Shibao Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shibao Li has a total of 243 co-authors. Here are the top co-authors by number of shared publications:
- Jianhang Liu
Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China
29 shared publications Jianhang Liu
22 shared publications- Xuerong Cui
China University of Petroleum (East China)
22 shared publications Xuerong Cui
18 shared publications- Tingpei Huang
China University of Petroleum (East China), Qingdao Institute of Software, College of Computer Science and Technology, Qingdao, China
10 shared publications - Bin Jiang
China University of Petroleum (East China)
9 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (10) , 22216-22227
CoGFormer: A Context-Gated Spatial Transformer With Temporal-Spatial Gated Graph Convolution for Traffic Flow Forecasting
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (10) , 22216-22227
CoGFormer: A Context-Gated Spatial Transformer With Temporal-Spatial Gated Graph Convolution for Traffic Flow Forecasting
- 29 June 2026
- Published by Elsevier in Journal of the Franklin Institute
- Vol. 363 (12)
Reconfigurable intelligent surface assisted UAV-to-everything communications: Beamforming optimization
- 29 June 2026
- Published by Elsevier in Journal of the Franklin Institute
- Vol. 363 (12)
Reconfigurable intelligent surface assisted UAV-to-everything communications: Beamforming optimization
- 13 June 2026
- Published by Elsevier in Physical Communication
- Vol. 78
A robust multipath delay estimation method for over-the-air computation
- 13 June 2026
- Published by Elsevier in Physical Communication
- Vol. 78
A robust multipath delay estimation method for over-the-air computation
- Open Access
- 3 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 84772-84785
Low-Complexity PAPR Reduction Method in RIS-OFDM Systems Using Hierarchical Codebook
Reconfigurable Intelligent Surface (RIS)-assisted OFDM millimeter-wave communication is a key technology for achieving high spectral efficiency and wide coverage in 6G. However, the inherent peak-to-average power ratio (PAPR) issue of OFDM persists. Considering the high computational complexity and poor adaptability to RIS hardware of traditional PAPR suppression algorithms, we suggest a novel PAPR reduction method based on hierarchical codebooks(HC). First, leveraging the HC structure in RIS beam training, a PAPR-aware hierarchical phase-perturbation codebook has been designed. Then, based on this codebook, both the classical selective mapping(SLM) and partial transmission sequence(PTS) algorithms were enhanced, resulting in two low-overhead, hardware-friendly PAPR suppression schemes: HC-SLM and HC-PTS. Simulation results demonstrate that under typical system configurations, the proposed algorithm reduces computational complexity by approximately 50-70% and decreases sideband information overhead to less than one-quarter of that achieved by conventional methods. Additionally, under various modulation schemes and typical signal-to-noise ratio(SNR) conditions, when the complementary cumulative distribution function (CCDF) is 10⁻³, the PAPR can be reduced by 0.1–0.5 dB. Its performance, constrained by low computational complexity, approaches and even partially surpasses that of traditional exhaustive search methods with significantly higher computational overhead. This provides an effective solution for the low-power, high-efficiency practical deployment of RIS-OFDM systems.
- 3 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 84772-84785
Open AccessLow-Complexity PAPR Reduction Method in RIS-OFDM Systems Using Hierarchical Codebook
Reconfigurable Intelligent Surface (RIS)-assisted OFDM millimeter-wave communication is a key technology for achieving high spectral efficiency and wide coverage in 6G. However, the inherent peak-to-average power ratio (PAPR) issue of OFDM persists. Considering the high computational complexity and poor adaptability to RIS hardware of traditional PAPR suppression algorithms, we suggest a novel PAPR reduction method based on hierarchical codebooks(HC). First, leveraging the HC structure in RIS beam training, a PAPR-aware hierarchical phase-perturbation codebook has been designed. Then, based on this codebook, both the classical selective mapping(SLM) and partial transmission sequence(PTS) algorithms were enhanced, resulting in two low-overhead, hardware-friendly PAPR suppression schemes: HC-SLM and HC-PTS. Simulation results demonstrate that under typical system configurations, the proposed algorithm reduces computational complexity by approximately 50-70% and decreases sideband information overhead to less than one-quarter of that achieved by conventional methods. Additionally, under various modulation schemes and typical signal-to-noise ratio(SNR) conditions, when the complementary cumulative distribution function (CCDF) is 10⁻³, the PAPR can be reduced by 0.1–0.5 dB. Its performance, constrained by low computational complexity, approaches and even partially surpasses that of traditional exhaustive search methods with significantly higher computational overhead. This provides an effective solution for the low-power, high-efficiency practical deployment of RIS-OFDM systems.
