Hui Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hui Li has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Huamin Chen
School of Information Science and Technology, Beijing University of Technology, Beijing 100124, China
6 shared publications - Shaofu Lin
Beijing University of Technology
4 shared publications Kun Zheng
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
3 shared publicationsGuangmin Sun
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
2 shared publications- Jin-Man Shen
School of Information Science and Technology, Beijing University of Technology, Beijing 100124, China
2 shared publications - Junjie Zhang
People’s Public Security University of China
2 shared publications
Latest Publications
- Open Access
Topology Reconstruction Algorithm Design for Multi-Node Failure Scenarios in FANET
With the advancement of UAV (Unmanned Aerial Vehicle) technology, flying ad-hoc networks (FANETs), composed of multiple coordinating UAVs, demonstrate tremendous application potential in disaster relief, environmental monitoring and intelligent logistics. However, inherent resource constraints and unpredictable operating environments make UAV failures a frequent and critical challenge. Particularly in mission-critical applications, simultaneous or consecutive failures of multiple UAVs can severely disrupt network topology, leading to catastrophic consequences such as network fragmentation and service interruptions. Furthermore, traditional topology reconstruction algorithms suffer from high computational overhead and significant communication delays. Primarily designed for single-node failure recovery, they are ill-equipped to address the challenge of concurrent multi-node failures. To address these challenges, this paper proposes a topology reconstruction algorithm tailored for multi-node failure scenarios in FANETs. The core objective of this algorithm is to minimize communication overhead and secondary damage to the network during the reconstruction process while ensuring basic reconstruction results, thereby improving the system’s energy efficiency and robustness. The proposed framework integrates three key phases: First, overlapping communication coverage areas among neighbors of failed nodes are leveraged to define first and second regions, enabling rapid identification of connection restoration candidate positions and avoiding computationally intensive global calculations. Second, a comprehensive importance evaluation mechanism is constructed based on the topological and functional attributes of node, categorizing nodes into different importance types. For failed nodes of varying importance, differentiated search ranges and retry strategies are employed to ensure the most suitable nodes are selected for reconstruction tasks. Third, the inflexibility of repulsion ranges in traditional artificial potential field (APF) method is addressed by introducing dynamic repulsion influence zones and a composite repulsion model. The improved APF algorithm enhances safety in high-speed scenarios and reduces the probability of UAVs becoming trapped in local minima. Finally, extensive simulations validate that the proposed algorithm accurately identifies critical network nodes and promptly implements effective reconstruction measures to minimize network damage.
Open AccessTopology Reconstruction Algorithm Design for Multi-Node Failure Scenarios in FANET
With the advancement of UAV (Unmanned Aerial Vehicle) technology, flying ad-hoc networks (FANETs), composed of multiple coordinating UAVs, demonstrate tremendous application potential in disaster relief, environmental monitoring and intelligent logistics. However, inherent resource constraints and unpredictable operating environments make UAV failures a frequent and critical challenge. Particularly in mission-critical applications, simultaneous or consecutive failures of multiple UAVs can severely disrupt network topology, leading to catastrophic consequences such as network fragmentation and service interruptions. Furthermore, traditional topology reconstruction algorithms suffer from high computational overhead and significant communication delays. Primarily designed for single-node failure recovery, they are ill-equipped to address the challenge of concurrent multi-node failures. To address these challenges, this paper proposes a topology reconstruction algorithm tailored for multi-node failure scenarios in FANETs. The core objective of this algorithm is to minimize communication overhead and secondary damage to the network during the reconstruction process while ensuring basic reconstruction results, thereby improving the system’s energy efficiency and robustness. The proposed framework integrates three key phases: First, overlapping communication coverage areas among neighbors of failed nodes are leveraged to define first and second regions, enabling rapid identification of connection restoration candidate positions and avoiding computationally intensive global calculations. Second, a comprehensive importance evaluation mechanism is constructed based on the topological and functional attributes of node, categorizing nodes into different importance types. For failed nodes of varying importance, differentiated search ranges and retry strategies are employed to ensure the most suitable nodes are selected for reconstruction tasks. Third, the inflexibility of repulsion ranges in traditional artificial potential field (APF) method is addressed by introducing dynamic repulsion influence zones and a composite repulsion model. The improved APF algorithm enhances safety in high-speed scenarios and reduces the probability of UAVs becoming trapped in local minima. Finally, extensive simulations validate that the proposed algorithm accurately identifies critical network nodes and promptly implements effective reconstruction measures to minimize network damage.
