检索结果-内蒙古大学图书馆

IEEE International Symposium on Multimedia

作者： Michael G. Adam Sebastian Eger Martin Piccolrovazzi Maged Iskandar Joern Vogel Alexander Dietrich Seongjien Bien Jon Skerlj Abdeldjallil Naceri Eckehard Steinbach Alin Albu-Schaeffer Sami Haddadin Wolfram Burgard Department of Computer Engineering School of Computation Information and Technology Chair of Media Technology Technical University of Munich Munich Germany Institute of Robotics and Mechatronics German Aerospace Center (DLR) Wessling Germany Department of Computer Engineering School of Computation Information and Technology Technical University of Munich Chair of Robotics and Systems Intelligence Munich Institute of Robotics and Machine Intelligence (MIRMI) Munich Germany Engineering Department University of Technology Nuremberg Nuremberg Germany

As labor shortage increases in the health sector, the demand for assistive robotics grows. However, the needed test data to develop those robots is scarce, especially for the application of active 3D object detection, where no real data exists at all. This short paper counters this by introducing such an annotated dataset of real environments. The captured environments represent areas which are already in use in the field of robotic health care research. We further provide ground truth data within one room, for assessing SLAM algorithms running directly on a health care robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence's Effects on Corporate Decision-Making Processes 6

Artificial Intelligence's Effects on Corporate Decision-Maki...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Kumari, Neeraj Gangwar, Kalpana Gaur, Vibhor Singh, K. Ranjith Antran Vijay, S. Arul Tamkhade, Jayashree CCSIT Teerthankar Mahaveer University Moradabad India Invertis University Department of Computer Applications Bareilly India School of Media Film & Television Studies IIMT University Meerut India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Karpagam College of Engineering Department of Computer Science Engineering Coimbatore India Vishwakarma Institute of Information Technology E & TC Department Pune India

ISBN: (纸本)9798350304480

With the introduction of artificial intellectual ability life choice machine learning, how has decision-changed? The predictability of the judgement state space, communication resources of the life choice procedure and result, size of the unconventional set, life choice rate, and representativeness are five key plans in place factors in this blog entry as the peculiarities of human and Machine learning strategic planning. The paper develops a novel paradigm describing why both modalities of judgement may be merged to best benefit the level of company judgement call upon an examination of individual and Digital taking decisions or something along those parameters. Three major categories-full human to AI outsourcing, mixed mortal and Cognitive technologies sequence strategic planning, and merged decision-making between humans and AI- are presented by the structure as ways in which party members'choices can be coupled with AI-based judgments. © 2023 IEEE.

关键词： Aggregated decision-making Alternative set size Artificial intelligence Computational planners corporate decision-making Decision search space Decision-making processes Decision-making speed Delegation Human-AI interaction Hybrid sequential decision-making Interpretability Judgement call Machine learning Replicability

来源：评论

学校读者我要写书评

暂无评论

Average Communication Rate for Networked Event-Triggered Stochastic Control Systems

引用

IEEE Transactions on Control of Network Systems 2025年

作者： Zhang, Zengjie Liu, Qingchen Mamduhi, Mohammad H. Hirche, Sandra Eindhoven University of Technology Department of Electrical Engineering Netherlands University of Science and Technology of China Department of Automation Hefei China University of Birmingham School of Computer Science United Kingdom Technical University of Munich Chair of Information-Oriented Control Munich Germany

Quantifying the average communication rate (ACR) of a networked event-triggered stochastic control system (NET-SCS) with deterministic thresholds is challenging due to the non-stationary nature of the system's stochastic processes. For a NET-SCS, the propagation of nonlinear statistics of the network communication status brought up by deterministic thresholds makes the precise computation of ACR difficult. Previous work used to over-simplify the computation using a Gaussian distribution without incorporating this nonlinearity, leading to sacrificed precision. This paper proposes a novel approach to calculate the exact ACR for a NET-SCS using a recursive model. We use theoretical analysis and a numerical study to qualitatively evaluate the deviation gap of the conventional approach that ignores the side information. The accuracy of our proposed method, alongside its comparison with the simplified results of the conventional approach, is validated by experimental studies. Our work is promising to benefit the efficient resource planning of networked control systems with limited communication resources by providing accurate ACR computation. © 2025 IEEE.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Imitation Behaviors of Gorilla Chest-Beating Based on Human Pose Estimation

Analyzing the Imitation Behaviors of Gorilla Chest-Beating B...

