检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Wang, Huafeng Zhang, Haodu Liu, Wanquan Hu, Zhimin Gao, Haoqi Lv, Weifeng Gu, Xianfeng School of Information Technology North China University of Technology Beijing100122 China School of Software Beihang University Beijing100191 China School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou510335 China University of Wisconsin Madison United States Department of Computer Science Stony Brook University NY11794-2424 United States

Integrating heterogeneous information in multimodal tasks presents challenges in effectively leveraging complementary information. This is particularly evident in the context of 6D pose estimation, where the effective utilization of RGB-D data is crucial for extracting supplementary information that complements 2D and 3D data. Another challenge is aligning modalities implicitly to obtain robust estimation results. To tackle these challenges, we propose a Transformer-based fusion module that facilitates hierarchical fusion across modalities at different stages. This approach effectively combines disparate features and complements global information in a non-convolutional manner. Additionally, we employ an attentional residual structure to address two primary challenges. Firstly, it mitigates information loss that may occur due to the stacking depth of layers. Secondly, it leverages attention weights to adapt the output of the preceding layer, thereby enhancing modal alignment. We validate our approach on two benchmark datasets: LineMOD [1] and YCB-Video [2]. Our method outperforms most existing methods on the LineMOD dataset and achieves state-of-the-art results on the YCB-Video dataset, showcasing its superior generalization ability. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data distribution aware clustering for parallel split learning in healthcare applications

引用

Future Generation computer systems 2025年

作者： Md. Tanvir Arafat Md. Abdur Razzaque Abdulhamed Alelaiwi Md. Zia Uddin Mohammad Mehedi Hassan Department of Computer Science and Engineering University of Dhaka Dhaka Bangladesh Department of Software Engineering King Saud University Riyadh Saudi Arabia SINTEF Digital Oslo Norway Department of Information Systems King Saud University Riyadh Saudi Arabia

Split learning, a promising approach in privacy-preserving machine learning, decentralizes model training by dividing it among client devices and a central server. However, split learning has exhibited a certain level of slowness in its vanilla approach, mainly due to the serial processing of devices. Recent research endeavours have addressed this challenge by introducing parallelism and thus accelerating the split learning process. However, the existing split learning methodologies often overlook the critical aspect of data distribution among client devices. This paper introduces a Data Distribution Aware Clustering-based Parallel Split Learning (DCSL), a scheme purposefully crafted to address the complexities stemming from non-identically and non-independently distributed (non-IID) data among client devices engaged in the split learning paradigm. In healthcare applications, comprehending the intricacies of data distribution is imperative, particularly given the non-IID nature of medical datasets, to ensure accurate analysis and decision-making. The DCSL leverages a novel clustering technique to create clusters of medical client devices, considering the data distributions of their local datasets, and employs parallel model training within the device clusters. It enhances model convergence and reduces training latency by optimizing the cluster formation. Extensive experiments demonstrate that DCSL outperforms traditional split learning approaches, significantly improving accuracy and reducing training latency across various applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Distributionally Robust Control for Interacting Agents under Logical Constraints

arXiv

引用

arXiv 2025年

作者： Kordabad, Arash Bahari Vlahakis, Eleftherios E. Lindemann, Lars Gros, Sebastien Dimarogonas, Dimos V. Soudjani, Sadegh The Max Planck Institute for Software Systems Kaiserslautern Germany The Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden The Thomas Lord Department of Computer Science the Ming Hsieh Department of Electrical and Computer Engineering Viterbi School of Engineering University of Southern California Los Angeles United States Trondheim Norway

In this paper, we propose a distributionally robust control synthesis for an agent with stochastic dynamics that interacts with other agents under uncertainties and constraints expressed by signal temporal logic (STL). We formulate the control synthesis as a chance-constrained program (CCP) with STL specifications that must be satisfied with high probability under all uncertainty tubes induced by the other agents. To tackle the CCP, we propose two methods based on concentration of measure (CoM) theory and conditional value at risk (CVaR) and compare the required assumptions and resulting optimizations. These approaches convert the CCP into an expectation-constrained program (ECP), which is simpler to solve than the original CCP. To estimate the expectation using a finite set of observed data, we adopt a distributionally robust optimization (DRO) approach. The underlying DRO can be approximated as a robust data-driven optimization that provides a probabilistic under-approximation to the original ECP, where the probability depends on the number of samples. Therefore, under feasibility, the original STL constraints are satisfied with two layers of designed confidence: the confidence of the chance constraint and the confidence of the approximated data-driven optimization, which depends on the number of samples. We then provide details on solving the resulting robust data-driven optimization numerically. Finally, we compare the two proposed approaches through case studies. Copyright © 2025, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

来源：评论

学校读者我要写书评

暂无评论

Unified resilience model using deep learning for assessing power system performance

