检索结果-内蒙古大学图书馆

2023 IEEE Transportation Electrification Conference and Expo, Asia-Pacific, ITEC Asia-Pacific 2023

作者： Kamijo, Taiga Aiso, Kohei Akatsu, Kan Aoyama, Yasuaki Shibaura Institute of Technology Electrical Engineering and Computer Science Tokyo Japan Shibaura Institute of Technology Department of Electrical Engineering Tokyo Japan Yokohama National University Division of Intelligent Systems Engineering Department of Faculty of Engineering Yokohama Japan Center for Technology Innovation - Materials Hitachi Ltd. Research & Development Group Ibaraki Japan

ISBN: (纸本)9798350314274

A novel drive system using Magnetic Multiple Spur Gear (MMSG) and multiple high-speed motors is characterized by small size, lightweight, and high efficiency even at high-speed region, it is expected to apply to in-wheel motor systems. However, there is a risk of contact between the rotors when applied to in-wheel motor system. In this study, a novel axial-gap MMSG is proposed to solve this problem, stabilize the air gap between the high-speed and low-speed rotors, and effectively utilize the magnets, and its performance is evaluated by finite element analysis. © 2023 IEEE.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Impact of multi-dimensional cognitive demands on takeover performance, physiological and eye-tracking measures in conditionally automated vehicles

引用

Transportation Research Part F: Traffic Psychology and Behaviour 2025年 114卷 461-475页

作者： Ange Wang Wenxin Shi Dengbo He Hai Yang Thrust of Intelligent Transportation Systems Hub The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Hong Kong SAR China Thrust of Robotics and Autonomous Systems Systems Hub The Hong Kong University of Science and Technology (Guangzhou) China HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Futian Shenzhen China

Before fully autonomous vehicles come true, drivers are still required to be responsible for driving safety and take over control of the vehicle when prompted by takeover requests in conditionally automated vehicles. Thus, drivers’ takeover performance can affect the safety of conditionally automated driving. However, though cognitive distraction can impair takeover performance in general, the influence of multi-dimensionality in the cognitive resources was under-investigated. At the same time, it is unknown how physiological and eye-tracking metrics are associated with different modalities of cognitive tasks in conditionally automated vehicles. Thus, through a driving simulation study with 42 participants, we investigated the effects of multidimensional cognitive demands, as imposed by multiple types of non-driving-related tasks, on drivers’ takeover performance, physiological responses, and eye-tracking metrics in conditionally automated vehicles. Results showed that certain takeover performance (i.e., vehicle speed and lateral acceleration), and physiological and eye-tracking metrics (i.e., differences between consecutive R-peaks, skin conductance level, variation in respiratory intervals, number of fixations, number of saccades and saccade angle) are still responsive to cognitive load in the context of driving automation. Further, the modality of the cognitive tasks can moderate the takeover performance (i.e., takeover time) and certain physiological (i.e., ratio of spectral power in the low- and high-frequency range and respiration depth) metrics. These findings suggest that, in future conditionally automated vehicles, in-vehicle task designs should consider the modality of the cognitive demands for driving safety and for the performance of the driver monitoring systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real Time Nanoscale Cleaning Phenomenon Observation During Enforcing MHz Wave By Evanescent Field 241

Real Time Nanoscale Cleaning Phenomenon Observation During E...

引用

241st ECST Meeting

作者： Terayama, Yutaka Khajornrungruang, Panart Suzuki, Keisuke Mori, Ryotaro Hamada, Satomi Wada, Yutaka Hiyama, Hirokuni Mechanical Science and Technology Division Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka iizuka820-8502 Japan Mechanical Science and Technology Division Department of Intelligent and Control Systems Ebara Corporation Ltd. Kanagawa fujisawa144-8510 Japan