引用

Cyber Science and technology Congress (CyberSciTech), IEEE

作者： Yu Qi Siyu Xiong Chongyang Zhang Bo Wu Graduate School of Bionics Computer and Media Sciences Tokyo University of Technology Tokyo Japan Department of Information Engineering Hebei Institute of Mechanical and Electrical Technology Xingtai China School of Computer Science Tokyo University of Technology Tokyo Japan

ISBN: (数字)9798331532093

ISBN: (纸本)9798331532109

In animal exercise classes course for acting majors, students enhance their physical flexibility and expressiveness by imitating the behaviors and actions of various animals. The gorilla's chest-beating action is a common exercise in this course. The accuracy of students' body postures when imitating animals often depends on the instructor's experience and personal preferences, leading to students with different levels and physical characteristics not receiving targeted guidance and practice. Human pose estimation technology is already quite mature, and we hope to apply it to animal exercise courses to analyze students' body movements when imitating animals, such as chest-beating. Therefore, this paper utilizes mediapipe technology to detect the elbow joint angles of students imitating the gorilla's chest-beating action, a two-way analysis of variance (ANOVA) was employed to examine the effects of experience and gender on joint angle variations. Additionally, the results of the U-test analyzing the differences between the gorilla and the participants confirmed that male students' elbow joint angles are closer to those of the gorilla than those of female students when mimicking the gorilla's chest-beating action. This has significant implications for improving the precision and personalization of performance training, and it also provides valuable insights for further research and practice in related fields.

关键词： Training Accuracy Animals Pose estimation Standardization Behavioral sciences Elbow Analysis of variance

来源：评论

学校读者我要写书评

暂无评论

IPFS: An Off-Chain Storage Solution for Blockchain 5th

IPFS: An Off-Chain Storage Solution for Blockchain

引用

5th International Conference on Recent Innovations in Computing, ICRIC 2022

作者： Kaur, Manpreet Gupta, Shikha Kumar, Deepak Raboaca, Maria Simona Goyal, S.B. Verma, Chaman Department of Computer Science and Engineering Chandigarh University Mohali India Department of Computer Science and Engineering Guru Nanak Dev Engineering College Ludhiana India Apex Institute of Technology Chandigarh University Mohali India National Research and Development Institute for Cryogenic and Isotopic Technologies-ICSI Râmnicu Vâlcea Romania Faculty of Information Technology City University London Malaysia Department of Media and Educational Informatics Eötvös Loránd University Budapest Hungary

ISBN: (纸本)9789811998751

Due to intrinsic properties such as transparency, immutability, decentralization, and cryptographic security, blockchain has emerged as a revolutionary technology. Despite its widespread application, blockchain is not used to store huge data due to the restricted storage capacity offered by each block. Furthermore, because the data contained in a block must be duplicated on many other nodes on the network, storage space is wasted. Off-chain storage is therefore required to store significant volumes of data while preserving the efficiency and performance of the network. Additionally, off-chain solutions such as Inter-Planetary File System (IPFS) would reduce the cost requirements of blockchain nodes as data stored and processed by these nodes would be reduced. Hence, strong decentralized storage is provided by IPFS that is a P2P-based content-addressed file sharing system that uses cryptographic hashes to store data. As a result, by combining blockchain with IPFS, an efficient file sharing system would be created. This paper presents a comprehensive IPFS architecture, a simplified version of this integrated approach, and potential applications that might assist to maximize the worth of both systems. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Learning-based Control for PMSM Using Distributed Gaussian Processes with Optimal Aggregation Strategy 49

