检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhao, Changyuan Du, Hongyang Liu, Guangyuan Niyato, Dusit College of Computing and Data Science Nanyang Technological University Singapore CNRS@CREATE 1 Create Way # 08-01 Create Tower 138602 Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong The Energy Research Institute @ NTU Interdisciplinary Graduate Program Singapore

Score-based generative models can effectively learn the distribution of data by estimating the gradient of the distribution. Due to the multi-step denoising characteristic, researchers have recently considered combining score-based generative models with the gradient boosting algorithm, a multi-step supervised learning algorithm, to solve supervised learning tasks. However, existing generative model algorithms are often limited by the stochastic nature of the models and the long inference time, impacting prediction performances. Therefore, we propose a Supervised Score-based Model (SSM), which can be viewed as a gradient boosting algorithm combining score matching. We provide a theoretical analysis of learning and sampling for SSM to balance inference time and prediction accuracy. Via the ablation experiment in selected examples, we demonstrate the outstanding performances of the proposed techniques. Additionally, we compare our model with other probabilistic models, including Natural Gradient Boosting (NGboost), Classification and Regression Diffusion Models (CARD), Diffusion Boosted Trees (DBT), and non-probabilistic GBM models. The experimental results show that our model outperforms existing models in both accuracy and inference time. © 2024, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive and Fair Deployment Approach to Balance Offload Traffic in Multi-UAV Cellular Networks

arXiv

引用

arXiv 2022年

作者： Lai, Chuan-Chi Bhola Tsai, Ang-Hsun Wang, Li-Chun The Department of Information Engineering and Computer Science Feng Chia University Taichung40724 Taiwan The Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Hsinchu30010 Taiwan The Department of Communications Engineering Feng Chia University Taichung40724 Taiwan The Department of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan

Unmanned aerial vehicle-aided communication (UAB-BS) is a promising solution to establish rapid wireless connectivity in sudden/temporary crowded events because of its more flexibility and mobility features than conventional ground base station (GBS). Because of these benefits, UAV-BSs can easily be deployed at high altitudes to provide more line of sight (LoS) links than GBS. Therefore, users on the ground can obtain more reliable wireless channels. In practice, the mobile nature of the ground user can create uneven user density at different times and spaces. This phenomenon leads to unbalanced user associations among UAV-BSs and may cause frequent UAV-BS overload. We propose a three-dimensional adaptive and fair deployment approach to solve this problem. The proposed approach can jointly optimize the altitude and transmission power of UAV-BS to offload the traffic from overloaded UAV-BSs. The simulation results show that the network performance improves by 37.71% in total capacity, 37.48% in total energy efficiency and 16.12% in the Jain fairness index compared to the straightforward greedy approach. Copyright © 2022, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Electrostatic Shield to Mitigate the High Frequency Circulating Bearing Current - A Study for Design Guidelines

Electrostatic Shield to Mitigate the High Frequency Circulat...

引用

Industrial Applications Society Annual Conference on Petroleum and Chemical Industry

作者： Marco T. A. Êvo Caio Eduardo Silva Isabela O. Zaparoli Hélder De Paula Electrical Engineering Department Federal University of São João del Rei São João del Rei MG Brazil Graduate Program in Electrical Engineering Federal University of Uberlândia Uberlândia MG Brazil Faculty of Electrical Engineering Federal University of Uberlândia Uberlândia MG Brazil

In a previous work, the authors addressed electrostatic shielding to reduce the bearing discharge currents (Electrostatic discharge machining currents - EDM). In order to expand the application of such a shielding device, this paper presents an analysis of its use to reduce the inverter-induced circulating bearing currents on induction machines. Employing finite element analysis (FEA), 2D and 3D models were developed to clarify the tradeoff between the shield effectiveness and the associated additional heat losses and motor efficiency reduction, considering different geometric arrangements and materials for the shielding device construction. The results provide very good guidelines for the shield design, contributing to its practical application viability. It is shown that it is possible to design a shielding configuration that achieves a high mitigating level with a negligible impact on the motor efficiency and developed torque. Furthermore, comparing calculation models of different complexities, the paper also shows the importance of representing all capacitive couplings inside the motor and the non-uniform current distribution in the shield to determine its effectiveness. Since a large fraction of the motor failures are caused by bearing currents, this paper can provide benefits to key topics for industry, such as equipment reliability and availability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Qualitative Comparison between the Brazilian Labeling program for Buildings and the Portuguese Energy Certification System for Buildings:Proposals for Improving Brazilian Regulations

