The AUT Journal of Electrical Engineering is pleased to announce an upcoming Special Issue titled Large Language Models and Foundation Intelligence in Electrical Engineering: From Power Grids to Biomedical Devices.
As large language models (LLMs) and foundation AI rapidly reshape how engineers design, operate, and maintain complex electrical and electronic systems, this special issue invites original research articles, critical reviews, survey articles, and case studies exploring their applications, adaptations, and challenges across the discipline. We particularly welcome contributions that bridge the gap between general-purpose AI capabilities and the domain-specific demands of electrical engineering, such as scarce data, tight power and latency budgets, and safety-critical reliability, as well as novel AI concepts, methods, and applications relevant to electrical engineering as a whole.
Topics of Interest
Power and Energy: LLM-driven grid operation, natural-language SCADA/EMS interfaces, fault diagnosis, renewable forecasting, and battery state-of-health assessment.
Infrastructure Inspection: Multimodal defect detection for transmission lines and substations, alongside automated inspection reporting from drone imagery.
Control and Automation: LLM-assisted control code generation and verification, safe adaptive control, industrial robotics, and human-machine collaboration.
Electronics and Instrumentation: LLM-assisted electronic design automation (EDA), AI-based instrument calibration, and lightweight on-device models for real-time sensing.
Computer Systems: Foundation models for hardware design and security, trustworthy and explainable AI subsystems, edge computing, and digital-twin simulation.
Telecommunications and Electromagnetics: Wireless network optimization, 6G automation, AI-accelerated electromagnetic design, and semantic communication systems.
Biomedical Technologies: Foundation and vision-language models for medical signal and image analysis, point-of-care diagnostics, and on-device wearable health monitoring.
Cross-Cutting Themes: Safety-critical explainability, data-efficient fine-tuning, low-power edge deployment, human-AI workflows, and engineering domain benchmarks.
Submission Details
Guest Editors: Prof. Mohammad Rahmati and Prof. Mohammad Mehdi Ebadzadeh (Department of Computer Engineering, Amirkabir University of Technology).
Accepted Submissions: Original research articles of archival value, critical reviews, survey articles, and case studies.
Submission Deadline: 28 February 2027.
For more information, click on the news image.