Learning-based Control for PMSM Using Distributed Gaussian P...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Yin, Zhenxiao Dai, Xiaobing Yang, Zewen Shen, Yang Hattab, Georges Zhao, Hang Robotics and Autonomous Systems Thrust Guangzhou China Technical University of Munich Chair of Information-oriented Control Munich Germany Berlin Germany Freie Universität Berlin Department of Mathematics and Computer Science Berlin Germany The Hong Kong University of Science and Technology Department of Electronic & Computer Engineering Hong Kong

ISBN: (纸本)9798350331820

The growing demand for accurate control in varying and unknown environments has sparked a corresponding increase in the requirements for power supply components, including permanent magnet synchronous motors (PMSMs). To infer the unknown part of the system, machine learning techniques are widely employed, especially Gaussian process regression (GPR) due to its flexibility of continuous system modeling and its guaranteed performance. For practical implementation, distributed GPR is adopted to alleviate the high computational complexity. However, the study of distributed GPR from a control perspective remains an open problem. In this paper, a control-aware optimal aggregation strategy of distributed GPR for PMSMs is proposed based on the Lyapunov stability theory. This strategy exclusively leverages the posterior mean, thereby obviating the need for computationally intensive calculations associated with posterior variance in alternative approaches. Moreover, the straightforward calculation process of our proposed strategy lends itself to seamless implementation in high-frequency PMSM control. The effectiveness of the proposed strategy is demonstrated in the simulations. © 2023 IEEE.

关键词： Synchronous motors

来源：评论

学校读者我要写书评

暂无评论

Task Offloading in Fog Computing with Deep Reinforcement Learning: Future Research Directions Based on Security and Efficiency Enhancements

arXiv

引用

arXiv 2024年

作者： Pakmehr, Amir Department of Computer and Information Technology Engineering Qazvin Branch Islamic Azad University Qazvin Iran Department of Electrical Engineering Media and Computer Science Ostbayerische Technische Hochschule Amberg-Weiden Amberg Germany

The surge in Internet of Things (IoT) devices and data generation highlights the limitations of traditional cloud computing in meeting demands for immediacy, Quality of Service, and location-aware services. Fog computing emerges as a solution, bringing computation, storage, and networking closer to data sources. This study explores the role of Deep Reinforcement Learning in enhancing fog computing's task offloading, aiming for operational efficiency and robust security. By reviewing current strategies and proposing future research directions, the paper shows the potential of Deep Reinforcement Learning in optimizing resource use, speeding up responses, and securing against vulnerabilities. It suggests advancing Deep Reinforcement Learning for fog computing, exploring blockchain for better security, and seeking energy-efficient models to improve the Internet of Things ecosystem. Incorporating artificial intelligence, Our results indicate potential improvements in key metrics, such as task completion time, energy consumption, and security incident reduction. These findings provide a concrete foundation for future research and practical applications in optimizing fog computing architectures. © 2024, CC BY-NC-ND.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SELECTION GUIDELINES FOR GEOGRAPHICAL SMR PROTOCOLS: A COMMUNICATION PATTERN-BASED LATENCY MODELING APPROACH

arXiv

引用

arXiv 2024年

作者： Shiozaki, Kohya Nakamura, Junya Department of Computer Science and Engineering Toyohashi University of Technology Aichi Toyohashi441-8580 Japan Information and Media Center Toyohashi University of Technology Aichi Toyohashi441-8580 Japan

State machine replication (SMR) is a replication technique that ensures fault tolerance by duplicating a service. Geographical SMR can enhance its robustness against disasters by distributing replicas in separate geographical locations. Several geographical SMR protocols have been proposed in the literature, each of which tailored to specific requirements;for example, protocols designed to meet the requirement of latency reduction by either sacrificing a part of their fault tolerance or limiting the content of responses to clients. However, this diversity complicates the decision-making process for selecting the best protocol for a particular service. In this study, we introduce a latency estimation model for these SMR protocols based on the communication patterns of the protocols and perform simulations for various cases. Based on the simulation results and an experimental evaluation, we present five selection guidelines for geographical SMR protocols based on their log management policy, distances between replicas, number of replicas, frequency of slow paths, and client distribution. These selection guidelines enable determining the best geographical SMR protocol for each situation. Copyright © 2024, The Authors. All rights reserved.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

