检索结果-内蒙古大学图书馆

MULSAM: Multidimensional Attention with Hardware Acceleration for Efficient Intrusion Detection on Vehicular CAN Bus

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Xu, He Shi, Xiaokang Liu, Hansheng Wang, Yanwen Lu, Jiwu Zeng, Haibo Li, Renfa Wu, Di Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology Hunan Changsha410082 China Hunan University College of Electrical and Information Engineering Hunan Changsha410082 China Hunan University Shenzhen Research Institute Shenzhen518000 China Virginia Tech Department of Electrical and Computer Engineering BlacksburgVA24061 United States Hunan University College of Computer Science and Electronic Engineering Hunan Changsha410082 China

Controller Area Network (CAN) protocol is an efficient standard enabling communication among Electronic Control Units (ECUs). However, the CAN bus is vulnerable to malicious attacks because of a lack of defense features. In this article, a novel vehicle Intrusion Detection System (IDS) is developed. The challenge is that existing techniques of Intrusion Detection Systems (IDS) rarely consider attacks with small-batch, which are characterized by their small attack scale and concealed attack patterns, posing a significant threat to driving safety. To solve this problem, we developed an algorithm model that merges Multi-dimensional Long Short-Term Memory (MD-LSTM) and Self-Attention Mechanism (SAM), shortly named MULSAM. The MULSAM model was compared with other baseline models, including Stacked LSTM, MD-LSTM, etc. Experiments show that our approach has the best detection accuracy (98.98%) and training stability. Further, to speed up the inference of MULSAM on edge, the hardware accelerator is implemented on FPGA devices using technologies such as parallelization, modular, pipeline, and fixed-point quantization. Experiments show that our FPGA-based acceleration scheme has a better energy efficiency than the CPU platform. Even with a certain degree of quantification, the acceleration model for MULSAM still displays a high detection accuracy of 98.81% and a low latency of 1.88 ms. © 1982-2012 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

SGPS-IMR: Efficiently inferring microbial resistance using self-supervised graph perturbation strategy

引用

Expert Systems with Applications 2025年 283卷

作者： Wang, Wentao Zhuo, Linlin Zhou, Zhecheng Fu, Xiangzheng Zou, Quan School of Data Science and Artificial Intelligence Wenzhou University of Technology Wenzhou325027 China College of Computer Science and Electronic Engineering Hunan University Changsha410012 China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu611730 China

Effectively inferring microbial resistance within the human body can assist in uncovering potential treatment solutions for certain major diseases. Computational methods, primarily driven by deep learning, can efficiently infer potential microbial resistances based on known resistance data. However, real-world data may contain unavoidable noise, which can limit the performance of these models to some extent. Furthermore, these models rely heavily on constructing complex feature extractors and classifiers, which diminishes their generalization capabilities. Our study develops the SGPS-IMR model, which is based on a self-supervised graph perturbation strategy, aiming to efficiently identify unknown microbial resistances. The SGPS-IMR model runs in a self-supervised learning manner, combining initial node features with the topology information of the microbe-drug graph, to reconstruct this graph and extract more comprehensive node representations. Instead of inputting the entire observed microbe-drug graph, the model inputs a graph with some edges removed. This perturbation strategy effectively mitigates the influence of noisy data, enhancing self-supervised training. Additionally, we design a collaborative decoder based on multi-hop node neighbors to limit the impact of information loss. Unlike traditional methods, SGPS-IMR does not focus on developing complex feature extractors or classifiers to enhance performance. Instead, SGPS-IMR employs straightforward graph perturbation and collaborative decoding strategies to improve node representation and the model's generalization ability. Additionally, the model's performance was assessed on three public datasets: MDAD, DrugVirus, and aBiofilm. The results indicate that the proposed model outperforms the current state-of-the-art by margins of 2.98% and 3.85%, 4.98% and 4.05%, and 2.63% and 3.47% in AUC and AUPR scores across three datasets, respectively. © 2025

关键词： Perturbation techniques

来源：评论

学校读者我要写书评

暂无评论

Multi-Keypoint Affordance Representation for Functional Dexterous Grasping

arXiv

引用

arXiv 2025年

作者： Yang, Fan Luo, Dongsheng Chen, Wenrui Lin, Jiacheng Cai, Junjie Yang, Kailun Li, Zhiyong Wang, Yaonan School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China College of Computer Science and Electronic Engineering Hunan University Changsha China

