Query：
学者姓名：郑海峰
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
Predicting traffic flow effectively alleviates congestion. However, traditional methods tend to rely solely on historical traffic flow data, overlooking the correlation between multimodal traffic data, such as speed and occupancy collected by sensors placed on the road. This limitation results in low tolerance for abnormal situations. Moreover, the decentralization of multimodal data on edge devices may pose data anomalies or partial modal missing due to equipment damage or absence. To address these challenges, we propose a Block-Term tensor decomposition-based multimodal data feature fusion algorithm for traffic prediction. This approach enhances the accuracy and robustness of traffic flow prediction by considering correlations between various modal data, such as speed and occupancy rate. In response to the issues of scattered multimodal data anomalies and missing data on edge devices, and to ensure address privacy and security issues, we employ federated learning methods to achieve adaptive extraction and fusion of multi-modal data at the edges. Our method is tested on a real highway dataset, demonstrating superior prediction performance and robustness compared to traditional methods, particularly in the context of data anomalies or missing modalities. © 2024 IEEE.
Keyword ：
Federated learning Federated learning Multimodal data Multimodal data Robustness Robustness Tensor decomposition Tensor decomposition Traffic flow Traffic flow
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Feng, S. , Feng, X. , Xu, L. et al. BTD-GTAN: Federated Traffic Flow Prediction with Multimodal Feature Fusion Considering Anomalies [未知]. |
| MLA | Feng, S. et al. "BTD-GTAN: Federated Traffic Flow Prediction with Multimodal Feature Fusion Considering Anomalies" [未知]. |
| APA | Feng, S. , Feng, X. , Xu, L. , Zheng, H. . BTD-GTAN: Federated Traffic Flow Prediction with Multimodal Feature Fusion Considering Anomalies [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Relying on a data-driven methodology, deep learning has emerged as a new approach for dynamic resource allocation in large-scale cellular networks. This paper proposes a knowledge-assisted domain adversarial network to reduce the number of poorly performing base stations (BSs) by dynamically allocating radio resources to meet real-time mobile traffic needs. Firstly, we calculate theoretical inter-cell interference and BS capacity using Voronoi tessellation and stochastic geometry, which are then incorporated into a neural network as key parameters. Secondly, following the practical assessment, a performance classifier evaluates BS performance based on given traffic-resource pairs as either poor or good. Most importantly, we use well-performing BSs as source domain data to reallocate the resources of poorly performing ones through the domain adversarial neural network. Our experimental results demonstrate that the proposed knowledge-assisted domain adversarial resource allocation (KDARA) strategy effectively decreases the number of poorly performing BSs in the cellular network, and in turn, outperforms other benchmark algorithms in terms of both the ratio of poor BSs and radio resource consumption. IEEE
Keyword ：
domain adversarial network domain adversarial network Dynamic scheduling Dynamic scheduling knowledge-assisted knowledge-assisted Measurement Measurement Mobile big data Mobile big data Neural networks Neural networks Real-time systems Real-time systems resource allocation resource allocation Resource management Resource management transfer learning transfer learning Transfer learning Transfer learning Wireless networks Wireless networks
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Y. , Zheng, Y. , Xu, J. et al. Knowledge-Assisted Resource Allocation With Domain Adversarial Neural Networks [J]. | IEEE Transactions on Network and Service Management , 2024 , 21 (6) : 1-1 . |
| MLA | Chen, Y. et al. "Knowledge-Assisted Resource Allocation With Domain Adversarial Neural Networks" . | IEEE Transactions on Network and Service Management 21 . 6 (2024) : 1-1 . |
| APA | Chen, Y. , Zheng, Y. , Xu, J. , Lin, H. , Cheng, P. , Ding, M. et al. Knowledge-Assisted Resource Allocation With Domain Adversarial Neural Networks . | IEEE Transactions on Network and Service Management , 2024 , 21 (6) , 1-1 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Cooperative perception is an advanced strategy within traffic systems designed to enhance the environmental perception capabilities of vehicles, where participants exchange cooperative perception messages (CPMs) through Vehicle-to-Everything (V2X) technology. However, most existing cooperative perception methods may ignore the communication bandwidth constraints of the system, potentially resulting in connected autonomous vehicles (CAVs) receiving outdated CPMs. In this paper, we propose a novel cooperative perception framework that enhances the accuracy of CAVs perception while reducing the transmission data size to meet the transmission delay requirements of CPMs under limited bandwidth. Furthermore, we propose a strategy for selecting cooperative partners and CPMs based on the Double Deep Q-Network (DDQN) algorithm. Additionally, an invalid action masking approach is presented to address the dynamic changes in the action space over time and reduce the size of the DDQN action space. Simulation results demonstrate that the proposed cooperative perception method consumes less data compared to some existing methods. Moreover, under limited communication bandwidth constraints, it achieves higher perception accuracy due to its ability to avoid transmission delay. © 2024 IEEE.