- 19 May 2026
- Published by Elsevier in Computer Networks
- Vol. 285
HierFedEHN: A hierarchical training framework for hypernetwork-based personalized federated learning
- 19 May 2026
- Published by Elsevier in Computer Networks
- Vol. 285
HierFedEHN: A hierarchical training framework for hypernetwork-based personalized federated learning
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (11) , 25071-25087
Improved Multiscale Networks and Collaborative Edge Computing for Precise and Real-Time Tool Fault Diagnosis in Industrial IoT
With the rapid evolution of smart manufacturing, achieving high-precision and real-time tool condition monitoring has become increasingly crucial for maintaining production efficiency and system reliability. To address this challenge, this work proposes a tool wear fault diagnosis framework that integrates deep learning with collaborative edge computing. At the core of this framework, a physically motivated and hierarchically coupled spatial–temporal modeling network, namely improved multiscale networks (IMSNets), is developed. Unlike conventional convolutional neural network (CNN)-long short-term memory (LSTM)-attention architectures, IMSNet is designed according to the intrinsic degradation characteristics of tool wear vibration signals. Specifically, a structured multiscale convolutional module is employed to extract spatial representations that capture heterogeneous frequency-axis interactions, while an LSTM network simultaneously models the temporal evolution embedded in raw vibration signals to characterize cumulative degradation dynamics. The complementary spatial and temporal features are then fused through a multihead attention mechanism for adaptive reliability-aware feature reweighting, enabling robust representation learning under nonstationary machining conditions. To meet stringent real-time requirements in industrial Internet of Thing (IIoT) systems, we further design a cloud-edge-device collaboration (CEDC) framework for adaptive task offloading and low-latency inference. The framework decomposes diagnostic workloads across device, edge, and cloud layers and dynamically coordinates computation within scheduling windows, thereby improving system responsiveness. Experiments demonstrate that IMSNet achieves 97.81% accuracy on the self-collected industrial dataset and 98.93% on the public PHM benchmark, and showing stable and generalizable performance under varying operating conditions. Meanwhile, the CEDC framework reduces task offloading latency by up to 17.4% compared with the advanced offloading strategies, while maintaining real-time responsiveness under varying workload conditions. To facilitate reproducibility and further research, the source code is publicly available at: https://github.com/lidongyang1/tool-fault-diagnosis-IIoT
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (11) , 25071-25087
Improved Multiscale Networks and Collaborative Edge Computing for Precise and Real-Time Tool Fault Diagnosis in Industrial IoT
With the rapid evolution of smart manufacturing, achieving high-precision and real-time tool condition monitoring has become increasingly crucial for maintaining production efficiency and system reliability. To address this challenge, this work proposes a tool wear fault diagnosis framework that integrates deep learning with collaborative edge computing. At the core of this framework, a physically motivated and hierarchically coupled spatial–temporal modeling network, namely improved multiscale networks (IMSNets), is developed. Unlike conventional convolutional neural network (CNN)-long short-term memory (LSTM)-attention architectures, IMSNet is designed according to the intrinsic degradation characteristics of tool wear vibration signals. Specifically, a structured multiscale convolutional module is employed to extract spatial representations that capture heterogeneous frequency-axis interactions, while an LSTM network simultaneously models the temporal evolution embedded in raw vibration signals to characterize cumulative degradation dynamics. The complementary spatial and temporal features are then fused through a multihead attention mechanism for adaptive reliability-aware feature reweighting, enabling robust representation learning under nonstationary machining conditions. To meet stringent real-time requirements in industrial Internet of Thing (IIoT) systems, we further design a cloud-edge-device collaboration (CEDC) framework for adaptive task offloading and low-latency inference. The framework decomposes diagnostic workloads across device, edge, and cloud layers and dynamically coordinates computation within scheduling windows, thereby improving system responsiveness. Experiments demonstrate that IMSNet achieves 97.81% accuracy on the self-collected industrial dataset and 98.93% on the public PHM benchmark, and showing stable and generalizable performance under varying operating conditions. Meanwhile, the CEDC framework reduces task offloading latency by up to 17.4% compared with the advanced offloading strategies, while maintaining real-time responsiveness under varying workload conditions. To facilitate reproducibility and further research, the source code is publicly available at: https://github.com/lidongyang1/tool-fault-diagnosis-IIoT
