检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dong, Wei Sun, Yuan Yang, Yiting Zhang, Xing Lin, Zhijun Yan, Qingsen Zhang, Haokui Wang, Peng Yang, Yang Shen, Hengtao College of Information and Control Engineering Xi'an University of Architecture and Technology China School of Computer Science Northwestern Polytechnical University China School of Computer Science and Engineering University of Electronic Science and Technology of China China School of Computer Science and Technology Tongji University China

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projection and up-projection matrices, with the bottleneck dimensionality being crucial for reducing the number of learnable parameters, as exemplified by prevalent methods like LoRA and Adapter. However, these low-rank strategies typically employ a fixed bottleneck dimensionality, which limits their flexibility in handling layer-wise variations. To address this limitation, we propose a novel PEFT approach inspired by Singular Value Decomposition (SVD) for representing the adaptation matrix. SVD decomposes a matrix into the product of a left unitary matrix, a diagonal matrix of scaling values, and a right unitary matrix. We utilize Householder transformations to construct orthogonal matrices that efficiently mimic the unitary matrices, requiring only a vector. The diagonal values are learned in a layer-wise manner, allowing them to flexibly capture the unique properties of each layer. This approach enables the generation of adaptation matrices with varying ranks across different layers, providing greater flexibility in adapting pre-trained models. Experiments on standard downstream vision tasks demonstrate that our method achieves promising fine-tuning performance. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Internet of Things in Mammography Screening Using Multicenter Transformation Between Unified Capsules

引用

IEEE Internet of Things Journal 2023年第2期10卷 1536-1545页

作者： Wang, Boyan Hu, Xuegang Zhang, Jinglin Xu, Chenchu Gao, Zhifan Hefei University of Technology School of Computer Science and Information Engineering Hefei China Shandong University School of Control Science and Engineering Jinan250061 China Anhui University School of Computer Science and Technology Hefei230093 China Sun Yat-sen University School of Biomedical Engineering Guangzhou510275 China

Mammography screening is one of the important applications for the intelligent Internet of Things (IoT). Due to the efficient and personalized cyber-medicine system, early diagnosis can successfully reduce the breast cancer mortality rate by AI-driven healthcare. However, it is a huge challenge to extend the conventional single-center into the multicenter mammography screening, thus improving the effectiveness and robustness of intelligent IoT-based devices. To address this problem, we utilize multicenter mammograms by the modified capsule neural network and propose a novel framework called multicenter transformation between unified capsules (MLT-UniCaps) in this article. The proposed MLT-UniCaps is composed of Attentional Pose Embedding, Dynamic Source Capsule Traversal, and Adaptive Target Capsule Fusion to realize an intelligent remote assistant diagnosis. Attentional Pose Embedding extracts feature vectors via variations in position, orientation, scale, and lighting as the poses through an adversarial convolutional neural network with an attention-based layer. Based on the pose presentation, Dynamic Source Capsule Traversal deploys a dynamic routing mechanism between neurons to build a source cancer classifier for single-center mammography screening. Using the source cancer classifier, Adaptive Target Capsule Fusion integrates various centers of mammograms as the universal cancer detectors and optimizes heterogeneous distribution among them by the transformation-likelihood maximization. Owing to the three components, MLT-UniCaps effectively improves the results of single-center mammography screening and works in the multicenter breast cancer diagnosis. By comprehensive experiments on 58 965 samples, the proposed MLT-UniCaps obtains 90.1% of overall classification accuracy on single-center trials and 73.8% of overall F1 score on multicenter trials. All the experimental results illustrated that our MLT-UniCaps, an intelligent IoT-based clinical tool, inures the be

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Deep Contrastive Clustering for Protocol Analysis in 5G Network engineering 4

Deep Contrastive Clustering for Protocol Analysis in 5G Netw...