- Open Access
- 24 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 912-918
A Design of Bayesian-OptimizedWeighted Probability Fusion Model for Early Gastric Cancer Screening
- 24 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 912-918
Open AccessA Design of Bayesian-OptimizedWeighted Probability Fusion Model for Early Gastric Cancer Screening
- Open Access
5G High-Precision Positioning in GNSS-Denied Environments Using a Positional Encoding-Enhanced Deep Residual Network
With the widespread deployment of 5G technology, high-precision positioning in global navigation satellite system (GNSS)-denied environments is a critical yet challenging task for emerging 5G applications, enabling enhanced spatial resolution, real-time data acquisition, and more accurate geolocation services. Traditional methods relying on single-source measurements like received signal strength information (RSSI) or time of arrival (TOA) often fail in complex multipath conditions. To address this, the positional encoding multi-scale residual network (PE-MSRN) is proposed, a novel deep learning framework that enhances positioning accuracy by deeply mining spatial information from 5G channel state information (CSI). By designing spatial sampling with multigranular data and utilizing multi-source information in 5G CSI, a dataset covering a variety of positioning scenarios is proposed. The core of PE-MSRN is a multi-scale residual network (MSRN) augmented by a positional encoding (PE) mechanism. The positional encoding transforms raw angle of arrival (AOA) data into rich spatial features, which are then mapped into a 2D image, allowing the MSRN to effectively capture both fine-grained local patterns and large-scale spatial dependencies. Subsequently, the PE-MSRN algorithm that integrates ResNet residual networks and multi-scale feature extraction mechanisms is designed and compared with the baseline convolutional neural network (CNN) and other comparison methods. Extensive evaluations across various simulated scenarios, including indoor autonomous driving and smart factory tool tracking, demonstrate the superiority of our approach. Notably, PE-MSRN achieves a positioning accuracy of up to 20 cm, significantly outperforming baseline CNNs and other neural network algorithms in both accuracy and convergence speed, particularly under real measurement conditions with higher SNR and fine-grained grid division. Our work provides a robust and effective solution for developing high-fidelity 5G positioning systems.
Open Access5G High-Precision Positioning in GNSS-Denied Environments Using a Positional Encoding-Enhanced Deep Residual Network
With the widespread deployment of 5G technology, high-precision positioning in global navigation satellite system (GNSS)-denied environments is a critical yet challenging task for emerging 5G applications, enabling enhanced spatial resolution, real-time data acquisition, and more accurate geolocation services. Traditional methods relying on single-source measurements like received signal strength information (RSSI) or time of arrival (TOA) often fail in complex multipath conditions. To address this, the positional encoding multi-scale residual network (PE-MSRN) is proposed, a novel deep learning framework that enhances positioning accuracy by deeply mining spatial information from 5G channel state information (CSI). By designing spatial sampling with multigranular data and utilizing multi-source information in 5G CSI, a dataset covering a variety of positioning scenarios is proposed. The core of PE-MSRN is a multi-scale residual network (MSRN) augmented by a positional encoding (PE) mechanism. The positional encoding transforms raw angle of arrival (AOA) data into rich spatial features, which are then mapped into a 2D image, allowing the MSRN to effectively capture both fine-grained local patterns and large-scale spatial dependencies. Subsequently, the PE-MSRN algorithm that integrates ResNet residual networks and multi-scale feature extraction mechanisms is designed and compared with the baseline convolutional neural network (CNN) and other comparison methods. Extensive evaluations across various simulated scenarios, including indoor autonomous driving and smart factory tool tracking, demonstrate the superiority of our approach. Notably, PE-MSRN achieves a positioning accuracy of up to 20 cm, significantly outperforming baseline CNNs and other neural network algorithms in both accuracy and convergence speed, particularly under real measurement conditions with higher SNR and fine-grained grid division. Our work provides a robust and effective solution for developing high-fidelity 5G positioning systems.
