School of Interdisciplinary Engineering & Sciences

Deep and Reinforcement Learning Lab

The Deep Learning Laboratory (DLL) at NUST embarked on its journey in 2016 under the leadership of Prof. Dr. Faisal Shafait. As part of the National Center of Artificial Intelligence (NCAI), DLL focuses on pioneering advancements in artificial intelligence, with a special emphasis on machine learning, computer vision, and natural language processing. Through a comprehensive and interdisciplinary approach, DLL aims to address real-world challenges in diverse fields such as healthcare, education, environment, and industry. Since its inception, the lab has fostered collaborations with renowned international research groups and organizations, enabling the experimental validation and deployment of cutting-edge AI solutions. DLL is committed to innovating and translating computational methodologies into scalable applications that create a tangible impact.

PI’s Profile:

Dr. Faisal Shafait is a Professor at School of Electrical Engineering and Computer Science (SEECS) in National University of Sciences and Technology (NUST), Islamabad where he has been teaching for the past nine years. Additionally, he is also an Adjunct Professor at the School of Computer Science and Software Engineering at The University of Western Australia in Perth, Australia. Dr. Shafait is also the director of Deep Learning Lab (DLL) at National Center of Artificial Intelligence (NCAI), NUST, Islamabad, Pakistan. His research interest is in machine learning with a primary focus on computer vision and document image analysis. 

Having raised funding of over 300 Million PKR, he maintains a highly active research collaborations with various funding agencies including Higher Education Commission (HEC) Pakistan, German Academic Exchange Service (DAAD), Pakistan Science Foundation (PSF) and National ICT RDF. I also received the IAPR/ICDAR Young Investigator Award by the International Association of Pattern Recognition in 2019 and have recently been included in the list of the World’s Top 2% Scientists compiled by Stanford University.  In August 2023, Dr. Shafait was honored with the Pride of Performance award by the Government of Pakistan.

Expertise/Capabilities of Lab:

  • Remote Sensing & Digital Forestry:
    • Digital Forestry: AI models for forest inventory management, deforestation monitoring, and carbon credit estimation using geospatial analytics.
    • Precision Agriculture: Satellite and UAV-based crop monitoring and water resource estimation.
  • Healthcare & Medical AI:
    • NeuReader: An explainable AI (XAI) solution for automated EEG analysis and pre-diagnostic screening of neurological disorders (Epilepsy, Seizures).
    • iDoc: Portable, low-cost screening devices for early dengue fever detection and retinal image analysis.
  • Native Language Processing (NLP) & Judiciary:
    • Judicial Automation: AI-driven decision support systems and document automation for the Supreme Court of Pakistan and legal sectors.
    • Urdu AI: Development of a robust Urdu OCR and Urdu Automatic Speech Recognition (U-ASR) system for digitizing printed and handwritten documents.
  • Smart Cities & Surveillance (VREX):
    • VREX (Vehicle Recognition): Automated vehicle surveillance, license plate recognition, and make/model verification for gated communities.

Projects:

  1. Wearable EEG for pre-diagnostic screening of Mental Diseases in Rural Areas
  2. AI-Driven Decision Support System for Pakistan Judiciary
  3. Urdu Automatic Speech Recognition System (U-ASR)
  4. Audio/Video Analytics (AV Analytics)
  5. The Fish Biodiversity Estimation by Low-Cost Non-Destructive Video Based Sampling
  6. Forest Monitoring and Change Detection using Remote Sensing Data
  7. Non-destructive approach for detecting Marine life in Fresh Waters of Pakistan
  8. Media News Analysis
  9. Cursive Urdu Script Recognition using Deep Learning
  10. iDoc: A portable, cost-effective diagnostic screening device for early dengue fever detection
  11. Crop Monitoring via Remote Sensing from Earth Observation Satellites to UAV
  12. Water resource estimation by Satellite Based Image analysis (WASABI)
  13. Intelligent Data Extraction from Mortgage Closing Disclosure Forms using OCR and Natural Language Processing – Acrux Technologies
  14. Document Image Understanding and Editing using Tesseract OCR – DocIT Solutions
  15. Customized Irrigation and Climate Advisory Service through Citizen Science
  16. Real Time Pose Estimation and Human Activity Recognition with Computer Vision
  17. AI-Powered Chatbots for Real-Estate Portal
  18. VREX: Vehicle Recognition and Verification

Lab Equipment/Resources:

  • Equipped with multiple high-performance workstations
  • NVIDIA RTX 3090 GPUs installed for accelerated computing
  • Optimized for training deep learning models
  • Capable of handling large-scale datasets efficiently

Human Resource:

Typical Enrollment of lab researchers: 8-10 MS/PhD researchers

Contact Us:

Dr. Faisal Shafait
Contact No.: +92-51-9085-2151
Email: [email protected]
Website: https://dll.seecs.nust.edu.pk/