检索结果-内蒙古大学图书馆

12th International Congress on advanced Applied Informatics, IIAI-AAI 2022

作者： Kawano, Ibuki Kurumida, Eri Terada, Syoma Hirata, Kouichi Kyushu Institute of Technology Department of Artificial Intelligence Iizuka820-8502 Japan Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering Iizuka820-8502 Japan

ISBN: (数字)9781665497558

ISBN: (纸本)9781665497558

In this paper, we classify Gram positive cocci and Gram negative bacilli in Gram stained smear images. We adopt pre-trained models of VGG16, VGG19, MobileNet and DenseNet by using ImageNet as learning models. Then, we give experimental results for classifying them, and the classification by MobileNet and DenseNet are more successful than that by VGG16 and VGG19. © 2022 IEEE.

关键词： Bacilli

来源：评论

学校读者我要写书评

暂无评论

Numerical Study on Structural Pattern Dependency of Aerodynamic Performance of Membrane Wings

Numerical Study on Structural Pattern Dependency of Aerodyna...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Nakai, Kanta Kanazaki, Masahiro Nagai, Hiroki Ikami, Tsubasa Tamaki, Yoshiharu Imamura, Taro Tokyo Metropolitan University Department of Aeronautics and Astronautics Graduate School of Systems Design 10-10 Hino-shi Tokyo191-0065 Japan Institute of Fluid Science Tohoku University 2-1-1 Katahira Miyagi Sendai980-857 Japan Department of Aeronautics and Astronautics School of Engineering The University of Tokyo 7-3-1 Hongo Tokyo Bunkyo-ku113-8656 Japan

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This study investigated the relationship between membrane wings and vein-like structural topologies to design membrane wings. The evaluation method employed coupled calculations using computational fluid dynamics (CFD) and a multi-particle membrane model. CFD utilizes a hierarchical Cartesian grid-based flow solver that can evaluate thin objects. Initially, this study examined a two-dimensional flat plate configured as a flexible membrane wing, exploring the effects of vein-like structures placed between the leading and trailing edges on membrane deformation and aerodynamic coefficients. Subsequently, the research was extended to a three-dimensional flat plate to analyze the impact on membrane deformation and aerodynamic coefficients when vein-like structures were positioned from the wing root to the wing tip. The results of the two-dimensional cases revealed differences in the deformation and aerodynamic coefficients depending on whether the vein-shaped structures were placed near the leading or trailing edge of the wing chord. Notably, when positioned at the center of the chord length, the lift-to-drag ratio improved. In the three-dimensional plate cases, the number of vein-like structures varied. With fewer structures, an increase in lift owing to membrane deformation was observed, along with an increase in drag. Conversely, with more structures, while membrane deformation and the corresponding increase in lift were suppressed, the drag was lower than that of a rigid flat plate. A visualization of the flow demonstrated that the design of vein-like structures influences the camber effect owing to membrane deformation and the suppression of flow separation. These insights provide guidelines for optimizing the lift-to-drag ratio during membrane wing design. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

KERNEL-BASED LEARNING WITH GUARANTEES FOR MULTI-AGENT APPLICATIONS

arXiv

引用

arXiv 2024年

作者： Kowalczyk, Krzysztof Wachel, Pawel Rojas, Cristian R. Department of Control Systems and Mechatronics CosmologyWroclaw University of Science and Technology Wroclaw Poland School of Electrical Engineering and Computer Science CosmologyKTH Royal Institute of Technology Stockholm Sweden

This paper addresses a kernel-based learning problem for a network of agents locally observing a latent multidimensional, nonlinear phenomenon in a noisy environment. We propose a learning algorithm that requires only mild a priori knowledge about the phenomenon under investigation and delivers a model with corresponding non-asymptotic high probability error bounds. Both non-asymptotic analysis of the method and numerical simulation results are presented and discussed in the paper. Copyright © 2024, The Authors. All rights reserved.

关键词： Asymptotic analysis

来源：评论

学校读者我要写书评

暂无评论

Motion Analysis of Simple Walking Models Driven by Minimalistic Periodic Input

Motion Analysis of Simple Walking Models Driven by Minimalis...