引用

4th International Conference on Communication technology and Information technology, ICCTIT 2024

作者： Lu, Jianhong Zhang, Kun Nanjing University of Science and Technology School of Cyber Science and Engineering Nanjing China Nanjing University of Science and Technology School of Computer and Engineering Nanjing China

ISBN: (纸本)9798331528973

With the widespread adoption of 5G networks in satellite communication and vehicular communication systems, the complexity of communication and signaling interactions has significantly increased. Traditional protocol analysis methods primarily focus on high-level structured data, often neglecting the low-level binary data critical for understanding 5G-specific protocols. This paper proposes a novel approach that employs a deep contrastive clustering framework to analyze and classify unknown protocols in 5G communication networks. The proposed method leverages depthwise separable convolutions for feature extraction, transforming binary protocol data into structured feature representations while significantly reducing computational overhead. Additionally, by integrating contrastive learning into the clustering process, the framework enhances the discrimination of protocol embeddings through a positive-negative sample feedback mechanism, ensuring more accurate clustering results. Additionally, this paper collected and analyzed a comprehensive dataset of 5 G protocols, which includes wireless access layer protocols and core network communication protocols. © 2024 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Advancing IoMT Defenses: Deep Collaborative Learning for Robust Healthcare Security

Advancing IoMT Defenses: Deep Collaborative Learning for Rob...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Otoum, Yazan Singh, Paritosh Nayak, Amiya Algoma University School of Computer Science and Technology Canada University of Ottawa School of Electrical Engineering and Computer Science Canada

ISBN: (纸本)9798350351255

The Internet of Medical Things (IoMT) plays a pivotal role in healthcare, connecting a myriad of medical devices and applications for efficient patient care. However, the rising prevalence of cyberattacks targeting healthcare institutions for patient data underscores the critical need for robust security measures. This paper introduces a novel Homogenous Collaborative Machine Learning (HCML)-based model to enhance the security of healthcare-connected devices. Utilizing a Deep Neural Network (DNN) algorithm, our model constructs a tailored security framework by integrating multiple device 'edges', enhancing the system's ability to thwart cyber threats. We investigate the impact of incorporating additional edges on the model's performance, employing various metrics and assessing execution times with the IoT healthcare security dataset. Our findings reveal that, compared to conventional centralized learning methods, our proposed HCML model achieves superior generalization, incremental learning, and performance enhancement while maintaining stringent data privacy. This research contributes significantly to the IoMT field by providing a scalable and robust security solution adaptable to the evolving landscape of cyber threats. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Bimetallic Ni-Co MOF@PAN modified electrospun separator enhances high-performance lithium-sulfur batteries

引用

Journal of Energy Chemistry 2023年第7期82卷 484-496,I0010页

作者： Xiaolong Leng Jie Zeng Mingdai Yang Changping Li S.V.Prabhakar Vattikuti Jielin Chen Shuang Li Jaesool Shim Tong Guo Tae Jo Ko School of Mechanical Engineering Yeungnam UniversityGyeongsangbuk-do 38541Republic of Korea College of Mechanical and Electrical Engineering Hunan University of Science and TechnologyXiangtan 411201HunanChina Key Laboratory for Soft Chemistry and Functional Materials of Ministry of Education Nanjing University of Science and TechnologyNanjing 210094JiangsuChina

Lithium-sulfur(Li-S)batteries with high energy density are considered promising energy storage devices for the next ***,the shuttle effect and the passive layer between the separator and the electrodes still seriously affect the cycle stability and ***,a bimetallic Ni-Co metal-organic framework(MOF)with adsorption and catalytic synergism for polysulfides was successfully synthesized as an electrospinning separator sandwich for Li-S *** porous Ni-Co MOF coatings into the separator provides more adsorption catalytic sites for polysulfides,prevents their diffusion to the anode,and enhances sulfur ***,the improved Li-S batteries with a Ni-Co MOF@PAN(NCMP)electrospun separator delivered excellent rate performance and outstanding cycle stability,yielding an ultra-high initial capacity of 1560 mA h g^(-1)at 0.1 ***,remarkable Li-S battery performance with a discharge capacity of 794 mA h g^(-1)(84.1%capacity retention)was obtained after500 cycles,while delivering a low capacity decay rate of 0.032%during long-term cycling(up to 500cycles)at 1 ***,even at the current density of 2 C,the capacity attenuation rate of 2000 cycles is only 0.034%per *** addition,compared with the Celgard separator,the NCMP separator also had high thermal stability(keeping the separator outline at 200℃)that ensured battery safety and excellent electrolyte wettability(73%porosity and 535%electrolyte absorption)and significantly enhanced the ionic conductivity and Li^(+) transfer number,and protected the surface integrity of the anode.

