检索结果-内蒙古大学图书馆

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Li, Chunying Guo, Shuxiang Kagawa University Graduate School of Engineering Hayashi-cho Takamatsu761-0396 Japan The Key Laboratory of Convergence Biomedical Engineering System and Healthcare Technology The Ministry of Industry and Information Technology Beijing Institute of Technology Beijing100081 China Southern University of Science and Technology The Department of Electronic and Electrical Engineering Guangdong Shenzhen518055 China

ISBN: (纸本)9798350320831

Due to the particularity and complexity of the underwater environment, the perception ability of Autonomous Underwater Vehicles (AUVs) has become a hot issue in recent years. In this paper, the detection system was developed for bioinspired Spherical Underwater Robots (SURs) based on the pressure sensor array. Firstly, the sensor array based on the SUR model was proposed using pressure sensors, adding new dimension to near-flow detection and perception method. Then, the detection system was constructed and the hydrodynamic pressure variables are analyzed. Next, the data acquisition of the pressure sensor array was described. Furthermore, the SUR prototype was assembled carrying the pressure sensor array. Finally, a series of locomotion experiments were performed to verify its performance. The experimental results validated the effectiveness of the proposed detection system, which had a certain reference value for AUV underwater detection and state estimation. © 2023 IEEE.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

A Hardware-Efficient Approximate Multiplier Combining Inexact Same-weight N:2 Compressors and Remapping Logic with Error Recovery

A Hardware-Efficient Approximate Multiplier Combining Inexac...

引用

IEEE International SOC Conference

作者： Renrui Duan Mingtao Zhang Yi Guo Shinichi Nishizawa Shinji Kimura Graduate School of Information Production and System Waseda University Kitakyushu Japan School of Information Science and Engineering Yunnan University Kunming China

Approximate computing can trade accuracy for smaller power, delay, and area. So, approximate computing is hardware-efficient for fault-tolerant applications which do not require full precision, such as image processing and machine learning. This paper proposes same-weight N:2 compressors based on the probability analysis, and construct approximate multipliers combining proposed N:2 compressors, remapping logic and constant-truncation with its error recovery circuit. Evaluation results using commercial 65 nm process library show that proposed 8×8 multiplier has good hardware-accuracy trade-off. It reduces the power by 39%, the delay by 17%, the area by 34% and the power-delay-area-product (PDAP) by 67% with an MRED of 1.27% when compared to the exact multiplier. The proposed methods show the better PDAP compared with other approximate multipliers with almost the same MRED.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modelling of Aggregates using Aperiodic Space-Filling and Physical Simulation 2

Modelling of Aggregates using Aperiodic Space-Filling and Ph...

引用

2021 2nd International Symposium on Automation, information and Computing, ISAIC 2021

作者： Gan, X. Ito, T. Takeshima, Y. Kikuchi, T. Graduate School of Media Science Tokyo University of Technology Hachioji Japan Department of System and Information Engineering Hachinohe Institute of Technology Hachinohe Japan School of Media Science Tokyo University of Technology Hachioji Japan

In this paper, we will explain to you how to procedural generate realistic aggregates. The program requires two or more 3D models, and the number of elements and friction values. There are two steps: the first requires user-input elements and a provided shape and fills the defined shape with non-overlapping elements;the second, together with user-input friction data, is a physical simulation to generate a more realistic pile. © Published under licence by IOP Publishing Ltd.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Label Estimation of Data Using the Modified Fisher Criterion

Label Estimation of Data Using the Modified Fisher Criterion

引用

2022 IEEE International Conference on systems, Man, and Cybernetics, SMC 2022

作者： Motoki, Ryuhei Jin'no, Kenya Tokyo City University Informatics Graduate School of Integrative Science and Engineering Tokyo Japan Tokyo City University Faculty of Information Technology Department of Intelligent System Tokyo Japan

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

In supervised learning, the amount of work required to assign labels to data becomes enormous as the input data increases. To reduce this work, we propose a method for label estimation using only a small amount of labeled data. The SVM separation hyperplane is moved by iterating label assignment and classification, and the results are evaluated using a new cluster evaluation criterion. This criterion is based on the Fisher criterion used for linearly separable data and applied to nonlinear data. Some semi-supervised learning methods, which are related to the proposed method, are also explained. We show that the proposed method is effective for linearly inseparable data through experiments. In addition, we compared the performance of the proposed method with some semi-supervised learning methods. The contributions of this study are the classification of data in situations where labeled data is scarce and the development of new criteria for evaluating non-linear classification results. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Smart Buoy-integrated Antenna for Monitoring Tidal Power Turbines

A Smart Buoy-integrated Antenna for Monitoring Tidal Power T...

