AI/ML-based Communications

Machine learning (ML)-based communication systems are a promising technology for 6G and beyond wireless communication systems. ML-based approaches can discover inherent linear or nonlinear characteristics from sufficient amount of data, which can be applied to wireless communication systems. As the structure of wireless communication systems is becoming more complex, designing optimal channel estimators and symbol detectors is extremely challenging, often impossible. Surprisingly, it has been shown that a deep neural network (DNN), e.g., deep convolutional neural network (CNN) or multi-layer perceptron (MLP), can achieve nearly optimal channel estimation and symbol detection performance. Also, wireless communications-based ML framework introduces various interesting systems that differ from the conventional systems, such as over-the-air federated learning systems. To make ML-based communication systems practical, however, the large training overhead and overfitting must be resolved, which require extensive research efforts.

In addition, there is also an active interest in semantic communication to significantly increase the data rate by exchanging 'semantic' of the data instead of the existing communication system that aims to transmit and receive 'bits' correctly. Various ideas such as DeepJSCC, reinforcement learning, and Generative AI model are being used to implement semantic communication system and AI-native communication system.

Recent publications

• H. Kim, J. Choi*, and D. J. Love, "ML-based Channel Prediction for Future Wireless Communications: Advances, Challenges, and Future Research Directions," submitted to IEEE Communications Magazine (COMMAG), Feb. 2024.

• H. Kim, J. Choi*, and D. J. Love, "Massive MIMO Channel Prediction Via Meta-Learning and Deep Denoising: Is a Small Dataset Enough?," IEEE Transactions on Wireless Communications (TWC), vol. 22, pp. 9278-9290, Dec. 2023.

• J. Cha, J. Choi*, and D. J. Love, "Practical Distributed Reception for Wireless Body Area Networks Using Supervised Learning," IEEE Transactions on Wireless Communications (TWC), vol. 21, no.7, pp. 4898-4908, Jul. 2022.

• H. Kim, S. Kim, H. Lee, C. Jang, Y. Choi, and J. Choi*, "Massive MIMO Channel Prediction: Kalman Filtering Vs. Machine Learning," IEEE Transactions on Communications (TCOM), vol. 69, no. 1, pp. 518-528, Jan. 2021.