检索结果-内蒙古大学图书馆

Self-Supervised Hyperbolic Spectro-Temporal Graph Convolution Network for Early 3D Behavior Prediction

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Liu, Peng Lai, Qin Li, Haibo Zhao, Chong Wang, Qicong Meng, Hongying Xiamen University Department of Computer Science and Technology School of Informatics Xiamen361102 China Brunel University London Department of Electronic and Electrical Engineering UxbridgeUB8 3PH United Kingdom

3D human behavior is a highly nonlinear spatiotemporal interaction process. Therefore, early behavior prediction is a challenging task, especially prediction with low observation rates in unsupervised mode. To this end, we propose a novel self-supervised early 3D behavior prediction frame-work that learns graph structures on hyperbolic manifold. Firstly, we employ the sequence construction of multi-dynamic key information to enlarge the key details of spatio-temporal behavior sequences, addressing the high redundancy between frames of spatio-temporal interaction. Secondly, for capturing dependencies among long-distance joints, we explore a unique graph Laplacian on hyperbolic manifold to perceive the subtle local difference within frames. Finally, we leverage the learned spatio-temporal features under different observation rates for progressive contrast, forming self-supervised signals. This facilitates the extraction of more discriminative global and local spatio-temporal information from early behavior sequences in unsupervised mode. Extensive experiments on three behavior datasets have demonstrated the superiority of our approach at low to medium observation rates. © 2016 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

ML-Inspired Multiple Relay Selection in UAV-Enabled Untrusted Networks

ML-Inspired Multiple Relay Selection in UAV-Enabled Untruste...

引用

IEEE Conference on Wireless Communications and Networking

作者： Lefteris Tsipi Emmanouel T. Michailidis Konstantinos Maliatsos Demosthenes Vouyioukas Dept. of Information and Communication Systems Engineering University of the Aegean Samos Greece Dept. of Informatics and Computer Engineering University of West Attica Egaleo Greece Dept. of Digital Systems University of Piraeus Piraeus Greece

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

In this paper, multiple relay selection (MRS) schemes for untrusted unmanned aerial vehicle (UAV)-enabled networks are proposed. In this context, various machine learning (ML) models are employed to improve secrecy performance by optimally selecting multiple aerial relays from the available ones, all of which are regarded as untrusted. Notably, these ML models can cope with the quickly changing and random positioning of the aerial relays, effectively decoupling the intricate coupling relationship between the secrecy rate, channel coefficients, and inter-node distances. The results indicate that the ML-based MRS schemes obtain sufficient accuracy and better decoupling than a respective exhaustive searching (ES) approach, while also maintaining a lower computational complexity.

关键词： Couplings Accuracy Predictive models Autonomous aerial vehicles Security Ensemble learning Relays Computational complexity Context modeling

来源：评论

学校读者我要写书评

暂无评论

EvAlignUX: Advancing UX Evaluation through LLM-Supported Metrics Exploration 25

EvAlignUX: Advancing UX Evaluation through LLM-Supported Met...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Qingxiao Zheng Minrui Chen Pranav Sharma Yiliu Tang Mehul Oswal Yiren Liu Yun Huang Computer Science and Engineering University at Buffalo Buffalo New York USA Informatics University of Illinois Urbana-Champaign Champaign Illinois USA Computer Science University of Illinois Urbana-Champaign Champaign Illinois USA Informatics University of Illinois at Urbana-Champaign Champaign Illinois USA Information Sciences University of Illinois at Urbana-Champaign Champaign Illinois USA

来源：评论

学校读者我要写书评

暂无评论

Virtual Network Embedding: Literature Assessment, Recent Advancements, Opportunities, and Challenges

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Satpathy, Anurag Sahoo, Manmath Narayan Swain, Chittaranjan Bellavista, Paolo Guizani, Mohsen Muhammad, Khan Bakshi, Sambit Missouri University of Science and Technology Department of Computer Science RollaMO United States National Institute of Technology Visual Surveillance Laboratory Department of Computer Science and Engineering Odisha Rourkela769008 India Atal Bihari Vajpayee Indian Institute of Information Technology and Management Department of Computer Science and Engineering Gwalior India Department of Computer Science and Engineering Italy Machine Learning Department Abu Dhabi United Arab Emirates Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Seoul03063 Korea Republic of