引用

International Conference on Renewable Energy Research and Applications (ICRERA)

作者： Takafumi Fujimoto Chai-Eu Guan Kaisei Inoue Yoko Maemura Graduate School of Integrated Science and Technology Nagasaki University Nagasaki Japan Graduate School of Engineering Nagasaki University Nagasaki Japan Faculty of Information System University of Nagasaki Nagasaki Japan

ISBN: (数字)9798350375589

ISBN: (纸本)9798350375596

In this paper, a low profile printed antenna is proposed for remote monitoring of offshore turbines. Simulated and measured results show that the bandwidth of 10dB-return loss satisfies the 920MHz band of the specified low power base station. The radiation pattern is omnidirectional vertically polarization and the direction of the maximum radiation is in low elevation angle. The absolute gain is also greater than the target value (3dBi). Moreover, the effects of the buoy on the antenna characteristics are discussed. The size of the final designed antenna is 0.67 $\lambda_{924\mathrm{M}}\mathrm{x}0.67\lambda_{924\mathrm{M}}\mathrm{x}0.14\lambda_{924\mathrm{M}}(\lambda_{f}$ is the free-space wavelength at $f$ Hz).

关键词： Antenna measurements Wireless communication Wireless sensor networks Sea measurements Microstrip antennas Loss measurement Tidal energy Turbines Remote monitoring Antenna radiation patterns

来源：评论

学校读者我要写书评

暂无评论

Optimization of End-to-End Throughput on Piggyback Network with drone-to-drone millimeter-wave communications

Optimization of End-to-End Throughput on Piggyback Network w...

引用

International Conference on information Networking

作者： Tatsuya Aida So Hasegawa Maki Arai Ryosuke Isogai Yozo Shoji Mikio Hasegawa Department of Electrical Engineering Graduate School of Engineering Tokyo University of Science Tokyo Japan Social-ICT System Laboratory National Institute of Information and Communications Technology Tokyo Japan

ISBN: (数字)9798350330946

ISBN: (纸本)9798350330953

A store-carry-forward network, incorporating high-speed wireless links and autonomous mobility, such as drones, enables significantly faster data transfer compared to conventional wide-area wireless networks. It has been referred to as a Piggyback Network and proposed as a key technology for Beyond 5G. Recent experiments have successfully demonstrated drone-to-drone direct communication using millimeter waves. This paper proposes an optimization method designed to maximize the throughput of the Piggyback network, which includes multiple data source nodes, destination nodes, and multiple drones equipped with millimeter communication links. We assume that high-speed communications among drones utilizing millimeter waves are available. We optimize the assignment of each transmitted data to drones, the paths of moving drones, and the routing of each data among multiple drones to minimize end-to-end data transfer time. Our simulation results indicate that introducing drone-to-drone millimeter-wave communication leads to faster data transport compared to the conventional Piggyback network.

关键词： Wireless networks Soft sensors Simulation Millimeter wave technology Data transfer Throughput Routing

来源：评论

学校读者我要写书评

暂无评论

The Effect of Digital Marketing on Micro, Small and Medium Enterprise in Indonesia 1

引用

International Conference on Applied Informatics and Media Design, AIMD 2019

作者： Sasongko, Alvin Igo Widjaja, Gregorius Christian Theodore, Jason Afriliana, Nunik Matsuo, Tokuro Gaol, Ford Lumban School of Information System Bina Nusantara University Jakarta Indonesia Faculty of Engineering and Informatics Universitas Multimedia Nusantara Tangerang Indonesia Computer Science Department Bina Nusantara University Jakarta Indonesia Graduate School of Industrial Technology Advanced Institute of Industrial Technology Tokyo Japan

