检索结果-内蒙古大学图书馆

16th International Conference on Social Robotics, ICSR + AI 2024

作者： Shindo, Arisa Kawasaki, Yosuke Takahashi, Masaki School of Science for Open and Environmental Systems Graduate School of Science and Technology Keio University Kanagawa Japan Department of System Design Engineering Faculty of Science and Technology Keio University Kanagawa Japan

ISBN: (纸本)9789819635214

Recent studies have explored the integration of large language models (LLMs) into caregiving robots. The use of LLMs facilitates the generation of human-like natural dialogues and diverse, varied expressions. However, in case of a lack of direct and specific instructions from a user, gaining an accurate understanding of the user's intent is challenging, which may result in miscommunication. Thus, this study proposed a method to achieve robust communication even in the absence of direct instructions by considering the uncertainty in destination prediction probabilities. The proposed system leveraged GPT-4 to generate various Japanese speech content candidates and employed neighborhood components analysis to facilitate dimensionality reduction. Consequently, notable features of the rich linguistic embeddings were preserved while transforming them into manageable data. The system selected appropriate utterances based on the destination prediction probabilities. Furthermore, this study investigated changes in the speech content according to the variations in these probabilities, and the incorporation of uncertainty in communication was validated. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Protecting Your Attention during Distributed Graph Learning: Efficient Privacy-Preserving Federated Graph Attention Network

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 1949-1964页

作者： Zhou, Jinhao Wu, Jun Ni, Jianbing Wang, Yuntao Pan, Yanghe Su, Zhou Waseda University Graduate School of Information Production and Systems Fukuoka808-0135 Japan Queen's University Department of Electrical and Computer Engineering KingstonONK7L 3N6 Canada Xi'An Jiaotong University School of Cyber Science and Engineering Xi'an710049 China

Federated graph attention networks (FGATs) are gaining prominence for enabling collaborative and privacy-preserving graph model training. The attention mechanisms in FGATs enhance the focus on crucial graph features for improved graph representation learning while maintaining data decentralization. However, these mechanisms inherently process sensitive information, which is vulnerable to privacy threats like graph reconstruction and attribute inference. Additionally, their role in assigning varying and changing importance to nodes challenges traditional privacy methods to balance privacy and utility across varied node sensitivities effectively. Our study fills this gap by proposing an efficient privacy-preserving FGAT (PFGAT). We present an attention-based dynamic differential privacy (DP) approach via an improved multiplication triplet (IMT). Specifically, we first propose an IMT mechanism that leverages a reusable triplet generation method to efficiently and securely compute the attention mechanism. Second, we employ an attention-based privacy budget that dynamically adjusts privacy levels according to node data significance, optimizing the privacy-utility trade-off. Third, the proposed hybrid neighbor aggregation algorithm tailors DP mechanisms according to the unique characteristics of neighbor nodes, thereby mitigating the adverse impact of DP on graph attention network (GAT) utility. Extensive experiments on benchmarking datasets confirm that PFGAT maintains high efficiency and ensures robust privacy protection against potential threats. © IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning of Grasping Arbitrary Objects On-the-Move

Self-Supervised Learning of Grasping Arbitrary Objects On-th...

引用

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Kiyokawa, Takuya Nagata, Eiki Tsurumine, Yoshihisa Kwon, Yuhwan Matsubara, Takamitsu Division of Information Science Robot Learning Laboratory Nara Ikoma Japan Osaka University Graduate School of Engineering Science Department of Systems Innovation Osaka Toyonaka Japan

