Innovative Computing Review https://journals.umt.edu.pk/index.php/icr <p style="text-align: justify;"><strong>Innovative Computing Review (ICR)</strong> is an international journal being published by the School of Systems and Technology (SST), University of Management and Technology (UMT), Lahore, Pakistan. <strong>ICR</strong> is committed to publishing high-quality studies in computing and related fields and is widely circulated, both nationally and internationally. It is focused on the publication of original research work and reviews in form of articles under the umbrella of computing science and it aims to introduce the latest developments in this rapidly growing subject.</p> en-US [email protected] (Editorial Office) [email protected] (Reamsha Khan) Tue, 23 Sep 2025 03:19:39 +0000 OJS 3.1.2.1 http://blogs.law.harvard.edu/tech/rss 60 oGoogleNet: An Optimized GoogleNet for Chest Infection Detection on the COVID-19 Dataset https://journals.umt.edu.pk/index.php/icr/article/view/3209 <p>The outbreak of SARS and, more recently, COVID-19 has highlighted the <br>need for accurate and quick diagnosis of chest diseases for pandemic prevention. While the<br>handling of theCOVID-19 pandemic has drawn attention to the weaknessesin the <br>healthcare systems worldwide, it has also enabled us to fully utilize the massive amounts<br>of data at our disposal in order to devise strategies for better handling outbreaks in the <br>future. Chest infection is a crucial symptom used to diagnose COVID-19 cases. <br>Moreover, it may also lead to various other diseases, including pneumonia, asthma, and <br>bronchitis. Researchers havebeen working on automatic chest infection detection for the <br>last few decades. In this study, we present oGoogleNet, a deep learning architecture for <br>chest infection detection, developed by optimizing GoogleNet through the addition of <br>layers and the modification of activation functions. The oGoogleNet iscompared with the <br>existing state-of-the-art deep networks on eight standard chest infection datasets, <br>containing 12,389 radiographs (with 777 COVID-19 radiographs). The experiments<br>demonstrate that oGoogleNet outperforms the other systems and achieves an accuracy of<br>91.25%.</p> Sumaira Zafar, Kanwal Majeed, Arjmand Majeed, Syed Farooq Ali, Aadil Zia Khan Copyright (c) 2025 Sumaira Zafar, Kanwal Majeed, Arjmand Majeed, Syed Farooq Ali, Aadil Zia Khan https://creativecommons.org/licenses/by/4.0 https://journals.umt.edu.pk/index.php/icr/article/view/3209 Tue, 23 Sep 2025 03:18:55 +0000