Jienan Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jienan Chen has a total of 127 co-authors. Here are the top co-authors by number of shared publications:
- Yakun Zhou
National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu, China
6 shared publications - Jianhao Hu
National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China
4 shared publications Jing Xing
National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu, China
4 shared publicationsPeizhi Lei
National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu, China
4 shared publicationsShengli Fu
Department of Electrical Engineering, University of North Texas, Denton, TX, USA
4 shared publications- Shengli Fu
Department of Electrical Engineering, University of North Texas, Denton, USA
4 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 72 (4) , 10152-10165
Energy-Efficient Precision-Scalable Inference for Battery-Powered Smart Cameras: A Spatial Deterministic Unary Computing Approach
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 72 (4) , 10152-10165
Energy-Efficient Precision-Scalable Inference for Battery-Powered Smart Cameras: A Spatial Deterministic Unary Computing Approach
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 9944-9956
Curriculum-Guided Heterogeneous Multi-Agent Intelligence for Multi-UAV Cooperative ISAC
Seamlessly unifying communication and sensing, sixth-generation (6G) networks are poised to transform into intelligent platforms with high spectral–energy efficiency and real-time environmental awareness. In the low-altitude economy, unmanned aerial vehicles (UAVs) enable air–ground integrated sensing and communication (ISAC) for applications such as logistics and inspection, yet most studies focus on single-UAV or homogeneous-agent designs. In contrast, this paper proposes a multi-UAV cooperative ISAC system that enables heterogeneous-agent collaboration between multiple UAVs and a ground base station (BS) for joint target sensing, tracking, and communication. The system is formulated as a posterior Cramér–Rao bound (PCRB) minimization problem under communication performance constraints, utilizing joint trajectory–beamforming optimization. To tackle the NP-hard nature of this problem, we design a curriculum-based heterogeneous-agent proximal policy optimization (C-HAPPO) algorithm, where curriculum learning guides progressive policy refinement and Kronecker/QR decomposition mitigates action dimensionality. Simulation results show that the proposed approach achieves more than a 30% improvement in sensing performance, faster convergence, and higher tracking accuracy than existing baselines, demonstrating its scalability and effectiveness for complex multi-UAV ISAC scenarios.
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 9944-9956
Curriculum-Guided Heterogeneous Multi-Agent Intelligence for Multi-UAV Cooperative ISAC
Seamlessly unifying communication and sensing, sixth-generation (6G) networks are poised to transform into intelligent platforms with high spectral–energy efficiency and real-time environmental awareness. In the low-altitude economy, unmanned aerial vehicles (UAVs) enable air–ground integrated sensing and communication (ISAC) for applications such as logistics and inspection, yet most studies focus on single-UAV or homogeneous-agent designs. In contrast, this paper proposes a multi-UAV cooperative ISAC system that enables heterogeneous-agent collaboration between multiple UAVs and a ground base station (BS) for joint target sensing, tracking, and communication. The system is formulated as a posterior Cramér–Rao bound (PCRB) minimization problem under communication performance constraints, utilizing joint trajectory–beamforming optimization. To tackle the NP-hard nature of this problem, we design a curriculum-based heterogeneous-agent proximal policy optimization (C-HAPPO) algorithm, where curriculum learning guides progressive policy refinement and Kronecker/QR decomposition mitigates action dimensionality. Simulation results show that the proposed approach achieves more than a 30% improvement in sensing performance, faster convergence, and higher tracking accuracy than existing baselines, demonstrating its scalability and effectiveness for complex multi-UAV ISAC scenarios.
- Open Access
- 27 May 2026
- Published by Elsevier in Digital Communications and Networks
- Vol. 12 (8) , 1266-1277
Approximate dynamic precision computation in large-scale MIMO systems: analysis and applications
- 27 May 2026
- Published by Elsevier in Digital Communications and Networks
- Vol. 12 (8) , 1266-1277
Open AccessApproximate dynamic precision computation in large-scale MIMO systems: analysis and applications
- 20 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (3) , 176-183
Large AI Model for Multimodal Integrated Sensing and Communication
Multimodal integrated sensing and communication (ISAC) exploits heterogeneous modalities to enhance perception accuracy, communication robustness, and environmental adaptability, becoming a key enabler of the Internet of Everything (IoE). Nevertheless, existing multimodal ISAC systems remain constrained by heterogeneous data characteristics, dynamic modality availability, and the limited adaptability of current fusion strategies. To overcome these limitations, we propose a LAM-enabled multimodal ISAC (LAM-MSAC) framework. First, modality-specific feature encoders are introduced to provide native compatibility for diverse sensing data. Second, to cope with dynamically changing modality combinations, we design a Mixture-of-Experts (MoE) fusion module in which multiple experts process different modal combinations. Finally, the MoE structure activates only a subset of experts for each inference, substantially reducing computational cost without sacrificing model capacity. A case study shows that LAM-MSAC achieves over 90% beam prediction accuracy while significantly lowering computation compared with maintaining multiple single- or multi-modality models. Potential research directions are further discussed to advance the integration of LAMs into multimodal ISAC.
