http://thenucleuspak.org.pk/index.php/Nucleus <p><em>The Nucleus</em> is a well-established, open-access, peer-reviewed multidisciplinary scientific journal that has been in publication since 1964. The journal offers free access to all its content, both electronically and in print, ensuring that research is widely available to the public without any cost barriers. It is accredited as Y-category journal by the Higher Education Commission (HEC), and published biannually. <em>The Nucleus</em> invites research scholars, faculty members, and academicians from various disciplines, particularly in the natural and applied sciences, to submit their original research manuscripts. The journal is committed to promoting flawless and unbiased research, adhering to international publishing standards. The publisher also actively promotes published articles worldwide through various media channels, in line with open access regulations, ensuring that the research reaches a broad audience.</p> <p>The motto of <em>The Nucleus</em> reflects its dedication to transparency, integrity, and the promotion of high-quality research.</p> <p><strong><!--a href='#' id="fullscope" >Read More >></a--></strong></p> en-US <p>For all articles published in <em>The Nucleus</em>, copyright is retained by the authors. Articles are licensed under an open access licence <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank" rel="noopener">[CC Attribution 4.0]</a> meaning that anyone may download and read the paper for free. In addition, the article may be reused and quoted provided that the original published version is cited properly.</p> editorinchief@thenucleuspak.org.pk (Dr. Maaz Khan (Editor-in-Chief)) editorialoffice@thenucleuspak.org.pk (Mr. Touseef Tufail (Editorial Assistant)) Mon, 14 Jul 2025 10:32:58 +0500 OJS 3.3.0.13 http://blogs.law.harvard.edu/tech/rss 60 http://thenucleuspak.org.pk/index.php/Nucleus/article/view/1461 <p class="NuclAbstract">This study explores how Deep Q Networks (DQNS) can be applied to classifying data with standard datasets. Though DQNs are designed for sequential decisions, this study uses the Iris and Diabetes datasets, which are both used for classification, to test the performance. It investigates DQNs with different data imbalances and compares their results based on the quantity of data. Models are assessed using accuracy, precision, recall, F1 score, ROC-AUC, the amount of memory required, and their training speed. As demonstrated by the results, DQNs can match other algorithms in accuracy while attaining accuracy rates between 84% and 95% for various datasets and modified configurations. Based on the study, performance can be affected by adjusting hyperparameters and the distribution of data classes. DQNs are more complex than common classifiers such as SVMs and decision trees, and their main contribution in simple classification is yet to be proven. It adds to the enthusiasm for using reinforcement learning models in the context of supervised learning. The paper highlights the value of correct evaluation, points out risks linked to model over-fitting and includes new areas to pursue in the future such as benchmarking, clarifying models and using hybrid systems.</p> M. Rehman, M. Baig Copyright (c) 2025 The Nucleus https://creativecommons.org/licenses/by/4.0 http://thenucleuspak.org.pk/index.php/Nucleus/article/view/1461 Mon, 14 Jul 2025 00:00:00 +0500