ISBN: (数字)9783031307690

ISBN: (纸本)9783031307683

Digital Marketing is a product marketing strategy using digital media and internet networks. Nowadays, digital marketing is a necessity for companies that thrive in the digital world. It greatly affects the growth of MSME (Micro, Small, Medium Enterprises) especially when it comes to increasing their sales performance by enhancing their brand awareness through various media or instruments such as a Facebook ad, Instagram advertising, Search Engine Optimization, and Search Engine Marketing. This research is aimed to measure how much impact of digital marketing utilization into Micro, Small, Medium enterprises. On the other hand, it also provides an understanding on what are the best digital marketing method to be utilized in the current situation. The method we used in this paper is quantitative. Data were collected through various questions constructed in an electronic questionnaire. This research provides a reference of digital marketing strategies for Micro, Small and Medium business owners. The result shows that digital marketing has a huge impact on the growth of Micro, Small and Medium Enterprise from increasing sales, increasing brand awareness, and gaining customers based on the data collected from both customer and Micro, Small, and Medium Enterprise players in Indonesia. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Brain-muscle Interaction Analysis with Time-variant Granger Causality

Brain-muscle Interaction Analysis with Time-variant Granger ...

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Nyi Nyi Tun Fumiya Sanuki Keiji Iramina Graduate School and Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan Graduate School of System Life Sciences Kyushu University Fukuoka Japan Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan

This study uses time-variant Granger causality to calculate the amount of functional interaction with the inference of information flow direction. Four different motor tasks were taken into consideration. They are real movement (RM), movement intention (Inten), motor imagery (MI), and only looking at the virtual hand in three-dimensional head-mounted display (OL) tasks. For the purpose of task instructions, we designed the experimental tasks in a 3D-HMD virtual reality environment. Examining the causality between two different biological signals is still challenging, and there have been few studies of causality between brain and muscle signals. Thus, the main aim of this study is to proclaim that time-variant Granger causality is an easy-to-apply and effective method for inferring information flow direction between ascending and descending pathways of brain and muscle signals. Generally, our final results strongly proved that brain-muscle functional interaction changes according to the motor tasks executed. Furthermore, high functional interaction appears in RM, Inten and MI tasks (in some subjects) rather than OL task in both afferent and efferent directions. Among many functional interaction methods, time-variant Granger causality is one of the most basic and reliable methods for investigating two different neurophysiological signals, such as EEG and EMG, to calculate the direction of information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WasteGAN: Data Augmentation for Robotic Waste Sorting through Generative Adversarial Networks

WasteGAN: Data Augmentation for Robotic Waste Sorting throug...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Alberto Bacchin Leonardo Barcellona Matteo Terreran Stefano Ghidoni Emanuele Menegatti Takuya Kiyokawa Department of Information Engineering Intelligent Autonomous System Lab University of Padova Padua Italy Department of Systems Innovation Graduate School of Engineering Science Osaka University Toyonaka Osaka Japan

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Robotic waste sorting poses significant challenges in both perception and manipulation, given the extreme variability of objects that should be recognized on a cluttered conveyor belt. While deep learning has proven effective in solving complex tasks, the necessity for extensive data collection and labeling limits its applicability in real-world scenarios like waste sorting. To tackle this issue, we introduce a data augmentation method based on a novel GAN architecture called wasteGAN. The proposed method allows to increase the performance of semantic segmentation models, starting from a very limited bunch of labeled examples, such as few as 100. The key innovations of wasteGAN include a novel loss function, a novel activation function, and a larger generator block. Overall, such innovations helps the network to learn from limited number of examples and synthesize data that better mirrors real-world distributions. We then leverage the higher-quality segmentation masks predicted from models trained on the wasteGAN synthetic data to compute semantic-aware grasp poses, enabling a robotic arm to effectively recognizing contaminants and separating waste in a real-world scenario. Through comprehensive evaluation encompassing dataset-based assessments and real-world experiments, our methodology demonstrated promising potential for robotic waste sorting, yielding performance gains of up to 5.8% in picking contaminants. The project page is available at https://***/bach05/***.

关键词： Training Technological innovation Computational modeling Semantic segmentation Grasping Computer architecture Data augmentation Generative adversarial networks Robots Sorting

来源：评论

学校读者我要写书评

暂无评论

WasteGAN: Data Augmentation for Robotic Waste Sorting through Generative Adversarial Networks

arXiv

引用

arXiv 2024年

作者： Bacchin, Alberto Barcellona, Leonardo Terreran, Matteo Ghidoni, Stefano Menegatti, Emanuele Kiyokawa, Takuya Intelligent Autonomous System Lab Department of Information Engineering University of Padova Padua Italy Department of Systems Innovation Graduate School of Engineering Science Osaka University Osaka Toyonaka Japan

关键词： Generative adversarial networks

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：