检索结果-内蒙古大学图书馆

13th International electrical engineering Congress, iEECON 2025

作者： Sa-Ing, Vera Srisomboon, Kanabadee Lee, Wilaiporn Kaewtreewong, Wasinee Thongruy, Kunlaya Chaysangchom, Mullika King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand Srinakharinwirot University Faculty of Science Department of Computer Science Bangkok Thailand

ISBN: (纸本)9798331543952

Pneumonia and COVID-19 are severe diseases that primarily affect the lungs, causing acute and significant respiratory distress. In clinical settings, patients are screened to differentiate between these two conditions using computerized chest X-ray imaging. To address this issue, researchers have explored the solutions based on deep learning model to automatic analysis on the chest X-ray images. This research evaluates the four neural network models consist of VGG16, ResNet50, MobileNet, and Xception to classify the chest X-ray images on three categories: pneumonia, COVID-19, and normal lungs. This research involved preprocessing three datasets of chest X-ray images, including artifact removal, image resizing, and data augmentation, prior to model training and testing processing. From our experimental results, Xception model demonstrated the highest performance, achieving training accuracy of 99.99%, validation accuracy of 98.00%, training loss of 0.15%, and validation loss of 7.42%, with an overall accuracy of 97.70%. Thus, the Xception model is the most effective for distinguishing and predicting lung conditions from chest X-ray images and should be considered for future applications in medical data analysis. © 2025 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Enhancing Voltage and Frequency Control in Islanded VSC-Based Microgrids: A PSO-Driven Multilayer Perceptron Approach

Enhancing Voltage and Frequency Control in Islanded VSC-Base...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Beyene, Yared Bekele Worku, Getachew Biru Tjernberg, Lina Bertling Addis Ababa University School of Electrical and Computer Engineering Addis Ababa Ethiopia Kth Royal Institute of Technology School of Electrical and Computer Science Stockholm Sweden

ISBN: (纸本)9789531842976

This paper proposes a novel design approach using the particle swarm optimization-trained multilayer perceptron neural network (PSO-MLPNN) for inner current and voltage controllers in voltage source converter (VSC)-based islanded AC microgrids. Unlike conventional controllers that depend on line parameters, our intelligent controller structure operates independently of these parameters. The PSO-MLPNN controller effectively replaces the traditional Proportional-Integral (PI) controller, achieving accurate power-sharing and excellent dynamic performance across various load scenarios. Simulation results validate the effectiveness of our proposed controller. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Multi-type MOOCs Recommendation: Leveraging Deep Multi-Relational Representation and Hierarchical Reasoning 39

Multi-type MOOCs Recommendation: Leveraging Deep Multi-Relat...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Ye Gao, Yanqi Wang, Dongjie Zhou, Yupeng He, Jinlong Sun, Zhaoyang Yin, Minghao College of Information Science and Technology Northeast Normal University China Electrical Engineering and Computer Science Department University of Kansas United States

ISBN: (纸本)157735897X

Massive open online courses (MOOCs) recommendation provides online courses tailored to learners' individual preferences. Existing literature is limited by: 1) Ignoring the interrelations among courses, knowledge concepts, and videos, which leads to suboptimal recommendation performance;2) Neglecting the hierarchical interactions between learners and components like courses, knowledge concepts, and videos, which makes it difficult to capture learners' intentions accurately. To address them, we propose a novel multi-type MOOCs recommendation framework, which enables multi-type educational content recommendations. This framework includes two important components: multi-relational representation and hierarchical reasoning. Regarding multi-relational representation, we first create two static course-relational and knowledge concept-relational graphs based on domain knowledge and construct a dynamic video-relational graph using learners' browsing historical sequences. Then, we capture the interactions among different components by learning the corresponding embeddings via graph neural networks. Regarding hierarchical reasoning, we implement a hierarchical beam search strategy to narrow down the candidate courses, knowledge concepts, and videos by calculating joint probability. Finally, we introduce an optional layer to increase the diversity and reasonableness of video recommendations by estimating learners' intentions. Extensive experiments are conducted to show the effectiveness, robustness, and interpretability of our method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A UWB Antenna for Wireless Body Area Network and its Characteristics Analysis 3

A UWB Antenna for Wireless Body Area Network and its Charact...

