9 June 2023 in IEEE Internet of Things Journal
Mobile communication technology is evolving rapidly and becoming increasingly ubiquitous, thereby increasing the demand for uplink data-intensive applications (e.g., personal broadcasting and live augmented/virtual reality videos). Recently, to facilitate a cost-effective and smooth transition from 4G to 5G networks, most carriers leverage existing 4G infrastructures using a dual connectivity (DC) feature. DC increases uplink throughput and mobility robustness; however, it also causes unprecedented dynamic fluctuations in radio channels due to the coverage discrepancy between 4G and 5G networks. Thus, in this article, we propose a self-attention-based deep learning model to predict uplink radio resources in 5G DC. We trained the proposed model on commercial 5G DC traffic data from three major carriers in South Korea and obtained an average prediction accuracy of 95.08% under various mobility and cell-load conditions. The proposed model explains the rationale for the obtained predictions by highlighting the parts of the input time-series data that are important to realize accurate prediction. We also demonstrate the usability of the proposed model using a network emulator based on real-world 5G trace data. Extensive evaluations demonstrate that the existing congestion control algorithms can achieve excellent performance when used with the proposed model.
4 March 2026 in IEEE Transactions on Green Communications and Networking
Channel estimation in backscatter communication (BackCom) systems remains a significant challenge due to the battery-free device nature, which often fail to respond to traditional pilot signals. While prior works have predominantly relied on simulation-based evaluations with ideal reception assumptions, such methods fall short in practical scenarios where pilot reachability and BackCom devices’ response cannot be guaranteed. In this work, we present the fully implemented and evaluated channel estimation framework for battery-free BackCom systems using a real-world testbed. We introduce Directional Random Phase Perturbation, a novel pilot beamforming technique that combines directional scanning with randomized phase perturbation to induce backscatter responses even in environments where pilot signal reachability is uncertain. We further propose a neural channel estimation model based on self-attention. The model is carefully designed to integrate both pilot signal features and Least Square-based (LS) initial estimates as inputs and to explicitly decompose the channel into transmit and receive components for improved estimation accuracy. In addition, we introduce task-specific data augmentation methods, including random phase shifting and antenna pseudo-flipping, to enhance the model under limited training data. Evaluated on the real testbed, our framework improves beamforming gain by up to 73.8% and achieves 28.8% higher data transmission success rates compared to conventional methods.
2 March 2022 in IEEE Access
Backscatter communication is a promising technology in the hyper-connected era. Because of its ultra-low energy consumption, it can be used in various applications, but there are performance issues due to high uncertainty. We propose a signal-to-data translation model that can transform an entire backscatter signal into the original data. To train the translation model, we developed an automation framework that can efficiently collect datasets.We also proposed a data augmentation technique suitable for backscatter signals. In extensive experiments, our model significantly outperformed a simple rule-based decoding method and a commercial RFID reader. The proposed model showed consistent performance gains across different locations, obstacles, and mobility scenarios indicating a good generalization of learning.