- 20 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (3) , 176-183
Large AI Model for Multimodal Integrated Sensing and Communication
Multimodal integrated sensing and communication (ISAC) exploits heterogeneous modalities to enhance perception accuracy, communication robustness, and environmental adaptability, becoming a key enabler of the Internet of Everything (IoE). Nevertheless, existing multimodal ISAC systems remain constrained by heterogeneous data characteristics, dynamic modality availability, and the limited adaptability of current fusion strategies. To overcome these limitations, we propose a LAM-enabled multimodal ISAC (LAM-MSAC) framework. First, modality-specific feature encoders are introduced to provide native compatibility for diverse sensing data. Second, to cope with dynamically changing modality combinations, we design a Mixture-of-Experts (MoE) fusion module in which multiple experts process different modal combinations. Finally, the MoE structure activates only a subset of experts for each inference, substantially reducing computational cost without sacrificing model capacity. A case study shows that LAM-MSAC achieves over 90% beam prediction accuracy while significantly lowering computation compared with maintaining multiple single- or multi-modality models. Potential research directions are further discussed to advance the integration of LAMs into multimodal ISAC.
- Open Access
An End-to-End Neural Network Transceiver Design for OFDM System with FPGA-Accelerated Implementation
The evolution toward sixth-generation (6G) wireless networks demands high-performance transceiver architectures capable of handling complex and dynamic environments. Conventional orthogonal frequency-division multiplexing (OFDM) receivers rely on cascaded discrete Fourier transform (DFT) and demodulation blocks, which are prone to inter-stage error propagation and suboptimal global performance. In this work, we propose two neural network (NN) models DFT-Net and Demodulation-Net (Demod-Net) to jointly replace the IDFT/DFT and demodulation modules in an OFDM transceiver. The models are trained end-to-end (E2E) to minimize bit error rate (BER) while preserving operator equivalence for hybrid deployment. A customized DFT-Demodulation Net Accelerator (DDNA) is further developed to efficiently map the proposed networks onto field-programmable gate array (FPGA) platforms. Leveraging fine-grained pipelining and block matrix operations, DDNA achieves high throughput and flexibility under stringent latency constraints. Experimental results show that the DL-based transceiver consistently outperforms the conventional OFDM system across multiple modulation schemes. With only a modest increase in hardware resource usage, it achieves approximately 1.5 dB BER gain and up to 66\% lower execution time.
Open AccessAn End-to-End Neural Network Transceiver Design for OFDM System with FPGA-Accelerated Implementation
The evolution toward sixth-generation (6G) wireless networks demands high-performance transceiver architectures capable of handling complex and dynamic environments. Conventional orthogonal frequency-division multiplexing (OFDM) receivers rely on cascaded discrete Fourier transform (DFT) and demodulation blocks, which are prone to inter-stage error propagation and suboptimal global performance. In this work, we propose two neural network (NN) models DFT-Net and Demodulation-Net (Demod-Net) to jointly replace the IDFT/DFT and demodulation modules in an OFDM transceiver. The models are trained end-to-end (E2E) to minimize bit error rate (BER) while preserving operator equivalence for hybrid deployment. A customized DFT-Demodulation Net Accelerator (DDNA) is further developed to efficiently map the proposed networks onto field-programmable gate array (FPGA) platforms. Leveraging fine-grained pipelining and block matrix operations, DDNA achieves high throughput and flexibility under stringent latency constraints. Experimental results show that the DL-based transceiver consistently outperforms the conventional OFDM system across multiple modulation schemes. With only a modest increase in hardware resource usage, it achieves approximately 1.5 dB BER gain and up to 66\% lower execution time.
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 4433-4447
Toward Communication–Computation Integrated Architectures for AI-Agent Communication Networks
As communication technologies evolve, the AI agent communication network (ACN) is expected to play a critical role in enabling future wireless services. These networks must meet diverse connectivity demands, provide enhanced intelligence, and provide reliable communication support for AI agents. In this work, we propose an integrated computation-communication (ICC) architecture that jointly addresses baseband signal processing and neural network (NN) inference within a shared computing framework. A unified modeling approach is established by combining multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) channel representation with neural network–based application modeling. On the communication side, we derive spectral efficiency and channel capacity expressions that incorporate quantization error, transmit power, and noise, thus characterizing hardware-induced constraints on channel performance. On the computation side, we analyze the model scaling in terms of depth, width, and input resolution. Building upon this framework, we formulate the joint resource allocation challenge as a Markov Decision Process (MDP). We introduce a learning-driven allocation algorithm that uniquely combines Gibbs sampling with a Proximal Policy Optimization (PPO) based reinforcement learning agent to solve this MDP. This enables the system to dynamically distribute resources across communication and computation, adapting to variations in datasets, Signal-to-Noise Ratio (SNR) regimes, model configurations, and scenario constraints. The proposed approach improves both task completion time and prediction accuracy compared to conventional fixed resource allocation schemes. Theoretical analysis and simulation results validate the effectiveness of the proposed architecture, highlighting its potential for efficient cross-layer co-design in next-generation ACNs.