引用

Energy engineering 2021年第3期118卷 615-629页

作者： Jaime Francisco de Sousa Resende Andrea Lucia Teixeira Charbel Teresa Cristina Bessa Nogueira Assunção Graduate Program in Energy Engineering Federal University of São João del ReiSão João del ReiBrazil Department of Thermal and Fluid Sciences Federal University of São João del ReiSão João del ReiBrazil Department of Electrical Engineering Federal University of São João del ReiSão João del ReiBrazil

Buildings represent a significant share of the world’s energy consumption,and the sector has drawn the attention of governments,which have adopted policies to reduce energy *** Certifications of Energy Efficiency in Buildings stand out as one possible solution to achieve this goal,employed in several countries *** European Union presents advanced energy assessment programs for buildings,being a reference and model for several other regulations in the *** Energy Certification System for Buildings(SCE)of Portugal is considered a success case,reflected in the significant number of energy certificates *** Brazilian Labeling program for Building(PBE Edifica),first launched in 2009,does not find a broad application today in the Brazilian *** work shows a synthesis of the European Energy Performance of Buildings Directive(EPBD)and the Brazilian and Portuguese regulations’history.A qualitative comparison is made between the SCE and the PBE Edifica to verify a European and a developing country’s regulations with a certain degree of cultural and climatic *** this comparison,proposals are made for improvements to Brazilian certification,seeking to improve its energy planning and energy policy concerning its building *** suggestions for improvement presented may also be appropriate for other developing countries that have started and have not yet successfully implemented their energy certification programs in buildings.

关键词： Energy efficiency energy policy building labeling energy certification improvement proposals

来源：评论

学校读者我要写书评

暂无评论

Assessing uncertainty in wind turbine electrical power production using Monte-Carlo simulation: A case study on Sidrap wind turbine, Sulawesi - Indonesia

引用

AIP Conference Proceedings 2024年第1期3039卷

作者： Leonard Lisapaly Post Graduate Program Electrical Engineering Department Universitas Kristen Indonesia (UKI) Jakarta Indonesia

As the number of populations worldwide, including Indonesia, increases annually, the need for electrical energy also increases. With fossil-based energy starting to decrease in some places, and the global need to achieve net zero-emission, renewable energy is gaining popularity as the source of electrical power generation, for example, wind energy. electrical power generated from wind turbines is one of the popular choices in many countries; among them is the Sidrap wind turbine plant in Sulawesi, Indonesia. electrical power generated by a wind turbine relies on the wind speed, which varies from time to time and season to season. Therefore, building wind turbines plant should not be based on a deterministic wind speed but should bring the wind speed uncertainty into account. Taking the Sidrap wind turbine plant in Sulawesi, Indonesia, as the case study, this work aims to predict the plant’s average power and uncertainty. This calculation is done by implementing the Monte-Carlo simulation to calculate the production uncertainty. The data used for simulation is public data set between 2004 and 2015, obtained from the EMD International website. The simulation result is then compared to the actual production in 2018 and 2019 for analysis. The result indicates that the product is still in the range estimated using the Monte Carlo simulation. This method can also estimate other electrical power potential and uncertainty in an area before a wind turbine plant is built, given enough data sets containing wind speed variation for years. It is expected that by correctly understanding the uncertainty in electrical power production, the decision-making process to build the plant can be accurately determined.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electrostatic Shielding for Bearing Current Mitigation - An Analysis of its Thermal Impact on the Motor

Electrostatic Shielding for Bearing Current Mitigation - An ...

