Zulfiqar Ahmad Khan
I am a research assistant and lab coordinator with experience in power generation and consumption forecasting for smart grid management, time-series data analysis, multimedia understanding for image processing, classification, object detection, and video surveillance data analysis for scene understanding, the IoT, and resource-constrained programming. I serve as the Coordinator of the Intelligent Media Laboratory (IMLab), where I lead a dynamic research group of 8 members and supervise laboratory projects. My technical skills include time-series data refinement and modelling for power generation and consumption forecasting, utilizing statistical, machine learning, and deep learning-based hybrid models, including CNN and RNN variants. I specialize in multimedia data analysis, applying advanced deep learning techniques such as object detection (YOLO, Faster R-CNN), anomaly recognition (FlowNet, I3D, 3D CNNs), and scene understanding. Additionally, I implement active and incremental learning techniques, enabling models to adapt to evolving data environments, and employ Explainable AI (XAI) methods for enhanced model interpretability and transparency in decision-making. My expertise extends to utilizing attention mechanisms, transformers, and ensemble learning techniques to enhance both prediction performance in time-series forecasting and model accuracy in computer vision tasks, ensuring robustness and improved accuracy in complex scenarios.
Sep 2019 ~ Feb 2025: Sejong University, Seoul, South Korea Thesis Title: A Study of Spatiotemporal Feature Analysis using Deep Hybrid Models for Power Forecasting. Aug 2016 ~ Aug 2018: Islamia College Peshawar, KPK, Pakistan Final Year Project: Towards smart home automation using IoT-enabled edge-computing paradigm.
Watch the demo here: Aug 2014 ~ Aug 2016: Govt. Post Graduate College, Timergara, Dir Lower, KPK, Pakistan June 2017 ~ Aug 2019: DIPLab, Islamia College Peshawar, KPK, Pakistan Participated in various projects including face recognition, image classification, object detection, Time series data analysis, IoT, an Samrt home Sep 2019 ~ Present: IMLab, Sejong University, Seoul, South Korea Since September 2019, I have been actively involved in several key research projects funded by the National Research Foundation of Korea (NRF), where my contributions have covered a variety of critical tasks. These include projects management, implementation of advanced algorithms and methodologies, drafting and publishing research articles, and developing patents based on innovative findings. Additionally, I have been responsible for preparing comprehensive yearly reports, ensuring that project progress is accurately documented and communicated to stakeholders. Authors: Zulfiqar Ahmad Khan, Fath U Min Ullah, Hikmat Yar, Waseem Ullah, Noman Khan, Min Je Kim, and Sung Wook Baik Accepted, 9 Dec 2024 Publisher: Elsevier Journal: Pattern Recognition Authors: Zulfiqar Ahmad Khan, Shabbir Ahmad Khan, Tanveer Hussain, Sung Wook Baik Volume: 356 Publisher: Elsevier Journal: Applied Energy Authors: Zulfiqar Ahmad Khan, Tanveer Hussain, Waseem Ullah, Sung Wook Baik Volume: 20 Publisher: IEEE Journal: IEEE Transactions on Industrial Informatics Authors: Zulfiqar Ahmad Khan, Tanveer Hussain, Sung Wook Baik Volume: 338 Publisher: Elsevier Journal: Applied Energy Authors: Waseem Ullah, Tanveer Hussain, Zulfiqar Ahmad Khan, Umair Haroon, Sung Wook Baik Volume: 253 Publisher: Elsevier Journal: Knowledge-Based Systems Authors: Zulfiqar Ahmad Khan, Tanveer Hussain, Fath U Min Ullah, Suneet Kumar Gupta, Mi Young Lee, Sung Wook Baik Volume: 116 Publisher: Elsevier Journal: Engineering Applications of Artificial Intelligence Authors: Hikmat Yar, Tanveer Hussain, Mohit Agarwal, Zulfiqar Ahmad Khan, Suneet Kumar Gupta, Sung Wook Baik Volume: 31 Publisher: IEEE Journal: IEEE Transactions on Image Processing Native Fluent
FluentEducation
Ph.D
MS.c
BS.c
Work
Research Assistant
Research Assistant
Selected Publications
Optimized Cross-Module Attention Network and Medium-Scale Dataset for Effective Fire Detection
DSPM: Dual sequence prediction model for efficient energy management in micro-grid
A Trapezoid Attention Mechanism for Power Generation and Consumption Forecasting
Dual stream network with attention mechanism for photovoltaic power forecasting
Intelligent dual stream CNN and echo state network for anomaly detection
Randomly initialized CNN with densely connected stacked autoencoder for efficient fire detection
Optimized dual fire attention network and medium-scale fire classification benchmark
Languages
Pashto Urdu English
