检索结果-内蒙古大学图书馆

Smart Grid Conference (SGC)

作者： Mohammad Seyfi Mehdi Mehdinejad Behnam Mohammad-Ivatloo Heidarali Shayanfar Center of Excellence for Power Systems Automation and Operation School of Electrical Engineering Iran University of Science and Technology Tehran Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran

ISBN: (纸本)9781665401661

In this paper, the peer-to-peer energy trading is performed between prosumers with energy surplus in the role of seller and prosumers with energy shortage in the role of buyer. In the proposed model, buyers, in addition to participating in local trading, can supply their demand shortage from the upstream market. These players can also participate in a price-based demand response program in a fully decentralized way to manage their energy and increase their welfare. The proposed problem is a fully decentralized problem that requires a decentralized approach to clear. In this paper, the decentralized alternating direction method of multipliers (ADMM) is used to solve the proposed problem. Numerical studies have been performed on a small distribution system with four sellers and three buyers. Numerical results show that the proposed model is a fully decentralized method, and the proposed approach ensures the convergence of negotiations and trading.

关键词： Demand response Convex functions Peer-to-peer computing Smart grids Numerical models Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Exploring Contextual Representation and Multi-Modality for End-to-End Autonomous Driving

arXiv

引用

arXiv 2022年

作者： Azam, Shoaib Munir, Farzeen Kyrki, Ville Jeon, Moongu Pedrycz, Witold Department of Electrical Engineering and Automation Aalto University Espoo Finland Finnish Center for Artificial Intelligence Finland School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of Department of Electrical and Computer Engineering University of Alberta EdmontonABT6R 2V4 Canada Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia Systems Research Institute Polish Academy of Sciences Warsaw01-447 Poland

Learning contextual and spatial environmental representations enhances autonomous vehicle’s hazard anticipation and decision-making in complex scenarios. Recent perception systems enhance spatial understanding with sensor fusion but often lack full environmental context. Humans, when driving, naturally employ neural maps that integrate various factors such as historical data, situational subtleties, and behavioral predictions of other road users to form a rich contextual understanding of their surroundings. This neural map-based comprehension is integral to making informed decisions on the road. In contrast, even with their significant advancements, autonomous systems have yet to fully harness this depth of human-like contextual understanding. Motivated by this, our work draws inspiration from human driving patterns and seeks to formalize the sensor fusion approach within an end-to-end autonomous driving framework. We introduce a framework that integrates three cameras (left, right, and center) to emulate the human field of view, coupled with top-down bird-eye-view semantic data to enhance contextual representation. The sensor data is fused and encoded using a self-attention mechanism, leading to an auto-regressive waypoint prediction module. We treat feature representation as a sequential problem, employing a vision transformer to distill the contextual interplay between sensor modalities. The efficacy of the proposed method is experimentally evaluated in both open and closed-loop settings. Our method achieves displacement error by 0.67m in open-loop settings, surpassing current methods by 6.9% on the nuScenes dataset. In closed-loop evaluations on CARLA’s Town05 Long and Longest6 benchmarks, the proposed method enhances driving performance, route completion, and reduces infractions. © 2022, CC BY.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

An improved semi-supervised segmentation of the retinal vasculature using curvelet-based contrast adjustment and generalized linear model

引用

Heliyon 2024年第18期10卷 e38027页

作者： Ghislain, Feudjio Beaudelaire, Saha Tchinda Daniel, Tchiotsop Research Unit of Condensed Matter Electronics and Signal Processing (UR-MACETS). Department of Physics Faculty of Sciences University of Dschang P.O. Box 67 Dschang Cameroon Research Unit of Automation and Applied Computer (UR-AIA) Electrical Engineering Department of IUT-FV University of Dschang P.O. Box: 134 Bandjoun Cameroon

