1. Home »
  2. Supervisor: Dr. Amina Jameel
Supervisor: Dr. Amina Jameel

 

Explainable AI for Embedded Systems: Enhancing  Interpretability of Deep Learning Models for Edge Devices

 

Supervisor: Dr. Amina Jameel, Senior Professor

Campus/School/Dept: BUIC/BSEAS/CE

Supervisory Record: 

  • PhD Produced: 4
  • PhD Enrolled: NA
  • MS/MPhil Produced: 4
  • MS/MPhil Enrolled: NA

 

Topic Brief Description: 

As AI becomes increasingly integrated into embedded systems, such as wearable devices, autonomous drones, and edge IoT devices, the need for explainable AI (XAI) becomes critical. Users and developers require clear, interpretable insights into the decisions made by these systems, especially in safety-critical applications. However, most XAI methods are resource-intensive, making them unsuitable for real-time deployment on edge devices with limited computational power. This research focuses on designing lightweight XAI techniques specifically optimized for embedded systems.

 

Research Objectives/Deliverables: 

  1. To develop resource-efficient XAI algorithms suitable for embedded systems.
  2. Create a framework for visualizing model decisions in real-time on edge devices.
  3. Evaluate the trade-offs between explainability, model performance, and computational efficiency.

 

Research Questions:  

  1. How can XAI techniques be adapted to operate on edge devices with constrained resources?
  2. What visual and textual explanation methods are most effective for non-technical users of embedded AI systems?
  3. What are the computational trade-offs between achieving high explainability and maintaining system performance in real-time?

 

Candidate’s Eligibility Profile: 

  1. The applicant must have an MS/MPhil/Equivalent degree in Computer Engineering, Electrical Engineering, Computer Science, or a related field, with a strong emphasis on AI, embedded systems, or software engineering with CGPA >0. Besides, applicants must have a strong background in mathematics, optimization theory and related fields.
  2. Experience with programming languages and familiarity with machine learning frameworks like TensorFlow, PyTorch, or Scikit-learn. Candidates should thrive in an international environment and have excellent communication skills to actively contribute to team research efforts.
  3. Proficiency in spoken and written English is essential. We value independence and responsibility while promoting teamwork and collaboration among colleagues.