- 10 May 2025
- Published by Springer Nature
- p. 509-520
An Overview of Physical Sidelink Shared Channel Design and Link Level Performance Evaluation
- 10 May 2025
- Published by Springer Nature
- p. 509-520
An Overview of Physical Sidelink Shared Channel Design and Link Level Performance Evaluation
- 10 May 2025
- Published by Springer Nature
- p. 439-450
An Overview of PSCCH Design and Performance Evaluation
- 10 May 2025
- Published by Springer Nature
- p. 439-450
An Overview of PSCCH Design and Performance Evaluation
- Open Access
A Novel Design for Joint Collaborative NOMA Transmission with a Two–Hop Multi–Path UE Aggregation Mechanism
With the exponential growth of devices, particularly Internet of things (IoT) devices, connecting to wireless networks, existing networks face significant challenges. Spectral efficiency is crucial for uplink, which is the dominant form of asymmetrical network in today’s communication landscape, in large-scale connectivity scenarios. In this paper, an uplink transmission scenario is considered and user equipment (UE) aggregation is employed, wherein some users act as cooperative nodes (CNs), and help to forward received data from other users requiring coverage extension, reliability improvement, and data–rate enhancement. Non–orthogonal multiple access (NOMA) technology is introduced to improve spectral efficiency. To reduce the interference impact to guarantee the data rate, one UE can be assisted by multiple CNs, and these CNs and corresponding assisted UEs are clustered into joint transmission pairs (JTPs). Interference-free transmission can be achieved within each JTP by utilizing different successive interference cancellation (SIC) decoding orders. To explore SIC gains and maximize data rates in NOMA–based UE aggregation, we propose a primary user CN–based channel–sorting algorithm for JTP construction and apply a whale optimization algorithm for JTP power allocation. Additionally, a conflict graph is established among feasible JTPs, and a greedy strategy is employed to find the maximum weighted independent set (MWIS) of the conflict graph for subchannel allocation. Simulation results demonstrate that our joint collaborative NOMA (JC–NOMA) design with two–hop multi–path UE aggregation significantly improves spectral efficiency and capacity under limited spectral resources.
Open AccessA Novel Design for Joint Collaborative NOMA Transmission with a Two–Hop Multi–Path UE Aggregation Mechanism
With the exponential growth of devices, particularly Internet of things (IoT) devices, connecting to wireless networks, existing networks face significant challenges. Spectral efficiency is crucial for uplink, which is the dominant form of asymmetrical network in today’s communication landscape, in large-scale connectivity scenarios. In this paper, an uplink transmission scenario is considered and user equipment (UE) aggregation is employed, wherein some users act as cooperative nodes (CNs), and help to forward received data from other users requiring coverage extension, reliability improvement, and data–rate enhancement. Non–orthogonal multiple access (NOMA) technology is introduced to improve spectral efficiency. To reduce the interference impact to guarantee the data rate, one UE can be assisted by multiple CNs, and these CNs and corresponding assisted UEs are clustered into joint transmission pairs (JTPs). Interference-free transmission can be achieved within each JTP by utilizing different successive interference cancellation (SIC) decoding orders. To explore SIC gains and maximize data rates in NOMA–based UE aggregation, we propose a primary user CN–based channel–sorting algorithm for JTP construction and apply a whale optimization algorithm for JTP power allocation. Additionally, a conflict graph is established among feasible JTPs, and a greedy strategy is employed to find the maximum weighted independent set (MWIS) of the conflict graph for subchannel allocation. Simulation results demonstrate that our joint collaborative NOMA (JC–NOMA) design with two–hop multi–path UE aggregation significantly improves spectral efficiency and capacity under limited spectral resources.
