检索结果-内蒙古大学图书馆

Smart Grid and Green Energy (ICSGGE), International Conference on

作者： Xin Peng Jingjie Huang Yuxia Hua Cuo Zhang State Key Laboratory of Disaster Prevention & Reduction for Power Grid Changsha University of Science and Technology Changsha China School of Electrical and Computer Engineering The University of Sydney Sydney Australia

ISBN: (数字)9798331542139

ISBN: (纸本)9798331542146

This article provides a concise analysis of the current limitations in PV systems and suggests improving the feasibility of engineering applications through the integration of energy storage devices, thereby establishing a distributed photovoltaic storage system model. Utilizing historical load and photovoltaic data from a company in South China, the study employs optimization programming software to achieve operational economic optimization on a typical day. Furthermore, it explores the economic advantages of the distributed photovoltaic storage system over an extended time scale in practical engineering scenarios.

关键词： Photovoltaic systems Economics Wind energy Tariffs Microgrids Stability analysis Software Smart grids Optimization Energy storage

来源：评论

学校读者我要写书评

暂无评论

Tailoring Highly Confined Electric-field Based Optical Skyrmions

Tailoring Highly Confined Electric-field Based Optical Skyrm...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： J. Chen X. Shen Y. Zeng Q. Zhan School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China Shanghai Key Laboratory of Modern Optical System University of Shanghai for Science and Technology Shanghai China

ISBN: (数字)9798350375909

ISBN: (纸本)9798350375916

Optical skyrmions are quasi-particles with nontrivial topological textures, which hold potential applications in optical information processing, transmission, and storage. There are various three-dimensional physical vectors to construct the optical skyrmions, such as spin skyrmions, Stokes skyrmions, Poynting vector skyrmions, and so on. Here, we present a method to construct tightly focused electric-field skyrmions based on the array antenna radiation theory. A multiple concentric-ring array of dipoles (MCAD) is placed at the focal region of the high numerical aperture (NA) lens to mimic the topological structure of the desired electric field skyrmion, and the radiation pattern of the MCAD is derived to form the incident fields at the pupil planes of the high NA lenses in a 4π focusing setup. The characteristics of the generated focal field are quantitatively evaluated by using the Debye diffraction integral theory. The results demonstrate that two types of electric field vector topologies, i.e., skyrmion and meron, can be created with adjustable polarity, vorticity, and helicity. Additionally, the normal direction of the plane containing the skyrmion or meron can also be customized, increasing the degrees of freedom in tailoring optical skyrmions.

关键词： Electric potential Optical diffraction Information processing Vectors Topology Electric fields Pupils

来源：评论

学校读者我要写书评

暂无评论

MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-Supervised Medical Image Segmentation 48

MPS-AMS: Masked Patches Selection and Adaptive Masking Strat...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wang, Xiangtao Wang, Ruizhi Tian, Biao Zhang, Jiaojiao Zhang, Shuo Chen, Junyang Lukasiewicz, Thomas Xu, Zhenghua Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment School of Health Sciences and Biomedical Engineering Tianjin China Shenzhen China Institute of Logic and Computation Tu Wien Vienna Austria University of Oxford Department of Computer Science Oxford United Kingdom

ISBN: (纸本)9781728163277

Existing self-supervised learning methods based on contrastive learning and masked image modeling have demonstrated impressive performances. However, current masked image modeling methods are mainly utilized in natural images, and their applications in medical images are relatively lacking. Besides, their fixed high masking strategy limits the upper bound of conditional mutual information, and the gradient noise is considerable, making less the learned representation information. Motivated by these limitations, in this paper, we propose masked patches selection and adaptive masking strategy based self-supervised medical image segmentation method, named MPS-AMS. We leverage the masked patches selection strategy to choose masked patches with lesions to obtain more lesion representation information, and the adaptive masking strategy is utilized to help learn more mutual information and improve performance further. Extensive experiments on three public medical image segmentation datasets (BUSI, Hecktor, and Brats2018) show that our proposed method greatly outperforms the state-of-the-art self-supervised baselines. © 2023 IEEE.