ISBN: (纸本)9798331531614

Mobile grasping enhances manipulation efficiency by utilizing robots' mobility. This study aims to enable a commercial off-the-shelf robot for mobile grasping, requiring precise timing and pose adjustments. Self-supervised learning can develop a generalizable policy to adjust the robot's velocity and determine grasp position and orientation based on the target object's shape and pose. Due to mobile grasping's complexity, action primitivization and step-by-step learning are crucial to avoid data sparsity in learning from trial and error. This study simplifies mobile grasping into two grasp action primitives and a moving action primitive, which can be operated with limited degrees of freedom for the manipulator. This study introduces three fully convolutional neural network (FCN) models to predict static grasp primitive, dynamic grasp primitive, and residual moving velocity error from visual inputs. A two-stage grasp learning approach facilitates seamless FCN model learning. The ablation study demonstrated that the proposed method achieved the highest grasping accuracy and pick-and-place efficiency. Furthermore, randomizing object shapes and environments in the simulation effectively achieved generalizable mobile grasping. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Examine the filter bubble with a focus on emotion and content 24

Examine the filter bubble with a focus on emotion and conten...

引用

8th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2024

作者： Kita, Shusaku Mine, Tsunenori Arakawa, Yutaka Department of Information Science and Technology Graduate School of Information Science and Electrical Engineering Kyushu University Fukuoka Japan Department of Advanced Information Technology Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan

ISBN: (纸本)9798400717383

Recommendation systems (RSs) have become popular in various Internet services, enabling the delivery of content tailored to user preferences. While RSs are designed to update recommended content to align more closely with user preferences based on browsing history and registration information, RSs may still present biased information due to inherent characteristics. This phenomenon is known as the "filter bubble,"a crucial aspect of the discourse on "informational health."Previous studies have examined the filter bubble phenomenon, focusing on the potential for bias in recommended content. However, there is no consensus on the definition of "bias,"and no agreement on the criteria for identifying a filter bubble state. In addition, the previous methods rely primarily on topic diversity as a metric, overlooking other important indicators. This study presents a more comprehensive approach to defining the state of the filter bubble. Our methodology employs two key indicators: content and emotion. We also evaluate the effectiveness of the proposed approach. © 2024 Copyright held by the owner/author(s).

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Linear Convergent Distributed Nash Equilibrium Seeking With Compression

引用

IEEE Transactions on Automatic control 2025年第5期70卷 3316-3323页

作者： Chen, Xiaomeng Wu, Yuchi Yi, Xinlei Huang, Minyi Shi, Ling Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Shanghai University School of Mechatronic Engineering and Automation Shanghai200444 China College of Electronics and Information Engineering Tongji University Department of Control Science and Engineering Shanghai201804 China Massachusetts Institute of Technology Lab for Information & Decision Systems CambridgeMA02139 United States Carleton University School of Mathematics and Statistics OttawaONK1S 5B6 Canada

Information compression techniques are majorly employed to reduce communication cost over peer-to-peer links. In this article, we investigate distributed Nash equilibrium (NE) seeking problems in a class of noncooperative games over directed graphs with information compression. To improve communication efficiency, a compressed distributed NE seeking (C-DNES) algorithm is proposed to obtain an NE for games, where the differences between decision vectors and their estimates are compressed. The proposed algorithm is compatible with a general class of compressors, including both unbiased and biased compressors. Moreover, our approach only requires the adjacency matrix of the directed graph to be row-stochastic, in contrast to past works that relied on balancedness or specific global network parameters. It is shown that C-DNES not only inherits the advantages of conventional distributed NE algorithms, achieving linear convergence rate for games with restricted strongly monotone mappings, but also saves communication costs in terms of transmitted bits. Finally, numerical simulations illustrate the advantages of C-DNES in saving communication cost by an order of magnitude under different compressors. © 1963-2012 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Energy-Free Sensing and Context Recognition Using Photovoltaic Cells

引用

IEEE Sensors Journal 2025年第9期25卷 15598-15611页

作者： Shintani, Kaede Rizk, Hamada Yamaguchi, Hirozumi Osaka University Graduate School of Information Science and Technology Department of Information Networking Suita565-0871 Japan Tanta University Tanta31733 Egypt RIKEN Center for Computational Science Kobe650-0047 Japan RIKEN Center for Computational Science Department of Computer and Control Engineering Kobe650-0047 Japan