ClipArtGAN: An Application of Pix2Pix Generative Adversarial Network for Clip Art Generation

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Elnabawy, Reham H. Abdennadher, Slim Hellwich, Olaf Eldawlatly, Seif Technische Universität Berlin Berlin Germany Computer Science and Engineering Department Faculty of Media Engineering and Technology German University in Cairo Cairo Egypt Computer Science Department Faculty of Informatics and Computer Science German International University New Administrative Capital Egypt Computer and Systems Engineering Department Faculty of Engineering Ain Shams University 1 El-sarayat st. Abbassia Cairo Egypt Computer Science and Engineering Department The American University in Cairo Cairo Egypt School of Information Technology New Giza University Giza Egypt

An image can convey a thousand words. This statement emphasizes the importance of illustrating ideas visually rather than writing them down. Although detailed image representation is typically instructive, there are several contexts where simplification of image representations may be more informative. One way to provide an abstract representation of an object is via clip art, which is a simple graphic illustration of an object that can be included in documents or presentations. Clip art representation can be utilized in graphic design for concepts expression and daily life objects illustration. Furthermore, clip art had shown remarkable advantages when compared to real images in terms of editing and manipulation since clip art geometry can be easily edited in addition to the feasibility of storing it in a resolution-independent manner. However, it can be difficult to automatically create clip arts that resemble any object. Here, we propose a novel deep learning model, named ClipArtGAN, that utilizes Generative Adversarial Networks (GANs) to convert a photo of an object to its corresponding clip art. To our knowledge, this is the first GAN model based on Pix2Pix architecture that is capable of automatically generating clip art for any arbitrary object. Three training datasets were collected to train and compare two GAN models based on Pix2Pix and CycleGAN architectures. Our results demonstrate that the mean accuracy obtained using ClipArtGAN utilizing Pix2Pix outperforms that of CycleGAN by 58% and that of Google Images-based search by 54%. These results indicate the efficacy of ClipArtGAN in generating representative clip art images. © The Author(s), under exclusive licence to Springer Science+Business media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Resilient, Federated Large Language Models over Wireless Networks: Why the PHY Matters

Resilient, Federated Large Language Models over Wireless Net...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Vlad C. Andrei Aladin Djuhera Xinyang Li Ullrich J. Mönich Walid Saad Holger Boche Chair of Theoretical Information Technology Technical University of Munich Munich Germany Electrical and Computer Engineering Department Virginia Tech Arlington VA USA Munich Center for Quantum Science and Technology

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

In this paper, the problem of training large language models (LLMs) in split federated learning over real-world wireless networks is investigated. In the considered system, the embedding layers of an LLM are first computed at a client and then trans-mitted over a wireless MIMO-OFDM link to a server instance for further processing, continuing the forward- and initiating the backpropagation of the training to the originating client. Due to channel impairments and adversarial attacks, the server needs to compute the model losses and gradients using corrupted parameters such as embeddings in LLMs. The computation of the corresponding model losses is rigorously characterized using such perturbed embeddings and a direct connection to the communication mean-squared error (MSE) for models beyond simple neural networks is established. Subsequently, the communication errors are modeled as part of the training process, and a method to design beamforming, scheduling and power allocation is proposed, ensuring high task performance and model convergence even in the case of worst-case jamming. Results on two natural language processing tasks using different LLM architectures confirm the validity of the theoretical analysis and prove the effectiveness of the proposed wireless system design in terms of accuracy and F1 score.

关键词： Training Wireless sensor networks Upper bound Computational modeling Large language models Wireless networks MIMO Servers Resource management Jamming

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：