检索结果-内蒙古大学图书馆

A Helmet Detection Algorithm Based on Transformers with Deformable Attention Module

Chinese Journal of Electronics 2025年第1期34卷 229-241页

作者： Songle Chen Hongbo Sun Yuxin Wu Lei Shang Xiukai Ruan Engineering Research Center of Post Big Data Technology and Application of Jiangsu Province Nanjing University of Posts and Telecommunications State Key Lab for Novel Software Technology Nanjing University Institute of Intelligent Locks Wenzhou University

Wearing a helmet is one of the effective measures to protect workers' safety. To address the challenges of severe occlusion, multi-scale, and small target issues in helmet detection, this paper proposes a helmet detection algorithm based on deformable attention transformers. The main contributions of this paper are as follows. A compact end-to-end network architecture for safety helmet detection based on transformers is proposed. It cancels the computationally intensive transformer encoder module in the existing detection transformer(DETR) and uses the transformer decoder module directly on the output of feature extraction for query decoding, which effectively improves the efficiency of helmet detection. A novel feature extraction network named Swin transformer with deformable attention module(DSwin transformer) is proposed. By sparse cross-window attention, it enhances the contextual awareness of multi-scale features extracted by Swin transformer, and keeps high computational efficiency simultaneously. The proposed method generates the query reference points and query embeddings based on the joint prediction probabilities, and selects an appropriate number of decoding feature maps and sparse sampling points for query decoding, which further enhance the inference capability and processing speed. On the benchmark safety-helmet-wearing-dataset(SHWD), the proposed method achieves the average detection accuracy mAP@0.5 of 95.4% with 133.35G floating-point operations per second(FLOPs) and 20 frames per second(FPS), the state-of-the-art method for safety helmet detection.

关键词： Head Accuracy Network architecture Benchmark testing Transformers Feature extraction Safety Decoding Computational efficiency Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

New Offloading Method of computing Task Based on Gray Wolf Hunting Optimization Mechanism for the IOV

引用

IEEE Transactions on Network and Service Management 2025年

作者： Zhang, Jie Zhang, De-Gan Qiao, Meng Hong-Lin, E. Zhang, Ting Zhang, Ping University of Macau Key Lab of Internet of Things for Smart City Faculty of Science and Technology 999078 China Tianjin University of Technology Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin300384 China Tianjin University of Sport School of Sports Economics and Management Tianjin301617 China

Task offloading, as an effective solution, provides low latency and sufficient computing resources for mobile users in the network. However, how to reasonably offload to reduce system overhead is a challenging issue today. This article takes user terminals, edge servers, and idle vehicles with resources as the network structure, and is inspired by the highly social nature of the gray wolf pack. It proposes a new offloading method of edge computing task based on hunting optimizing mechanism of gray wolf for the Internet of Vehicle (IOV). Firstly, an adaptive weight factor is proposed to balance the weight ratio of delay and energy consumption in the system cost under the constraints of delay and energy consumption. With delay and computing resources of vehicles and servers as constraints, a multi constraint minimization system cost problem is proposed. Secondly, the hunting process of the gray Wolf optimization algorithm is used to find the optimal solution of the unloading scheme, The Levy flight strategy was added to enhance the global search ability of the algorithm, and a dynamic weight strategy was introduced to improve the convergence performance of the algorithm. Finally, the improved gray Wolf optimization algorithm was used to solve the optimal unloading plan and minimum *** simulation results show that compared with traditional gray Wolf optimization algorithm offloading schemes, the proposed scheme in this paper requires lower system costs. © 2004-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

DCAS-BMT: Dynamic Construction and Adjustment of Skewed Bonsai Merkle Tree for Performance Enhancement in Secure Non-Volatile Memory

引用

IEEE Transactions on Computers 2025年

作者： Zhang, Yu Chen, Renhai Yan, Hangyu Wu, Hongyue Feng, Zhiyong Tianjin University College of Intelligence and Computing Tianjin300350 China Nanjing University State Key Lab. for Novel Software Technology Nanjing210023 China Yunnan University of Finance and Economics Yunnan Key Lab. of Service Computing Kunming650221 China

