检索结果-内蒙古大学图书馆

9th International Conference on Signal Processing and Intelligent Systems, ICSPIS 2023

作者： Rochadiani, Theresia Herlina Heryadi, Yaya Sonata, Ilvico Lukas Suparta, Wawan Bina Nusantara University Binus Graduate Program- Computer Science Jakarta Indonesia Universitas Katolik Indonesia Atma Jaya Cognitive Engineering Research Group Jakarta Indonesia Institut Teknologi Nasional Yogyakarta Department of Electrical Engineering Yogyakarta Indonesia

ISBN: (纸本)9798350369922

Our surroundings' auditory landscapes are a wealth of knowledge, providing insights into a range of outdoor pursuits. The automatic classification of these actions using audio event detection and classification (AEDC) systems has a great deal of potential applications in environmental monitoring, security, surveillance, and driverless cars. Even though AEDC has advanced significantly in indoor settings, difficulties still exist outside because of the variable and changing acoustic conditions brought on by elements like the weather, different sound sources, and ambient noise from traffic and industry. This study suggests an outdoor audio event categorization model based on convolutional neural networks (CNNs). The suggested model shows passable accuracy by utilizing adaptation to the downstream task using the ESC-50 dataset and transfer learning from a pre-trained model. The effectiveness of multi-class audio classification models in downstream tasks is analyzed in this paper, with an emphasis on the effect of an increasing number of output classes on accuracy. Three models - three, four, and five classes - with different output class configurations are used in the study, and their training and validation accuracies are assessed. Although the accuracy scores above 80% are commendable, the data show a discernible reduction in performance as the number of classes rises. Notably, the three-class model attains a validation accuracy exceeding 90%, whereas the four-class and five-class models exhibit reduced accuracies, falling below 90% and 85%, respectively. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Octopus-Like Soft Robot Hand for Handling Vegetables and Fruits

Octopus-Like Soft Robot Hand for Handling Vegetables and Fru...

引用

International Conference on Advanced Mechatronic Systems (ICAMechS)

作者： Yuri Hotoda Kazuyuki Ito Major in Electrical and Electronic Engineering Graduate School of Science and Engineering Hosei University Tokyo Japan Department of Electrical Electronic Engineering Faculty of Science and Engineering Hosei University Tokyo Japan

In this paper, we propose an octopus-like soft robot hand for handling vegetables and fruits. The soft hand mimics octopus behavior, utilizing the dynamics of its soft body, and can pick up objects of various shapes, such as vegetables and fruits, without requiring complex control signals. The interaction between the soft hand and objects results in complex behavior to handle various objects. Experiments were conducted to demonstrate the performance of the developed soft hand, and the results confirmed that was capable of handling oranges, avocados, bananas, bell peppers, and tomatoes using simple control signals. Therefore, we conclude that the proposed soft robot hand effectively handles objects of different shapes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a 3 Degree-of-Freedom Upper-Limb Active Exoskeleton with Cable-Driven Actuators for Neuromotor Rehabilitation 1

Design of a 3 Degree-of-Freedom Upper-Limb Active Exoskeleto...

引用

1st IEEE Colombian Caribbean Conference, C3 2023

作者： Dias, Eduardo Ulhoa, Pedro Andrade, Rafhael Universidade Federal Do Espírito Santo Department of Mechanical Engineering. Vitória Brazil Universidade Federal Do Espírito Santo Department of Electrical Engineering Vitória Brazil Universidade Federal Do Espírito Santo Graduate Program in Mechanical Engineering Vitória Brazil

ISBN: (纸本)9798350341799

Exoskeletons are wearable mechanisms which, parallel to the wearer's joints, modulate movements through active or passive torque application. While existing upper-limb exoskeletons offer benefits in strength augmentation and therapy, they often suffer from limited degrees of freedom and excessive bulk, hindering their utility in neuromotor rehabilitation. This study introduces a three degree-of-freedom active upper-limb exoskeleton optimized for neuromotor rehabilitation. Employing anthropometric data and rigorous kinematic analysis, the design accommodates elbow flexion/extension, forearm pronation/supination, and hand gripping. The upper limb dynamics, kinematics, and physiology were evaluated to provide adequate joint ranges of motion. Cable-driven actuators in the elbow and forearm joints were designed to provide low worn weight through the relocation of the motor units away from the user's joints. The result is a lightweight, compact exoskeleton that provides optimal conditions for neuromotor rehabilitation. Finally, a preliminary control strategy was tested using myoelectric signals to trigger motion. © 2023 IEEE.

关键词： Actuators

来源：评论

学校读者我要写书评

暂无评论

Toward Sustainable Smart Cities in Bahrain: A Study on Power Generation Using Speed Breakers for Enhanced Energy Efficiency

Toward Sustainable Smart Cities in Bahrain: A Study on Power...