ISBN: (纸本)9781607685395

Post-CMP Cleaning phenomenon is considered as the detachment of the nanoparticle from the substrate surface to be cleaned, and the occasional reattachment of the nanoparticle to surface in nanoscale. However, residual contamination on the substrate has been usually inspected only after the cleaning process. Therefore, the cleaning mechanism of nanoparticles has not already clearly known. Hence, we have established dynamically observation of cleaning phenomena near the surface by applying the evanescent light which occurred a few hundred nm from the surface. In this article, detachments of φ30, 50, 70 nm silica particles and the acoustic cavitation effect were observed during enforcing 1.1 MHz waves in 60 frames per second. The main phenomenon was described that some of each silica nanoparticles were randomly intermittently detached from the surface when the cavitation effect repeatedly irregularly occurs and decays near the surface or remained on the surface during enforcing MHz wave. © 2022 ECS - The Electrochemical Society.

关键词： Silica nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Oil Spill Detection: A Machine Learning Approach for Satellite Image Classification

Revolutionizing Oil Spill Detection: A Machine Learning Appr...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Sherif, Khaled Rizk, Faris H. Zaki, Ahmed Mohamed Eid, Marwa M. Khodadadi, Nima Ibrahim, Abdelhameed Abdelhamid, Abdelaziz A. Abualigah, Laith El-Kenawy, El-Sayed M. Delta Higher Institute of Engineering and Technology Department of Communications and Electronics Mansoura35111 Egypt Computer Science and Intelligent Systems Research Center BlacksburgVA24060 United States Delta University for Science and Technology Faculty of Artificial Intelligence Mansoura35111 Egypt University of Miami Department of Civil and Architectural Engineering Coral GablesFL United States Isa Town Bahrain Ain Shams University Faculty of Computer and Information Sciences Department of Computer Science Cairo11566 Egypt Al al-Bayt University Computer Science Department Mafraq25113 Jordan Middle East University MEU Research Unit Amman11831 Jordan Jadara Research Center Jadara University Irbid Jordan

ISBN: (纸本)9798350351408

Identifying and labeling oil spills in satellite imagery is an essential activity of both environmental monitoring and disaster response actions. This work is dedicated to applying an Artificial Neural Network (ANN) model for gathering oil spill data by using a dataset that is specially curated for this reason. Our dataset was developed from satellite pictures of the ocean, some of which depict oil spills and some that do not. The features were extracted from each picture using computer vision algorithms. Our ANN model is trained to distinguish between two classes: The metrics that are looked at consist of accuracy, sensitivity, specificity, PPV, NPV, and statistical significance, and they illustrate how the model performs. As a result, the ANN model gets an accuracy of 96.88% and a sensitivity of 92.86% at the same time, while the specificity is 99.88%. The sensitivity of this diagnostic test is 96.30%, and the specificity is 94.74%. A p-value of 0.985997 means that the reported finding reaches a statistical significance, which is enough to support our hypothesis. This can be concluded from the results of ANN, showing the potential of this model to successfully classify the image patches into two sets, namely the ones covered by oil spills and the oil spill-free ones. The research work is a great contribution to the development of the area of environmental monitoring through the machine learning methods used for quick and appropriate detection of environmental hazards. © 2024 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Mode-switching single-pixel imaging via a high-performance perovskite-Si dual-mode photodetector

引用

Photonics Research 2024年第12期12卷 2873-2880页

作者： YUJIN LIU DONGXU LIN JINGYANG XING HANYAN ZHAO HONGLING WAN HAO WANG ZHONG JI XUELI CHEN Innovation Center for Advanced Medical Imaging and Intelligent Medicine Guangzhou Institute of TechnologyXidian UniversityGuangzhou 510555China Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Department of Mechanical and Energy EngineeringSUSTech Energy Institute for Carbon NeutralitySouthern University of Science and TechnologyShenzhen 518055China Center for Biomedical-Photonics and Molecular Imaging Advanced Diagnostic-Therapy Technology and Equipment Key Laboratory of Higher Education Institutions in Shaanxi ProvinceSchool of Life Science and TechnologyXidian UniversityXi’an 710126China