Traditional DRAM-based memory solutions face challenges, including high energy consumption and limited scalability. Non-Volatile Memory (NVM) offers low energy consumption and high scalability. However, security challenges, particularly data remanence vulnerabilities, persist. Prevalent methods such as the Bonsai Merkle Tree (BMT) are employed to ensure data security. However, the consistency requirements for integrity tree updates have led to performance issues. It is observed that compared to a secure NVM system without persistent secure metadata, the average overhead for updating and persisting the BMT root with persistent secure metadata is as high as 2.48 times. Therefore, this paper aims to mitigate these inefficiencies by leveraging the principle of memory access locality. We propose the Dynamic Construction and Adjustment of Skewed Bonsai Merkle Tree (DCAS-BMT). The DCAS-BMT is dynamically built and continuously adjusted at runtime according to access weights, ensuring frequently accessed memory blocks reside on shorter paths to the root node. This reduces the verification steps for frequently accessed memory blocks, thereby lowering the overall cost of memory authentication and updates. Experimental results using the USIMM memory simulator demonstrate that compared to the widely used BMT approach, the DCAS-BMT scheme shows a performance improvement of 34.1%. © 1968-2012 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

CESFusion: Cross-Frequency Enhanced Spatial—Spectral Fusion Network for Hyperspectral and Multispectral Image Fusion

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Haozheng Yang, Yanhong Li, Chaoyang Lu, Yanjie Zhang, Guodao Chen, Shengyong Tianjin University of Technology School of Computer Science and Engineering Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China School of Computer Science and Engineering Tianjin300384 China Hangzhou Dianzi University Institute of Intelligent Media Computing Hangzhou310018 China

The fusion of hyperspectral and multispectral images (MSIs) involves integrating a high spectral resolution hyperspectral image (HSI) and a high spatial resolution MSI to generate an HSI with high-resolution HSI (HR-HSI). Existing HSI-MSI fusion methods primarily focus on information fusion within the spatial domain;however, few solutions have explored the employment of frequency analysis to enhance spatial resolution, limiting their capability for global perception. In this article, we propose an efficient and novel paradigm for HSI-MSI fusion through the cross-frequency enhanced spatial-spectral fusion network, named CESFusion, exploring the complementary fusion of information between the spatial and frequency domains. Specifically, we first present the cross-frequency fusion module (CFFM) to perform global analysis through the Fourier transform (FT) and effectively integrate and enhance the frequency domain information from both HSI and MSI. Subsequently, we propose the spectral modeling module (SpeMM) based on a state space model (SMM) to capture long-range spectral dependencies with linear complexity, and integrate it with the spatial residual block-based module (SRM) for joint spatial-spectral feature extraction. Finally, to enable sufficient interaction between the spatial and frequency domains, we adopt the cross-domain interaction module (CDIM), capturing and integrating complementary information from both domains. Moreover, a frequency-based loss function is purposely designed to further improve the restoration of global information. Extensive experiments conducted on both synthetic and real datasets demonstrate the superiority of our CESFusion, as evidenced by both quantitative and qualitative evaluation results. © 1980-2012 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Secure, Fair and Scalable Data Sharing in Zero-Trust Edge-End Environment

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 2056-2069页

作者： Xu, Xiaolong Meng, Ke Xiang, Haolong Cui, Guangming Xia, Xiaoyu Dou, Wanchun Nanjing210044 China Nanjing University of Information Science and Technology School of Software and the Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing210044 China RMIT University School of Computing Technologies MelbourneVIC3000 Australia Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China

In edge computing, the Zero-Trust Security Model (ZTSM), as a key enabling technology for next-generation networks, plays a crucial role in providing authentication for addressing data sharing concerns, such as frequent data breaches, data misuse, and cyberattacks. However, due to the complexity and diversity of edge environments, ZTSM struggles to meet the security requirements of data sharing frameworks solely through enhanced authentication. Consequently, such frameworks with ZTSM still face challenges in ensuring data integrity, evaluating various node behaviors, and coping with the increasing complexity of node attributes. To address these issues, we propose a blockchain-enabled secure, fair and scalable data sharing framework in a zero-trust edge-end environment in this paper. Specifically, we first propose a Merkle forest-based data storage model for the classified storage of loosely coupled data, consequently enhancing the scalability of the model. Then, we design a node behavior-based reputation assessment mechanism to ensure fairness during data sharing. Moreover, a data sharing protocol supervised by smart contract is proposed, working with the aforementioned storage and assessment schemes, to ensure the security of data sharing. Finally, comprehensive security analysis validates the security, fairness and scalability of the proposed framework. Extensive experimental results show that, as transaction volume grows, the time cost of data traversal in the storage model becomes progressively more efficient. Additionally, when the size of the smart contract is increased tenfold, the maximum time cost of the data sharing protocol rises by only 4.98 times. © 1983-2012 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Superpoint Graph Transformer for Weakly Supervised 3D Semantic Segmentation