引用

Industrial Applications Society Annual Conference on Petroleum and Chemical Industry

作者： Marco T. A. Êvo Arismar M. G. Júnior Caio Eduardo Silva Hélder De Paula Electrical Engineering Department Federal University of São João del Rei São João del Rei MG Brazil Graduate Program in Electrical Engineering Federal University of Uberlândia Uberlândia MG Brazil Faculty of Electrical Engineering Federal University of Uberlândia Uberlândia MG Brazil

This work presents a study on the use of electrostatic shields to reduce bearing currents (both Electrostatic discharge machining and circulating currents), focusing on its thermal impact on the motor operation. 2-D finite element models are utilized to analyze the temperature distribution inside the coil winding slot of motors both with and without shielding. The results show that the shielding device can be used with a negligible influence on the temperature rise inside the slot. In addition, it is demonstrated that for some shield configurations, the stator winding eddy current loss can be attenuated. In such cases, the shield presence can also lead to a temperature reduction in the stator conductors. Furthermore, the developed models can be expanded to be used in the analysis of any other motor equipped with this type of solution, aiding the design and implementation of the shielding device. Keeping in mind that the majority of the motor failures are due to bearing problems, this paper contributes to the industry by addressing issues closely related to the reliability topic, such as solutions to increase the motor availability, which is the very case of the shielding device.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EllipsoNet: Deep-learning-enabled optical ellipsometry for complex thin films

arXiv

引用

arXiv 2022年

作者： Wang, Ziyang Lin, Yuxuan Cosmi Zhang, Kunyan Wu, Wenjing Huang, Shengxi Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Department of Electrical Engineering and Computer Sciences University of California BerkeleyCA94720 United States Department of Electrical Engineering The Pennsylvania State University University ParkPA16802 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States

Optical spectroscopy is indispensable for research and development in nanoscience and nanotechnology, microelectronics, energy, and advanced manufacturing. Advanced optical spectroscopy tools often require both specifically designed high-end instrumentation and intricate data analysis techniques. Beyond the common analytical tools, deep learning methods are well suited for interpreting high-dimensional and complicated spectroscopy data. They offer great opportunities to extract subtle and deep information about optical properties of materials with simpler optical setups, which would otherwise require sophisticated instrumentation. In this work, we propose a computational ellipsometry approach based on a conventional tabletop optical microscope and a deep learning model called EllipsoNet. Without any prior knowledge about the multilayer substrates, EllipsoNet can predict the complex refractive indices of thin films on top of these nontrivial substrates from experimentally measured optical reflectance spectra with high accuracies. This task was not feasible previously with traditional reflectometry or ellipsometry methods. Fundamental physical principles, such as the Kramers-Kronig relations, are spontaneously learned by the model without any further training. This approach enables in-operando optical characterization of functional materials within complex photonic structures or optoelectronic devices. © 2022, CC BY.

关键词： Refractive index

来源：评论

学校读者我要写书评

暂无评论

Deep STI: Deep Stochastic Time-series Imputation on Electronic Health Records

Deep STI: Deep Stochastic Time-series Imputation on Electron...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Ming-Che Cheng Yi-Hsien Hsieh Te-Cheng Hsu Tung-Hung Su Che Lin Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan Graduate Institute of Communication Engineering National Taiwan University (NTU) Taipei Taiwan Dept. of Internal Medicine Division of Gastroenterolgy and Hepatology National Taiwan University Hospital Taipei Taiwan Department of Electrical Engineering NTU Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine NTU Taipei Taiwan Smart Medicine and Health Informatics Program NTU Taipei Taiwan

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Electronic Health Records (EHRs) are a cornerstone of modern healthcare analytics, offering rich datasets for various disease analyses through advanced deep learning algorithms. However, the pervasive issue of missing values in EHRs significantly hampers the development and performance of these models. Addressing this challenge is crucial for enhancing clinical decision-making and patient care. Existing methods for handling missing data, ranging from simple imputation to more sophisticated approaches, often fall short of capturing the temporal dynamics inherent in EHRs. To bridge this gap, we introduce the Deep Stochastic Time-series Imputation (Deep STI) algorithm, an innovative end-to-end deep learning model that seamlessly integrates a sequence-to-sequence generative network with a prediction network. Deep STI is designed to leverage the observed time-series data in EHRs, learning to infer missing values from the temporal context with high accuracy. We evaluated Deep STI on the liver cancer data from the National Taiwan University Hospital (NTUH), Taiwan. Our results showed that Deep STI achieved better 5-year hepatocellular carcinoma predictions (19.21% in the area under the precision-recall curve) than extreme gradient boosting (18.15%) and Transformer (18.09%). The ablation study also illustrates the efficacy of our generative architecture design compared to regular imputations. This approach not only promises to improve the reliability of disease analysis in the presence of incomplete data but also sets a new standard for utilizing EHRs in predictive healthcare. Our work aims to advance the field of healthcare analytics and open new avenues for research in deep learning applications to EHRs.

