RESEARCH

🤖 Machine Learning for Wireless Communications

[ENGLISH]
We integrate machine learning into wireless systems for enhanced channel prediction and adaptive training. The research includes temporal channel forecasting, meta-learning for rapid adaptation, and neural architectures for reduced training overhead.

[KOREAN]
무선 시스템에서의 채널 예측 정확도 향상과 적응적 학습을 위해 머신러닝을 도입하고 있습니다. 시간 기반 채널 예측, 소량 데이터 적응을 위한 메타러닝, 학습 오버헤드를 줄이는 신경망 구조 등에 중점을 둡니다.

📚 Related Publications

• Hwanjin Kim, Junil Choi, and David J. Love, "Massive MIMO Channel Prediction Via Meta-Learning and Deep Denoising: Is a Small Dataset Enough?," IEEE Transactions on Wireless Communications, vol. 22, no. 12, pp. 9278-9290, Dec. 2023.

• Hwanjin Kim, Sucheol Kim, Hyeongtaek Lee, Chulhee Jang, Yongyun Choi, and  Junil Choi, "Massive MIMO Channel Prediction: Kalman Filtering vs. Machine Learning," IEEE Transactions on Communications, vol. 69, no. 1, pp. 518-528,  Jan. 2021.

• Beomsoo Ko, Hwanjin Kim, Minje Kim, and Junil Choi, "Machine Learning-based Channel Prediction in Wideband Massive MIMO Systems with Small Overhead for Adaptive Online Training,"  IEEE Open Journal of the Communications Society, vol. 5, pp. 5289-5305, 2024.

• Jihoon Cha*, Hwanjin Kim*, and Junil Choi, "Meta-Learning-Based People Counting and Localization Models Employing CSI from Commodity WiFi NICs," submitted to IEEE Internet of Things Journal, Apr. 2025. (*equally contributed) [under review, R2]

🧠 Federated Learning for Wireless Communications

[ENGLISH]
We develop robust federated learning frameworks tailored to wireless networks. This includes over-the-air (OTA) aggregation under imperfect CSI, and scalable FL with RIS-aided and edge-deployed architectures.

[KOREAN]
무선 네트워크 특성을 반영한 견고한 연합학습 프레임워크를 개발하고 있습니다. 불완전한 채널 상태 정보 하에서의 OTA 연합학습, RIS 기반 확장형 학습 구조 등이 주요 연구 대상입니다.

📚 Related Publications

• Hwanjin Kim, Hongjae Nam, Jonggyu Jang, Christopher G. Brinton, and David J. Love, "Robust Over-the-Air Federated Learning Under Imperfect CSI," submitted to IEEE Transactions on Wireless Communications, Apr. 2025.

• Hwanjin Kim, Hongjae Nam, and David J. Love, "Robust Over-the-Air Federated Learning," 2024 58th Annual Conference on Information Sciences and Systems (CISS), Princeton, NJ, USA, 2024, pp. 1-6 .

🛰️ Satellite Communications

[ENGLISH]
We investigate resource allocation and error modeling for LEO and GEO satellite systems, along with analysis of pointing errors in inter-satellite Free Space Optical (FSO) communications.

[KOREAN]
LEO 및 GEO 위성 시스템의 자원 할당, 간섭 관리, 자유공간 광통신(FSO)에서의 오차 분석 등을 수행하고 있습니다. 특히, 위성 간 FSO 통신에서의 pointing error에 주목합니다.

📚 Related Publications

• Minje Kim, Hongjae Nam, Hyeongjun Park, Beomsoo Ko, Hwanjin Kim, and Junil Choi, "Analysis on Beam Misalignment Effect in Inter-Satellite FSO Links ," in preparation.

[ENGLISH]
This research explores advanced signal processing techniques for massive MIMO systems with low-resolution analog-to-digital converters (ADCs). We focus on mitigating quantization loss caused by 1-bit or few-bit ADCs through efficient channel and AoA estimation techniques.

[KOREAN]
본 연구는 저해상도 ADC를 사용하는 massive MIMO 시스템에서 발생하는 양자화 손실을 극복하기 위한 신호처리 기법을 다룹니다. 1비트 ADC 환경에서의 채널 추정과 AoA(도착각) 추정 알고리즘 개발에 중점을 둡니다.

📚 Related Publications

• Hwanjin Kim and Junil Choi, "Channel Estimation for Spatially/Temporally Correlated Massive MIMO Systems with One-Bit ADCs," EURASIP Journal on Wireless Communications and Networking, vol. 267, Dec. 2019. 

• Hwanjin Kim and Junil Choi, "Channel AoA Estimation for Massive MIMO Systems Using One-Bit ADCs," Journal of Communications and Networks, vol. 20, no. 4, pp. 374-382, Aug. 2018. 

• Hwanjin Kim and Junil Choi, "Channel Estimation for One-Bit Massive MIMO Systems Exploiting Spatio-Temporal Correlations," 2018 IEEE Global Communications Conference (GLOBECOM), Abu Dhabi, United Arab Emirates, 2018, pp. 1-6.  [Slide]