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Fan, Yan Wang, Yu Zhu, Pengfei Hui, Le Xie, Jin Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin300350 China Ministry of Education of the People's Republic of China Engineering Research Center of City Intelligence and Digital Governance China Haihe Laboratory of Itai Tianjin China Northwestern Polytechnical University School of Electronics and Information Shaanxi Key Laboratory of Information Acquisition and Processing China Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

Weakly supervised 3D semantic segmentation has successfully mitigated the labor-intensive and time-consuming task of annotating 3D point clouds. However, reliably utilizing the minimal point-wise annotations for unlabeled data in complex and large-scale scenes is still challenging, such as only 20 points labeled in 2 million points. To tackle this challenge, we propose a new Uncertainty-aware Superpoint Graph Transformer (UaSGT) framework that utilizes minimal annotations for unlabeled data learning through reliable long-range supervision propagation from labeled superpoints to unlabeled superpoints. First, we propose a superpoint graph transformer to achieve long-range supervision propagation along the attention-based fuzzy subsets defined on superpoints. The attention-based fuzzy subset measures the membership of unlabeled superpoints to clusters centered on labeled superpoints. Second, we employ an uncertainty-aware membership rectification technique on the fuzzy subset to ensure reliable propagation among superpoints within the same category. This technique integrates an uncertainty prediction module to mask the influence of unreliable membership and a spatial prior refinement module to reduce uncertainty in intra-class membership degrees. Finally, experimental results on two large-scale benchmarks S3DIS and ScanNet-V2 demonstrate the superiority of our approach compared to the state-of-the-art with at least 90% annotation reduction, and our method also achieves comparable performance to fully supervised methods with less than 0.1% labeled points. Our code is available at https://***/fanyan0411/UaSGT. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

K-ON: Stacking Knowledge On the Head Layer of Large Language Model

arXiv

引用

arXiv 2025年

作者： Guo, Lingbing Zhang, Yichi Bo, Zhongpu Chen, Zhuo Sun, Mengshu Zhang, Zhiqiang Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China School of Software Technology Zhejiang University China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Recent advancements in large language models (LLMs) have significantly improved various natural language processing (NLP) tasks. Typically, LLMs are trained to predict the next token, aligning well with many NLP tasks. However, in knowledge graph (KG) scenarios, entities are the fundamental units and identifying an entity requires at least several tokens. This leads to a granularity mismatch between KGs and natural languages. To address this issue, we propose K-ON, which integrates KG knowledge into the LLM by employing multiple head layers for next k-step prediction. K-ON can not only generate entity-level results in one step, but also enables contrastive loss against entities, which is the most powerful tool in KG representation learning. Experimental results show that K-ON outperforms state-of-the-art methods that incorporate text and even the other modalities. Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Predictive ISAC Beamforming Using LoRA-Transformer LSTM Integrated with GNN in Ultra-Dense D2D mmWave Networks

引用

IEEE Transactions on Vehicular technology 2025年

作者： Liu, Haochen Bi, Jia Li, Bohan Xiang, Luping Yang, Xin Zhang, Zhaolin Wang, Ling Northwestern Polytechnical University School of Electronics and Information Xi'an710019 China Rutherford Appleton Laboratory Scientific Computing Department STFC DidcotOX11 0QX United Kingdom Ocean University of China Faculty of Information Science and Engineering Qingdao266100 China Nanjing University State Key Laboratory of Novel Software Technology Nanjing210008 China School of Intelligent Software and Engineering Suzhou China