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 4433-4447
Toward Communication–Computation Integrated Architectures for AI-Agent Communication Networks
As communication technologies evolve, the AI agent communication network (ACN) is expected to play a critical role in enabling future wireless services. These networks must meet diverse connectivity demands, provide enhanced intelligence, and provide reliable communication support for AI agents. In this work, we propose an integrated computation-communication (ICC) architecture that jointly addresses baseband signal processing and neural network (NN) inference within a shared computing framework. A unified modeling approach is established by combining multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) channel representation with neural network–based application modeling. On the communication side, we derive spectral efficiency and channel capacity expressions that incorporate quantization error, transmit power, and noise, thus characterizing hardware-induced constraints on channel performance. On the computation side, we analyze the model scaling in terms of depth, width, and input resolution. Building upon this framework, we formulate the joint resource allocation challenge as a Markov Decision Process (MDP). We introduce a learning-driven allocation algorithm that uniquely combines Gibbs sampling with a Proximal Policy Optimization (PPO) based reinforcement learning agent to solve this MDP. This enables the system to dynamically distribute resources across communication and computation, adapting to variations in datasets, Signal-to-Noise Ratio (SNR) regimes, model configurations, and scenario constraints. The proposed approach improves both task completion time and prediction accuracy compared to conventional fixed resource allocation schemes. Theoretical analysis and simulation results validate the effectiveness of the proposed architecture, highlighting its potential for efficient cross-layer co-design in next-generation ACNs.
- Open Access
Channel Charting based Fast Beam Tracking Design and Implementation
In the beyond fifth-generation (B5G) and upcoming sixth-generation (6G) wireless communication systems, millimeter (mmWave) wave technology is a promising solution for offering additional bandwidth resources and mitigating spectrum congestion. Beam tracking is an essential procedure for providing reliable communication services in the mmWave communication system, with the challenge of providing consistent and accurate tracking performance. In this study, we introduce a low-overhead beam tracking algorithm based on channel charting, which significantly reduces beam scanning times during the tracking process. By projecting the beam information to the channel chart, the beam tracking problem is transformed into the acquisition of the beam cluster in the channel chart. Leveraging contrastive learning, the proposed channel chart projects high-dimensional channel state information into a low-dimensional feature space that preserves spatial proximities. Using a dynamic candidate beam acquisition strategy, the complexity of our beam tracking algorithm is significantly reduced. The proposed algorithm significantly reduces scanning complexity while maintaining high prediction accuracy, achieving an accuracy of 98.27\% in simulation environments. Compared to existing methods, the proposed method can reduce beam scanning times by up to 55.9\%. In addition, we also performed field tests, and the measured results demonstrated excellent communication quality during mobility.
Open AccessChannel Charting based Fast Beam Tracking Design and Implementation
In the beyond fifth-generation (B5G) and upcoming sixth-generation (6G) wireless communication systems, millimeter (mmWave) wave technology is a promising solution for offering additional bandwidth resources and mitigating spectrum congestion. Beam tracking is an essential procedure for providing reliable communication services in the mmWave communication system, with the challenge of providing consistent and accurate tracking performance. In this study, we introduce a low-overhead beam tracking algorithm based on channel charting, which significantly reduces beam scanning times during the tracking process. By projecting the beam information to the channel chart, the beam tracking problem is transformed into the acquisition of the beam cluster in the channel chart. Leveraging contrastive learning, the proposed channel chart projects high-dimensional channel state information into a low-dimensional feature space that preserves spatial proximities. Using a dynamic candidate beam acquisition strategy, the complexity of our beam tracking algorithm is significantly reduced. The proposed algorithm significantly reduces scanning complexity while maintaining high prediction accuracy, achieving an accuracy of 98.27\% in simulation environments. Compared to existing methods, the proposed method can reduce beam scanning times by up to 55.9\%. In addition, we also performed field tests, and the measured results demonstrated excellent communication quality during mobility.