The field of energy-free sensing and context recognition has recently gained significant attention as it allows operating systems without external power sources. Photovoltaic cells can convert light energy into electrical energy to power sensing devices, but their power may not be sufficient to ensure energy-free sensing due to the varying power needs of sensors and high computational demands. In this article, we propose the use of photovoltaic cells as a standalone sensor for the recognition of different contexts, including user identification, step counting, and location tracking. The system utilizes the photocurrent readings generated by the photovoltaic cells to capture the unique mobility patterns of different users. By analyzing these patterns, the system can accurately identify the user, count the number of steps taken, and track the user’s location. We propose a computationally efficient dynamic time warping (DTW) to match the variable length sequences of photocurrent readings to a database of known patterns and identify the closest subject and location matches. The system was rigorously evaluated in a realistic environment, and the results indicate that it can accurately estimate step count, identify subjects, and localize them with an accuracy of 88%, 90%, and 43 cm, respectively. This is achieved while the proposed system is nonintrusive and can operate without external power sources, making it a promising technology for energy-free sensing and context recognition. © 2001-2012 IEEE.

关键词： Photovoltaics

来源：评论

学校读者我要写书评

暂无评论

Phase-bias-blind computational ghost imaging with optical phased array

引用

Optics Express 2025年第10期33卷 21132-21141页

作者： Hirata, Sota Matsuda, Naoki Komatsu, Kento Tanemura, Takuo Horisaki, Ryoichi Department of Information Physics and Computing Graduate School of Information Science and Technology The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan Department of Electrical Engineering and Information Systems Graduate School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan

We propose a method for computational ghost imaging (CGI) with an optical phased array (OPA), wherein phase biases on the phase shifters are intrinsically unknown. In our method, an object is illuminated with a number of light fields from the OPA using random phase shifts, and the light from the object is captured by a single-pixel detector. The object and the phase biases are simultaneously estimated from the measured intensity signals. We numerically demonstrate the proposed method. Furthermore, we present complex amplitude field acquisition in OPA-based CGI with intensity measurements performed without reference light by simply adding an iris to the detector. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Computational imaging Imaging systems Phase shift Phased arrays Scattering media Spatial light modulators

来源：评论

学校读者我要写书评

暂无评论

Robust Health Monitoring for Lithium-Ion Batteries under Guidance of Proxy Labels: A Deep Multi-Task Learning Approach

引用

IEEE Transactions on Power Electronics 2025年第8期40卷 10272-10285页

作者： Guo, Ruohan Zhang, Kui He, Shangyang Tao, Shengyu Zhang, Xuan Liu, Kailong Li, Xiangjun Tian, Jinpeng Shen, Weixiang Chung, Chi Yung The Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Research Centre for Grid Modernisation Kowloon999077 Hong Kong Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518055 China Shandong University School of Control Science and Engineering Jinan250100 China China Electric Power Research Institute Beijing100192 China Swinburne University of Technology School of Engineering MelbourneVIC3122 Australia

State of health (SOH) estimation is foundational for effective health prognosis and management of lithium-ion batteries. However, conventional data-driven approaches struggle to ensure robust generalisability when training data lacks sufficient SOH labels. In this work, we explore the potential utility of ageing information, gathered from routine operational data beyond the standard input collection region, as proxy labels (PLs) to establish nonlinear mappings between a short charging segment and SOH. To achieve this, we develop a multi-task learning (MTL) framework for battery health monitoring, which comprises two critical components: (1) a deep MTL model, and (2) a multivariate Gaussian process regression (GPR) model. The deep MTL model is designed with four distinct tasks, each with a specific goal to exploit data under different labelling conditions, facilitating the extraction of domain-invariant and target-specific features for PL estimation. Using the estimated PLs, the GPR model is employed to provide precise mappings to SOH. Validations are conducted on batteries with diverse chemistries and cycling temperatures, particularly under severe label scarcity below 5%. The results confirm the effectiveness of the proposed method, outperforming baseline methods and achieving a mean absolute error of less than 1.3% in all case studies. © 1986-2012 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Modulated Structure Formation in Dislocation Cells in 316L Stainless Steel Fabricated by Laser Powder Bed Fusion