Diagnosis of most ophthalmic conditions, such as diabetic retinopathy, generally relies on an effective analysis of retinal blood vessels. Techniques that depend solely on the visual observation of clinicians can be tedious and prone to numerous errors. In this article, we propose a semi-supervised automated approach for segmenting blood vessels in retinal color images. Our method effectively combines some classical filters with a Generalized Linear Model (GLM). We first apply the Curvelet Transform along with the Contrast-Limited Histogram Adaptive Equalization (CLAHE) technique to significantly enhance the contrast of vessels in the retinal image during the preprocessing phase. We then use Gabor transform to extract features from the enhanced image. For retinal vasculature identification, we use a GLM learning model with a simple link identity function. Binarization is then performed using an automatic optimal threshold based on the maximum Youden index. A morphological cleaning operation is applied to remove isolated or unwanted segments from the final segmented image. The proposed model is evaluated using statistical parameters on images from three publicly available databases. We achieve average accuracies of 0.9593, 0.9553 and 0.9643, with Receiver Operating Characteristic (ROC) analysis yielding Area Under Curve (AUC) values of 0.9722, 0.9682 and 0.9767 for the CHASE_DB1, STARE and DRIVE databases, respectively. Compared to some of the best results from similar approaches published recently, our results exceed their performance on several datasets. © 2024 The Authors

关键词： Curvelet transform Gabor filters Generalized linear model Image segmentation Retinal blood vessel

来源：评论

学校读者我要写书评

暂无评论

On the approximation error for approximating convex bodies using multiobjective optimization

arXiv

引用

arXiv 2021年

作者： Löhne, Andreas Zhao, Fangyuan Shao, Lizhen Friedrich Schiller University Jena Faculty of Mathematics and Computer Science Jena Germany University of Science and Technology Beijing School of Automation and Electrical Engineering Beijing China

A polyhedral approximation of a convex body can be calculated by solving approximately an associated multiobjective convex program (MOCP). An MOCP can be solved approximately by Benson type algorithms, which compute outer and inner polyhedral approximations of the problem's upper image. Polyhedral approximations of a convex body can be obtained from polyhedral approximations of the upper image of the associated MOCP. We provide error bounds in terms of the Hausdorff distance for the polyhedral approximations of a convex body in dependence of the stopping criterion of the primal and dual Benson type algorithms which are applied to the associated MOCP. © 2021, CC BY.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Energy-Saving Practice of Variable Frequency Drive Technology in Data Center HVAC System

Energy-Saving Practice of Variable Frequency Drive Technolog...

引用

International Conference on Power and Energy Technology (ICPET)

作者： Chuanxian Ai Jinpeng Yang Rui Chen Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Branch The National Computer Network Emergency Response Technical Team/Coordination Center of China Kunming China Power Dispatch Control Center Guizhou Power Grid Co. Ltd. China Southern Power Grid Co. Ltd Guiyang China

The variable-frequency drive technology (VFD) can modify the motor speed or torque by varying the frequency and voltage of the AC motor input power according to the load demand as a way to save energy. To analyse the energy saving effect of variable-frequency drive technology applied to data centre heating, ventilation, and air conditioning (HVAC) systems, this paper applies VFD technology to data centre fluorine pump-compressor composite air conditioning systems, implements monitoring and analysis of the operational energy efficiency of this system before and after retrofit, and combines the actual application of this technology. The findings indicate that the VFD technology can substantially reduce the number of compressor starts and stops, reduce the compressor start-up inrush current, and improve the power system’s stability. Furthermore, utilising this technology, the HVAC system can effectively synchronise with the load and fluctuations in outdoor temperature and humidity, resulting in accurate temperature regulation and optimal utilisation of outdoor cooling resources. This approach can lead to significant energy conservation of up to 42.95% when compared to extreme hot and cold weather conditions. The findings of the study indicate that the utilisation of VFD technology exhibits commendable adaptability and yields favourable outcomes in regions with varying temperature ranges. The minimum PUE value recorded was 1.228.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning based optimal control for constrained nonlinear system via a novel state-dependent transformation

Research Square

引用

Research Square 2021年

作者： Yan, Lei Liu, Zhi Chen, C.L. Philip Zhang, Yun Wu, Zongze School of Automation Guangdong University of Technology Guangdong Guangzhou China Faculty of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China

This paper focus on developing an optimal controller for the strict-feedback nonlinear systems with or without asymmetric time-varying full state constraints. A novel nonlinear state-dependent transformation function is presented, by which the strict-feedback nonlinear systems with state constraints is transformed into a new strict-feedback where the state constraints is implicit in. Optimized backstepping technique is utilized to develop the optimal controller for the new strict-feedback system to track the desired reference signal without the feasibility conditions. Reinforcement learning (RL) is exploited to implement the optimal control in every step, where identifier, critic and action network are used to estimate the unknown system dynamics and generate the control output, respectively. It is theoretically proved that all the signals in the close loop system are bounded and the proposed optimal controller can track the desired signal with or without time-varying asymmetric full state constraints. Two simulation examples are presented demonstrating the efficacy of the proposed scheme. © 2021, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Typical curve with G1 constraints for curve completion

