“Creating smart applications and novel characterization techniques for electromagnetic fields and waves in electrical engineering is my passion. In research and education we explore future solutions for electromagnetic compatibility (EMC), signal integrity (SI), and power intergrity (PI) in combination with machine learning and AI.”

“There is always a better way to enhance your designs through increasingly advanced modeling and measurement techniques in electromagnetic (EM) engineering. In science and engineering, we address challenging problems and develop attractive solutions in areas such as electromagnetic compatibility (EMC), bioelectromagnetics (BioEM), and reconfigurable EM surfaces, integrating machine learning techniques and software-defined hardware.”

“Asking insightful questions and trying to provide effective answers helps us grow. I am passionate about tackling complex electromagnetic problems and devising innovative solutions. My current focus is on adapting machine learning methods to address bio-electromagnetic compatibility issues, which are crucial for human and environment safety. My goal is to develop efficient, comprehensive frameworks that enhance performance in solving these vital challenges and assist to deliver reliable results.”

“I am focused on advancing the development of ultra-high-speed PCB interconnects through innovative research and technology. Leveraging machine learning methods, my goal is to enhance the design process for high-speed connections, aiming for faster and more efficient data transport. I am working on creating a comprehensive SI/PI database to develop a hybrid design flow that combines data-driven and physics-based methods for improved performance.”

“The way forward to meet the technological challenges of solving humanity’s problems, such as combating climate change, is through scientific progress. My research is on EMC filters for electric vehicles and is in collaboration with a partner from industry. I explore new approaches to finding innovative and relevant solutions to improve development by means of modeling, simulation, and data-driven methods.”

A fundamental principle for effective machine learning implementations in electrical engineering is maintaining a holistic perspective when addressing specific problems. In my research, I draw inspiration from a range of fields. Integrating physical knowledge with data-driven methodologies is essential for novel tools that assist in ensuring the power integrity compliance of PCBs.

” Harnessing the power of machine learning (ML) tools to develop smart solutions in the fields of electromagnetic compatibility (EMC), signal integrity (SI), and power integrity (PI) is what keeps me busy. I strive to adapt and use ML in data efficient paradigms to enhance performance and reliability. I am dedicated to socially responsible engineering for technology that benefits humanity. ”