关键词： Deep learning Time series analysis Stochastic processes Predictive models Transformers Imputation Reliability Electronic medical records Standards Diseases

来源：评论

学校读者我要写书评

暂无评论

Utilizing multimodal approach to identify candidate pathways and biomarkers and predicting frailty syndrome in individuals from UK Biobank

引用

GeroScience 2024年第1期46卷 1211-1228页

作者： Tseng, Watson Hua-Sheng Chattopadhyay, Amrita Phan, Nam Nhut Chuang, Eric Y. Lee, Oscar K. Institute of Clinical Medicine National Yang Ming Chiao Tung University Taipei Taiwan Bioinformatics and Biostatistics Core Centers of Genomic and Precision Medicine National Taiwan University Taipei Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics Department of Electrical Engineering National Taiwan University Taipei Taiwan Center for Translational Genomics and Regenerative Medicine China Medical University Hospital Taichung Taiwan Stem Cell Research Center National Yang Ming Chiao Tung University Taipei Taiwan Department of Orthopedics China Medical University Hospital Taichung Taiwan Biomedical Technology and Device Research Laboratories Industrial Technology Research Institute Hsinchu Taiwan

Frailty, a prevalent clinical syndrome in aging adults, is characterized by poor health outcomes, represented via a standardized frailty-phenotype (FP), and Frailty Index (FI). While the relevance of the syndrome is gaining awareness, much remains unclear about its underlying biology. Further elucidation of the genetic determinants and possible underlying mechanisms may help improve patients’ outcomes allowing healthy aging. Genotype, clinical and demographic data of subjects (aged 60–73 years) from UK Biobank were utilized. FP was defined on Fried’s criteria. FI was calculated using electronic-health-records. Genome-wide-association-studies (GWAS) were conducted and polygenic-risk-scores (PRS) were calculated for both FP and FI. Functional analysis provided interpretations of underlying biology. Finally, machine-learning (ML) models were trained using clinical, demographic and PRS towards identifying frail from non-frail individuals. Thirty-one loci were significantly associated with FI accounting for 12% heritability. Seventeen of those were known associations for body-mass-index, coronary diseases, cholesterol-levels, and longevity, while the rest were novel. Significant genes CDKN2B and APOE, previously implicated in aging, were reported to be enriched in lipoprotein-particle-remodeling. Linkage-disequilibrium-regression identified specific regulation in limbic-system, associated with long-term memory and cognitive-function. XGboost was established as the best performing ML model with area-under-curve as 85%, sensitivity and specificity as 0.75 and 0.8, respectively. This study provides novel insights into increased vulnerability and risk stratification of frailty syndrome via a multi-modal approach. The findings suggest frailty as a highly polygenic-trait, enriched in cholesterol-remodeling and metabolism and to be genetically associated with cognitive abilities. ML models utilizing FP and FI + PRS were established that identified frailty-syndrome patients with

关键词： Aging Frailty index (FI) Frailty phenotype (FP) Frailty syndrome GWAS UK-Biobank XGboost

来源：评论

学校读者我要写书评

暂无评论

Full-Duplex Beamforming in the Sub-Terahertz Regime

Full-Duplex Beamforming in the Sub-Terahertz Regime

引用

International Conference on Infrared and Millimeter Waves

作者： Subhajit Karmakar Atsutse Kludze Jacques Doumani Andrey Baydin Junichiro Kono Yasaman Ghasempour Department of Electrical and Computer Engineering Princeton University Princeton NJ USA Department of Electrical and Computer Engineering Rice University Houston TX USA Applied Physics Graduate Program Smalley-Curl Institute Rice University Houston TX USA Smalley-Curl Institute Rice University Houston TX USA Department of Physics and Astronomy Rice University Houston TX USA Department of Material Science and NanoEngineering Rice University Houston TX USA

We propose a novel architecture that realizes full-duplex directional beamforming in the sub-terahertz regime. Our architecture leverages the frequency-controlled beam steering of leaky-wave antenna together with the polarization-dependent response of aligned single-wall carbon nanotubes. We evaluate the performance of this architecture via preliminary experiments.

关键词：

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：