Keyword ：
Connected automated vehicles Connected automated vehicles cooperative perception cooperative perception deep reinforcement learning deep reinforcement learning invalid action masking invalid action masking
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, F. , Chen, C. , Zheng, H. et al. Delay-Aware Cooperative Perception with Deep Reinforcement Learning in Vehicular Networks [未知]. |
| MLA | Xu, F. et al. "Delay-Aware Cooperative Perception with Deep Reinforcement Learning in Vehicular Networks" [未知]. |
| APA | Xu, F. , Chen, C. , Zheng, H. , Feng, X. . Delay-Aware Cooperative Perception with Deep Reinforcement Learning in Vehicular Networks [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. In recent years, the emergence of pseudo point clouds has led to an increasing number of 3D object detection tasks introducing this modality, but not every point in the pseudo point cloud generated by depth completion is reliable. In order to better utilize pseudo point clouds in 3D object detection tasks based on point cloud image fusion, we propose the EppNet framework in this paper, which enables the network to learn the anti noise features of pseudo point clouds. In this framework, we use VoxelNet [1] and VirConv Net [2] to extract features from point clouds and pseudo point clouds, respectively. Besides, we utilize a attentive RoI fusion strategy to make fuller use of information from different types of point clouds. Extensive experiments on KITTI, a benchmark for real-world traffic object identification, revealed that EppNet is able to perform favorably in comparison to earlier, well-respected detectors. © 2024 IEEE.
Keyword ：
3D modeling 3D modeling Cloud platforms Cloud platforms Image fusion Image fusion Object detection Object detection Object recognition Object recognition
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Yuren , Feng, Xinxin , Zheng, Haifeng . EppNet: Enhanced Pseudo and Point Cloud Fusion for 3D Object Detection [C] . 2024 : 29-32 . |
| MLA | Chen, Yuren et al. "EppNet: Enhanced Pseudo and Point Cloud Fusion for 3D Object Detection" . (2024) : 29-32 . |
| APA | Chen, Yuren , Feng, Xinxin , Zheng, Haifeng . EppNet: Enhanced Pseudo and Point Cloud Fusion for 3D Object Detection . (2024) : 29-32 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Federated learning (FL) has been extensively studied as a means of ensuring data privacy while cooperatively training a global model across decentralized devices. Among various FL approaches, asynchronous federated learning (AFL) has distinct advantages in overcoming the straggler problem via server-side aggregation as soon as it receives a local model. However, AFL still faces several challenges in large-scale real-world applications, such as stale model problems and modality heterogeneity across geographically distributed and industrial devices with different functions. In this article, we propose a multimodal fusion framework for AFL to address the aforementioned problems. Specifically, a novel multilinear block fusion model is designed to fuse various multimodal information, which serves as an enhancement for perceiving and transmitting the important modality and block during local training. An adaptive aggregation strategy is further developed to fully utilize heterogeneous data by allowing the global model to favor the received local model based on both freshness and the importance of the local data. Extensive simulations with different data distributions demonstrate the superiority of the proposed framework in heterogeneity scenarios, which exhibits significant merits in the improvement of modality-based generalization without sacrificing convergence speed and communication consumption.