Functional dexterous grasping requires precise hand-object interaction, going beyond simple gripping. Existing affordance-based methods primarily predict coarse interaction regions and cannot directly constrain the grasping posture, leading to a disconnection between visual perception and manipulation. To address this issue, we propose a multi-keypoint affordance representation for functional dexterous grasping, which directly encodes task-driven grasp configurations by localizing functional contact points. Our method introduces Contact-guided Multi-Keypoint Affordance (CMKA), leveraging human grasping experience images for weak supervision combined with Large Vision Models for fine affordance feature extraction, achieving generalization while avoiding manual keypoint annotations. Additionally, we present a Keypoint-based Grasp matrix Transformation (KGT) method, ensuring spatial consistency between hand keypoints and object contact points, thus providing a direct link between visual perception and dexterous grasping actions. Experiments on public real-world FAH datasets, IsaacGym simulation, and challenging robotic tasks demonstrate that our method significantly improves affordance localization accuracy, grasp consistency, and generalization to unseen tools and tasks, bridging the gap between visual affordance learning and dexterous robotic manipulation. The source code and demo videos will be publicly available at https://***/PopeyePxx/MKA. Copyright © 2025, The Authors. All rights reserved.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

Multimodal Feature-Driven Deep Learning for the Prediction of Duck Body Dimensions and Weight

arXiv

引用

arXiv 2025年

作者： Xiao, Wenbo Han, Qiannan Shu, Gang Liang, Guiping Zhang, Hongyan Wang, Song Xu, Zhihao Wan, Weican Li, Chuang Jiang, Guitao Xiao, Yi College of Information and Technology Hunan Agricultural University Hunan Changsha410129 China Hunan Institute of Animal and Veterinary Science Hunan Changsha410131 China College of Animal Science and Technology Sichuan Agricultural University Sichuan Chengdu611130 China School of Computer Science and Engineering the University of New South Wales SydneyNSW2052 Australia

Accurate body dimension and weight measurements are critical for optimizing poultry management, health assessment, and economic efficiency. This study introduces an innovative deep learning-based model leveraging multimodal data—2D RGB images from different views, depth images, and 3D point clouds—for the non-invasive estimation of duck body dimensions and weight. A dataset of 1,023 Linwu ducks, comprising over 5,000 samples with diverse postures and conditions, was collected to support model training. The proposed method innovatively employs PointNet++ to extract key feature points from point clouds, extracts and computes corresponding 3D geometric features, and fuses them with multi-view convolutional 2D features. A Transformer encoder is then utilized to capture long-range dependencies and refine feature interactions, thereby enhancing prediction robustness. The model achieved a mean absolute percentage error (MAPE) of 6.33% and an R2 of 0.953 across eight morphometric parameters, demonstrating strong predictive capability. Unlike conventional manual measurements, the proposed model enables high-precision estimation while eliminating the necessity for physical handling, thereby reducing animal stress and broadening its application scope. This study marks the first application of deep learning techniques to poultry body dimension and weight estimation, providing a valuable reference for the intelligent and precise management of the livestock industry with far-reaching practical significance. Copyright © 2025, The Authors. All rights reserved.

关键词： Weighing

来源：评论

学校读者我要写书评

暂无评论

FasterCReW: Performance or Efficiency? A Lightweight Conditional Residual DNN-based Watermarking Based on FasterNet

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Wang, Baowei Zhang, Jianbo Wu, Yufeng Cui, Qi Nanjing University of Information Science and Technology Engineering Research Center of Digital Forensics Ministry of Education The School of Computer Science The Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology The Jiangsu Yuchi Blockchain Technology Research Institute Nanjing210044 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China