关键词： Li-S batteries Ni-Co MOF Adsorption catalysis Synergistic effect

来源：评论

学校读者我要写书评

暂无评论

Recommendation Algorithm Based on Social Influence Diffusion 17

Recommendation Algorithm Based on Social Influence Diffusion

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Jin, Xin Chen, Shiyu Nanjing University of Science and Technology School of Mechanical Engineering Nanjing China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350351637

Social influence is everywhere in people's lives. It controls users' activities in social networks. Understanding the mechanism of interactions between users in social networks can benefit various applications, such as recommendations. Traditional recommendation systems based on collaborative filtering suppose that the behaviors of users are independent of each other and ignore the influence relationships among users. However, different historical behaviors and social relationships of users result in different influences among users. First, the complete user behavior sequences are fed into a recurrent neural network to capture long term patterns of user interest in items. Secondly, a self-attention network is used to obtain short lived interests of users. Then the outputs of the recurrent neural network as queries are fed into another self-attention network to obtain user representations that combine transient effect of and long term patterns of users' interests, thereby predicting the ratings of users to items. Finally, the proposed recommendation system is used to recommend products that need to be promoted to the maximum number of users. The proposed method is verified to outperform the state-of-the-art algorithms on three real-world datasets. © 2024 IEEE.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

DIEONet:Domain-Invariant Information Extraction and Optimization Network for Visual Place Recognition

引用

computers, Materials & Continua 2025年第3期82卷 5019-5033页

作者： Shaoqi Hou Zebang Qin Chenyu Wu Guangqiang Yin Xinzhong Wang Zhiguo Wang School of Computer Science and Technology Xinjiang UniversityUrumqi830046China School of Information and Software Engineering University of Electronic Science and Technology ofChinaChengdu611731China Institute of Public Security Kash Institute of Electronics and Information IndustryKashi844000China

Visual Place Recognition(VPR)technology aims to use visual information to judge the location of agents,which plays an irreplaceable role in tasks such as loop closure detection and *** is well known that previous VPR algorithms emphasize the extraction and integration of general image features,while ignoring the mining of salient features that play a key role in the discrimination of VPR *** this end,this paper proposes a Domain-invariant Information Extraction and Optimization Network(DIEONet)for *** core of the algorithm is a newly designed Domain-invariant Information Mining Module(DIMM)and a Multi-sample Joint Triplet Loss(MJT Loss).Specifically,DIMM incorporates the interdependence between different spatial regions of the feature map in the cascaded convolutional unit group,which enhances the model’s attention to the domain-invariant static object *** Loss introduces the“joint processing of multiple samples”mechanism into the original triplet loss,and adds a new distance constraint term for“positive and negative”samples,so that the model can avoid falling into local optimum during *** demonstrate the effectiveness of our algorithm by conducting extensive experiments on several authoritative *** particular,the proposed method achieves the best performance on the TokyoTM dataset with a Recall@1 metric of 92.89%.

关键词： Visual place recognition domain-invariant information mining module multi-sample joint triplet loss

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Real-Time Radar Modeling with Consideration of False and Missed Alarms for Autonomous Driving Simulation

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-12页

作者： Huang, Kaibo Deng, Weiwen Wang, Ying Zhao, Rui Ding, Juan School of Transportation Science and Engineering Beihang University Beijing China College of Computer Science and Technology Jilin University Jilin China PanoSim Technology Company Limited Jiaxing Zhejiang China

Simulation is crucial for autonomous driving technology evolution. Radar, as an essential sensor in this field, significantly influences decision-making with its outputs. High-fidelity autonomous driving simulations require radar models that replicate radar outputs, including false alarms, missed alarms, and measurement errors, both in real-time and with high fidelity. The radar detection process is highly complex, and false and miss alarms add significant uncertainty to the detection results. Current radar models cannot accurately predict radar outputs. To address these issues, this study introduces a data-driven radar modeling approach. Initially, an analysis of factors influencing radar detection outcomes was conducted. Then proposes a labeling method for radar output objects, identify the corresponding scene targets, and distinguish between ghost and real objects. Following this, it introduces a modeling technique that separates radar output status and parameters, aiming to accurately predict radar outputs in the presence of false and missed alarms. It further decouples output parameters to boost prediction accuracy. Radar data is then collected to create a dataset. The radar model is developed and validated against conventional models. The model achieves a 96.5% accuracy in predicting false and missed alarms, with its predictions for radar output parameters closely approximating actual values. Compared to traditional models, there are improvements exceeding 70.60% and 93.68% respectively. Its 5-millisecond processing speed is substantially faster than actual radar speeds. This demonstrates the method's ability to create high-fidelity, real-time models. IEEE

