Research and Publication
MS Thesis
Title: Machine and Deep Learning-Based Event Detection Methods and Applications to Enable Smarter Societies
Abstract: The aim of this thesis is to develop machine and deep learning-based event detection methods and applications to enable smarter societies. Towards this aim, we developed an event detection framework that comprises three case studies to elucidate the use of event detection methods for smart societies. The case studies are developed and implemented in detail as follows. 1. We developed an online proctoring system using object detection techniques and biometric authentication including face detection, face recognition, and eye blinking detection that provide robust instruments to detect unfair, unethical, and illegal behaviour during classes and exams. 2. We developed Potrika, the largest and the most extensive dataset for Bangla news articles that contains 185 million words and 12 million sentences in 665,000 news articles, providing five attributes, classified into eight distinct categories. It can be used for text classification, text summarization, text generation, and other NLP-related research. Potrika is publicly and freely available. 3. We developed a news event detection system using machine learning and deep learning algorithms that detects several events including National, Sports, International, Entertainment, Economy, Education, Politics, and Science & Technology from Bangla news articles text. We tested the system on Potrika. 4. We developed automatic labelling methods using Latent Dirichlet Allocation (LDA) and investigate the performance of single-label and multi-label article classification methods.
Supervisors: Prof. Rashid Mehmood, Director of Research, HPC Center, King Abdulaziz University, Jeddah, Saudi Arabia
Dr Fahad AlQurashi, Associate professor, Computer Science, King Abdulaziz University, Jeddah, Saudi Arabia
Undergraduate Thesis
Title: Cough Detection with Speech Analysis
Supervisor: Dr Mohammad Nurul Huda, Professor and MSCSE Coordinator, United International University
2022
Ahmad I, Alqurashi F, Mehmood R. Machine and Deep Learning Methods with Manual and Automatic Labelling for News Classification in Bangla Language. arXiv preprint.2022. DOI: https://doi.org/10.48550/arXiv.2210.10903
Ahmad I, Alqurashi F, Mehmood R. Potrika: Raw and Balanced Newspaper Datasets in the Bangla Language with Eight Topics and Five Attributes. arXiv preprint.2022. DOI: https://doi.org/10.48550/arXiv.2210.09389
Ahmad I, Alqurashi F, Abozinadah E, Mehmood R. Deep Journalism and DeepJournal V1.0: A Data-Driven Deep Learning Approach to Discover Parameters for Transportation. Sustainability. 2022; 14(9):5711. https://doi.org/10.3390/su14095711
Ahmad I, Alqurashi F, Abozinadah E, Mehmood R. "Deep Journalism and DeepJournal V1.0: A Data-Driven Deep Learning Approach to Discover Parameters for Transportation (As A Case Study)", Preprint. 2022. DOI: https://doi.org/10.20944/preprints202203.0245.v1
Ahmad, Istiak; Alqurashi, Fahad; Abozinadah, Ehab; Mehmood, Rashid (2022), “Web of Science Transportation Dataset (WST202201)”, Mendeley Data, V1. DOI: https://doi.org/10.17632/tnfw2dh5nj.1
Ahmad, Istiak; Alqurashi, Fahad; Abozinadah, Ehab; Mehmood, Rashid (2022), “Traffic Technology Today Transportation Dataset (TTIT202201)”, Mendeley Data, V1, DOI: https://doi.org/10.17632/k4bgjwktyp.1
Ahmad, Istiak; Alqurashi, Fahad; Abozinadah, Ehab; Mehmood, Rashid (2022), “Guardian Transportation Dataset (GT202201)”, Mendeley Data, V1, DOI: https://doi.org/10.17632/yvxx6s5xhh.1
2021
Istiak Ahmad, Fahad AlQurashi, Ehab Abozinadah, Rashid Mehmood. "A Novel Deep Learning-based Online Proctoring System using Face Recognition, Eye Blinking, and Object Detection Techniques", International Journal of Advanced Computer Science and Applications 12 (10), 2021. DOI: http://dx.doi.org/10.14569/ijacsa.2021.0121094
Ahmad, Istiak; Mehmood, Rashid; Abozinadah, Ehab; Al Qurashi, Fahad (2021), “Potrika: Raw and Balanced Newspaper Datasets in the Bangla Language with Eight Topics and Five Attributes”, Mendeley Data, V2, DOI: https://doi.org/10.17632/v362rp78dc.2