检索结果-内蒙古大学图书馆

5th International Conference on Power engineering and Renewable Energy, ICPERE 2022

作者： Li, Mingran Fujita, Goro Graduate School of Engineering and Science Shibaura Institute of Technology Electrical Engineering and Computer Science Tokyo Japan College of Engineering Shibaura Institute of Technology Department of Electrical Engineering Tokyo Japan

ISBN: (纸本)9781665455480

This paper describes the research found and design processes that implemented while developing Three-Phase Inverter System. The report will begin with research on inverters, inverter control, and components used in this design. This article explores methods and possibilities for implementing low-cost photovoltaic grid-connected power generation systems. This system can meet the needs of on-campus teaching and small-scale distributed power generation. © 2022 IEEE.

关键词： Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

Enhancing photoluminescence performance of perovskite quantum dots with plasmonic nanoparticles: insights into mechanisms and light-emitting applications

引用

Nanoscale Advances 2024年第3期6卷 782-791页

作者： Kumar, Gautham Lin, Chien-Chung Kuo, Hao-Chung Chen, Fang-Chung Department of Photonics College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Graduate Institute of Photonics and Optoelectronics Department of Electrical Engineering National Taiwan University Taipei10617 Taiwan Center for Emergent Functional Matter Science National Yang Ming Chiao Tung University Hsinchu30010 Taiwan

Perovskite quantum dots (QDs) are considered as promising materials for numerous optoelectronic applications due to their narrow emission spectra, high color purity, high photoluminescence quantum yields (PLQYs), and cost-effectiveness. Herein, we synthesized various types of perovskite QDs and incorporated Au nanoparticles (NPs) to systematically investigate the impact of plasmonic effects on the photoluminescence performance of perovskite QDs. The PLQYs of the QDs are enhanced effectively upon the inclusion of Au NPs in the solutions, with an impressive PLQY approaching 99% achieved. The PL measurements reveal that the primary mechanism behind the PL improvement is the accelerated rate of radiative recombination. Furthermore, we integrate perovskite QDs and Au NPs, which function as color conversion layers, with blue light-emitting diodes (LEDs), achieving a remarkable efficiency of 140.6 lm W−1. Additionally, we prepare photopatternable thin films of perovskite QDs using photocrosslinkable polymers as the matrix. Microscale patterning of the thin films is accomplished, indicating that the addition of plasmonic NPs does not adversely affect their photopatternable properties. Overall, our research not only elucidates the underlying mechanisms of plasmonic effects on perovskite QDs but presents a practical method for enhancing their optical performance, paving the way for next-generation optoelectronic applications, including high-definition micro-LED panels. © 2024 The Royal Society of Chemistry.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Development of Buffer Zone into Living Lab-Garuda Smart City Framework: Systematic Review 10

Development of Buffer Zone into Living Lab-Garuda Smart City...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Emmanuel, Gunadi Supangkat, Suhono Harso Gaol, Ford Lumban Ranti, Benny Bina Nusantara University Doctor of Computer Science Jakarta Indonesia Univ. Katolik Musi Charitas Fakultas Sains Dan Teknologi Palembang Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Bina Nusantara University Binus Graduate Program-Doctor of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350339543

The phenomenon of urbanization in Indonesia is inevitable. The new residential and economic centers in suburban areas is also a problem in city development. The gradual planning and development of smart cities in a living lab require consideration of the right location for a living lab. This study wants to show that suburban areas as city buffer zones can become living laboratories for smart city development. The diversity of situations in cities and regencies across Indonesia, the potential for resources, and the problems faced are the challenges of developing a living lab-Garuda Smart City Framework. This research uses the method of reviewing the literature of research publications for the last five years (2019-2023) to obtain information on Smart City development in Indonesia. We collected selected articles from databases in Google Scholar, IEEE, and Scopus using the Publish and Perish 8. The search keywords used were garuda AND Smart city AND Framework. The findings show the potential and dynamics of buffer zones to become appropriate living laboratories. Smart city regional planning can more holistically involve neighborhoods and address urban issues. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Bearing Remaining Useful Life Prediction Based on BERT Fine-tuning 14

Bearing Remaining Useful Life Prediction Based on BERT Fine-...

