Shariq Bashir

shariq.bashir@ubd.edu.bn

Assistant Professor, Institute of Applied Data Analytics



               

Shariq Bashir is an assistant professor of big data and machine learning at Institute of Applied Data Analytics (IADA), Universiti Brunei Darussalam (UBD). Previously he was associate professor of computer science at Foundation University Islamabad, Pakistan. In different times of his academic carrier he has worked with the Foundation University Islamabad, Imam Muhammad Ibn Saud Islamic University (KSA), Capital University of Science & Technology (Pakistan), New York University Abu Dhabi(UAE), National University of Computer and Emerging Sciences (Pakistan) and Vienna University of Technology (Austria). In 2013, he was postdoctoral researcher with the New York University Abu Dhabi. From 2007 to 2011, he was research assistant and PhD candidate at Information Management and Preservation Group (IMP) at Vienna University of Technology. During his PhD research he worked closely with Information Retrieval Facility at Vienna. Dr. Andreas Rauber (a former winner of Cor-Baayen Award) supervised his PhD research thesis. He has published numerous papers in refereed journals and international conferences and served as a reviewer and committee member for several major journals, conferences and workshops. His research interests cover the broad scope of data science, machine learning information retrieval and machine learning including specifically approximate frequent itemset mining, sentiment analysis, retrievability analysis, learning to rank, query expansion, and automatic analysis of retrieval models.

EDUCATION

PostDoc: New York University Abu Dhabi (NYUAD), 2013
PhD (Computer Science): Vienna University of Technology, Austria (2007-2011)
MS (Computer Science): National University of Computer & Emerging Sciences (NUCES), Islamabad, Pakistan (2003-2006)
BS (Computer Science): University of the Punjab, Lahore, Pakistan (1999-2003)

RESEARCH INTERESTS

Information Retrieval, Private Web Search, Data Science, Data Mining, Machine Learning, Sensor Networks

FUTURE PROJECTS

Private web search using query obfuscation

The aim of the project is to develop a novel Information Retrieval (IR) system, which is a web search facility, that uses our proposed proxy-terms based query obfuscation technique that allows users to search information through proxy queries without submitting true queries, harnessing the high computational and storage power of High Performance Computing (HPC). As part of the IR system architecture to support 1) data collection of large amount of retrieved documents from the web and 2) to support high computational, intelligent IR processing of documents using smart and artificial intelligence technologies, a HPC infrastructure will be incorporated. As a first project, we will focus in the medical domain. Not only will the large amount of data collect enable us to develop novel IR systems, it allows us to do research in the areas of medical web search privacy and use of HPC in medical analytics or big data medical analytics and infrastructure. Search engines store users’ queries in query log. However, query log causes privacy concerns. Private web search (PWS) provides privacy-preserving technique that allows users to retrieve information from IR system without revealing true search queries. Existing techniques achieve web search privacy in an isolated manner without considering similarity between consecutive queries. In this project, we want to propose a proxy-terms based query obfuscation technique that allows users to search information through proxy queries without submitting true queries.


Applications Invited
594

Google Scholar Citations

13

Google Scholar h-index

18

Google Scholar i10-index

RECENT PUBLICATIONS

Shariq Bashir, Daphne Teck Ching, Lai, Mining Approximate Itemsets using Pattern Growth Approach. Accepted, Information Technology and Control, 2021, JCR Impact factor (1.228).

Muhammad Fahad Khan; Khalid Saleem, Mohammed Ali Alshara and Shariq Bashir. Multilevel Information Fusion for Cryptographic Substitution Box Construction based on Inevitable Random Noise in Medical Imaging. Nature Scientific Reports, Springer 2021, JCR Impact factor (3.998).

Shariq Bashir, Akmal Saeed Khattak, Mohameed Ali Alshara, "Automatically Transforming Full Length Bio Medical Articles into Search Queries for Retrieving Related Articles", Egyptian Informatics Journal, Elsevier, 2020, JCR Impact Factor (3.119).

Shariq Bashir, "An efficient pattern growth approach for mining fault tolerant frequent itemsets", Expert Systems with Applications (Elsevier), Volume 143, 2020, Impact Factor (4.292).

Shariq Bashir, "Broken Link Repairing System for Constructing Contextual Information Portals", Journal of King Saud University - Computer and Information Sciences, Impact Factor (13.473). 2017.

TOP PUBLICATIONS

Shariq Bashir, "An efficient pattern growth approach for mining fault tolerant frequent itemsets", Expert Systems with Applications (Elsevier), Volume 143, 2020, Impact Factor (4.292).

Shariq Bashir, Ranking Entities on the Basis of Users' Opinions, Multimedia Tools and Applications, Springer Journal, 2015, Impact Factor (1.346).

Shariq Bashir, Wasif Afzal, A. Rauf Baig, Opinion-based Entity Ranking using Learning to Rank, Applied Soft Computing, Elsevier Journal, 2015, Impact Factor (2.810).


Shariq Bashir, Andreas Rauber, Automatic Analysis and Ranking of Retrieval Models Effectiveness using Retrievability Measurement, Knowledge and Information System Journal, Springer, Volume 41(1), 2014, Impact Factor (1.782).

Shariq Bashir, Andreas Rauber, On the Relationship between Query Characteristics and IR Functions Retrieval Bias, Journal of American Society for Information Science and Technology (JASIST), Volume 62, Issue 8, 2011, Impact Factor (2.081).