Faculty Achievement Faculty Achievements
IBA faculty co-authors paper on intrusion detection systems
Dr. Tariq Mahmood, Associate Professor, Department of Computer Science, has coauthored a paper titled "A Novel Deep Learning Framework for Intrusion Detection System" in IEEE's International Conference on Advances in the Emerging Computing Technologies (AECT, 2019), which was held in Al-Madinah Al-Munawwarah (KSA).
The paper is based on work of an intensive graduate course project at the IBA Karachi and uses auto-encoder technology to detect network intrusions through data analysis, and Recurrent network technology to predict the type of network intrusion.
The publication can be accessed at: https://ieeexplore.ieee.org/document/9194224
IBA faculty delivers keynote address for online deep learning and AI forum
Dr. Tariq Mahmood, Associate Professor, Department of Computer Science, delivered a keynote speech titled "Concept Drift in Machine Learning of Streaming Data: A Systematic Literature Review" at the online NeurIPS Meetup 2020, which was organized by NeurIPS and Aladin Solutions (URL: https://sites.google.com/a/nu.edu.pk/noman-islam/deep-learning-meetup
The talk was based on work done by a research-survey student at the IBA Karachi, Tatheer Fatima, and comprised a systematic literature review to determine different approaches in research for concept drift or change in probability distribution of predicted business KPIs. The talk was well-accepted by industry and academic professionals.
IBA faculty uses data science to predict Pakistan Cricket Team's performance
Dr. Tariq Mahmood has published his paper entitled "Is the performance of a cricket team really unpredictable? A case study on Pakistan team using machine learning" in the Indian Journal of Science and Technology, an HEC-recognized journal. This work targets the application of a comprehensive data science methodology to determine the extent to which the performance of Pakistan's ODI cricket team can be predicted in advance. The main motivation of this work is the "unpredictable" tag which is associated with Pakistan's team. This work shows that, in fact, using intensive data science models, it is possible to extract useful patterns or regularities in Pakistan's performance and to predict this performance with a high accuracy of 82% (before the match starts).
This work can be presented to cricketing authorities of Pakistan or of any cricketing nation to help them understand the reasons for a win or a loss and to predict this performance right at the start of the match.
The publication can be accessed at: https://indjst.org/articles/is-the-performance-of-a-cricket-team-really-unpredictable-a-case-study-on-pakistan-team-using-machine-learning
IBA faculty discusses big data applications for healthcare systems
Dr. Tariq Mahmood has published his paper entitled "Big Data Analytics in Healthcare - A Systematic Literature Review and Roadmap for Practical Implementation" in IEEE's journal of Automatica Sinica (Impact Factor: 5.142). This was done as part of a PhD work and is the most comprehensive systematic literature review on big data and its analytical applications to patient care and related healthcare domains. The article can be accessed at: https://ieeexplore.ieee.org/document/9205683(early access)