Keyword ：
Asynchronous federated learning (AFL) Asynchronous federated learning (AFL) block term (BT) decomposition block term (BT) decomposition multimodal fusion multimodal fusion
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gao, Min , Zheng, Haifeng , Du, Mengxuan et al. Multimodal Fusion With Block Term Decomposition for Asynchronous Federated Learning [J]. | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS , 2024 , 20 (12) : 14083-14093 . |
| MLA | Gao, Min et al. "Multimodal Fusion With Block Term Decomposition for Asynchronous Federated Learning" . | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 20 . 12 (2024) : 14083-14093 . |
| APA | Gao, Min , Zheng, Haifeng , Du, Mengxuan , Feng, Xinxin . Multimodal Fusion With Block Term Decomposition for Asynchronous Federated Learning . | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS , 2024 , 20 (12) , 14083-14093 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Due to the rapidly increasing number of base stations (BSs) in the operational cellular networks, their energy consumption is escalating. In this paper, we propose an intelligent data-driven BS sleeping mechanism relying on a wireless traffic prediction model that measures the BSs' capacity in different regions. Firstly, a spatio-temporal cellular traffic prediction model is proposed, where a multi-graph convolutional network (MGCN) is developed to capture the associated spatial features. Furthermore, a multi-channel long short-term memory (LSTM) solution involving hourly, daily, and weekly periodic data is used to capture the relevant temporal features. Secondly, the capacities of macro-cell BSs (MBSs) and small-cell BSs (SBSs) having different environment characteristics are modeled, where both clustering and transfer learning algorithms are adopted for quantifying the traffic supported by the MBSs and SBSs. Finally, an optimal BS sleeping strategy is proposed for minimizing the network's power consumption. Experimental results show that the proposed MGCN-LSTM model outperforms the existing models in terms of its cellular traffic prediction accuracy, and the proposed BS sleeping strategy using an approximated non-linear model of the associated capacity function achieves near-maximal energy-saving at a modest complexity.
Keyword ：
BS sleeping BS sleeping Cellular networks Cellular networks cellular traffic prediction cellular traffic prediction Convolution Convolution Convolutional neural networks Convolutional neural networks Energy consumption Energy consumption graph convolutional network graph convolutional network Predictive models Predictive models Real-time systems Real-time systems Roads Roads transfer learning. transfer learning.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Jiansheng , Chen, Youjia , Zheng, Haifeng et al. A Data-Driven Base Station Sleeping Strategy Based on Traffic Prediction [J]. | IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING , 2024 , 11 (6) : 5627-5643 . |
| MLA | Lin, Jiansheng et al. "A Data-Driven Base Station Sleeping Strategy Based on Traffic Prediction" . | IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 11 . 6 (2024) : 5627-5643 . |
| APA | Lin, Jiansheng , Chen, Youjia , Zheng, Haifeng , Ding, Ming , Cheng, Peng , Hanzo, Lajos . A Data-Driven Base Station Sleeping Strategy Based on Traffic Prediction . | IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING , 2024 , 11 (6) , 5627-5643 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
We consider the problem of hyperspectral image (HSI) reconstruction, which aims to recover 3D hyperspectral data from 2D compressive HSI measurements acquired by a coded aperture snapshot spectral imaging (CASSI) system. Existing deep learning methods have achieved acceptable results in HSI reconstruction. However, these methods did not consider the imaging system degradation pattern. In this article, based on observing the initialized HSIs obtained by shifting and splitting the measurements, we propose a dynamic Fourier network based on degradation learning, called the degradation-aware dynamic Fourier-based network (DADF-Net). We estimate the degradation feature maps from the degraded hyperspectral images to realize the linear transformation and dynamic processing of the features. In particular, we use the Fourier transform to extract the HSI non-local features. Extensive experimental results show that the proposed model outperforms state-of-the-art algorithms on simulation and real-world HSI datasets.