- 5 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (12) , 15004-15019
Low-Complexity Inverse Matrix Mini-Batch Gradient Descent for MIMO Equalization and Precoding
As the size of base station antenna arrays continues to grow, even with linear processing algorithms, the computational complexity and power consumption required for massive MIMO equalization or precoding (EoP) matrix computation increase exponentially. This paper proposes an inverse matrix minibatch gradient descent (IM-MBGD) method for MIMO EoP. The proposed method leverages minibatch gradient descent to compute the pseudo-inverse of the Gram matrix instead of directly calculating the EoP matrix. Since the pseudo-inverse matrix has significantly lower dimensions compared to the EoP matrix, this approach effectively reduces computational complexity and accelerates convergence. Based on our convergence analysis, to further minimize the iteration time and improve the accuracy of the EoP matrix, we optimize the IM-MBGD method using a finite-alphabet neighborhood search. The finite-alphabet search performs neighborhood optimization to achieve the optimal solution. Compared to state-of-the-art alphabet-based equalizers, our proposed method achieves a 14-fold reduction in computational complexity for EoP matrix calculation. Furthermore, in terms of storage and the overall equalization process, our method reduces overhead by 80% compared to linear equalizers.
- 5 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (12) , 15004-15019
Low-Complexity Inverse Matrix Mini-Batch Gradient Descent for MIMO Equalization and Precoding
As the size of base station antenna arrays continues to grow, even with linear processing algorithms, the computational complexity and power consumption required for massive MIMO equalization or precoding (EoP) matrix computation increase exponentially. This paper proposes an inverse matrix minibatch gradient descent (IM-MBGD) method for MIMO EoP. The proposed method leverages minibatch gradient descent to compute the pseudo-inverse of the Gram matrix instead of directly calculating the EoP matrix. Since the pseudo-inverse matrix has significantly lower dimensions compared to the EoP matrix, this approach effectively reduces computational complexity and accelerates convergence. Based on our convergence analysis, to further minimize the iteration time and improve the accuracy of the EoP matrix, we optimize the IM-MBGD method using a finite-alphabet neighborhood search. The finite-alphabet search performs neighborhood optimization to achieve the optimal solution. Compared to state-of-the-art alphabet-based equalizers, our proposed method achieves a 14-fold reduction in computational complexity for EoP matrix calculation. Furthermore, in terms of storage and the overall equalization process, our method reduces overhead by 80% compared to linear equalizers.
- 27 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (1) , 71-82
PCBRouteNet: Dynamic Quadrilateral-Flow Dataset and Benchmarks for Machine-Learning PCB Routing
As the complexity and density of electronic components continue to increase, manual printed circuit board (PCB) routing has become an increasingly labor-intensive and costly task. However, the lack of large, publicly available datasets for training machine-learning (ML) models has hindered potential advancements in this field. To address this gap, we introduce PCBRouteNet, a comprehensive, large-scale dataset specifically designed to accelerate ML innovations in automated PCB routing. To handle the high complexity of PCB data and enhance extraction efficiency, we propose a dynamic, adjustable, quadrilateral network flow model. This model constructs a network flow graph composed of quadrilateral tiles, efficiently transforming the original design data into a network flow-based format. This format facilitates feature extraction for both global and detailed routing tasks. Additionally, we introduce and analyze various flow-encoding methods to explore the generalization and relationships between data size and network parameters, leveraging scaling laws. Our dataset features a diverse array of layouts with varying complexities, such as multilayer boards and high-density interconnects. Furthermore, we propose several practical ML tasks that utilize PCBRouteNet to demonstrate its potential in improving the efficiency and effectiveness of automated PCB routing solutions.
- 27 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (1) , 71-82
PCBRouteNet: Dynamic Quadrilateral-Flow Dataset and Benchmarks for Machine-Learning PCB Routing
As the complexity and density of electronic components continue to increase, manual printed circuit board (PCB) routing has become an increasingly labor-intensive and costly task. However, the lack of large, publicly available datasets for training machine-learning (ML) models has hindered potential advancements in this field. To address this gap, we introduce PCBRouteNet, a comprehensive, large-scale dataset specifically designed to accelerate ML innovations in automated PCB routing. To handle the high complexity of PCB data and enhance extraction efficiency, we propose a dynamic, adjustable, quadrilateral network flow model. This model constructs a network flow graph composed of quadrilateral tiles, efficiently transforming the original design data into a network flow-based format. This format facilitates feature extraction for both global and detailed routing tasks. Additionally, we introduce and analyze various flow-encoding methods to explore the generalization and relationships between data size and network parameters, leveraging scaling laws. Our dataset features a diverse array of layouts with varying complexities, such as multilayer boards and high-density interconnects. Furthermore, we propose several practical ML tasks that utilize PCBRouteNet to demonstrate its potential in improving the efficiency and effectiveness of automated PCB routing solutions.