检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2024年第2期9卷 1119-1133页

作者： Huang, Jia-Yan Xu, Xin-Xin Luo, Shao-Ye Zhao, Wan-Qi Fan, Hao-Yi Grau, Antoni Guerra, Edmundo Wang, Chuan-Sheng Zhang, Fu-Quan New Engineering Industry College Putian University Putian351100 China The University of Sheffield SheffieldS10 2TN United Kingdom School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China Department of Automatic Control Technical Polytechnic University of Catalonia Barcelona08034 Spain Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

Image dehazing is an important research topic and hotspot in the fields of image processing and computer vision. Therefore, evaluating the performance of image dehazing algorithms has become an import research issue. However, current image quality assessment (IQA) algorithms only judge the final dehazed image and do not give an analysis of the capabilities of the image dehazing algorithm. In order to fill this gap, we propose an image dehazing quality assessment method that integrated the dark channel prior with image depth estimation. The proposed method first uses the dark channel prior to estimate the absolute amount of haze removed from each pixel as an indication of the performance of dehazing. Then, a dual-scale variance ratio method is introduced to estimate the scene depth of the image. Finally, the relative dehazing is calculated from the obtained absolute dehazing and the image depth to represent the capability of the dehazing algorithm. The method proposed in this paper first introduces the concepts of relative and absolute dehazing quantities, along with pioneering a pixel-level evaluation of dehazing outcomes. Extensive experiments show that the algorithm proposed in this paper is more in line with human subjective judgment than other IQA algorithms. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Fault-tolerant architecture for Cache: Summaries, Assessments and Trends 4

Fault-tolerant architecture for Cache: Summaries, Assessment...

引用

2021 4th International Conference on Mechatronics and computer Technology engineering, MCTE 2021

作者： Wang, Xuru Gao, Xin Liang, Zongnan Nian, Jiawei Liu, Hongjin Beijing Institute of Control Engineering Beijing100090 China Beijing SunWise Space Technology Ltd Beijing100090 China School of Computer Science and Technology Xidian University Shanxi Xi'an710071 China

Fault-tolerant design of cache is a key aspect of highly reliable processor design. In this paper, based on the key metrics in Cache architecture design: reliability, power consumption, latency and area, we divided the related research into two categories: one is to maximize reliability with guaranteed latency, power consumption and area, the other is to minimize latency, power consumption and area loss while ensuring fault tolerance reliability. Based on the classification, by analyzing different studies of Data and Tag in Cache, this paper gives the characteristics of these methods and the future development trend. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

An industrial implementation of a C4 hydrocarbon soft sensor to optimise a debutaniser column

引用

IFAC-PapersOnLine 2021年第21期54卷 180-185页

作者： Stefan Botha Ian K. Craig Analyte Control Pretoria South Africa Department of Electrical Electronic and Computer Engineering University of Pretoria Pretoria South Africa

The bottoms product of a debutaniser column in a Fischer-Tropsch refining catpoly unit should be maximised to ensure optimal operation of the downstream units. An accurate estimate of the C4 hydrocarbons in the bottoms product is required to ensure that the specification is not violated. This work demonstrates a practical implementation of a soft sensor to estimate the %C4 material in the bottoms product of the debutaniser using the General Distillation Shortcut (GDS) method and a random forest (RF) machine learned model. The paper highlights practical challenges when deploying a soft sensor to an industrial plant. It is shown how the GDS method soft sensor had to be refitted after unit maintenance was carried out. In comparison the RF model soft sensor uses more reliable measurements and did not require refitting after unit commissioning. Both soft sensors performed well and the choice of soft sensor depends on the available measurements and measurement reliability.

关键词： industrial applications of process control machine learning petrochemical refining random forests soft sensor

来源：评论

学校读者我要写书评

暂无评论

On the Gaussian Filtering for Nonlinear Dynamic Systems Using Variational Inference

On the Gaussian Filtering for Nonlinear Dynamic Systems Usin...

