Enhancing Lung Cancer Detection with Hybrid Machine Learning: Integrating Ant Colony Optimization
Main Article Content
Abstract
This paper aims to analyze the approaches to improve the diagnostics medical and particularly detect Lung Cancer using Ant Colony Optimization (ACO) and hybrid models. In this paper, a new technique of feature selection is introduced, called ACO, an optimization algorithm based on the foraging strategy used by ants: In high-dimensional data sets frequently seen in medical data bases, the proposal makes use of the ACO for feature selection in machine learning models. ACO has been interlinked with other optimization approaches like Genetic Algorithm and Particle Swarm Optimization and the results were satisfactory in terms of model enhancements. Furthermore, the intersection of ACO with deep learning is presented as one attractive area of study; the study also discusses the further insight into deep neural networks where ACO may help with feature selection. Incorporation of Mixed models is also expounded in the paper and it discusses how more than one diagnostic technique is used to develop more effective diagnostic tools. Beware, that using other types of hybrids ACO with machine learning classifiers, such as Support Vector Machines, Neural Networks and others, remarkable enhancements have been noticed in the sphere of early lung cancer detection. But at the same time, the paper does not avoid the critical aspects of these approaches, including computational difficulties and problems with interpreting the results of using hybrid models. The findings of this study show that the utilization of features chosen by ACO enhances the accuracy of DNN in detection of lung cancer and reviewed the false positive of the model circuits. The studies analyzed also show that ACO and hybrid models have the potential to improve medical diagnostics especially under the flexible ACO and hybrid models discussed here as well as provide suggestions for future work particularly in the field of personalized medicine and early diagnosis.
Article Details
How to Cite
Iqbal, S., Ahmed, S., Hassan, B., Abid, M., & Husain, I. (2024). Enhancing Lung Cancer Detection with Hybrid Machine Learning: Integrating Ant Colony Optimization. Technical Journal, 29(03), 74-86. Retrieved from https://tj.uettaxila.edu.pk/index.php/technical-journal/article/view/2199
Section
COMPUTER SCIENCE
Copyright (c) 2024 Technical Journal
The author transfers all copyright ownership of the manuscript entitled (title of article) to the Technical Journal in the event the work is published.