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 18 (3) , 71-86
DDRAM: Dynamic Driving Risk Assessment Method Based on Predictable Multidimensional Kinematic Features
As autonomous driving technologies continue to evolve, the demand for precise and prompt risk assessment in complex traffic scenarios has become increasingly critical to guarantee driving safety. Traditional driving risk field models typically trigger warnings only when vehicles enter each other’s risk zones, thereby failing to predict potential future spatial conflicts. This limitation significantly compromises the timeliness and reliability of warnings, particularly in multiagent scenarios such as intersections. To mitigate this limitation, we accordingly propose a dynamic driving risk assessment method (DDRAM) based on predictable multidimensional kinematic features. Based on the distributed digital twin information system architecture, a “query-centric” multimodal trajectory prediction algorithm driven by agent interaction is designed to achieve high-precision predictions of the upcoming motion states of traffic participants. By deconstructing the predicted kinematic features, we construct a multisource fusion model to dynamically assess collision risks. Furthermore, we design a quantifiable risk warning matrix to characterize potential risks with greater accuracy. This method significantly enhances the early warning capabilities in complex traffic scenarios. Experimental results demonstrate that DDRAM significantly increases the average precollision warning time (PCWT) by 76% and reduces the average precollision warning error (PCWE) by 72% compared with existing approaches.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 18 (3) , 71-86
DDRAM: Dynamic Driving Risk Assessment Method Based on Predictable Multidimensional Kinematic Features
As autonomous driving technologies continue to evolve, the demand for precise and prompt risk assessment in complex traffic scenarios has become increasingly critical to guarantee driving safety. Traditional driving risk field models typically trigger warnings only when vehicles enter each other’s risk zones, thereby failing to predict potential future spatial conflicts. This limitation significantly compromises the timeliness and reliability of warnings, particularly in multiagent scenarios such as intersections. To mitigate this limitation, we accordingly propose a dynamic driving risk assessment method (DDRAM) based on predictable multidimensional kinematic features. Based on the distributed digital twin information system architecture, a “query-centric” multimodal trajectory prediction algorithm driven by agent interaction is designed to achieve high-precision predictions of the upcoming motion states of traffic participants. By deconstructing the predicted kinematic features, we construct a multisource fusion model to dynamically assess collision risks. Furthermore, we design a quantifiable risk warning matrix to characterize potential risks with greater accuracy. This method significantly enhances the early warning capabilities in complex traffic scenarios. Experimental results demonstrate that DDRAM significantly increases the average precollision warning time (PCWT) by 76% and reduces the average precollision warning error (PCWE) by 72% compared with existing approaches.
- 28 November 2025
- Published by Elsevier in Physical Communication
- Vol. 74
Joint beamforming and phase optimization for UAV-RIS systems by gradient-based adaptive meta-learning
- 28 November 2025
- Published by Elsevier in Physical Communication
- Vol. 74
Joint beamforming and phase optimization for UAV-RIS systems by gradient-based adaptive meta-learning
- 26 November 2025
- Published by Elsevier in Ocean Engineering
- Vol. 344
An adaptive stratification algorithm for sound velocity profile based on NSGA-II multi-objective optimization
- 26 November 2025
- Published by Elsevier in Ocean Engineering
- Vol. 344
An adaptive stratification algorithm for sound velocity profile based on NSGA-II multi-objective optimization