Visible–near-infrared(VIS-NIR)dual-mode imaging can expand the human perception ***,the development of dual-mode image sensors is still challenging due to complex fabrication processes and readout circuit ***,we design a simple-structured(perovskite-Au/Si/Ag)dual-mode *** unique asymmetric electrode design allows the device to support two operating modes at zero *** device exhibits a detection range covering 400–1100 nm under top illumination mode,with a peak specific detectivity of up to 5.56×1013 *** bottom illumination mode,the device demonstrates pronounced narrowband NIR response *** importantly,we develop a dual-mode single-pixel imaging system based on this device,bypassing the fabrication processes of high-density array image *** system exhibits excellent VISNIR dual-mode imaging results,effectively separating NIR and VIS information and enhancing infrared details in the fused ***,we discover that the system can effectively suppress ringing artifacts,achieving infrared information perception at a low sampling rate,which can accelerate the imaging speed by∼16 times(reduced from∼3.2 s to∼0.2 s).Our proposed dual-mode single-pixel imaging technology offers new means for material identification and intelligent perception.

关键词： mode illumination details

来源：评论

学校读者我要写书评

暂无评论

Learning Adaptation and Generalization from Human-Inspired Meta-Reinforcement Learning Using Bayesian Knowledge and Analysis 6

Learning Adaptation and Generalization from Human-Inspired M...

引用

6th IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023

作者： Ho, Joshua Wang, Chien-Min King, Chung-Ta You, Yi-Hsin Feng, Chi-Wei Chen, Yen-Min Kuo, Bo-Yi Institute of Information Science Academia Sinica Taipei11529 Taiwan Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Taiwan University Taipei10631 Taiwan Center of Intelligent Healthcare National Taiwan University Hospital Taipei10022 Taiwan

ISBN: (纸本)9798350331288

Over the last decades, there has been growing interest in research in multiple and interdisciplinary fields of human-AI computing. In particular, approaches integrating the intersecting design with reinforcement learning (RL) have received more attention. However, the current research on RL may need to consider its enhancement from a humaninspired approach further. In the present work, we focus on enabling a meta-reinforcement learning (meta-RL) agent to achieve adaptation and generalization according to modeling Markov decision processes using Bayesian knowledge and analysis. By introducing a novel framework called human-inspired meta-RL (HMRL), we incorporate the agent performing resilient actions to leverage the dynamic dense reward based on the knowledge and prediction of a Bayesian analysis. The proposed framework can make the agent learn generalization and prevent the agent from failing catastrophically. The experimental results show that our approach helps the agent reduce computational costs with learning adaptation. Finally, we conclude and anticipate that integrating human-inspired meta-RL can enable learning more formulations relating to robustness and scalability, leading to promising directions and more complex AI goals in the future. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multitarget–Multidetection Tracking Using the Kernel SME Filter

Multitarget–Multidetection Tracking Using the Kernel SME Fi...

引用

International Conference on Information Fusion

作者： Eugen Ernst Florian Pfaff Marcus Baum Uwe D. Hanebeck Intelligent Sensor-Actuator-Systems Laboratory (ISAS) Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology (KIT) Germany Data Fusion Group Institute of Computer Science Georg-August-University Göttingen Germany

With the growing availability of high-resolution sensors, processing more than one detection per target becomes increasingly critical when tracking multiple extended objects. However, contemporary sensors often generate spurious detections that need to be considered. Naively employing standard multitarget trackers may result in poor tracking performance for multitarget–multidetection tracking in cluttered environments, and the relevant extensions are nontrivial. This paper introduces a version of the kernel symmetric measurement equation (SME) filter that considers both multidetections and clutter. For a simulated scenario, our novel filter achieved a higher accuracy than the global nearest neighbor (GNN) and a fast variant of the joint probabilistic data association filter (JPDAF).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of monocular slam algorithms using tum and euroc benchmarks 15th

Comparative analysis of monocular slam algorithms using tum ...