引用

2024 Arab ICT Conference, AICTC 2024

作者： Mohammed, M.N. Aljibori, H.S.S. Jameel Al-Tamimi, Adnan N. Alfiras, M. Hamza, Ali Elyas, Komail Alani, Zuhair Nafea Abdullah, Oday I. Abbas Helmi, Rabab Alayham Ahmad, Ahmad Sukri Al-Warith Center for Crowd Engineering and Management Research University of Warith Al-Anbiyaa Karbala Iraq College of Technical Engineering Al-Farahidi University Baghdad Iraq College of Engineering Gulf University Electrical and Electronic Engineering Department Sanad Bahrain College of Engineering Gulf University Architectural and Interior Design Engineering Department Sanad Bahrain University of Baghdad Dept of Energy Engineering Baghdad Iraq College of Engineering Gulf University Mechanical Engineering Department Sanad Bahrain School of Graduate Studies Management & Science University Shah Alam Selangor Malaysia Petronas Research Sdn Bhd Jln Ayer Hitam Selangor Malaysia

ISBN: (纸本)9798350342086

The increasing demand for energy in urban environments necessitates innovative solutions to harness untapped energy sources and enhance energy efficiency. In the context of Bahrain's efforts toward sustainable smart city development, this research article presents a comprehensive study on power generation using speed breakers as a novel energy-harvesting mechanism to supplement the electricity grid and promote energy efficiency in urban areas. The proposed energy-harvesting speed breaker (EHSB) system using rack-and-pinion mechanism employs a mechanical-to-electrical energy conversion mechanism, transforming the kinetic energy generated by vehicles passing over speed breakers into electrical energy. The study includes the design, construction, and testing of a prototype of the power generation system using speed breakers. The results of the study show that the EHSB system is a viable and sustainable method for generating electricity. The system is capable of generating significant amounts of energy, and it has the potential to contribute to the energy needs of communities located near highways and busy roads. The findings of this research provide valuable insights for Bahrain's policymakers, urban planners, and energy stakeholders, highlighting the potential of innovative energy-harvesting solutions such as the energy-harvesting speed breaker system in promoting energy efficiency and sustainability in urban environments. By incorporating the EHSB system into Bahrain's smart city development strategy, the nation can take a significant step toward a greener, more energy-efficient future. © 2024 IEEE.

关键词： Sustainable city

来源：评论

学校读者我要写书评

暂无评论

High-Frequency Load-Independent Wireless Power Charging System

High-Frequency Load-Independent Wireless Power Charging Syst...

引用

Wireless Power Week (WPW)

作者： Jiaxin Yan Wenqi Zhu Akihiro Konishi Kien Nguyen Hiroo Sekiya Xiuqin Wei Graduate School of Science and Engineering Chiba University Chiba Japan Department of Electrical and Electronic Engineering Chiba Institute of Technology Chiba Japan

ISBN: (数字)9798350349139

ISBN: (纸本)9798350349146

This paper proposes a load-independent high-frequency wireless power transfer (WPT) system. The proposed system achieves mode switching between constant current (CC) and constant voltage (CV) output modes, which can be applied to rechargeable batteries. In the proposed system, a single switch component is added on the receiver side to change the topology of the compensation circuit. As a result, the switching between CC and CV modes is accomplished on the receiver side, which means wireless communication about the load-information feedback from the receiver to the transmitter becomes unnecessary. By achieving zero-voltage switching (ZVS) in both CC and CV modes through the load-independent operation, the proposed system achieves high power-delivery efficiency even at high frequencies. Therefore, the proposed WPT system contributes to cost reduction, system simplification, and circuit downsizing. The experimental results agreed with the analytical predictions quantitatively, which verified the effectiveness of the proposed circuits.

关键词： Wireless communication Costs Transmitters Receivers Switches Voltage Zero voltage switching

来源：评论

学校读者我要写书评

暂无评论

Wireless Data Transmission Using a Resonant Tunneling Diode Transmitter and Receiver at a Frequency Range Exceeding 800 GHz

Wireless Data Transmission Using a Resonant Tunneling Diode ...

引用

International Conference on Infrared and Millimeter Waves

作者： Feifan Han Nguyen H. Ngo Masayuki Fujita Safumi Suzuki Department of Electrical and Electronic Engineering Tokyo Institute of Technology Meguro Japan Graduate School of Engineering Science Osaka University Toyonaka Japan

ISBN: (数字)9798350370324

ISBN: (纸本)9798350370331

Resonant tunneling diode (RTD) oscillators are considered promising candidates for developing novel terahertz electronic devices owing to their capability of ultrahigh-frequency operation. Here we demonstrate gigabit wireless data transmissions at approximately 860 GHz using an RTD transmitter and receiver based on an on-off keying modulation.