Effective beamforming is crucial in ultra-dense device-to-device (D2D) mmWave networks to reduce interference and optimize communication. However, current methods often struggle to balance high data rates with minimal signaling overhead, especially with imperfect channel state information (CSI). This paper introduces a machine learning-assisted beamforming design tailored for integrated sensing and communication (ISAC), combining an efficient Low-Rank Adaptation Blocked LSTM Transformer with Message Passing Graph Neural Network that is called as LoRA_BLT-MPGNN. The LoRA_BLT component provides a key advantage by efficiently capturing both temporal and spatial patterns through fixed-weight updates during training and low-rank approximation for fine-tuning, significantly reducing computational complexity without sacrificing accuracy. Using historical channel data, the method implicitly captures channel characteristics and directly predicts the beamforming matrix for the subsequent time slot, minimizing signaling overhead while maximizing the achievable sum rate. Our research and simulation results show that the proposed predictive beamforming design maintains robust sensing performance and achieves a sum rate closely approaching the upper bound achievable with perfect CSI. Additionally, the incorporation of MPGNNs enables efficient modeling and learning of complex inter-node relationships, making the approach adaptable to networks of varying sizes and densities. Simulations further demonstrate that the LoRA_BLT-MPGNN model can be generalized across different network densities and coverage areas, reducing computational complexity by approximately 32× in terms of Tensor Floating Point Operations (TFLOPs) compared to conventional methods while maintaining high performance. © 2025 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Diff-Reg v2: Diffusion-Based Matching Matrix Estimation for Image Matching and 3D Registration

arXiv

引用

arXiv 2025年

作者： Wu, Qianliang Jiang, Haobo Ding, Yaqing Luo, Lei Xie, Jin Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China School of Computer Science and Engineering Nanjing University of Science and Technology China Nanyang Technological University Singapore Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Intelligence Science and Technology Nanjing University Suzhou China

Establishing reliable correspondences is crucial for all registration tasks, including 2D image registration, 3D point cloud registration, and 2D-3D image-to-point cloud registration. However, these tasks are often complicated by challenges such as scale inconsistencies, symmetry, and large deformations, which can lead to ambiguous matches. Previous feature-based and correspondence-based methods typically rely on geometric or semantic features to generate or polish initial potential correspondences. Some methods typically leverage specific geometric priors, such as topological preservation, to devise diverse and innovative strategies tailored to a given enhancement goal, which cannot be exhaustively enumerated. Additionally, many previous approaches rely on a single-step prediction head, which can struggle with local minima in complex matching scenarios. To address these challenges, we introduce an innovative paradigm that leverages a diffusion model in matrix space for robust matching matrix estimation. Our model treats correspondence estimation as a denoising diffusion process in the matching matrix space, gradually refining the intermediate matching matrix to the optimal one. Specifically, we apply the diffusion model in the doubly stochastic matrix space for 3D-3D and 2D-3D registration tasks. In the 2D image registration task, we deploy the diffusion model in a matrix sub-space, where dual-softmax projection regularization is applied. For all three registration tasks, we provide adaptive matching matrix embedding implementations tailored to the specific characteristics of each task while maintaining a consistent"match-to-warp" encoding pattern. Furthermore, we adopt a lightweight design for the denoising module. In inference, once points or image features are extracted and fixed, this module performs multi-step denoising predictions through reverse sampling. Evaluations on both 2D and 3D registration tasks demonstrate the effectiveness of our approach. Copyrigh

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Modeling Multilevel Business Process Monitoring via BPMN Extension

引用

Concurrency and Computation: Practice and Experience 2025年第12-14期37卷

作者： Kang, Guosheng Wang, Zhen Cheng, Hangyu Liu, Jianxun Wen, Yiping Peng, Jun School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology Hunan University of Science and Technology Xiangtan China School of Computer Science and Technology Xi'an Jiaotong University Xi'an China School of Computer Science Fudan University Shanghai China

Business process monitoring involves real-time supervision of a series of activities carried out by an organization to achieve specific objectives. Process event monitoring points (PEMP) are used to pinpoint specific locations within a process model where expected events are anticipated to occur. However, in general business process modeling languages, such as business process model and notation (BPMN), there is a lack of explicit modeling for PEMPs. This article proposes a method for modeling pairwise event monitoring points in business process models to track the execution status of specific activities or process segments via BPMN extension. Specifically, process monitoring points are designed by expanding the modeling element of sequence flow. Moreover, the business process model is decomposed using the refined process structure tree (RPST) to verify the soundness of the designed pairwise monitoring points. The proposed method allows flexible monitoring at the process segment level. And the process monitoring data could be used for a clear understanding of business progress, especially useful in heterogeneous business process model to support decision-making. Through case study from real-world business processes, the effectiveness and usefulness of the proposed process monitoring modeling method is validated. © 2025 John Wiley & Sons Ltd.

关键词： Electronic trading

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：