引用

Heliyon 2025年第4期11卷 e42802页

作者： Artemchuk, Volodymyr Garbuz, Iurii Jamil Alsayaydeh, Jamil Abedalrahim Shkarupylo, Vadym Oliinyk, Andrii Bin Yusof, Mohd Faizal Herawan, Safarudin Gazali Department of Mathematical and Econometric Modelling G.E. Pukhov Institute for Modelling in Energy Engineering of the NAS of Ukraine Kyiv Ukraine Department of Environmental Protection Technologies and Radiation Safety Center for Information-analytical and Technical Support of Nuclear Power Facilities Monitoring of the NAS of Ukraine Kyiv Ukraine Department of Іnformation Systems in Economics Kyiv National Economic University Named After Vadym Hetman Kyiv Ukraine Department of Computerized Control System National Aviation University Kyiv Ukraine Department of Engineering Technology Fakulti Teknologi Dan Kejuruteraan Elektronik Dan Komputer (FTKEK) Universiti Teknikal Malaysia Melaka (UTeM) Melaka 76100 Malaysia Department of Computer Systems Networks and Cybersecurity of the National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine Department of Software Tools Faculty of Computer Science and Technology Zaporizhzhia Polytechnic National University Zaporizhzhia Ukraine Research Section Faculty of Resilience Rabdan Academy Abu Dhabi United Arab Emirates Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta 11480 Indonesia

Energy resilience in renewable energy sources dissemination components such as batteries and inverters is crucial for achieving high operational fidelity. Resilience factors play a vital role in determining the performance of power systems, regardless of their operating environment and interruptions. This article introduces a Unified Resilience Model (URM) using Deep Learning (DL) to enhance power system performance. The proposed model analyzes environmental factors impacting the resilience of batteries and energy storage devices. This deep learning approach trains performance-impacting factors using previously known low resilience drain data. The learning output is utilized to augment various strengthening factors, thereby improving resilience. Drain mitigation and performance improvements are combined for direct impact verification. This process validates the model's fidelity in enhancing power system performance, with a specific focus on the impact of weather factors. © 2025 The Authors

关键词： Deep learning Energy resilience Fidelity Weather impact

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Energy-Aware Offloading in Edge-Cloud Vehicular Networks 18

Machine Learning-based Energy-Aware Offloading in Edge-Cloud...

引用

18th International Conference on Mobile systems and Pervasive Computing, MobiSPC 2021, The 16th International Conference on Future Networks and Communications, FNC 2021 and the 11th International Conference on Sustainable Energy Information Technology, SEIT 2021

作者： Ismail, Leila Materwala, Huned Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates National Water and Energy Center United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates

A vehicular network underpinned by the 3-tier vehicle-edge-cloud infrastructure enables an efficient and safer travel experience. The compute-intensive vehicular applications are often offloaded to the edge and/or cloud servers to enhance the applications' Quality of Services (QoS). The underlying edge-cloud servers consume a high among of energy. Consequently, it becomes crucial to optimizing energy consumption in the offloading process. Current energy-efficient offloading strategies in 2-tier vehicle-edge infrastructure, do not account for cloud computing energy consumption. In this paper, we address this void by proposing a machine learning-based energy-aware offloading algorithm, which optimizes the energy of the edge-cloud computing platform. The offloading strategy is enabled by the Support Vector Machine (SVM) regression model machine learning algorithm used for the edge-cloud power prediction. The experimental results show that the proposed algorithm is a promising approach in energy savings. © 2021 Elsevier B.V.. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Based Approach to Identify Resource Bottlenecks for Multiple Services Interactions in Cloud Computing Environments 16th

A Reinforcement Learning Based Approach to Identify Resource...

引用

16th EAI International Conference on Collaborative Computing: Networking, Applications, and Worksharing, CollaborateCom 2020

作者： Xu, Lingxiao Xu, Minxian Semmes, Richard Li, Hui Mu, Hong Gui, Shuangquan Tian, Wenhong Wu, Kui Buyya, Rajkumar School of Software and Information Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Co. Ltd. Chengdu China Department of Computer Science University of Victoria Victoria Canada CLOUDS Lab School of Computing and Information Systems University of Melbourne Melbourne Australia

ISBN: (纸本)9783030675394

Cloud service providers are provisioning resources including a variety of virtual machine instances to support customers that migrate their services to the cloud. From the customers’ perspective, selecting the appropriate amount of resources is tightly coupled with performance and cost. By identifying the potential resource bottlenecks in the early stage of the service deployment process, resource planning can be significantly optimized. However, due to the unpredictable workloads and heterogeneous resources, it is difficult to identify resource bottlenecks that can degrade system performance. To support system non-functional requirements (NFR) in a better manner, we propose a reinforcement learning based approach to support the NFR management of system concerning the multiple services interactions scenario by identifying the potential resource bottleneck and optimizing the demanded resources. The proposed approach can predict the resource bottleneck for multiple services interactions, e.g. bottleneck in CPU or overloads in specific service, and provide guidance for resource planning. We modeled and simulated the proposed approach using an extended version of the CloudSim toolkit. Comprehensive evaluations with realistic use case from Siemens Digital Industries software’s MindSphere Solution on AliCloud show that our proposed approach can achieve high accuracy in terms of performance metrics, such as response time, queries per second (QPS), and resource usage. © 2021, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Domain adaptive person re-identification via homogeneous hierarchical progressive adaptation and multi-view consistency