关键词： Conditional Entropy Medical Image Segmentation Mutual Information Self-supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Improving Multiple Sclerosis Disease Prediction Using Hybrid Deep Learning Model

引用

computers, Materials & Continua 2024年第10期81卷 643-661页

作者： Stephen Ojo Moez Krichen Meznah A.Alamro Alaeddine Mihoub Gabriel Avelino Sampedro Jaroslava Kniezova Department of Electrical and Computer Engineering College of EngineeringAnderson UniversityAndersonSC 29621USA Faculty of Computing and Information Al-Baha UniversityAl-Baha65528Saudi Arabia ReDCAD Laboratory University of SfaxSfax3038Tunisia Department of Information Technology College of Computer&Information SciencePrincess Nourah Bint Abdul Rahman UniversityRiyadh11564Saudi Arabia Department of Management Information Systems College of Business and EconomicsQassim UniversityP.O.Box 6640Buraidah51452Saudi Arabia School of Management and Information Technology De La Salle-College of Saint BenildeManila1004Philippines Department of Information Management and Business Systems Faculty of ManagementComenius University BratislavaBratislava 2582005Slovakia

Myelin damage and a wide range of symptoms are caused by the immune system targeting the central nervous system in Multiple Sclerosis(MS),a chronic autoimmune neurological *** disrupts signals between the brain and body,causing symptoms including tiredness,muscle weakness,and difficulty with memory and *** methods for detecting MS are less precise and time-consuming,which is a major gap in addressing this *** gap has motivated the investigation of new methods to improve MS detection consistency and *** paper proposed a novel approach named FAD consisting of Deep Neural Network(DNN)fused with an Artificial Neural Network(ANN)to detect MS with more efficiency and accuracy,utilizing regularization and combat *** use gene expression data for MS research in the GEO GSE17048 *** dataset is preprocessed by performing encoding,standardization using min-max-scaler,and feature selection using Recursive Feature Elimination with Cross-Validation(RFECV)to optimize and refine the ***,for experimenting with the dataset,another deep-learning hybrid model is integrated with different ML models,including Random Forest(RF),Gradient Boosting(GB),XGBoost(XGB),K-Nearest Neighbors(KNN)and Decision Tree(DT).Results reveal that FAD performed exceptionally well on the dataset,which was evident with an accuracy of 96.55%and an F1-score of 96.71%.The use of the proposed FAD approach helps in achieving remarkable results with better accuracy than previous studies.

关键词： Multi Sclerosis(MS) machine learning deep learning artificial neural network healthcare

来源：评论

学校读者我要写书评

暂无评论

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

arXiv

引用

arXiv 2024年

作者： Shi, Yubin Chen, Yixuan Dong, Mingzhi Yang, Xiaochen Li, Dongsheng Wang, Yujiang Dick, Robert Lv, Qin Zhao, Yingying Yang, Fan Lu, Tun Gu, Ning Shang, Li China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Mathematics Statistics University of Glasgow United Kingdom Microsoft Research Asia Shanghai China Department of Engineering Science University of Oxford United Kingdom Department of Electrical Engineering and Computer Science University of Michigan United States Department of Computer Science University of Colorado Boulder United States School of Microelectronics Fudan University China

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized models to attain a more efficient and fruitful training strategy. Empirical evidence reveals that when scaling down into network modules, such as heads in self-attention models, we can observe varying learning patterns implicitly associated with each module's trainability. To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue λmax. A large λmax indicates that the module learns features with better convergence, while those miniature ones may impact generalization negatively. Inspired by the discovery, we propose a novel training strategy termed Modular Adaptive Training (MAT) to update those modules with their λmax exceeding a dynamic threshold selectively, concentrating the model on learning common features and ignoring those superfluous ones. Unlike most existing training schemes with a complete BP cycle across all network modules, MAT can significantly save computations by its partially-updating strategy and can further improve performance. Experiments show that MAT nearly halves the computational cost of model training and outperforms the accuracy of baselines. © 2024, CC BY.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

