Artificial intelligence (AI) is stimulating innovation by combining and merging with science and technology in various fields. There are active attempts to apply AI in the electromagnetic field as well. Accordingly, experts from the Korean Institute of Electromagnetic Engineering and Science gathered together to put their heads together to prepare for the future of electromagnetic waves and AI convergence.

The Korea Electromagnetic Engineering Society's Radio Education Research Group held a workshop on the topic of 'Fusion of AI and Electromagnetic Technology' at the Telecommunications Technology Association (TTA) in Seongnam City on the 31st.

Park Hak-byeong, chairman of the Radio Education Research Association, said in his opening remarks, “In recent years, artificial intelligence has been introduced to various fields of technology, and attempts are being made to utilize AI in electromagnetic wave design and analysis.” He added, “I believe that electromagnetic wave design and construction methods will change significantly in the near future.”

This workshop featured lectures and discussions on the latest research trends in the technological convergence of AI and electromagnetic waves.

Through a total of four sessions, including △Physics AI & Generative AI (Moderator: Professor Kyung-young Jeong of Hanyang University), △Digital Twin (Moderator: Senior Researcher Hyung-cheol Moon of TTA), △Deep Learning and Electromagnetic Technology (Moderator: Professor Jae-young Jeong of Seoul National University of Science and Technology), and △Panel Discussion (Moderator: Hak-byung Park, Samsung Electronics Professional), insights on trends in AI technology application in the electromagnetic field and the latest research were shared.

Cho Chun-sik, the president of the Korean Institute of Electromagnetic Engineering and Science (professor at Korea Aerospace University), said, “Recently, major companies are developing generative AI platforms to improve productivity, and the use of AI is expected to begin in earnest this year.” He added, “A lot of research and workshops related to AI are being conducted in the field of electromagnetic technology, and deep learning technology is being widely applied in areas such as antennas, radar, medical care, noise analysis, and spectrum analysis.”

In addition, President Cho Chun-sik added, “I hope that this workshop will be an opportunity for electromagnetic technology practitioners to think about the capabilities they need and prepare for the future.”

■ AI Future Talks by Electromagnetic Field Expertsrong>

In the field of electromagnetic waves, discussions were held on various perspectives such as AI technology convergence and the resulting ethical issues, educational perspectives, future capabilities, and research directions through panel discussions.

When asked about the necessity of introducing AI in electromagnetic technology, Professor Kim Young-wook of Sogang University stated, “Electromagnetic wave (EM) simulation is a task that requires a long time, so introducing AI can help in terms of optimization.” He also stated, “The problem of population decline in Korean society is directly related to the decrease in RF manpower, so in order to meet the ever-increasing hardware specifications, it will be necessary to reduce time, manpower, and cost with the help of AI.”

Professor Jeong-Jun Han of Hanyang University questioned the applicability of AI to electromagnetic waves in the direction of simply collecting a lot of data and training it, and pointed out that “it seems that the amount of investment would be excessive for individual companies to create a foundation model equivalent to a large language model (LLM) in EM, so we need to think about how to improve data efficiency.”

In addition, concerns have been raised that individual companies are highly unlikely to disclose their own data as a prerequisite for creating EM foundation models for PCB and RF designs. Design data is a core element of each company, so it is difficult to create a model by exposing it externally.

Accordingly, Professor Kim Young-wook proposed a methodology to create a single foundation model by conducting federated learning based on the models that each company individually models.

In the development of hospital and healthcare applications, collecting data from each hospital is also considered a challenge. Accordingly, federated learning, which trains AI models without directly sharing individual data, is of the opinion that it can contribute to building an EM foundation model while protecting individual company design IP.

In addition, the panel opinion predicted the high cost of AI countermeasure design and raised the view that it would be difficult to apply the advanced EM foundation model to PCB design. From the perspective of applying this to the field, it was suggested to approach it in the direction of utilizing it in high-cost countermeasure designs that require a large layout, such as system-level EMC.

■ Electromagnetic wave-AI fusion, excessive data and resources must be resolved first

Professor Jeong-Jun Jeong recently introduced research trends in which electromagnetic waves are used to implement artificial intelligence. He explained that AI operations consume excessive GPU resources, and optical analog computing (OAC) with multiple layers can reduce the excessive power consumption in convolutional layers or hidden layers, and that the concept idea is being studied in related academic circles.

Also, a method of implementing edge detection of objects using metalens, metaelements, etc. was introduced. The image extracted here has a problem of deterioration, and a method of restoring it using a neural network is being studied. This technology is expected to be applicable to radar image detection and radio wave technology.

Professor Jeong said that if the concept of deep learning backpropagation is introduced to electromagnetic waves and implemented with Maxwell's equations, it is expected to solve existing problems that require tens of thousands to millions of training data for simulation, and that he is conducting research on this.

Meanwhile, Professor Jeong's Radio-AI Lab is conducting research and development on: △Radio/optical device design techniques using AI algorithms; △Metamaterials, metasurfaces, and metalens.