引用

3rd International Conference on Advancement in electrical and Electronic engineering, ICAEEE 2024

作者： Rahman, H M Arifur Shovon, Md. Nakib Alam Hoque, Md. Ariful Khan, Mohammad Monirujjaman Yeboah-Akowuah, Bright North South University Department of Electrical and Computer Engineering Dhaka Bangladesh Kwame Nkrumah University of Science and Technology Department of Computer Engineering Kumasi Ghana

ISBN: (纸本)9798350388282

A newly designed small, almost square shaped Ultra Wideband antenna is presented in this paper. Free space simulations provided promising results with a wider bandwidth and high efficiency up to 97.68% within the UWB range. The antenna was intended for Wireless Body Area Network (WBAN) application. To verify its human on-body performance, a 3D human torso phantom was created and re-simulated the results by placing the antenna in its near field. To determine the effects of the presence of the human body, further distance-based studies were done by placing the antenna in five different distances from the torso phantom. The results were compared with each other and with free space simulations to determine how the distance influences its behaviors. Highest gain was recorded while the antenna was placed on 4mm and above with maximum value of 8.13dB. The results were summarized in terms of antenna parameters such as return loss, voltage standing wave ratio, farfield and 2D radiation patterns, efficiency, and gains. The antenna shows operability in wide frequency range within the UWB spectrum with optimistic gain values. © 2024 IEEE.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

Advancing Mars Exploration: Development of a Large-Scale Gravity Compensation System for Landers during Descent

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 6697-6710页

作者： Sun, Haining Tang, Xiaoqiang Ge, Shuzhi Sam Agency for Science Technology and Research Singapore Institute of Manufacturing Technology 138634 Singapore Tsinghua University Department of Mechanical Engineering State Key Laboratory of Tribology Beijing100084 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore

As space exploration advances, an increasing number of planets are becoming targets for landing missions. Before officially launching a lander, it is essential to conduct landing tests on Earth to verify the functionality of the lander. One key challenge is to simulate the target planet's gravity environment during the lander's descent. In this study, a large-scale gravity compensation system is developed to physically simulate the Martian gravity for the landing tests of a Mars lander. The system integrates a constant force mechanism and electronic control systems, working closely to ensure smooth transitions between working states during the landing tests. Based on the principle of minimum potential energy, an expression for the output force of the constant force mechanism is established, and the influence of factors such as mechanical parameters on the output force is analyzed. Experimental results show that the system can provide gravity compensation for a 720-kg Mars lander. It maintains a nearly constant output force even when the lander touches the ground and during the subsequent period, demonstrating its adaptability to transient collisions and sudden state changes. © 1965-2011 IEEE.

关键词： Space research

来源：评论

学校读者我要写书评

暂无评论

Robust Adaptive HCS MPPT Algorithm-Based Wind Generation System Using Power Prediction Mode 8

Robust Adaptive HCS MPPT Algorithm-Based Wind Generation Sys...

引用

8th IEEE International Energy Conference, ENERGYCON 2024

作者： Badawi, Ahmed Elzein, I.M. Ali, Hassan Ismail, Nasser Zyoud, Alhareth Soliman, Mostafa College of Engineering Technology University of Doha for Science and Technology Doha Qatar Department of Electrical and Computer Engineering Birzeit University Birzeit Ramallah Palestine

ISBN: (纸本)9798350382150

In this research, an innovative approach is presented to enhance the power energy production of the wind turbines (WTs). Robust adaptive hill climbing search (HCS) algorithm based on variable step size is integrated with power prediction mode (PPM) technique. The objective is to achieve the maximum power point of the wind energy conversion system (WECS), thereby capturing the highest possible power from the wind source. Conventional methods of maximum power point tracking (MPPT) are unable to precisely track and reach the optimal point under unpredicted wind speeds. To address this issue, adaptive HCS is utilized due to its ability to overcome certain well-perceived challenges such as detection delays and the number of iterations in detecting the optimal peak point. More specifically, the PPM technique is combined with the adaptive HCS algorithm. The proposed Adaptive HCS-PPM technique is shown to demonstrate higher efficiency and faster trenching capability in reaching the optimal point, resulting in reduced power fluctuations, and improved overall performance of WECS as well as overcoming the oscillations around the optimal point. ©2024 IEEE.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

DIFFAR: DENOISING DIFFUSION AUTOREGRESSIVE MODEL FOR RAW SPEECH WAVEFORM GENERATION 12

DIFFAR: DENOISING DIFFUSION AUTOREGRESSIVE MODEL FOR RAW SPE...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Benita, Roi Elad, Michael Keshet, Joseph Department of Electrical and Computer Engineering Technion - Israel Institute of Technology Haifa Israel Department of Computer Science Technion - Israel Institute of Technology Haifa Israel

Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a waveform (i.e., a vocoder). This work proposes a diffusion probabilistic end-to-end model for directly generating the raw speech waveform. The proposed model is autoregressive, generating overlapping frames sequentially, where each frame is conditioned on a portion of the previously generated one. Hence, our model can effectively synthesize an unlimited speech duration while preserving high-fidelity synthesis and temporal coherence. We implemented the proposed model for unconditional and conditional speech generation, where the latter can be driven by an input sequence of phonemes, amplitudes, and pitch values. Working directly on the waveform has some empirical advantages. Specifically, it allows the creation of local acoustic behaviors, like vocal fry, which makes the overall waveform sounds more natural. Furthermore, the proposed diffusion model is stochastic and not deterministic;therefore, each inference generates a slightly different waveform variation, enabling abundance of valid realizations. Experiments show that the proposed model generates speech with superior quality compared with other state-of-the-art neural speech generation systems. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Implications of EU Battery Regulation on Circular Economy: Barriers and Opportunities for Repurposing Electric Vehicle Batteries