引用

14th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Hangzhou 2023

作者： Zhu, Junan Long, Zhuo Ma, Xiaoguang Luan, Feng School of Computer Science and Engineering Northeast University Shenyang China School of Electrical and Information Engineering Changsha University of Science and Technology Changsha China Foshan Graduate School Northeastern University Foshan China

ISBN: (纸本)9798350301359

Rotating machinery are the cornerstone of industrial, and the prediction of critical bearing life model has always been a research hotspot. However, the prediction accuracy of most bearing remaining useful life(RUL) prediction networks still needs to be improved, and the training time can be further shortened. This paper proposed a fine-tuning BERT model for predicting the RUL of bearings. Based on the output form of the BERT model word segmentation module and the NLP task, the health index from bearing vibration data was extracted, and combined with the BERT model to achieve bearing RUL prediction. The performance of the proposed method was verified on the XJTU-SY bearing dataset. The results showed that the BERT model achieved superior RUL prediction performance in training speed and prediction accuracy, indicating its great potential for the field. © 2023 IEEE.

关键词： BERT Feature Extraction Remaining useful life (RUL) Rolling Bearing

来源：评论

学校读者我要写书评

暂无评论

Efficient Hyperparameter Optimization Using Deep Q-Network and BRKGA 13

Efficient Hyperparameter Optimization Using Deep Q-Network a...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Kobayashi, Kosei Aritsugi, Masayoshi González, Pedro Henrique Mendonça, Israel Graduate School of Science and Technology Kumamoto University Kumamoto Japan Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan System Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (纸本)9798350308365

Hyperparameter optimization (HPO) is paragon to maximize performance when designing machine learning models. Among different HPO methods, Genetic Algorithm (GA) based optimization is considered effective because it allows a wide and diverse range of solutions to be explored. However, GA's exploratory nature makes this type of algorithm to evaluate many solutions that do not improve the overall performance. This is specially costly when the objective function to be evaluated is time-consuming, like in the HPO field. In this paper, we propose an efficient hybrid algorithm that is able to reduce computational cost by combining deep reinforcement learning with the Biased Random Key Genetic Algorithm (BRKGA), a variant of genetic algorithms. Our reinforcement learning agent has a decision-making role during the population's fitness calculation, in which it filters out chromosomes that would not improve the overall fitness of the population. The agent uses small amounts of pre-trained data to identify trends in potentially good solutions, and carry out its decision process. We conduct experiments on eight different datasets to assess the effectiveness of the proposed method, and the results show that the proposed method can significantly reduce the computation time of hyperparameter search using BRKGA (up to 44% reduction in computational time) without compromising the quality of the solution (no statistically difference in results). © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

SPD Manifold-Based Graph Neural Network for Fault Diagnosis of Harmonic Drive 3

SPD Manifold-Based Graph Neural Network for Fault Diagnosis ...

引用

3rd International Conference on Electronic Information engineering and computer Communication, EIECC 2023

作者： Cheng, Wei Long, Zhuo Ma, Xiaoguang Li, Chuanwen School of Computer Science and Engineering Northeastern University Shenyang China School of Electrical and Information Engineering Changsha University of Science and Technology Changsha China Foshan Graduate School Northeastern University Foshan China

ISBN: (纸本)9798350359961

Harmonic drive (HD), as an essential component of industrial robots, is susceptible to damage due to product manufacturing and working conditions. Therefore, it is imperative to conduct a comprehensive test to accurately diagnose potential HD faults. In this paper, a SPD Manifold-based Graph Neural Network (SPD-GNN) is proposed to accurately identify different faults of HD. In the time-frequency domain, the high-definition vibration signals obtained from multiple sensors are segmented. The resulting multi-channel spatial covariance matrices (MSCM) act as vertices in a time-frequency graph. A SPD-GNN is then utilized to extract classification details while preserving discriminative capabilities. Subsequently, the SPD matrices are projected to the tangent space using a logarithmic mapping (LOG) layer. Ultimately, the data is input into a cross-entropy loss function for subsequent computation. The SPD-GNN uses graph convolutional techniques tailored for SPD matrices to capture HD features in the time-frequency domain. © 2023 IEEE.