引用

Nippon Kinzoku Gakkaishi/Journal of the Japan Institute of Metals 2025年第5期89卷 175-181页

作者： Sun, Fei Ogawa, Toshio Adachi, Yoshitaka Sato, Kazuhisa Takagi, Shunya Miyamoto, Goro Suzuki, Asuka Yamanaka, Akinori Nakada, Nobuo Ishimoto, Takuya Nakano, Takayoshi Koizumi, Yuichiro Department of Material Design Innovation Engineering Nagoya University Nagoya464-8603 Japan Research Center for Ultra-High Voltage Electron Microscopy Osaka University Ibaraki Osaka567-0047 Japan Tohoku University Sendai980-8577 Japan Tsukuba305-0047 Japan Department of Materials Process Engineering Graduate School of Engineering Nagoya University Nagoya464-8603 Japan Division of Advanced Mechanical Systems Engineering Institute of Engineering Tokyo University of Agriculture and Technology Koganei184-8588 Japan Department of Materials Science and Engineering Tokyo Institute of Technology Yokohama226-8502 Japan Aluminium Research Center University of Toyama Toyama930-8555 Japan Division of Materials and Manufacturing Science Graduate School of Engineering Osaka University Suita565-0871 Japan Anisotropic Design & Additive Manufacturing Research Center Osaka University Suita565-0871 Japan

Metal additive manufacturing enables producing complex geometric structures with high accuracy and breaks the design constraints of traditional manufacturing methods. Laser powder bed fusion, a typical additive manufacturing process, presents a challenge in experimentally understanding the nano-scaled microstructure-process relationship regarding the wide range of process parameters. In this study, we aim to reveal the novel nanoscale structural features by advanced scanning transmission electron microscopy to clarify the formation mechanisms in 316L stainless steel by laser powder bed fusion. Here we show that the slender columnar grains were confined to the centreline of the melt pool along the build direction, and the columnar cell structure at the side branching of the melt pool grew along orthogonal directions to follow drastic changes in thermal gradient across adjacent melt pools. Novel nano-scaled modulated structures have been observed in the dislocation cells parallel to the laser scan direction, which were mainly caused by the elastic strain involving the thermal gradient inside the melt pool and across adjacent melt pools as well as the effective strain field in the dislocation cell interiors. An in-depth understanding of microstructure developments is worthy of fabricating high-performance materials by controlling the additive manufacturing process. ©2025 The Japan Institute of Metals and Materials.

关键词： Refining

来源：评论

学校读者我要写书评

暂无评论

Vision-based Robotic Assembly from Novel Graphical Instructions

Vision-based Robotic Assembly from Novel Graphical Instructi...

引用

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Wang, Chenxi Wang, Zhenting Kiyokawa, Takuya Wan, Weiwei Yamanobe, Natsuki Harada, Kensuke Osaka University Graduate School of Engineering Science Department of Systems Innovation 1-3 Machikaneyama Osaka Japan Aomi 2-4-7 Tokyo Japan

ISBN: (纸本)9798331531614

For the purpose of performing robotic assembly from a novel graphical instruction, this paper proposes a new method for aligning assembly parts based on the visual information guided by the image in a graphical instruction manual. Our proposed method comprises two phases: We first detect an assembly part drawn in the instruction manual and then estimate its relative pose among multiple assembly parts to be assembled. For the detection of assembly parts, we build the matching algorithm based on fast-directional chamfer matching (FDCM) by utilizing multiple images of actual assembly parts captured from multiple angles. For the relative pose estimation, we collect the poses of the identified parts and match them with the assembly scenes in the graphical instruction manuals. We conducted collaborative assembly experiments between a human and a robot for a set of furniture parts. We confirmed that the captured images matched the graphics contained in the assembly manual well. In addition, we confirm that, with the help of a human, a robot can efficiently assemble furniture with a novel instruction manual. © 2025 IEEE.

关键词： Robotic assembly

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：