引用

International Conference on advanced Robotics and Mechatronics (ICARM)

作者： Cong Yan Fumihiko Asano Department of Mechanical Engineering Ritsumeikan University Kusatsu Shiga Japan Graduate School of Advanced Science and Technology Japan Advanced Institute of Science and Technology Nomi Ishikawa Japan

In dynamic bipedal walking, it is generally expected that simple and efficient control methods can generate stable limit cycle gaits. Therefore, we assume that well-designed periodic inputs can achieve excellent walking performance while maintaining stability without relying on feedback. This study compares two typical bipedal walker models, namely the rimless wheel(RW) and the biped, to validate this assumption. The results demonstrate that both models can successfully generate a stable limit cycle gait. By fine-tuning the control parameters, we confirmed that the bipedal model with swing legs exhibited a higher susceptibility to entrainment compared to the RW model. Our work demonstrates the existence of time-symmetric input reaching spatially asymmetric results in walking robots, which has important implications for understanding symmetry breaking in nature and the behavior of complex systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cyberoception: Finding A Painlessly-Measurable New Sense In The Cyberworld Towards Emotion-awareness In Computing 25

Cyberoception: Finding A Painlessly-Measurable New Sense In ...

引用

2025 CHI Conference on Human Factors in Computing systems, CHI 2025

作者： Okoshi, Tadashi Gao, Zexiong Tan, Yi Zhen Karasawa, Takumi Miki, Takeshi Sasaki, Wataru Balan, Rajesh Krishna Faculty of Environment and Information Studies Keio University Kanagawa Fujisawa Japan Graduate School of Interdisciplinary Information Studies The University of Tokyo Tokyo Tokyo Japan School of Computing and Information Systems Singapore Management University Singapore Singapore Singapore Graduate School of Media and Governance Keio University Kanagawa Pref Fujisawa city Japan Department of Engineering University of Cambridge Cambridge Cambridge United Kingdom Graduate School of Science and Technology Nara Institute of Science and Technology Nara Ikoma Japan

ISBN: (纸本)9798400713941

In Affective computing, recognizing users' emotions accurately is the basis of affective human-computer interaction. Understanding users' interoception contributes to a better understanding of individually different emotional abilities, which is essential for achieving inter-individually accurate emotion estimation. However, existing interoception measurement methods, such as the heart rate discrimination task, have several limitations, including their dependence on a well-controlled laboratory environment and precision apparatus, making monitoring users' interoception challenging. This study aims to determine other forms of data that can explain users' interoceptive or similar states in their real-world lives and propose a novel hypothetical concept "cyberoception,"a new sense (1) which has properties similar to interoception in terms of the correlation with other emotion-related abilities, and (2) which can be measured only by the sensors embedded inside commodity smartphone devices in users' daily lives. Results from a 10-day-long in-lab/in-the-wild hybrid experiment reveal a specific cyberoception type "Turn On"(users' subjective sensory perception about the frequency of turning-on behavior on their smartphones) significantly related to participants' emotional valence. We anticipate that cyberoception to serve as a fundamental building block for developing more "emotion-aware", user-friendly applications and services. © 2025 Copyright held by the owner/author(s).

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Low-speed Limit Cycle Walking of Planar X-shaped Bipedal Robot with Special Properties

Low-speed Limit Cycle Walking of Planar X-shaped Bipedal Rob...

引用

International Conference on advanced Robotics and Mechatronics (ICARM)

作者： Fumihiko Asano Cong Yan Graduate School of Advanced Science and Technology Japan Advanced Institute of Science and Technology Nomi Ishikawa Japan Department of Mechanical Engineering Ritsumeikan University Kusatsu Shiga Japan