引用

International Conference on Information Fusion

作者： Yi Liu Xi Li Le Yang Lyudmila Mihaylova Ji Li Department of Electrical and Computer Engineering University of Canterbury Christchurch NZ State Key Lab of Complex Electromagnetic Environment Effects on Electronics and Information Systems National University of Defense Technology Changsha China Department of Automatic Control and System Engineering University of Sheffield Sheffield UK Locaris Electronic Technology Co. Ltd Zhengzhou China

ISBN: (数字)9781737749769

ISBN: (纸本)9798350371420

This paper introduces a new variational Gaussian filtering approach for estimating the state of a nonlinear dynamic system. We first assume that the predictive distribution of the state is Gaussian and derive an iterative method for updating the state posterior in the natural parameter space through KullbackLeibler divergence minimization. The obtained update rule is the same as that of the conjugate-computation variational inference technique in Bayesian learning. The derivation here is simpler and more insightful. We then impose a Wishart prior on the inverse of the state prediction covariance to take into account the impact of approximating the state predictive distribution using a Gaussian density on the state posterior estimation. The prediction covariance is identified jointly with the state using variational inference and the established state posterior update rule to achieve the desired Gaussian filtering. Simulation study examines the performance of the proposed filtering framework in target tracking based on bearing and range measurements.

关键词： Target tracking Smoothing methods Filtering Estimation Filtering algorithms Prediction algorithms Minimization Nonlinear dynamical systems Bayes methods Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Generalized Cauchy–Riemann Equations with Power-law Singularities in Coefficients of Lower Order

Generalized Cauchy–Riemann Equations with Power-law Singula...

引用

International Scientific Conference on Modern Methods, Problems and Applications of Operator Theory and Harmonic Analysis, OTHA 2020

作者： Soldatov, A.P. Rasulov, A.B. Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Center for Fundamental and Applied Mathematics Moscow Russia National Research University "Moscow Power Engineering Institute" Moscow Russia

ISBN: (纸本)9783030774929

The generalized Cauchy-Riemann equation uz¯+ au+ bū= f is considered with coefficients having power singularities at the origin. More exactly it is assumed that a(z) = O(|z|−α−1), α∈ , and b(z) = O(|z|−1) as z → 0. With the help of so called modified Pompeiu integral a general solution of this equation is described. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Integral equations

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Particle Flow Energy Distribution Using Deep Learning Algorithms

arXiv

引用

arXiv 2024年

作者： Zhang, Han Lin, Shengxiang Zhang, Xingyi Wang, Yu Zhang, Yangguang College of Aritificial Intelligence and Automation Hohai University Nanjing211100 China Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an710049 China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China School of Control and Computer Engineering North China Electric Power University Beijing071003 China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China

In high-energy particle physics, extracting information from complex detector signals is crucial for energy reconstruction. Recent advancements involve using deep learning to process calorimeter images from various sub-detectors in experiments like the Large Hadron Collider (LHC) for energy map reconstruction. This paper compares classical algorithms—MLP, CNN, U-Net, and RNN—with variants that include self-attention and 3D convolution modules to evaluate their effectiveness in reconstructing the initial energy distribution. Additionally, a test dataset of jet events is utilized to analyze and compare models’ performance in handling anomalous high-energy events. The analysis highlights the effectiveness of deep learning techniques for energy image reconstruction and explores their potential in this area. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Model of decentralized cross-chain energy trading for power systems

引用

Global Energy Interconnection 2021年第3期4卷 324-334页

作者： Shaomin Zhang Cong Hou School of Control and Computer Engineering North China Electric Power UniversityEngineering Research Center of Intelligent Computing for Complex Energy SystemsMinistry of EducationHebei Baoding 071003P.R.China