Deep neural networks (DNNs) based watermarking algorithms have made significant strides in recent years. However, existing methods either demand substantial resources for image feature extraction during watermark embedding, sacrificing efficiency, or completely neglect image texture information, resulting in suboptimal performance. Moreover, current algorithms struggle with real-time watermark extraction. To address these limitations, we propose a lightweight conditional residual watermarking (CReW) architecture. Specifically, CReW employs a Conditional Generative Adversarial Network (CGAN) framework to generate an adaptive residual image guided by the structure of the cover image, which is decoupled from the network to reduce computational complexity. This design enables CReW to achieve an optimal balance between performance and efficiency. Additionally, by directly optimizing the residual image to capture variations in watermark behavior under distortion, CReW significantly enhances robustness. Furthermore, we design redundancy coding blocks to increase the mutual information of the watermark, along with a patch-level discriminator to improve local patch discrimination, thereby further enhancing image quality. Finally, by reducing channel redundancy and leveraging FasterNet, we developed a low-complexity network architecture, Faster-CReW, which facilitates real-time watermark embedding and extraction. Extensive experimental results demonstrate that, despite having 36× fewer network parameters and 30× fewer floating point operations (FLOPs) than Adaptor, Faster-CReW exhibits excellent robustness against distortions such as cropout, JPEG compression, and Gaussian noise. Furthermore, Faster-CReW significantly outperforms other existing DNN-based watermarking algorithms in terms of running speed, achieving an 8× speed increase over UDH and a 28× increase over Adaptor on an Intel Core i7-8750H CPU. (Figure presented) © 2025 IEEE. All rights reserved.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Adhesion mechanisms of SBS modified asphalt mixtures: Molecular dynamics and density functional theory analysis under aging and chloride erosion

引用

Construction and Building Materials 2025年 483卷

作者： Xie, Huijun Liu, Yizhou Long, Zhengwu Li, Zhenyu Guo, Nanning Dai, Botao Yang, Hao Xu, Fu Jin, Dongzhao You, Lingyun College of Civil Engineering Xiangtan University Hunan Xiangtan411105 China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Hubei Wuhan430074 China Department of Civil Environmental and Geospatial Engineering Michigan Technological University 1400 Townsend Drive HoughtonMI49931-1295 United States

The study aims to understand the adhesion damage mechanism of SBSMA (Styrene-Butadiene-Styrene Modified Asphalt) at the interface with aggregates in complex service environments. Molecular models of SBS at various aging stages were created and assessed for their physicochemical properties, such as infrared spectra and chemical reactivity, using quantum chemical simulation methods. The accuracy of the SBSMA models was verified through parameters like density and cohesive energy density. Interface models with different mineral aggregates in pure water and salt solutions were constructed to study the adhesion characteristics under varying thermo-oxidative aging intensities, mineral types, and chloride salt concentrations. The study found that as aging intensity increases, SBS molecules experience agglomeration, chain breaking, and polarity enhancement. This leads to intensified migration and diffusion, causing competitive adsorption at the interface and a tendency for SBS molecules to be adsorbed more on the side of the aggregates. Water molecules can permeate the aggregate surface, forming a strong hydrogen bonding network and occupying numerous adsorption sites, which weakens the adhesion properties between asphalt and aggregate. However, the presence of ions disrupts this network, and ionic bridges can indirectly increase the adhesive strength between asphalt and aggregate, particularly with age. Using a calcium carbonate substrate results in ion pairs being adsorbed close to the aggregate, forming a solvated shell layer with upper water molecules, which delays the increase in adhesion energy. This study provides significant insights into composite modification and reclaimed pavements of SBSMA, highlighting the impact of aging intensity, mineral type, and chloride concentration on the adhesion properties of asphalt-aggregate interfaces. © 2025 Elsevier Ltd

关键词： Hydrogen bonds

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Stable Data Trading for Unknown Market Based on Blockchain

引用

IEEE Transactions on Mobile Computing 2025年

作者： Deng, Qingyong Zuo, Qinghua Li, Zhetao Liu, Haolin Xie, Yong Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin541004 China College of Information Science and Technology Jinan University Guangzhou510632 China School of Computer Science Xiangtan University Xiangtan Hunan411105 China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing Jiangsu210042 China