引用

Visual Computing for Industry,Biomedicine,and Art 2021年第1期4卷 283-294页

作者： Chuan He Gang Zhao Aizeng Wang Fei Hou Zhanchuan Cai Shaolin Li School of Mechanical Engineering and Automation Beihang UniversityBeijing 100191China State Key Laboratory of Lunar and Planetary Sciences Macao University of Science and TechnologyMacao 999078China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of SciencesBeijing 100049China Faculty of Information Technology Macao University of Science and TechnologyMacao 999078China

This paper presents a novel algorithm for planar G1 interpolation using typical curves with monotonic *** G1 interpolation problem is converted into a system of nonlinear equations and sufficient conditions are provided to check whether there is a *** proposed algorithm was applied to a curve completion *** main advantages of the proposed method are its simple construction,compatibility with NURBS,and monotonic curvature.

关键词： Typical curves Monotonic curvature G1 interpolation Curve completion Euler spiral

来源：评论

学校读者我要写书评

暂无评论

Quantification of Honey Adulteration Using a Planar Microstrip Metamaterial-Motivated Sensor and Software-Defined Radio

引用

IEEE Sensors Journal 2025年

作者： Hasar, Ugur C. Hasar, Hafize Kaya, Yunus Ozturk, Hamdullah Korkmaz, Huseyin Kosunalp, Selahattin Iliev, Teodor Islam, Mohammad Tariqul Nayyeri, Vahid Ramahi, Omar Mustafa Gaziantep University Department of Electrical and Electronics Engineering Gaziantep27310 Turkey Directorate of Provincial Agriculture and Forestry Ministry of Agriculture and Forestry of the Republic of Turkey Gaziantep Turkey Bayburt University Department of Electronics and Automation Bayburt69010 Turkey Gaziantep Islam Science and Technology University Department of Electrical and Electronics Engineering Gaziantep27010 Turkey Bandırma Onyedi Eylül University Department of Computer Technologies Bandırma10200 Turkey University of Ruse "Angel Kanchev" Department of Telecommunication Ruse7017 Bulgaria Faculty of Engineering and Built Environment Department of Electrical Electronic and Systems Engineering Bangi43600 Malaysia Iran University of Science and Technology School of Advanced Technologies Tehran*** Iran University of Waterloo Department of Electrical and Computer Engineering ON WaterlooN2L 3G1 Canada

This work presents the application of a planar microstrip metamaterial (MM)- motivated sensor in the form of a split-ring resonator (SRR) for the detection and quantification of water adulteration in honey samples. The proposed sensor utilizes inexpensive software-defined radio (SDR) measurements, offering a cost-effective solution. Unlike previous MM sensors employing SRR configuration, our proposed MM-motivated sensor is integrated with a microstrip feedline and an additional vertical bar, enhancing its sensing capability. To enable accurate measurements, a simple calibration procedure based on baseline normalization is implemented, allowing for amplitude-only transmission measurements (|S21|) using the SDR. A special sample holder was designed to increase repeatability of measurements. We separately employ two post-processing techniques, namely the rolling average (RA) approach and the Savitzky-Golay (SG) filter, to effectively eliminate ripples in the measured |S21| data obtained from the SDR. For validation and evaluation of the proposed sensor and post-processing techniques, measurements of flower honey samples with water adulteration levels (δ) up to 10% (mass-to-mass basis) were also performed using a vector network analyzer. The resonance frequency of |S21| is utilized as the basis for analysis. We establish a metric function (linear function) that correlates the shift in resonance frequency with the δ. It is observed that this function fits to measured resonance frequency values with an R2 value greater than 0.96 for both post-processing techniques with or without the sample holder. By inverting this function, we can predict δ with considerable accuracy for a given resonance frequency by using another linear function. It is observed that percentage variations between predicted and measured δ values are between 1.54% and 6.46% for testing samples with δ = 5% and δ = 7%. © 2001-2012 IEEE.