引用

Advanced engineering Informatics 2025年 67卷

作者： Wang, Zhengyang Ye, Xiufen Shang, Xue Guo, Shuxiang College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150001 China Department of Electrical Computer and Software Engineering University of Auckland Auckland1142 New Zealand Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China

Domain adaptive person re-identification (Re-ID) encounters significant challenges when models trained on one dataset are deployed in new environments. It is particularly critical in engineering applications where surveillance infrastructure must be rapidly adapted to new environments without compromising security system reliability. The problem represents a knowledge-intensive engineering task that requires sophisticated knowledge representation and transfer mechanisms to support automated system reconfiguration decisions. These challenges include preserving fine-grained visual details, handling camera-specific variations, generating reliable pseudo-labels, maintaining consistency across multiple camera views, and managing varying difficulty levels in domain transfer. To address these issues, we propose a novel framework that separates adaptation into intra-domain and cross-domain learning phases. Our approach introduces several key innovations: an adaptive fine-grained network that preserves spatial details while ensuring domain invariance, a memory-guided learning method for stable feature representation, and a hierarchical adaptation strategy for reliable intra-domain learning. Additionally, we incorporate a progressive learning strategy for gradual domain adaptation and a consistency reinforcement mechanism to resolve cross-camera identity conflicts. Experiments on the Market-1501, DukeMTMC-reID, and MSMT17 datasets across four domain adaptation tasks show that our method outperforms state-of-the-art approaches, significantly improving both mAP and CMC accuracy. This work contributes to engineering informatics by providing a reliable solution for automating knowledge-intensive tasks across diverse engineering domains, while also laying the foundation for advancements in intelligent surveillance systems and automated decision-making in engineering infrastructures. © 2025 Elsevier Ltd

关键词： Automatic identification

来源：评论

学校读者我要写书评

暂无评论

Level of Trust and Privacy Management in 6G Intent-based Networks for Vertical Scenarios

Level of Trust and Privacy Management in 6G Intent-based Net...

引用

6G Networking (6GNet), International Conference on

作者： Jesú s A. Alonso-Lupez Luis Alberto Martí nez Herná ndez Sandra Pé rez Arteaga Ana Lucila Sandoval Orozco Luis Javier Garcí a Villalba Antonio Pastor Diego Ló pez Garcí a Department of Software Engineering and Artificial Intelligence (DISIA) Faculty of Computer Science and Engineering Office 431 Group of Analysis Security and Systems (GASS) Universidad Complutense de Madrid (UCM) Madrid Spain CTIO Unit Telef&#x00F3 nica I+D Ronda de la Comunicacion S/N Madrid Spain

Security is one of the main concerns when designing future 6G networks. Most of the components of service chains are software-based and their security must be ensured. In this work we propose a system that will check the level of trust of 6G services following 3 complementary approaches: attestation, generation of proofs of transit and usage of smart contracts whose execution will be published via Distributed Ledger Technology in order to enable their traceability. The service orchestration function will use reinforcement learning to formulate optimised service orchestration decisions. Services will be specified in a declarative model, following a privacy-aware flavour of intent-based networking. The proposed architecture will take into account privacy of every stakeholder: final users, service providers and infrastructure providers.

关键词： 6G mobile communication Privacy Distributed ledger Network topology Smart contracts Reinforcement learning Service-oriented architecture

来源：评论

学校读者我要写书评

暂无评论

Discovering Spatio-Temporal Patterns in Precision Agriculture Based on Triclustering 15th

Discovering Spatio-Temporal Patterns in Precision Agricultur...

引用

15th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2020

作者： Melgar-García, Laura Godinho, Maria Teresa Espada, Rita Gutiérrez-Avilés, David Brito, Isabel Sofia Martínez-Álvarez, Francisco Troncoso, Alicia Rubio-Escudero, Cristina Data Science & Big Data Lab Pablo de Olavide University Seville41013 Spain Department of Mathematical and Physical Sciences Polytechnic Institute of Beja Beja Portugal Center for Mathematics Fundamental Applications and Operations Research University of Lisboa Lisbon Portugal Associação dos Agricultores do Baixo Alentejo Beja Portugal Department of Engineering Polytechnic Institute of Beja Beja Portugal Instituto de Desenvolvimiento de Novas Tecnologias - Centre of Technology and Systems Lisbon Portugal Department of Computer Languages and Systems University of Seville Seville Spain

ISBN: (纸本)9783030578015

Agriculture has undergone some very important changes over the last few decades. The emergence and evolution of precision agriculture has allowed to move from the uniform site management to the site-specific management, with both economic and environmental advantages. However, to be implemented effectively, site-specific management requires within-field spatial variability to be well-known and characterized. In this paper, an algorithm that delineates within-field management zones in a maize plantation is introduced. The algorithm, based on triclustering, mines clusters from temporal remote sensing data. Data from maize crops in Alentejo, Portugal, have been used to assess the suitability of applying triclustering to discover patterns over time, that may eventually help farmers to improve their harvests. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Precision agriculture

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：