Network virtualization (NV) allows service providers (SPs) to instantiate logically isolated entities called virtual networks (VNs) on top of a substrate network (SN). Though VNs bring about multiple benefits, particularly in terms of economic costs and elasticity, they also force various technical challenges to be addressed. The primary one is the issue of optimally allocating resources to VNs, also termed virtual network embedding (VNE). This paper presents an exhaustive survey of VNE by extensively covering the state-of-the-art research field in this very active field and focusing on the emerging research trends in industry and academia over the last decade. In addition, this survey originally contributes to the literature by proposing a novel taxonomy for existing VNE solutions and providing a thorough comparative study of their strategies. © 1998-2012 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enhanced Energy-Efficient Architectures for Sustainable Internet of Things Ecosystems 1st

Blockchain-Enhanced Energy-Efficient Architectures for Susta...

引用

1st International Conference on Advanced Network Technologies and Computational Intelligence, ICANTCI 2024

作者： Goyal, S.B. Rajawat, Anand Singh Verma, Chaman Illés, Zoltán Singh, Jaiteg Faculty of Information Technology City University Petaling Jaya46100 Malaysia School of Computer Sciences and Engineering Sandeep University Nashik India Department of Media and Educational Informatics Faculty of Informatics Eötvös Loránd University Budapest Hungary Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

ISBN: (纸本)9783031860683

Novel technique are required to ensure the long-term viability and maximize the efficiency of energy consumption in the constantly changing Internet of Things (IoT) landscape. In order to accomplish these objectives, this study examines the potential use of blockchain technology into IoT architectural concepts. Our approach utilizes blockchain technology to effectively manage and enhance energy consumption in IoT devices and networks. This is achieved by capitalizing on the decentralized, secure, and transparent characteristics of blockchain. Our objective is to do this by developing a decentralized ledger system that documents all energy transactions and interactions inside an Internet of Things (IoT) environment. This strategy utilizes blockchain technology to provide accountability and real-time monitoring of energy consumption, hence facilitating improved energy allocation and consumption. We delve into the concept and execution of smart contracts that ensure transactions and automate energy-conservation procedures, thereby diminishing the necessity for centralized authority and alleviating energy wastage. In addition, we examine the possibility of blockchain technology to enable direct energy transfer between Internet of Things (IoT) devices. This feature facilitates the development of a self-sustaining Internet of Things ecosystem by enabling devices with surplus energy to vend it to those requiring it. We also tackle the difficulties associated with the integration of blockchain with IoT, such as the energy consumption resulting from blockchain activities and the ability to effectively handle large volumes of data. Furthermore, we offer resolutions to these problems. The proposed framework improves the energy efficiency of IoT ecosystems and promotes their sustainability by advocating for the use of renewable energy sources and decreasing carbon footprints. Through the utilization of simulations and real-world illustrations, we showcase the efficacy of our bl

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Impact of Data Cleaning for Improving Road Damage Detection Through Vision Transformer

Evaluating the Impact of Data Cleaning for Improving Road Da...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Andy Desman Kahlil Muchtar Maulisa Oktiana Maya Fitria Yuwaldi Away Fardian Fardian Hammam Riza Dept. of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Dept. of Electrical and Computer Engineering Department of Informatics Universitas Syiah Kuala The Master Program in Artificial Intelligence Universitas Syiah Kuala (USK) Banda Aceh Indonesia Department of Informatics BRIN (National Research and Innovation Agency) Indonesia The Master Program in Artificial Intelligence Universitas Syiah Kuala Banda Aceh Indonesia

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The WHO predicts that by 2030 road accidents will be the 5th leading cause of death. Globally, road accidents account for 1.25 million casualties each year, and road defects cause 34% of these casualties. The road survey process in many countries have several challenges, one of which is detection using cameras that do not have a recognition system. In this study, a model with YOLOS architecture based on Vision Transformer trained on the RDD2022 dataset successfully recognizes road damage well, as indicated by the number of objects detected, bounding box on accurate objects, and the ability to recognize objects with inconsistent shadow and light inference. This research uses assessment parameters such as Average Precision (AP) and Average Recall (AR) to determine the overall performance of the model. The model achieves the highest AP value at Intersection of Union (IoU) 0.5, 0.75, and 0.5-0.95, worth 62.1%, 37.1%, and 36.2% respectively, and the highest AR value in Large, Medium, and Small Areas, worth 42.1%, 60.3%, and 75.4% respectively. The supplementary material can be found through this link: https://***/watch?v=LzkI2e_IORE.

