Intelligent Computing Lab
Research Field
Dr. Qazi Mazhar ul Haq is currently working as Assistant Professor in Computer Science and Engineering at Yuan Ze University Taiwan. He holds a PhD in Electronics and Computer Engineering from the National Taiwan University of Science and Technology. His research interests include object detection, incremental learning, anomaly detection, image processing, deep learning, as well as the 3D object detection.
Welcome to the Intelligent Computing Lab at Yuan Ze University. In this dynamic and innovative environment, we embark on a journey at the intersection of cutting-edge technologies, exploring the realms of autonomous vehicles, deep learning, and anomaly detection. This lab serves as a hub for exploration, experimentation, and innovation, where we delve into the transformative potential of networking technologies in shaping the future of transportation and safety.
Autonomous Vehicles: At the core of our lab's focus lies the realm of autonomous vehicles – a groundbreaking domain that is revolutionizing the way we perceive mobility. We delve into the intricate world of self-driving cars, exploring the fusion of networking technologies with sensors, actuators, and control systems. Our mission is to contribute to the advancement of autonomous vehicles by developing networking solutions that enable seamless communication, real-time data sharing, and cooperative decision-making among vehicles and infrastructure.
Deep Learning: As we navigate the era of artificial intelligence, deep learning emerges as a pivotal force driving the advancement of various applications. In this lab, we harness the power of deep learning techniques to unlock the potential of autonomous vehicles. We explore neural networks, convolutional networks, recurrent networks, and beyond, seeking to optimize perception, decision-making, and control systems in autonomous vehicles. Through data-driven approaches, we strive to enhance the capabilities of these vehicles to understand their environment and respond intelligently.
Anomaly Detection: Ensuring the safety and reliability of autonomous vehicles is paramount. This is where our emphasis on anomaly detection comes into play. We develop and deploy cutting-edge algorithms that can identify and respond to unexpected situations – a critical aspect in the deployment of autonomous systems. By leveraging networking principles, data fusion, and deep learning, we equip autonomous vehicles with the ability to detect anomalies and adapt their behavior accordingly, ensuring the safety of passengers, pedestrians, and other road users.
Collaborative Learning Environment: The Networking Lab is not just a physical space; it's a collaborative ecosystem that fosters interdisciplinary discussions, fosters creativity, and encourages hands-on exploration. Our team of researchers, engineers, and students work together to push the boundaries of what's possible in the world of autonomous vehicles and intelligent transportation systems. Whether you're an aspiring researcher, a curious student, or a passionate innovator, you'll find a welcoming space to contribute and learn.
Incremental Learning: Incremental learning involves developing algorithms and techniques that allow systems to adapt and learn from new data as it arrives over time. This is particularly useful when dealing with evolving environments, where models need to continuously improve their performance and adapt to changing conditions without forgetting the previously acquired knowledge.
2D/3D Object Detection: Object detection is the process of identifying and locating specific objects within images or videos. In the case of 2D object detection, this involves recognizing objects in 2D images, while 3D object detection extends this to capturing spatial information for objects in a 3D scene. This technology has applications in areas such as autonomous driving, robotics, and surveillance.
Medical Image Processing: Medical image processing focuses on the analysis, enhancement, and interpretation of images from medical imaging modalities such as X-rays, MRIs, and CT scans. This field is crucial for aiding medical professionals in diagnosing and treating various medical conditions accurately and non-invasively.
Anomaly Detection: Anomaly detection involves identifying patterns or instances that deviate significantly from the norm in a given dataset. This technique is valuable in various contexts, such as detecting fraud in financial transactions, identifying faults in industrial processes, and even spotting anomalies in medical images to diagnose rare conditions.
Autonomous Vehicles: Autonomous vehicles represent a transformative technology that aims to enable vehicles to navigate and make decisions without human intervention. This involves a fusion of technologies, including computer vision, machine learning, sensor integration, and real-time decision-making, to create safe and efficient self-driving systems.
| Projects | Grants |
IBN@TEIN: An AI-driven Intent-based Networking Platform for Service Deployment with QoS Assurance IBN(Intent based Networking) platform is an AI driven network technology to optimize the performance of TEIN network. PERN Pakistan is the counterpart of this network and is part of the consortium and will be participating in this project. The project will conduct activities under the objective of Asi@Connect objectives to benefit the Asi@Connect communities, thereby bridging the digital divide. The project is funded by international body, Asi@Connect.
| 34 Million PKR |
I have honor of the following scholarships:
Chinese scholarship council
NTUST University scholarship
HEC/IDP Scholarship
Jan 2022-Aug 2022 Post-Doctoral Researcher in Electrical Engineering, National Taipei University of Technology, Taiwan
During my Postdoc I worked on Anomaly detection, Person re-identification and Human Emotion detection. A tri-cycle project in collaboration with MIT.
Supervisor: Prof. Leehter Yao.
Sept 2018- Dec 2021 PhD in Electronics and Computer Engineering, National Taiwan University of Science and Technology, Taiwan
This Program was focused on core and advanced topics in Computer Engineering along with innovation and research methodologies.
Thesis: An edge-aware feature extraction stereo matching of binocular images Supervisor: Prof. Shanq-Jang Ruan.
Sept 2014-Aug 2016 Master of Science in Electrical Engineering, National University of Sciences and Technology, Pakistan
This Program was focused on core and advanced topics in communication engineering along with innovation and research methodologies.
Thesis: Image de-noising and compression using statistical-based thresholding in 2D Discrete wavelet transform. Supervisor: Prof. Dr. Imran Touqir
Sept 2010-Nov 2014 Bachelor in Telecommunication Engineering, University of Engineering and
Technology, Pakistan
Thesis: Cooperate cognitive networks; performance analysis by energy detection Technique”
Supervisor: Prof. Dr. Imran Khan
Job Description
Specific tasks include developing and testing UAV navigation models in simulation environments, integrating perception modules such as object detection or depth estimation, and evaluating navigation performance using predefined metrics. The intern may also assist in implementing reinforcement learning or control-based approaches, conducting simulation experiments, and contributing to research reports, presentations, or academic publications.
Preferred Intern Educational Level
Master’s or PhD student in Computer Science, Electrical Engineering, Robotics, Artificial Intelligence, or a closely related field.
Skill sets or Qualities
Basic knowledge of UAV systems, robotics, or autonomous navigation
Familiarity with Python and/or C++ programming
Understanding of machine learning or reinforcement learning concepts is preferred
Experience with simulation platforms (e.g., AirSim, Gazebo) is an advantage
Strong analytical and problem-solving skills
Ability to work independently and collaborate in a research-oriented environment
Good academic writing and communication skills in English
Job Description
Specific tasks include developing and testing UAV navigation models in simulation environments, integrating perception modules such as object detection or depth estimation, and evaluating navigation performance using predefined metrics. The intern may also assist in implementing reinforcement learning or control-based approaches, conducting simulation experiments, and contributing to research reports, presentations, or academic publications.
Preferred Intern Educational Level
Master’s or PhD student in Computer Science, Electrical Engineering, Robotics, Artificial Intelligence, or a closely related field.
Skill sets or Qualities
Basic knowledge of UAV systems, robotics, or autonomous navigation
Familiarity with Python and/or C++ programming
Understanding of machine learning or reinforcement learning concepts is preferred
Experience with simulation platforms (e.g., AirSim, Gazebo) is an advantage
Strong analytical and problem-solving skills
Ability to work independently and collaborate in a research-oriented environment
Good academic writing and communication skills in English