Keyword ：
Convolution Convolution Deep learning Deep learning Degradation Degradation Feature extraction Feature extraction fourier transform fourier transform Heuristic algorithms Heuristic algorithms hyperspectral images hyperspectral images Image reconstruction Image reconstruction Imaging Imaging Mathematical models Mathematical models snapshot compressive imaging snapshot compressive imaging
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Ping , Liu, Lei , Zheng, Haifeng et al. Degradation-Aware Dynamic Fourier-Based Network for Spectral Compressive Imaging [J]. | IEEE TRANSACTIONS ON MULTIMEDIA , 2024 , 26 : 2838-2850 . |
| MLA | Xu, Ping et al. "Degradation-Aware Dynamic Fourier-Based Network for Spectral Compressive Imaging" . | IEEE TRANSACTIONS ON MULTIMEDIA 26 (2024) : 2838-2850 . |
| APA | Xu, Ping , Liu, Lei , Zheng, Haifeng , Yuan, Xin , Xu, Chen , Xue, Lingyun . Degradation-Aware Dynamic Fourier-Based Network for Spectral Compressive Imaging . | IEEE TRANSACTIONS ON MULTIMEDIA , 2024 , 26 , 2838-2850 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Decentralized federated learning (DFL) is a novel distributed machine-learning paradigm where participants collaborate to train machine-learning models without the assistance of the central server. The decentralized framework can effectively overcome the communication bottleneck and single-point-of-failure issues encountered in federated learning (FL). However, most existing DFL methods may ignore the communication resource constraints of the system. This may result in these methods unsuitable for many practical scenarios because the given resource constraints cannot be guaranteed. In this article, we propose a novel DFL, called DFL with adaptive compression ratio (AdapCom-DFL), that can adaptively adjust the compression ratio of transmission data to keep the communication latency within the constraint. Furthermore, we propose a communication network topology pruning approach to reduce communication overhead by pruning poor links with low data rates while ensuring the convergence. Additionally, a power allocation approach is presented to improve the performance by reallocating the power of communication links while complying with the communication energy constraint. Extensive simulation results demonstrate that the proposed AdapCom-DFL with network pruning and power allocation approach achieves better performance and requires less bandwidth under the given resource constraints compared with some existing approaches.
Keyword ：
Decentralized federated learning (DFL) Decentralized federated learning (DFL) network topology pruning network topology pruning power allocation power allocation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Du, Mengxuan , Zheng, Haifeng , Gao, Min et al. Adaptive Decentralized Federated Learning in Resource-Constrained IoT Networks [J]. | IEEE INTERNET OF THINGS JOURNAL , 2024 , 11 (6) : 10739-10753 . |
| MLA | Du, Mengxuan et al. "Adaptive Decentralized Federated Learning in Resource-Constrained IoT Networks" . | IEEE INTERNET OF THINGS JOURNAL 11 . 6 (2024) : 10739-10753 . |
| APA | Du, Mengxuan , Zheng, Haifeng , Gao, Min , Feng, Xinxin . Adaptive Decentralized Federated Learning in Resource-Constrained IoT Networks . | IEEE INTERNET OF THINGS JOURNAL , 2024 , 11 (6) , 10739-10753 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Sampling is a crucial concern for outdoor light detection and ranging (LiDAR) point cloud registration due to the large amounts of point cloud. Numerous algorithms have been devised to tackle this issue by selecting key points. However, these approaches often necessitate extensive computations, giving rise to challenges related to computational time and complexity. This letter proposes a multi-domain uniform sampling method (MDU-sampling) for large-scale outdoor LiDAR point cloud registration. The feature extraction based on deep learning aggregates information from the neighbourhood, so there is redundancy between adjacent features. The sampling method in this paper is carried out in the spatial and feature domains. First, uniform sampling is executed in the spatial domain, maintaining local point cloud uniformity. This is believed to preserve more potential point correspondences and is beneficial for subsequent neighbourhood information aggregation and feature sampling. Subsequently, a secondary sampling in the feature domain is performed to reduce redundancy among the features of neighbouring points. Notably, only points on the same ring in LiDAR data are