Discussion of the master\u2019s thesis in the College of Computer Science and Mathematics -Department of software: \u201cA Systematic Approach to Requirements Traceability Using Machine Learning\u201d<\/p>\n
Master\u2019s thesis by Shafaq Azzam Noori<\/p>\n
supervised by \u00a0\u00a0Dr. Najla Akram Youniss Al-Saati<\/p>\n
This study aims to improve software requirements traceability by automating the link between textual requirements and source code using advanced semantic vectorization techniques and machine learning models. Five algorithms were evaluated, with Random Forest achieving the best performance (accuracy 0.8, F1-score 0.52), showing a good balance between precision and recall. Logistic Regression had the highest recall but low precision, limiting its practical use. The results highlight the potential of AI to enhance traceability accuracy and reduce human error. The study focused on eTour dataset which consists of Italian-language documents, translated it to English, assuming separate sets for requirements and design.<\/p>\n
The discussion committee consists of<\/p>\n
(Chairman) Prof. Dr. Safwan Omar Hasoon.<\/p>\n
(Member) Asst. Prof. Dr. Jamal Salahuddin Sayyed Majid.<\/p>\n
(Member) Asst. Prof. Tawfiq Muqdad Tawfiq.<\/p>\n
(member and supervisor) Prof. Dr. Najla Akram Youniss<\/p>\n","protected":false},"excerpt":{"rendered":"
Discussion of the master\u2019s thesis in the College of Computer Science and Mathematics -Department of software: \u201cA Systematic Approach to Requirements Traceability Using Machine Learning\u201d Master\u2019s thesis by Shafaq Azzam Noori supervised by \u00a0\u00a0Dr. Najla Akram Youniss Al-Saati This study aims to improve software requirements traceability by automating the link between textual requirements and source code using advanced semantic vectorization techniques and machine learning models. Five algorithms were evaluated, with Random Forest achieving the best performance (accuracy 0.8, F1-score 0.52), showing a good balance between precision and recall. Logistic Regression had the highest recall but low precision, limiting its practical use. [Read More]<\/a><\/p>\n","protected":false},"author":24,"featured_media":39380,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[],"class_list":["post-39379","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-viva"],"_links":{"self":[{"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/posts\/39379","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/users\/24"}],"replies":[{"embeddable":true,"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/comments?post=39379"}],"version-history":[{"count":1,"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/posts\/39379\/revisions"}],"predecessor-version":[{"id":39381,"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/posts\/39379\/revisions\/39381"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/media\/39380"}],"wp:attachment":[{"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/media?parent=39379"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/categories?post=39379"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/uomosul.edu.iq\/en\/computerscience\/wp-json\/wp\/v2\/tags?post=39379"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}