关键词： Adulteration honey metamaterials microwaves planar structures rolling average Savitzky-Golay filter sensors water

来源：评论

学校读者我要写书评

暂无评论

Self-Knowledge Distillation from Target-Embedding AutoEncoder for Multi-Label Classification

Self-Knowledge Distillation from Target-Embedding AutoEncode...

引用

IEEE International Conference on Big Knowledge (ICBK)

作者： Qizheng Pan Ming Yan Guoqi Li Jianmin Li Ying Ma College of Computer and Information Engineering Xiamen University of Technology Xiamen China Institute of High Performance Computing Agency for Science Technology and Research Singapore Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Computing Harbin Institute of Technology Harbin China

Target-Embedding Autoencoder (TEA) has been successfully utilized in Multi-Label Classification (MLC), where each instance is associated with multiple labels. However, most existing TEA-based approaches mainly focus on the latent space alignment in their encoding phase, ignoring the output bias induced by overfitting in the training process. To address this issue, we provide a new approach named Self-Knowledge Distillation from TEA (SKDTEA) by removing the latent space alignment of TEA-based solutions with self-knowledge distillation in a simple yet effective manner. Unlike conventional self-knowledge distillation in multi-class learning, our SKDTEA leverages self-knowledge distillation by fully exploring the relationship between label smoothing and knowledge distillation. Specifically, an auxiliary module of SKDTEA is designed for ground-truth targets reconstruction, which outputs the recovered outputs as knowledge in a learned multi-label smoothing manner. The whole distillation process provides an efficient regularization to alleviate the overfitting issue in the training process. As far as we know, we are the first attempt to introduce the self-knowledge distillation into TEA-based approaches for the MLC. Experimental results demonstrate our proposed method achieves significant superiority over the well-established approaches in MLC.

关键词： Training Smoothing methods Encoding Decoding Standards

来源：评论

学校读者我要写书评

暂无评论

Generalized Implicit Neural Representation for Efficient MRI Parallel Imaging Reconstruction

arXiv

引用

arXiv 2023年

作者： Li, Hao Zhou, Yusheng Liu, Jianan Liu, Xiling Huang, Tao Lyu, Zhihan Cai, Weidong Chen, Wei Department of Neuroradiology University Hospital Heidelberg Heidelberg Germany School of Electrical Engineering and Automation Wuhan University Wuhan China Momoni AI Gothenburg Sweden Department of Stomatology Shenzhen People's Hospital Shenzhen China College of Science and Engineering James Cook University SmithfieldQLD4878 Australia Department of Game Design Faculty of Arts Uppsala University Sweden School of Computer Science University of Sydney Sydney Australia School of Biomedical Engineering The University of Sydney Camperdown Australia

High-resolution magnetic resonance imaging (MRI) is essential in clinical diagnosis. However, its long acquisition time remains a critical issue. Parallel imaging (PI) is a common approach to reduce acquisition time by periodically skipping specific k-space lines and reconstructing images from undersampled data. This study presents a generalized implicit neural representation (INR)- based framework for MRI PI reconstruction, addressing limitations commonly encountered in conventional methods, such as subject-specific or undersampling scale-specific requirements and long reconstruction time. The proposed method overcomes these limitations by leveraging prior knowledge of voxel-specific features and integrating a novel scale-embedded encoder module. This encoder generates scale-independent voxel-specific features from undersampled images, enabling robust reconstruction across various undersampling scales without requiring retraining for each specific scale or subject. The framework's INR model treats fully sampled MR images as a continuous function of spatial coordinates and prior voxel-specific features, efficiently reconstructing high-quality MR images from undersampled data. Extensive experiments on publicly available MRI datasets demonstrate the superior performance of the proposed method in reconstructing images at multiple acceleration factors (4×, 5×, and 6×), achieving higher evaluation metrics and visual fidelity compared to stateof- the-art methods. In terms of efficiency, this INR-based approach exhibits notable advantages, including reduced floating point operations and GPU usage, allowing for accelerated processing times while maintaining high reconstruction quality. The generalized design of the model significantly reduces computational resources and time consumption, making it more suitable for real-time clinical applications. The proposed framework represents a promising solution for faster and more flexible MRI acquisition, capable of enhancing the cl

关键词： Magnetic resonance imaging

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：