This paper proposes a novel planar semicircular-footed X-shaped bipedal robot in which the center of mass of each leg link is at the same position as the hip joint, and discusses a method for generating a stable limit cycle gait on level ground. First, we outline the assumptions of the robot model with four degrees of freedom, and develop the mathematical equations of motion and collision. Second, we set the relative hip-joint angle as a control output and design a control system to follow it to the desired trajectory specified as a fifth-order function of time. Third, we mathematically show that there are special properties: the angular velocity of the swing leg does not change before and after the collision, and the time-integral of the control input becomes zero in a steady gait. We also mathematically show that the model has the feature that approximate linearization is effective and the antigravity effect of semicircular feet can be utilized. Through numerical simulations, we verify the validity of the theoretical results, and analyze some fundamental gait properties such as convergence speed and mechanical energy restoration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Path Planning Algorithm Based on D∗ Search

Research on Path Planning Algorithm Based on D∗ Search

引用

2023 International Conference on Ocean Studies, ICOS 2023

作者： Leng, Jiajun Fu, Li Wang, Lingling Tang, Ning Laboratory of Science and Technology on Marine Navigation and Control China State Shipbuilding Corporation Beijing100036 China Tianjin Navigation Instruments Research Institute Tianjin300131 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Bauman Moscow State Technical University Moscow Department of Automatic Control Systems 105005 Russia

ISBN: (纸本)9798350382457

Path planning algorithms are current research hotspots. Heuristic algorithms that can solve dynamic environment problems are gradually becoming the mainstream research direction. The D∗ algorithm, as one of the new heuristic algorithms, has the advantages of being more computationally efficient than the A ∗ algorithm and being able to solve dynamic problems, and has played an important role in two-dimensional path planning projects such as the NASA Mars rover. But its theoretical research and practical application in 3D environment are very rare. In this context, this paper carries out an in-depth study of the path planning problem based on the D∗ algorithm, and completes the theoretical derivation and simulation process in 2D and 3D environments. In this paper, a complex random 2D map is established by random generation, and the simulation of D∗ algorithm is realized on the map with the help of Python language, which realizes the finding of the relative optimal path. Then, in order to study the feasibility of D∗ solving in 3D environment, the simulation of D∗ algorithm under 3D map is realized with the help of Python and Unity3d. The research results show that the simulation results are good, which is valuable for the theoretical research and practical application of heuristic algorithms, and plays a role in the application of robot path planning algorithms. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Relip: Reliable in-Band Parallel Communication for Magnetic MIMO Wireless Power Transfer System

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Xinyu Zhou, Wangqiu Zhou, Hao Jiang, Shenyao Liu, Zhi Wang, Xiaoyan Ji, Yusheng Song, Qi City University of Hong Kong Department of Computer Science Hong Kong University of Science and Technology of China School of Computer Science and Technology Hefei230027 China The University of Electro-Communications Graduate School of Informatics and Engineering Tokyo182-8585 Japan Ibaraki University Graduate School of Science and Engineering Ibaraki310-8512 Japan National Institute of Informatics Information Systems Architecture Science Research Division Tokyo101-0003 Japan

In magnetic resonant coupling (MRC) based wireless power transfer (WPT) systems, receiver (RX) feedback communication is promising to enhance the capability and efficiency of the system. Although some studies have explored in-band implementations with low overhead costs, it has not been comprehensively investigated. In this paper, we propose Relip, a Reliable layer-level in-band parallel feedback communication mechanism for MIMO MRC-WPT systems, which addresses the impact of RX-RX couplings (i.e., non-negligible interference from strong couplings and positive effects of relay phenomenon), and provides a theoretical analysis of communication reliability. Technically, we first devise an On-Off based two-phase modulation mechanism to achieve RX identification and dependency detection under relay phenomenon. Then, we utilize observed channel decomposability to collect group-level power transfer channel conditions for eliminating the interference caused by strong RX-RX couplings. Furthermore, we perform RX selection to optimize the trade-off between communication reliability and time overhead. We design and implement the Relip prototype and conduct extensive experiments. The results validate the effectiveness of our mechanism, i.e., Relip can provide ≥99% average decoding accuracy for concurrent feedback communication of 14 devices, achieving an 18.31% improvement compared to the state-of-the-art solution. © 2002-2012 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Adaptive UAV-Assisted Hierarchical Federated Learning: Optimizing Energy, Latency, and Resilience for Dynamic Smart IoT Networks