关键词： fault diagnosis graph neural network harmonic drive multi-sensor symmetric positive definite manifold

来源：评论

学校读者我要写书评

暂无评论

Optimization of Node Reduction Using BRKGA for GNN-Based Traffic Speed Forecasting 13

Optimization of Node Reduction Using BRKGA for GNN-Based Tra...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Inokuchi, Yuto González, Pedro Henrique Mendonça, Israel Aritsugi, Masayoshi Graduate School of Science and Technology Kumamoto University Kumamoto Japan Federal University of Rio de Janeiro System Engineering and Computer Science Program Rio de Janeiro Brazil Kumamoto University Faculty of Advanced Science and Technology Kumamoto Japan

ISBN: (纸本)9798350308365

While Spatio-Temporal Graph Convolutional Networks (STGCNs) are an effective method for traffic speed fore-casting, their training and inference tend to be time-consuming. In this paper, we aim to refine these networks by strategically reducing their number of nodes, thereby boosting computational efficiency. The nodes in these graphs represent data observed for road segments, and by analyzing the interconnections and layout of the graph, we can identify nodes with minimal contribution to overall performance. Removing these nodes can potentially decrease computation time while maintaining the prediction accuracy. We employ the Biased Random-Key Genetic Algorithm (BRKGA) to identify a good set of nodes for removal, based on a predefined percentage reduction of the original graph size (e.g., retaining 95 % of the original graph). We evaluate different graph size configurations, ranging from 95 % to 70 % node retention, to determine the least impactful node set performance. Our experiments on three real-world datasets reveal that reducing nodes can decrease computation time by up to 29%, and as a byproduct of removing noise, even improve the prediction accuracy. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

3D Image Generation from X-ray Projections Using Generative Adversarial Networks 23

3D Image Generation from X-ray Projections Using Generative ...

引用

23rd IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2023

作者： AlShurbaji, Mohammad Dhou, Salam Biomedical Engineering Graduate Program American University of Sharjah Sharjah United Arab Emirates Department of Computer Science and Engineering American University of Sharjah Sharjah United Arab Emirates

ISBN: (纸本)9798350393118

The human brain can effortlessly imagine a 3D image from only 2D images with a little expertise and imagination, but for machines, this is not a trivial task. Because of this, reconstructing 3D images from 2D ones is a hot topic and has many applications. In this paper, we propose a Generative Adversarial Network (GAN)-based approach that generates CT-like images using pairs of orthogonal X-ray projections taken from different angles. In this work, a variety of orthogonal pairs from different angles, ranging from 0 &90 to 60 &150, were considered as input to the 3D image generation model. The effectiveness of the proposed method was assessed by measuring the Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR), which resulted in values of 0.641 and 29.21, respectively. Furthermore, the model's ability to capture the respiratory motion in the input projections and reflect it in the generated images was also assessed. This work demonstrated the feasibility of generating CT-like images from X-ray projections captured from different orthogonal angles taking into consideration the respiratory motion exhibited in these projections. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Domain Aware Multi-task Pretraining of 3D Swin Transformer for T1-Weighted Brain MRI 17th

Domain Aware Multi-task Pretraining of 3D Swin Transformer ...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Kim, Jonghun Kim, Mansu Park, Hyunjin Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of Center for Neuroscience Imaging Research Institute for Basic Science Suwon Korea Republic of AI Graduate School Gwangju Institute of Science and Technology Gwangju Korea Republic of

ISBN: (纸本)9789819609000

The scarcity of annotated medical images is a major bottleneck in developing learning models for medical image analysis. Hence, recent studies have focused on pretrained models with fewer annotation requirements that can be fine-tuned for various downstream tasks. However, existing approaches are mainly 3D adaptions of 2D approaches ill-suited for 3D medical imaging data. Motivated by this gap, we propose novel domain-aware multi-task learning tasks to pretrain a 3D Swin Transformer for brain magnetic resonance imaging (MRI). Our method considers the domain knowledge in brain MRI by incorporating brain anatomy and morphology as well as standard pretext tasks adapted for 3D imaging in a contrastive learning setting. We pretrain our model using large-scale brain MRI data of 13,687 samples spanning several large-scale databases. Our method outperforms existing supervised and self-supervised methods in three downstream tasks of Alzheimer’s disease classification, Parkinson’s disease classification, and age prediction tasks. The ablation study of the proposed pretext tasks shows the effectiveness of our pretext tasks. Our code is available at ***/jongdory/DAMT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Deterministic inverse design of spectral line shapes using thin-film-based Fano resonators

Deterministic inverse design of spectral line shapes using t...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Yoo, Young Jin Ko, Joo Hwan Park, Jin-Hwi Jeon, Hae-Gon Song, Young Min School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of AI Graduate School Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of

We present an inverse design approach for spectral line shapes using thin-film-based Fano resonators. Stochastic gradient descent (SGD)-based learning provides CMOS-compatible process parameters for spectral line shap... 详细信息

ISBN: (纸本)9781957171258

关键词： Resonators

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：