An Approach to Evaluate Modeling Adequacy for Small-Signal Stability Analysis of IBR-related SSOs in Multimachine Systems

arXiv

引用

arXiv 2024年

作者： Karunaratne, Lilan Chaudhuri, Nilanjan Ray Yogarathnam, Amirthagunaraj Yue, Meng The School of Electrical Engineering and Computer Science Penn State University University ParkPA United States The Interdisciplinary Science Department Brookhaven National Laboratory UptonNY United States

Time-varying phasor-based analysis of subsynchronous oscillations (SSOs) involving grid-following converters (GFLCs) and its benchmarking with electromagnetic transient (EMT) models have so far been restricted to highly simplified grid models with constant voltage sources behind series R-L circuits. In this paper, modeling adequacy of bulk power systems with synchronous generators (SGs), transmission systems, loads, and GFLCs are considered. To this end, we revisit the notions of time-varying phasor calculus, highlighting the distinction between space-phasor-calculus (SPC) and two often interchangeably used frameworks namely baseband-abc and generalized averaging. We present the models of grids in SPC framework that include transmission line dynamics, load dynamics, and SG stator transients. Next, we propose a generic approach to study modeling adequacy in small-signal sense by (a) identifying critical modes through eigenvalue and singular value analysis followed by (b) using weighted maximum singular value error magnitudes as metrics, and (c) further cross-validation. Using a modified 4-machine IEEE benchmark model with up to 3 GFLCs we show that SPC framework can be used for analysis of SSOs. Further, we consider the quasistationary phasor calculus (QPC) framework that neglects transmission line, load, and SG stator dynamics to show its adequacy in SSO modeling and analysis. Time-domain and frequency-domain results with EMT models are also presented. © 2024, CC BY.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Super-Resolution on Low-Resolution Micro-Expression Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Zhou, Ling Wang, Mingpei Huang, Xiaohua Zheng, Wenming Mao, Qirong Zhao, Guoying Macau University of Science and Technology School of Computer Science and Engineering 999078 China Nanjing Institute of Technology School of International Education Oulu School Jiangsu Nanjing211167 China Southeast University Key Laboratory of Child Development and Learning Science Ministry of Education Nanjing210096 China Southeast University Research Center for Learning Science China Southeast University School of Biological Science and Medical Engineering Jiangsu Nanjing210096 China Jiangsu University School of Computer Science and Communication Engineering Jiangsu Zhenjiang212013 China University of Oulu Center for Machine Vision and Signal Analysis 90014 Finland

Micro-expression recognition (MER) in low-resolution (LR) scenarios presents an important and complex challenge, particularly for practical applications such as group MER in crowded environments. Despite considerable advancements in super-resolution (SR) techniques for enhancing the quality of LR images and videos, few study has focused on investigate SR for improving LR MER. The scarcity of investigation can be attributed to the inherent difficulty in capturing the subtle motions of micro-expressions, even in original-resolution MER samples, which becomes even more challenging in LR samples due to the loss of distinctive features. Furthermore, a lack of systematic benchmarking and thorough analysis of SR-assisted MER methods has been noted. This paper tackles these issues by conducting a series of benchmark experiments that integrate both SR and MER methods, guided by an in-depth literature survey. Specifically, we employ seven cutting-edge state-of-the-art (SOTA) MER techniques and evaluate their performance on samples generated from 22 SOTA SR techniques, thereby addressing the problem of SR in MER. Through our empirical study, we uncover the primary challenges associated with SR-assisted MER and identify avenues to tackle these challenges by leveraging recent advancements in both SR and MER methodologies. Our analysis provides insights for progressing toward more efficient SR-assisted MER. © 2010-2012 IEEE.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Scenario Generation for Cooling,Heating,and Power Loads Using Generative Moment Matching Networks

引用

CSEE Journal of Power and Energy Systems 2022年第6期8卷 1730-1740页

作者： Wenlong Liao Yusen Wang Yuelong Wang Kody Powell Qi Liu Zhe Yang Department of Energy Technology Aalborg UniversityAalborg 9220Denmark School of Electrical Engineering and Computer Science KTH Royal Institute of TechnologyStockholmSE-10044Sweden State Grid Tianjin Chengxi Electric Power Supply Branch Tianjin 300100China Department of Chemical Engineering University of UtahUT 84112America Key Laboratory of Smart Grid of Ministry of Education Tianjin UniversityTianjin 300072China