considered as neighbouring points, eliminating the need for additional neighbouring point search and thereby speeding up processing rates. Experimental results demonstrate that the approach enhances accuracy and robustness compared with benchmarks. The feature extraction based on deep learning aggregates information from the neighbourhood, so there is redundancy between adjacent features. The sampling method in this paper is carried out in the spatial and feature domains, reducing the computational resources for registration. The proposed method preserves more effective information compared to other algorithms. Points are only considered on the same ring in LiDAR data as neighbouring points, eliminating the need for additional neighbouring point search. This makes it efficient and suitable for large-scale outdoor LiDAR point cloud registration. image
Keyword ：
artificial intelligence artificial intelligence robot vision robot vision signal processing signal processing SLAM (robots) SLAM (robots)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ou, Wengjun , Zheng, Mingkui , Zheng, Haifeng . MDU-sampling: Multi-domain uniform sampling method for large-scale outdoor LiDAR point cloud registration [J]. | ELECTRONICS LETTERS , 2024 , 60 (5) . |
| MLA | Ou, Wengjun et al. "MDU-sampling: Multi-domain uniform sampling method for large-scale outdoor LiDAR point cloud registration" . | ELECTRONICS LETTERS 60 . 5 (2024) . |
| APA | Ou, Wengjun , Zheng, Mingkui , Zheng, Haifeng . MDU-sampling: Multi-domain uniform sampling method for large-scale outdoor LiDAR point cloud registration . | ELECTRONICS LETTERS , 2024 , 60 (5) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Sampling is a crucial concern for outdoor light detection and ranging (LiDAR) point cloud registration due to the large amounts of point cloud. Numerous algorithms have been devised to tackle this issue by selecting key points. However, these approaches often necessitate extensive computations, giving rise to challenges related to computational time and complexity. This letter proposes a multi-domain uniform sampling method (MDU-sampling) for large-scale outdoor LiDAR point cloud registration. The feature extraction based on deep learning aggregates information from the neighbourhood, so there is redundancy between adjacent features. The sampling method in this paper is carried out in the spatial and feature domains. First, uniform sampling is executed in the spatial domain, maintaining local point cloud uniformity. This is believed to preserve more potential point correspondences and is beneficial for subsequent neighbourhood information aggregation and feature sampling. Subsequently, a secondary sampling in the feature domain is performed to reduce redundancy among the features of neighbouring points. Notably, only points on the same ring in LiDAR data are considered as neighbouring points, eliminating the need for additional neighbouring point search and thereby speeding up processing rates. Experimental results demonstrate that the approach enhances accuracy and robustness compared with benchmarks. The feature extraction based on deep learning aggregates information from the neighbourhood, so there is redundancy between adjacent features. The sampling method in this paper is carried out in the spatial and feature domains, reducing the computational resources for registration. The proposed method preserves more effective information compared to other algorithms. Points are only considered on the same ring in LiDAR data as neighbouring points, eliminating the need for additional neighbouring point search. This makes it efficient and suitable for large-scale outdoor LiDAR point cloud registration. image
Keyword ：
artificial intelligence artificial intelligence robot vision robot vision signal processing signal processing SLAM (robots) SLAM (robots)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ou, Wengjun , Zheng, Mingkui , Zheng, Haifeng . MDU-sampling: Multi-domain uniform sampling method for large-scale outdoor LiDAR point cloud registration [J]. | ELECTRONICS LETTERS , 2024 , 60 (5) . |
| MLA | Ou, Wengjun et al. "MDU-sampling: Multi-domain uniform sampling method for large-scale outdoor LiDAR point cloud registration" . | ELECTRONICS LETTERS 60 . 5 (2024) . |
| APA | Ou, Wengjun , Zheng, Mingkui , Zheng, Haifeng . MDU-sampling: Multi-domain uniform sampling method for large-scale outdoor LiDAR point cloud registration . | ELECTRONICS LETTERS , 2024 , 60 (5) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