arXiv

引用

arXiv 2025年

作者： Yang, Xiaohong Liwang, Minghui Fu, Liqun Su, Yuhan Hosseinalipour, Seyyedali Wang, Xianbin Hong, Yiguang School of Informatics Xiamen University Fujian China Department of Control Science and Engineering The National Key Laboratory of Autonomous Intelligent Unmanned Systems China Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai China School of Electronic Science and Engineering Xiamen University Xiamen China Department of Electrical Engineering University at Buffalo-SUNY BuffaloNY United States Department of Electrical and Computer Engineering Western University ON Canada

Hierarchical Federated Learning (HFL) introduces intermediate aggregation layers, addressing the limitations of conventional Federated Learning (FL) in geographically dispersed environments with limited communication infrastructure. An application of HFL is in smart IoT systems, such as remote monitoring, disaster response, and battlefield operations, where cellular connectivity is often unreliable or unavailable. In these scenarios, UAVs serve as mobile aggregators, providing connectivity to the terrestrial IoT devices. This paper studies an HFL architecture for energy-constrained UAVs in smart IoT systems, pioneering a solution to minimize global training cost increased caused by UAV disconnection. In light of this, we formulate a joint optimization problem involving learning configuration, bandwidth allocation, and device-to-UAV association, and perform global aggregation in time before UAV drops disconnect and redeployment of UAVs. The problem explicitly accounts for the dynamic nature of IoT devices and their interruptible communications and is unveiled to be NP-hard. To address this, we decompose it into three subproblems. First, we optimize the learning configuration and bandwidth allocation using an augmented Lagrangian function to reduce training costs. Second, we propose a device fitness score, integrating data heterogeneity (via Kullback-Leibler divergence), device-to-UAV distances, and IoT device resources, and develop a twin-delayed deep deterministic policy gradient (TD3)-based algorithm for dynamic device-to-UAV assignment. Third, We introduce a low-complexity two-stage greedy strategy for finding the location of UAVs redeployment and selecting the appropriate global aggregator UAV. Experiments on real-world datasets demonstrate significant cost reductions and robust performance under communication interruptions. © 2025, CC BY-NC-ND.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Multi-Agent Framework for Voltage control in Distribution systems with High Penetration of Inverter-Based Resources

A Multi-Agent Framework for Voltage Control in Distribution ...

引用

International Middle-East Power System Conference, MEPCON

作者： Ahmed Bedawy Yutaka Sasaki Yoshifumi Zoka Naoto Yorino Graduate School of Advanced Science and Engineering Hiroshima University Higashi-Hiroshima Japan Department of Electrical Engineering Faculty of Engineering South Valley University Qena Egypt National Institute of Technology (KOSEN) Kure College Kure Japan

ISBN: (数字)9798350379648

ISBN: (纸本)9798350379655

The increasing penetration of inverter-based resources (IBRs) such as photovoltaic (PV) systems, electric vehicles (EVs), and battery energy storage systems (BESSs) in distribution networks presents new challenges for maintaining voltage within the standard limits. Traditional voltage control methods are often insufficient to manage the complex dynamics introduced by decentralized and variable power sources. This paper proposes a multi-agent framework for voltage control in distribution systems with a high penetration of IBRs. The framework leverages decentralized agents coordinating with a voltage regulator agent, including PV, EV, and fuel cell agents. Each agent monitors and controls its local voltage and power generation or consumption while communicating with the voltage regulator to ensure system-wide voltage control. The novelty lies in the proposed framework’s flexibility, scalability, and adaptability to varying network conditions, particularly under high renewable energy penetration. Simulation results demonstrate that the proposed framework effectively mitigates voltage deviations, decreases the control operation of the voltage regulator, and supports the seamless integration of IBRs into the distribution network. This approach shows promise for enhancing the resilience and efficiency of future power systems with high shares of renewable energy.

关键词： Reactive power Renewable energy sources Regulators Scalability Power system dynamics Distribution networks Voltage control Vehicle dynamics Stress Standards

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：