{"id":34275,"date":"2026-02-08T08:32:52","date_gmt":"2026-02-08T05:32:52","guid":{"rendered":"https:\/\/bti.stu.edu.iq\/?p=34275"},"modified":"2026-02-08T09:34:39","modified_gmt":"2026-02-08T06:34:39","slug":"assistant-lecturer-waleed-jaloob-khudhair-publishes-a-scientific-research-paper","status":"publish","type":"post","link":"https:\/\/bti.stu.edu.iq\/en\/34275\/","title":{"rendered":"Assistant Lecturer Waleed Jaloob Khudhair Publishes a Scientific Research Paper"},"content":{"rendered":"<p dir=\"ltr\" style=\"text-align: left;\" data-start=\"196\" data-end=\"285\">Assistant Lecturer Waleed Jaloob Khudhair Publishes a Joint Scientific Research Paper<\/p>\n<p dir=\"ltr\" style=\"text-align: left;\">Assistant Lecturer Waleed Jaloob Khudhair, from the Department of Production Mechanical Technologies at the Technological Technical Institute in Basra, has published a joint scientific research paper entitled:<\/p>\n<p dir=\"ltr\" style=\"text-align: left;\" data-start=\"506\" data-end=\"601\">\u201cIntelligent Detection and Classification of Security Attacks in WSNs Using Deep Learning.\u201d<\/p>\n<p dir=\"ltr\" style=\"text-align: left;\" data-start=\"603\" data-end=\"794\">The research was published in the <em data-start=\"637\" data-end=\"676\">Journal of Robotics and Control (JRC)<\/em>, a journal indexed in the Scopus database and ranked in the first quartile (Q1), with a CiteScore of 6.5.<\/p>\n<p dir=\"ltr\" style=\"text-align: left;\" data-start=\"796\" data-end=\"1337\">Wireless Sensor Networks (WSNs) are considered fundamental components of modern communication systems; however, they remain vulnerable to increasingly complex and diverse cyber threats. This research proposes a hybrid framework that integrates Generative Adversarial Networks (GANs) and Recurrent Neural Networks (RNNs) to address security challenges in wireless sensor networks. The RNN module captures temporal dependencies for accurate attack detection, while the GAN module generates synthetic samples to mitigate data imbalance.<\/p>\n<p dir=\"ltr\" style=\"text-align: left;\" data-start=\"1339\" data-end=\"1738\">The proposed framework achieved a detection rate of 98.47% and an accuracy of 98.79%, significantly outperforming traditional methods such as Support Vector Machines, Na\u00efve Bayes classifiers, and Random Forests, with statistical significance (p &lt; 0.05). In addition, the framework maintained a low false alarm rate of 2%, ensuring minimal disruption to legitimate network operations.<\/p>\n<p dir=\"ltr\" style=\"text-align: left;\" data-start=\"1740\" data-end=\"2153\">The adaptability of the framework was validated through case studies on heterogeneous wireless sensor network architectures, including low-power Internet of Things (IoT) sensor networks and large-scale industrial deployments. Specifically, experiments conducted on the CICIDS and UNSW-NB15 datasets demonstrated the system\u2019s effectiveness in dynamic environments where attack patterns evolve in real time.<\/p>\n<p dir=\"ltr\" style=\"text-align: left;\" data-start=\"2155\" data-end=\"2804\">Real-time detection capability was confirmed by achieving an average inference time of 1.25 seconds per sequence, making the framework suitable for time-sensitive applications such as military surveillance and industrial automation. To further enhance attack resilience, the system incorporates adversarial training techniques, gradient regularization, and jamming detection mechanisms, ensuring robustness against evasive attack strategies and adversarial samples. Experimental evaluations showed that jamming detection reduced attack evasion rates by 36.8%, thereby improving the reliability of security measures in practical applications.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Assistant Lecturer Waleed Jaloob Khudhair Publishes a Joint Scientific Research Paper Assistant Lecturer Waleed Jaloob Khudhair, from the Department of Production Mechanical Technologies at the Technological Technical Institute in Basra, has published a joint scientific research paper entitled: \u201cIntelligent Detection and Classification of Security Attacks [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":34235,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[116],"tags":[],"table_tags":[],"class_list":["post-34275","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"_links":{"self":[{"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/posts\/34275","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/users\/14"}],"replies":[{"embeddable":true,"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/comments?post=34275"}],"version-history":[{"count":3,"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/posts\/34275\/revisions"}],"predecessor-version":[{"id":34278,"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/posts\/34275\/revisions\/34278"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/media\/34235"}],"wp:attachment":[{"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/media?parent=34275"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/categories?post=34275"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/tags?post=34275"},{"taxonomy":"table_tags","embeddable":true,"href":"https:\/\/bti.stu.edu.iq\/en\/wp-json\/wp\/v2\/table_tags?post=34275"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}