关键词： Wireless communication Millimeter wave devices Frequency modulation Transmitters Resonant frequency Receivers Packaging Resonant tunneling devices Data communication Oscillators

来源：评论

学校读者我要写书评

暂无评论

Accelerating Maximal Biclique Enumeration on GPUs

arXiv

引用

arXiv 2024年

作者： Hsieh, Chou-Ying Chang, Chia-Ming Cheng, Po-Hsiu Kuo, Sy-Yen Department of Electrical Engineering National Taiwan University Taipei Taiwan Graduate Institute of Electronic Engineering National Taiwan University Taipei Taiwan

Maximal Biclique Enumeration (MBE) holds critical importance in graph theory with applications extending across fields such as bioinformatics, social networks, and recommendation systems. However, its computational complexity presents barriers for efficiently scaling to large graphs. To address these challenges, we introduce cuMBE, a GPU-optimized parallel algorithm for MBE. Utilizing a unique data structure, called compact array, cuMBE eradicates the need for recursion, thereby significantly minimizing dynamic memory requirements and computational overhead. The algorithm utilizes a hybrid parallelism approach, in which GPU thread blocks handle coarse-grained tasks associated with part of the search process. Besides, we implement three fine-grained optimizations within each thread block to enhance performance. Further, we integrate a work-stealing mechanism to mitigate workload imbalances among thread blocks. Our experiments reveal that cuMBE achieves an average speedup of 6.1x and 6.3x compared to the state-of-the-art serial algorithm and parallel CPU-based algorithm on both common and real-world datasets, respectively. © 2024, CC BY.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Embedded Magnetic Absolute Encoder in SPMSM with Permanent Magnets of Different Magnetic Flux Densities

Embedded Magnetic Absolute Encoder in SPMSM with Permanent M...

引用

Annual Conference of Industrial electronics Society

作者： Yuto Watanabe Takashi Ohhira Hideki Hashimoto Graduate School of Science and Engineering Chuo University Tokyo Japan Department of Electrical Electronic and Communication Engineering Chuo University Tokyo Japan

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

Surface-mounted permanent magnet synchronous motors (SPMSMs) are used in various fields because of their high efficiency and high power density characteristics. Because they are generally driven by vector control, a type of current control, the position of the rotor must be detected. Rotor position detection is generally achieved by attaching an encoder or resolver to the exterior of a motor. This inevitably increases the volume and weight of the exterior of a motor. Although sensorless methods are available for determining the rotor position, their detection accuracy is low and it is difficult to acquire stable position information over the entire speed range. An embedded magnetic absolute encoder, which detects the rotor position by observing its magnetic flux, can acquire the rotor position without requiring the need for an external position sensor. However, calculating the absolute angle when two or more SPMSM pole pairs exist is difficult. This study proposes an embedded magnetic absolute encoder in an SPMSM that can calculate absolute angles. The proposed SPMSM enables the calculation of absolute angles using permanent magnets with different magnetic flux densities.

关键词： Industrial electronics Current control Magnetic flux density Power system measurements Accuracy Density measurement Rotors Permanent magnet motors Permanent magnets Machine vector control

来源：评论

学校读者我要写书评

暂无评论

Approximating Probabilistic Boundary of Future State Trajectory by Minimum-Volume Polynomial Sublevel Sets with Chance Constraints

Approximating Probabilistic Boundary of Future State Traject...

引用

American Control Conference (ACC)

作者： Xun Shen Ye Wang Graduate School of Engineering Osaka University Suita City Osaka JAPAN Department of Electrical and Electronic Engineering The University of Melbourne Melbourne Australia

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

The probabilistic boundary is necessary for safetycritical validation and control in uncertain dynamical systems. This paper addresses the problem of computing minimum-volume polynomial sublevel sets with chance constraints. Due to chance constraints, the original problem is intractable. To resolve this issue, we propose a sample-based continuous approximation method to approximate the original chance constraints, which leads to an approximate problem. The approximate problem is a tractable nonlinear optimization problem. We show that the optimal solution and cost of the approximate problem converge to those of the original one. The probabilistic feasibility of the approximate solution with finite samples is also discussed. Finally, a numerical example has been conducted to validate the proposed method.

关键词： Costs Probabilistic logic Polynomials Trajectory Approximation methods Dynamical systems Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Networks for Accurate Solar Module Classification in Thermal Images

Deep Convolutional Neural Networks for Accurate Solar Module...

引用

International electrical engineering Congress (iEECON)

作者： Chutinun Phungket Prasit Nangthin The Graduate Program Faculty of Engineering Faculty of Engineering Pathumwan Institute of Technology Bangkok Thailand Department of Electrical Engineering Faculty of Engineering Pathumwan Institute of Technology Bangkok Thailand

ISBN: (数字)9798350383591

ISBN: (纸本)9798350383607

The rapid and continuous technological advancements in computer and internet technologies, combined with data management techniques, find applications in various domains. For example, they aid in predictive maintenance systems, evaluate the performance of solar modules, and differentiate efficiently performing solar modules from less efficient ones using thermal imagery. The accuracy of solar module classification significantly impacts the subsequent assessment. In this study, we employ advanced techniques, particularly deep learning through Convolutional Neural Networks (CNN), to classify thermal images of solar modules. The practical aspects of applying CNN to the dataset of thermal images are explored, including transfer learning from pretrained CNN architectures and custom CNN architecture training. Experiments are conducted with three prominent types of solar module conditions: normal, cracked, and dusty. The results reveal that the most effective approach involves learning and fine-tuning pre-trained architectures on detailed studies, achieving a classification accuracy of up to 94.5 % .

关键词： Training Photovoltaic cells Transfer learning Neural networks Computer architecture Thermal conductivity Thermal analysis

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：