关键词： YOLO Surveys computer vision Road accidents Roads Manuals Transformers Cameras Cleaning Tuning

来源：评论

学校读者我要写书评

暂无评论

Polychromatic Coloring of Tuples in Hypergraphs

arXiv

引用

arXiv 2025年

作者： Biniaz, Ahmad De Carufel, Jean-Lou Maheshwari, Anil Smid, Michiel Smorodinsky, Shakhar Stojaković, Miloš School of Computer Science University of Windsor Canada School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada School of Computer Science Carleton University Ottawa Canada Department of Computer Science Ben-Gurion University of the Negev Be’er Sheva Israel Department of Mathematics and Informatics University of Novi Sad Novi Sad Serbia

A hypergraph H consists of a set V of vertices and a set E of hyperedges that are subsets of V . A t-tuple of H is a subset of t vertices of V . A t-tuple k-coloring of H is a mapping of its t-tuples into k colors. A coloring is called (t, k, f)-polychromatic if each hyperedge of E that has at least f vertices contains tuples of all the k colors. Let fH(t, k) be the minimum f such that H has a (t, k, f)-polychromatic coloring. For a family of hypergraphs H let fH(t, k) be the maximum fH(t, k) over all hypergraphs H in H. Determining fH(t, k) has been an active research direction in recent years. This is challenging even for t = 1. We present several new results in this direction for t ≥ 2. • Let H be the family of hypergraphs H that is obtained by taking any set P of points in 2, setting V := P and E := {d ∩ P : d is a disk in R2}. We prove that fH(2, k) ≤ 3.7k, that is, the pairs of points (2-tuples) can be k-colored such that any disk containing at least 3.7k points has pairs of all colors. We generalize this result to points and balls in higher dimensions. • For the family H of hypergraphs that are defined by grid vertices and axis-parallel rectangles in the plane, we show that fH(2, k) ≤ √ck ln k for some constant c. We then generalize this to higher dimensions, to other shapes, and to tuples of larger size. • For the family H of shrinkable hypergraphs of VC-dimension at most d we prove that fH(d+1, k) ≤ ck for some constant c = c(d). Towards this bound, we obtain a result of independent interest: Every hypergraph with n vertices and with VC-dimension at most d has a (d+1)-tuple T of depth at least n/c , i.e., any hyperedge that contains T also contains nc other vertices. We also present analogous bounds for coloring pairs of points with respect to pseudo-disks in the plane. • For the relationship between t-tuple coloring and vertex coloring in any hypergraph H we establish the inequality 1/e · tk1/t ≤ fH(t, k) ≤ fH(1, tk1/t ). For the special case of k = 2, ref

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Pose Estimation of Spacecraft Using Dual Transformers and Efficient Bayesian Hyperparameter Optimization

引用

International Journal of Advanced computer Science and Applications 2025年第4期16卷 629-644页

作者： Raja, N. Kannaiya Ramesh, Janjhyam Venkata Naga El-Ebiary, Yousef A. Baker Muniyandy, Elangovan Reddy, N. Konda Kumar, Vanipenta Ravi Devarasetty, Prasad School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh Bhopal466114 India Department of CSE Graphic Era Hill University Dehradun248002 India Department of CSE Graphic Era Deemed To Be University Uttarakhand Dehradun248002 India Faculty of Informatics and Computing UniSZA University Malaysia Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602 105 India Applied Science Research Center Applied Science Private University Amman Jordan Department of Engineering Mathematics K L University Greenfields Guntur Dist Andhra Pradesh Vaddeswaram522302 India Department of Mathematics Annamacharya University New Boyanapalli Rajampet India Department of Computer Science and Engineering DVR & Dr HS MIC College of Technology Andhra Pradesh Kanchikacherla India

