate real-world challenges, provided their parameters are fine-tuned judiciously to balance exploration and exploitation.

show abstract

Section: (Iii) Crossovermentioning

confidence: 99%