关键词： Radar cross section

来源：评论

学校读者我要写书评

暂无评论

Digital twin empowered lightweight and efficient blockchain for dynamic internet of vehicles

引用

Digital Communications and Networks 2024年第6期10卷 1698-1707页

作者： Haoye Chai Supeng Leng Jianhua He Ke Zhang School of Information and Communication Engineering University of Electronic Science and Technology of China(UESTC)Chengdu611731China Shenzhen Institute for Advanced Study UESTCShenzhen518000China School of Computer Science and Electronic Engineering University of EssexColchesterCO43SQUK

The Internet of Vehicles(Io V)has great potential for Intelligent Transportation Systems(ITS),enabling interactive vehicle applications,such as advanced driving and *** is crucial to ensure the reliability during the vehicle-to-vehicle interaction *** the emerging blockchain has superiority in handling security-related issues,existing blockchain-based schemes show weakness in highly dynamic Io *** the transaction broadcast and consensus process require multiple rounds of communication throughout the whole network,while the high relative speed between vehicles and dynamic topology resulting in the intermittent connections will degrade the efficiency of *** this paper,we propose a Digital Twin(DT)-enabled blockchain framework for dynamic Io V,which aims to reduce both the communication cost and the operational latency of *** address the dynamic context,we propose a DT construction strategy that jointly considers the DT migration and blockchain computing ***,a communication-efficient Local Perceptual Multi-Agent Deep Deterministic Policy Gradient(LPMA-DDPG)algorithm is designed to execute the DT construction strategy among edge servers in a decentralized *** simulation results show that the proposed framework can greatly reduce the communication cost,while achieving good security *** dynamic DT construction strategy shows superiority in operation latency compared with benchmark *** decentralized LPMA-DDPG algorithm is helpful for implementing the optimal DT construction strategy in practical ITS.

关键词： Digital twin Blockchain Internet of vehicles Multi-agent DDPG

来源：评论

学校读者我要写书评

暂无评论

ASL-OOD:Hierarchical Contextual Feature Fusion with Angle-Sensitive Loss for Oriented Object Detection

引用

computers, Materials & Continua 2025年第2期82卷 1879-1899页

作者： Kexin Wang Jiancheng Liu Yuqing Lin Tuo Wang Zhipeng Zhang Wanlong Qi Xingye Han Runyuan Wen Northwest Institute of Mechanical and Electrical Engineering Xianyang712099China School of Information Engineering Chang’an UniversityXi’an710064China School of Computer Science and Technology Xidian UniversityXi’an710071China

Detecting oriented targets in remote sensing images amidst complex and heterogeneous backgrounds remains a formidable challenge in the field of object *** frameworks for oriented detection modules are constrained by intrinsic limitations,including excessive computational and memory overheads,discrepancies between predefined anchors and ground truth bounding boxes,intricate training processes,and feature alignment *** overcome these challenges,we present ASL-OOD(Angle-based SIOU Loss for Oriented Object Detection),a novel,efficient,and robust one-stage framework tailored for oriented object *** ASL-OOD framework comprises three core components:the Transformer-based Backbone(TB),the Transformer-based Neck(TN),and the Angle-SIOU(Scylla Intersection over Union)based Decoupled Head(ASDH).By leveraging the Swin Transformer,the TB and TN modules offer several key advantages,such as the capacity to model long-range dependencies,preserve high-resolution feature representations,seamlessly integrate multi-scale features,and enhance parameter *** improvements empower the model to accurately detect objects across varying *** ASDH module further enhances detection performance by incorporating angle-aware optimization based on SIOU,ensuring precise angular consistency and bounding box *** approach effectively harmonizes shape loss and distance loss during the optimization process,thereby significantly boosting detection *** evaluations and ablation studies on standard benchmark datasets such as DOTA with an mAP(mean Average Precision)of 80.16 percent,HRSC2016 with an mAP of 91.07 percent,MAR20 with an mAP of 85.45 percent,and UAVDT with an mAP of 39.7 percent demonstrate the clear superiority of ASL-OOD over state-of-the-art oriented object detection *** findings underscore the model’s efficacy as an advanced solution for challenging remote sensing object detection tasks.

关键词： Oriented object detection transformer deep learning

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：