引用

15th International Conference on Electromechanics and robotics Zavalishin’s Readings, ERZR 2020

作者： Mingachev, Eldar Lavrenov, Roman Magid, Evgeni Svinin, Mikhail Intelligent Robotics Department Higher Institute for Information Technology and Intelligent Systems Kazan Federal University Kazan Russia College of Information Science and Engineering Ritsumeikan University Kyoto Japan

ISBN: (纸本)9789811555794

Stable and robust path planning and movement in ground mobile robots require a combination of accuracy and low latency in their state estimation. However, state estimation algorithms must provide these qualities under the computational and power constraints of embedded hardware. Simultaneous localization and mapping (SLAM) algorithms are the best choices for state estimation in these scenarios, in addition to their ability to operate without external localization from motion capture or global positioning systems. Moreover, a single-camera setup is the most common solution for robotic platforms, which reduces our domain of interest to the specific SLAM algorithms type—monocular SLAM. Yet, it is still not clear from the existing literature, which monocular SLAM algorithms perform well under the accuracy, latency, and computational constraints of a ground mobile robot with onboard state estimation. This paper evaluates an array of the most recent publicly available monocular SLAM methods: ORB-SLAM2, DSO, and LDSO. The evaluation considers the pose estimation accuracy (alignment error, absolute trajectory error, and relative pose error) while processing the TUM Mono and EuRoC datasets on the specific hardware platform with a balanced amount of computational resources and power consumption. We present our complete results as a benchmark for the research community. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Wavelength-division-multiplexed Transmission and Dispersion Compensation Enabled by Soliton Microcombs and Cascaded Microrings

Wavelength-division-multiplexed Transmission and Dispersion ...

引用

CLEO: science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Liu, Yuanbin Zhang, Hongyi Liu, Jiacheng Lu, Liangjun Du, Jiangbing Li, Yu He, Zuyuan Chen, Jianping Zhou, Linjie Poon, Andrew W. State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Lab of Navigation and Location Services Shanghai Institute for Advanced Communication and Data Science Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu314200 China Photonic Device Laboratory Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong

We demonstrate wavelength-division-multiplexed data transmission and dispersion compensation of 25 Gb/s × 9 on-off-keying signals over a 20-km singlemode fiber using an integrated single-soliton microcomb and a c... 详细信息

关键词： Dispersion compensation

来源：评论

学校读者我要写书评

暂无评论

Policy Design in Long-Run Welfare Dynamics

arXiv

引用

arXiv 2025年

作者： Wu, Jiduan Abebe, Rediet Hardt, Moritz Stoica, Ana-Andreea Max Planck Institute for Intelligent Systems Tübingen AI Center Tübingen Germany Department of Computer Science ETH Zürich Switzerland ELLIS Institute Tübingen Germany

Improving social welfare is a complex challenge requiring policymakers to optimize objectives across multiple time horizons. Evaluating the impact of such policies presents a fundamental challenge, as those that appear suboptimal in the short run may yield significant long-term benefits. We tackle this challenge by analyzing the long-term dynamics of two prominent policy frameworks: Rawlsian policies, which prioritize those with the greatest need, and utilitarian policies, which maximize immediate welfare gains. Conventional wisdom suggests these policies are at odds, as Rawlsian policies are assumed to come at the cost of reducing the average social welfare, which their utilitarian counterparts directly optimize. We challenge this assumption by analyzing these policies in a sequential decision-making framework where individuals’ welfare levels stochastically decay over time, and policymakers can intervene to prevent this decay. Under reasonable assumptions, we prove that interventions following Rawlsian policies can outperform utilitarian policies in the long run, even when the latter dominate in the short run. We characterize the exact conditions under which Rawlsian policies can outperform utilitarian policies. We further illustrate our theoretical findings using simulations, which highlight the risks of evaluating policies based solely on their short-term effects. Our results underscore the necessity of considering long-term horizons in designing and evaluating welfare policies;the true efficacy of even well-established policies may only emerge over time. © 2025, CC BY-NC-ND.

关键词： Stochastic systems

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：