Scenario generations of cooling,heating,and power loads are of great significance for the economic operation and stability analysis of integrated energy *** this paper,a novel deep generative network is proposed to model cooling,heating,and power load curves based on generative moment matching networks(GMMNs)where an auto-encoder transforms highdimensional load curves into low-dimensional latent variables and the maximum mean discrepancy represents the similarity metrics between the generated samples and the real *** training the model,the new scenarios are generated by feeding Gaussian noises to the scenario generator of the *** the explicit density models,the proposed GMMN does not need to artificially assume the probability distribution of the load curves,which leads to stronger *** simulation results show that the GMMN not only fits the probability distribution of multiclass load curves very well,but also accurately captures the shape(e.g.,large peaks,fast ramps,and fluctuation),frequency-domain characteristics,and temporal-spatial correlations of cooling,heating,and power ***,the energy consumption of generated samples closely resembles that of real samples.

关键词： Deep learning generative moment matching networks integrated energy systems scenario generations

来源：评论

学校读者我要写书评

暂无评论

A Case Study on Modeling Adequacy of a Grid with Subsynchronous Oscillations Involving IBRs

arXiv

引用

arXiv 2024年

作者： Karunaratne, Lilan Chaudhuri, Nilanjan Ray Yogarathnam, Amirthagunaraj Yue, Meng School of Electrical Engineering and Computer Science Pennsylvania State University University ParkPA United States Interdisciplinary Science Department Brookhaven National Laboratory UptonNY United States

A case study on modeling adequacy of a grid in presence of renewable resources based on grid-forming converters (GFCs) is the subject matter of this paper. For this purpose, a 4-machine 11-bus IEEE benchmark model is modified by considering GFCs replacing synchronous generators that led to unstable subsynchronous oscillations (SSOs). We aim to: (a) understand if transmission network dynamics should be considered in such cases, (b) revisit the space-phasor-calculus (SPC) in d-q frame under balanced condition that captures such phenomena and lends itself to eigenvalue analysis, and (c) emphasize limitations of such models while underscoring their importance for large-scale power system simulations. Time-domain and frequency-domain results from SPC and quasistationary phasor calculus (QPC) models are compared with electromagnetic transient (EMT)based simulations. It is shown that models with transmission line dynamics in SPC framework can capture the SSO mode while QPC models that neglect these dynamics fail to do so. © 2024, CC BY.

关键词： Electric power transmission networks

来源：评论

学校读者我要写书评

暂无评论

Flexible Link Adaptation in Fully-Decoupled RAN: A Machine Learning Approach

Flexible Link Adaptation in Fully-Decoupled RAN: A Machine L...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Zou, Xianfeng Zhao, Jiwei Yu, Kai Chen, Jiacheng Zhou, Haibo Shen, Xuemin Sherman Nanjing University School of Electronic Science and Engineering Nanjing210023 China Peng Cheng Laboratory Department of Mathematics and Theories Shenzhen518000 China University of Waterloo Department of Electrical and Computer Engineering 200 University Avenue West WaterlooONN2L 3G1 Canada

ISBN: (纸本)9798350345384

Fully decoupled radio access network (FD-RAN), as an emerging radio access architecture through physical uplink-downlink decoupling and control-data decoupling, has potential in flexible spectrum utilization and network cooperation. However, real-time uplink feedback is challenging in FD-RAN due to the complete physical decoupling of control and data base stations. In this paper, we propose a flexible link adaptation mechanism that leverages outdated channel state information (CSI) to determine the appropriate Modulation and Coding Scheme (MCS) for the user in the FD-RAN downlink. Specifically, we first utilizes kernel recursive least squares to predict the CSI at the future moment. We then select the optimal modulation and coding scheme based on the predicted CSI and the frame error rate estimated by a neural network. Simulation results show that the proposed link adaptation mechanism has a significant throughput performance gain in various scenarios. © 2023 IEEE.

关键词： Radio access 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：