Crowdsensing Data Trading (CDT) has emerged as a novel data trading paradigm, where market stability is crucial during the transaction matching process. However, most existing CDT systems usually assume that the preferences of both parties are known and the third-party trading platform is trustworthy, which is impractical in real-world scenarios and leads to significant challenges in reliability and privacy preservation. To address these challenges, we propose a Privacy-Preserving and Stable Data Trading for Unknown Market based on Blockchain and Bilateral Reputation (PPSDT-UMBBR) scheme in the decentralized CDT system. Firstly, a privacy-preserving bilateral preference initialization method is designed to achieve the initial matching of buyers and sellers without exposing their location and attribute privacy. Then, a stable matching method based on dynamic bilateral preference updating is proposed, integrating Differential Privacy, Stable matching theory, and a strategy based on Asymmetric Bilateral Preferences with Multi-armed Bandits (DPS-ABPMAB). Finally, we theoretically analyze the security and prove that the market outcome is δ stable. Furthermore, compared to other benchmark methods based on real datasets, our proposed DPS-ABPMAB algorithm improves the average accumulative reward by at least 4.22%, and reduces the average accumulative regret and the mean evaluation error rate by at least 66.86% and 7.35%, respectively. © 2025 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Covert Communication in RSMA-Assisted Ambient Backscatter Communication Systems

引用

IEEE Transactions on Wireless Communications 2025年

作者： Zhang, Zhuo Yang, Liang Lei, Hongjiang Li, Xingwang Niyato, Dusit Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Hunan University College of Computer Science and Electronic Engineering China Jishou University School of Communication and Electronic Engineering China Chongqing University of Posts and Telecommunications School of Communications and Information Engineering The Chongqing Key Laboratory of Mobile Communications Technology Chongqing400065 China Henan Polytechnic University School of Physics and Electronic Information Engineering Jiaozuo454003 China Nanyang Technological University College of Computing and Data Science Singapore639798 Singapore

In this paper, we investigate covert communication in rate-splitting multiple access (RSMA)-assisted ambient backscatter communication (AmBC) systems. Specifically, in the presence of illegitimate users, a base station applies RSMA to the downlink transmission of covert users and common users in the the primary system of ambient backscatter. To evaluate the covertness of the system, we derive closed-form expressions for the detection error probability (DEP), outage probability (OP), and covert rate (CR), where the DEP is applied to evaluate the ability of the warden to detect the presence or absence of communication behaviors between the base station and the covert user. Based on these expressions, we also conduct an asymptotic analysis of the outage probability, an upper bound analysis of the covert rate, and an analysis of the impact of the power allocation factor on system performance. Numerical results show that the RSMA scheme has a higher covert rate and a higher minimum DEP value compared to the non-orthogonal multiple access (NOMA) scheme, but it may reduce its outage performance. Additionally, an appropriate use of the power allocation factor can enhance the covertness of the system. Furthermore, we find that the co-channel interference between the primary and secondary systems in the ambient backscatter system can degrade the covert performance of the primary system. © 2002-2012 IEEE.

关键词： Backscattering

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Interpolation Methods for Enriching WiFi Fingerprint Database 24

Performance Comparison of Interpolation Methods for Enrichin...

引用

9th International Conference on Cloud Computing and Internet of Things, CCIOT 2024

作者： Vu-Thanh, Trung He, Jing Duong-Bao, Ninh Thi, Luong Nguyen Lee, Seon-Woo Nguyen-Huu, Khanh College of Computer Science and Electronic Engineering Hunan University Changsha China Faculty of Mathematics and Informatics Dalat University Dalat Viet Nam Faculty of Information Technology Dalat University Dalat Viet Nam Division of Software Hallym University Chuncheon Korea Republic of Department of Electronics and Telecommunications Dalat University Dalat Viet Nam

ISBN: (纸本)9798400717161

Recently, WiFi Fingerprinting-based indoor positioning systems have gained significant attention due to the low cost of infrastructure deployment. In the data collection process, a higher density of reference points may lead to better positioning results. However, it makes this process time-consuming and laborious. To solve this problem, this study applies and compares different interpolation methods to enrich the fingerprint database without increasing the cost of the collection process. To evaluate the performance of the chosen methods, five interpolation methods are implemented in a multi-condition WiFi Fingerprinting dataset. Moreover, to check the robustness of the methods, different numbers of reference points are considered when creating the new interpolated fingerprint databases. According to the results, inverse distance weighting (IDW) is the most suitable interpolation method with low complexity and stable performance. The IDW-based database achieves an average interpolation error of less than 6 dBm compared to the original database. When applying this interpolated database to perform positioning tasks, it helps reduce the collection cost by 30% with slightly lower positioning results compared to the original database. This work demonstrates the feasibility of using interpolation to ease the data collection process of WiFi Fingerprinting, especially in complex and big areas such as airports or hospitals. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Wi-Fi

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：