Implications of EU Battery Regulation on Circular Economy: B...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Lin, Yi-Chun Beyene, Yared Bekele Tjernberg, Lina Bertling Kth Royal Institute of Technology School of Electrical and Computer Science Stockholm Sweden Addis Ababa University School of Electrical and Computer Engineering Addis Ababa Ethiopia

ISBN: (纸本)9789531842976

This paper presents a study of the impact of EU battery regulations, specifically Regulation (EU) 2023/1542, on end-of-life batteries, primarily focusing on repurposing within the supply chain. Qualitative data was gathered from stakeholders in the battery supply chain using a combination of surveys and interviews. Interviews provide deeper insights into aspects beyond the survey's scope, enhancing our understanding of how EU regulations influence the supply chain. The findings reveal a nuanced landscape where EU regulations bring advantages through defined producer responsibilities, improved safety standards, and facilitated data sharing. The study explores various circular business models within this context, emphasizing the need for a functional value network and effective stakeholder coordination. This research contributes valuable insights as the EU pursues circularity in the battery supply chain. By addressing barriers, capitalizing on opportunities, and promoting collaboration, it supports a sustainable and circular future in the EV battery supply chain, optimizing initial investments and aligning with the energy transition goals. © 2024 IEEE.

关键词： Battery Pack

来源：评论

学校读者我要写书评

暂无评论

Enhanced Vehicle Detection by Optimized Image Compression in NextG Wireless Network Autonomous Vehicles System 100

Enhanced Vehicle Detection by Optimized Image Compression in...

引用

100th IEEE Vehicular technology Conference, VTC 2024-Fall

作者： Monir, Md Fahad Hossain, Md Junayed Barkatullah, Mohammad Hoque, Md Mozammal Hassan, Zoheb Ahmed, Tarem Virginia Polytechnic Institute and State University Department of Electrical and Computer Engineering United States Department of Computer Science & Engineering Bangladesh University of Houston Department of Engineering Technology United States Université Laval Department of Electrical and Computer Engineering Canada

ISBN: (纸本)9798331517786

Autonomous Vehicle System (AVS) is rapidly advancing and is expected to completely transform the transportation industry, bringing about a new era of mobility. As digital data proliferation strains network resources, the demand for performing resource-intensive edge-assisted Deep Learning tasks in AVS with limited computational resources becomes increasingly challenging. The advent of 5G and future cellular networks (NextG) offers the promise of facilitating the seamless execution of these tasks. This research aims to diminish dataset size, in harmony with the integration capabilities of the Semantic and Flexible Open Radio Access Network (SEMO-RAN) framework, which is anticipated to reduce latency and refine resource allocation in vehicle image processing. The focus of this study is on optimizing image compression without compromising the accuracy of vehicle classification, leveraging esteemed Convolutional Neural Network models like YOLOv5. By employing Generative Adversarial Network compression and Wavelet Image Compression methods, our study achieves an impressive 81.82% reduction in data size while maintaining a 96.97% accuracy in classification tasks. This underscores the potential for significant efficiency gains in AVS through improved data management, supported by Digital Twins (DT), Integrated Sensing and Communication (ISAC), and O-RAN. © 2024 IEEE.

关键词： Radio access networks

来源：评论

学校读者我要写书评

暂无评论

Efficient conversion of acoustic vortex using extremely anisotropic metasurface

引用

Frontiers of physics 2024年第4期19卷 257-264页

作者： Zhanlei Hao Haojie Chen Yuhang Yin Cheng-Wei Qiu Shan Zhu Huanyang Chen Institute of Electromagnetics and Acoustics and Department of Physics College of Physical Science and TechnologyXiamen UniversityXiamen 361005China Department of Electrical and Computer Engineering National University of Singapore4 Engineering Drive 3117583Singapore Department of Mechanical and Electrical Engineering Xiamen UniversityXiamen 361005China Pen-Tung Sah Institute of Micro-Nano Science and Technology Xiamen UniversityXiamen 361005China

Vortex wave and plane wave,as two most fundamental forms of wave propagation,are widely applied in various research ***,there is currently a lack of basic mechanism to enable arbitrary conversion between *** this paper,we propose a new paradigm of extremely anisotropic acoustic metasurface(AM)to achieve the efficient conversion from 2D vortex waves with arbitrary orbital angular momentum(OAM)to plane *** underlying physics of this conversion process is ensured by the symmetry shift of AM medium parameters and the directional compensation of ***,this novel phenomenon is further verified by analytical calculations,numerical demonstrations,and acoustic experiments,and the deflection angle and direction of the converted plane waves are qualitatively and quantitatively confirmed by a simple *** work provides new possibilities for arbitrary manipulation of acoustic vortex,and holds potential applications in acoustic communication and OAM-based devices.

关键词： efficient wave conversion vortex wave plane wave orbital angular momentum acoustic metasurface

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：