Spacecraft pose estimation is an essential contribution to facilitating central space mission activities like autonomous navigation, rendezvous, docking, and on-orbit servicing. Nonetheless, methods like Convolutional Neural Networks (CNNs), Simultaneous Localization and Mapping (SLAM), and Particle Filtering suffer significant drawbacks when implemented in space. Such techniques tend to have high computational complexity, low domain generalization capacity for varied or unknown conditions (domain generalization problem), and accuracy loss with noise from the space environment causes such as fluctuating lighting, sensor limitations, and background interference. In order to overcome these challenges, this study suggests a new solution through the combination of a Dual-Channel Transformer Network with Bayesian Optimization methods. The innovation is at the center with the utilization of EfficientNet, augmented with squeeze-and-excitation attention modules, to extract feature-rich representations without sacrificing computational efficiency. The dual-channel architecture dissects satellite pose estimation into two dedicated streams—translational data prediction and orientation estimation via quaternion-based activation functions for rotational precision. Activation maps are transformed into transformer-compatible sequences via 1×1 convolutions, allowing successful learning in the transformer's encoder-decoder system. To maximize model performance, Bayesian Optimization with Gaussian Process Regression and the Upper Confidence Bound (UCB) acquisition function makes the optimal hyperparameter selection with fewer queries, conserving time and resources. This entire framework, used here in Python and verified with the SLAB Satellite Pose Estimation Challenge dataset, had an outstanding Mean IOU of 0.9610, reflecting higher accuracy compared to standard models. In total, this research sets a new standard for spacecraft pose estimation, by marrying the versatility of deep le

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks

arXiv

引用

arXiv 2025年

作者： Oliynyk, Daryna Mayer, Rudolf Rauber, Andreas CDL AsTra Faculty of Computer Science University of Vienna Vienna Austria SBA Research Vienna Austria Institute of Information Systems Engineering Faculty of Informatics TU Wien Vienna Austria

Machine learning (ML) models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other attack methods, substitute model training is an all-encompassing attack applicable to any machine learning model whose behaviour can be approximated from input-output queries. Whereas previous works mainly focused on improving the performance of substitute models by, e.g. developing a new substitute training method, there have been only limited ablation studies that try to understand the impact the strength of an attacker has on the substitute model’s performance. As a result, different authors came to diverse, sometimes contradicting, conclusions. In this work, we exhaustively examine the ambivalent influence of different factors resulting from varying the attacker’s capabilities and knowledge on a substitute training attack. Our findings suggest that some of the factors that have been considered important in the past are, in fact, not that influential;instead, we discover new correlations between attack conditions and success rate. In particular, we demonstrate that better-performing target models enable higher-fidelity attacks and explain the intuition behind this phenomenon. Further, we propose to shift the focus from the complexity of target models toward the complexity of their learning tasks. Therefore, for the substitute model, rather than aiming for a higher architecture complexity, we suggest focusing on getting data of higher complexity and an appropriate architecture. Finally, we demonstrate that even in the most limited data-free scenario, there is no need to overcompensate weak knowledge with unrealistic capabilities in the form of millions of queries. Our results often exceed or match the performance of previous attacks that assume a stronger attacker, suggesting that these stronger attacks are likely endangering a model owner’s intellectual property to a significantly higher degree than shown until now. Cop

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

On the Rate-Exponent Region of Integrated Sensing and Communications With Variable-Length Coding

arXiv

引用

arXiv 2025年

作者： Papoutsidakis, Ioannis Alexandropoulos, George C. Department of Informatics and Telecommunications National and Kapodistrian University of Athens Panepistimiopolis Ilissia Athens15784 Greece Department of Electrical and Computer Engineering University of Illinois ChicagoIL60601 United States

This paper considers the achievable rate-exponent region of integrated sensing and communication systems in the presence of variable-length coding with feedback. This scheme is fundamentally different from earlier studies, as the coding methods that utilize feedback impose different constraints on the codewords. The focus herein is specifically on the Gaussian channel, where three achievable regions are analytically derived and numerically evaluated. In contrast to a setting without feedback, we show that a trade-off exists between the operations of sensing and communications. Copyright © 2025, The Authors. All rights reserved.

关键词： Codes (symbols)

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：