- Open Access
- 1 January 2024
- Published by American Institute of Mathematical Sciences (AIMS) in Electronic Research Archive
- Vol. 32 (4) , 2745-2771
Incorporating eyebrow and eye state information for facial expression recognition in mask-obscured scenes
Facial expression recognition plays a crucial role in human-computer intelligent interaction. Due to the problem of missing facial information caused by face masks, the average accuracy of facial expression recognition algorithms in mask-obscured scenes is relatively low. At present, most deep learning-based facial expression recognition methods primarily focus on global facial features, thus they are less suitable for scenarios where facial expressions are obscured by masks. Therefore, this paper proposes a facial expression recognition method, TransformerKNN (TKNN), which integrates eyebrow and eye state information in mask-obscured scenes. The proposed method utilizes facial feature points in the eyebrow and eye regions to calculate various relative distances and angles, capturing the state information of eyebrows and eyes. Subsequently, the original face images with masks are used to train a Swin-transformer model, and the eyebrow and eye state information is used to train a k-Nearest Neighbor (KNN) model. These models are then fused at the decision layer to achieve automated emotion computation in situations when facial expressions are obscured by masks. The TKNN method offers a novel approach by leveraging both local and global facial features, thereby enhancing the performance of facial expression recognition in mask-obscured scenes. Experimental results demonstrate that the average accuracy of the TKNN method is 85.8% and 70.3%, respectively. This provides better support for facial expression recognition in scenarios when facial information is partially obscured.
- 1 January 2024
- Published by American Institute of Mathematical Sciences (AIMS) in Electronic Research Archive
- Vol. 32 (4) , 2745-2771
Open AccessIncorporating eyebrow and eye state information for facial expression recognition in mask-obscured scenes
Facial expression recognition plays a crucial role in human-computer intelligent interaction. Due to the problem of missing facial information caused by face masks, the average accuracy of facial expression recognition algorithms in mask-obscured scenes is relatively low. At present, most deep learning-based facial expression recognition methods primarily focus on global facial features, thus they are less suitable for scenarios where facial expressions are obscured by masks. Therefore, this paper proposes a facial expression recognition method, TransformerKNN (TKNN), which integrates eyebrow and eye state information in mask-obscured scenes. The proposed method utilizes facial feature points in the eyebrow and eye regions to calculate various relative distances and angles, capturing the state information of eyebrows and eyes. Subsequently, the original face images with masks are used to train a Swin-transformer model, and the eyebrow and eye state information is used to train a k-Nearest Neighbor (KNN) model. These models are then fused at the decision layer to achieve automated emotion computation in situations when facial expressions are obscured by masks. The TKNN method offers a novel approach by leveraging both local and global facial features, thereby enhancing the performance of facial expression recognition in mask-obscured scenes. Experimental results demonstrate that the average accuracy of the TKNN method is 85.8% and 70.3%, respectively. This provides better support for facial expression recognition in scenarios when facial information is partially obscured.
- Open Access
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Biosciences and Engineering
- Vol. 20 (6) , 11238-11259
Fall detection based on dynamic key points incorporating preposed attention
Accidental falls pose a significant threat to the elderly population, and accurate fall detection from surveillance videos can significantly reduce the negative impact of falls. Although most fall detection algorithms based on video deep learning focus on training and detecting human posture or key points in pictures or videos, we have found that the human pose-based model and key points-based model can complement each other to improve fall detection accuracy. In this paper, we propose a preposed attention capture mechanism for images that will be fed into the training network, and a fall detection model based on this mechanism. We accomplish this by fusing the human dynamic key point information with the original human posture image. We first propose the concept of dynamic key points to account for incomplete pose key point information in the fall state. We then introduce an attention expectation that predicates the original attention mechanism of the depth model by automatically labeling dynamic key points. Finally, the depth model trained with human dynamic key points is used to correct the detection errors of the depth model with raw human pose images. Our experiments on the Fall Detection Dataset and the UP-Fall Detection Dataset demonstrate that our proposed fall detection algorithm can effectively improve the accuracy of fall detection and provide better support for elderly care.
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Biosciences and Engineering
- Vol. 20 (6) , 11238-11259
Open AccessFall detection based on dynamic key points incorporating preposed attention
Accidental falls pose a significant threat to the elderly population, and accurate fall detection from surveillance videos can significantly reduce the negative impact of falls. Although most fall detection algorithms based on video deep learning focus on training and detecting human posture or key points in pictures or videos, we have found that the human pose-based model and key points-based model can complement each other to improve fall detection accuracy. In this paper, we propose a preposed attention capture mechanism for images that will be fed into the training network, and a fall detection model based on this mechanism. We accomplish this by fusing the human dynamic key point information with the original human posture image. We first propose the concept of dynamic key points to account for incomplete pose key point information in the fall state. We then introduce an attention expectation that predicates the original attention mechanism of the depth model by automatically labeling dynamic key points. Finally, the depth model trained with human dynamic key points is used to correct the detection errors of the depth model with raw human pose images. Our experiments on the Fall Detection Dataset and the UP-Fall Detection Dataset demonstrate that our proposed fall detection algorithm can effectively improve the accuracy of fall detection and provide better support for elderly care.
- Open Access
- 1 January 2022
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Biosciences and Engineering
- Vol. 19 (5) , 5153-5168
Shielding facial physiological information in video
With the recent development of non-contact physiological signal detection methods based on videos, it is possible to obtain the physiological parameters through the ordinary video only, such as heart rate and its variability of an individual. Therefore, personal physiological information may be leaked unknowingly with the spread of videos, which may cause privacy or security problems. In this paper a new method is proposed, which can shield physiological information in the video without reducing the video quality significantly. Firstly, the principle of the most widely used physiological signal detection algorithm: remote photoplethysmography (rPPG) was analyzed. Then the region of interest (ROI) of face contain physiological information with high signal to noise ratio was selected. Two physiological information forgery operation: single-channel periodic noise addition with blur filtering and brightness fine-tuning are conducted on the ROIs. Finally, the processed ROI images are merged into video frames to obtain the processed video. Experiments were performed on the VIPL-HR video dataset. The interference efficiencies of the proposed method on two mainly used rPPG methods: Independent Component Analysis (ICA) and Chrominance-based Method (CHROM) are 82.9 % and 84.6 % respectively, which demonstrated the effectiveness of the proposed method.
- 1 January 2022
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Biosciences and Engineering
- Vol. 19 (5) , 5153-5168
Open AccessShielding facial physiological information in video
With the recent development of non-contact physiological signal detection methods based on videos, it is possible to obtain the physiological parameters through the ordinary video only, such as heart rate and its variability of an individual. Therefore, personal physiological information may be leaked unknowingly with the spread of videos, which may cause privacy or security problems. In this paper a new method is proposed, which can shield physiological information in the video without reducing the video quality significantly. Firstly, the principle of the most widely used physiological signal detection algorithm: remote photoplethysmography (rPPG) was analyzed. Then the region of interest (ROI) of face contain physiological information with high signal to noise ratio was selected. Two physiological information forgery operation: single-channel periodic noise addition with blur filtering and brightness fine-tuning are conducted on the ROIs. Finally, the processed ROI images are merged into video frames to obtain the processed video. Experiments were performed on the VIPL-HR video dataset. The interference efficiencies of the proposed method on two mainly used rPPG methods: Independent Component Analysis (ICA) and Chrominance-based Method (CHROM) are 82.9 % and 84.6 % respectively, which demonstrated the effectiveness of the proposed method.