With the development of the energy Internet, more distributed generators are connected to the power grid, resulting in numerous heterogeneous energy networks. However, different energy networks cannot perform efficient energy trading in the centralized management mode, this deeply affecting the complementary ability of heterogeneous energy, resulting in the islanded energy phenomenon. In this model, the same energy on the chain is traded within the chain, and the heterogeneous energy on different chains is traded across chains. To trade energy between heterogeneous energy networks more efficiently, the blockchain-based cross-chain model is proposed based on the existing infrastructure. Heterogeneous energy nodes are assigned to different energy sub-chains and cross-chain energy transactions are performed through a relay-chain, which utilizes the improved Boneh–Lynn–Shacham signature scheme consensus algorithm based on the proof-of-stake and practical Byzantine fault tolerance. The experimental simulations on energy trading efficiency, throughput, and security, show its superiority over existing systems. Further, the simulation results provide a reference for the application of cross-chain technology in energy interconnection.

关键词： Energy internet Blockchain Cross-chain transaction Distributed generation Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of miRNA and Disease Association based on Graph Convolution Network using Latent Feature Vector by Positive Samples

Prediction of miRNA and Disease Association based on Graph C...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jiancheng Zhong Jiedong Kang Xingran Song Qiu Xiao Yi Pan School of Information Science and Engineering Hunan Normal University Changsha China School of Computer Science and Control Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen Guangdong China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

The traditional approach of wet biological experiments tends to reveal whether there is an association between specific miRNA molecules and diseases, resulting in a lack of reliable negative samples of miRNA-disease associations in existing databases. To deal with the problem that many current computational methods treat unknown miRNA-disease associations in benchmark datasets as negative samples directly, we propose a graph convolutional neural network model, named DNMFGCN-MDA, based on feature extractions of positive samples. Firstly, by only using a dynamic matrix with positive samples, we extracted the potential feature vectors U and V of miRNAs and diseases in low-dimensional space. Then, we combined known miRNA-disease associations with potential feature vectors U and V to construct heterogeneous graph neural networks. Finally, we adopted graph convolutional neural networks to learn the structural features of the heterogeneous graph network and predicted the potential miRNA-disease associations by using linkage prediction. We use a 5-fold cross-validation experiment to evaluate the performance of our mode, and it turns out that our model has an average AUC of 95.23% and 96.07% on the HMDD v2.0 and HMDD v3.2 datasets, respectively, and achieves better-associated performance than that of the comparison method.

关键词： Couplings Databases Predictive models Benchmark testing Feature extraction Graph neural networks Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Edge Data Based Trailer Inception Probabilistic Matrix Factorization for Context-Aware Movie Recommendation

arXiv

引用

arXiv 2022年

作者： Chen, Honglong Li, Zhe Wang, Zhu Ni, Zhichen Li, Junjian Xu, Ge Aziz, Abdul Xia, Feng College of Control Science and Engineering China University of Petroleum Qingdao266580 China College of Computer and Control Engineering Minjiang University Fuzhou350108 China School of Software Dalian University of Technology Dalian116620 China School of Engineering IT and Physical Sciences Federation University Australia BallaratVIC3353 Australia

The rapid growth of edge data generated by mobile devices and applications deployed at the edge of the network has exacerbated the problem of information overload. As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data. The visual information in the movie trailer is a significant part of the movie recommender system. However, due to the complexity of visual information extraction, data sparsity cannot be remarkably alleviated by merely using the rough visual features to improve the rating prediction accuracy. Fortunately, the convolutional neural network can be used to extract the visual features precisely. Therefore, the end-to-end neural image caption (NIC) model can be utilized to obtain the textual information describing the visual features of movie trailers. This paper proposes a trailer inception probabilistic matrix factorization model called Ti-PMF, which combines NIC, recurrent convolutional neural network, and probabilistic matrix factorization models as the rating prediction model. We implement the proposed Ti-PMF model with extensive experiments on three real-world datasets to validate its effectiveness. The experimental results illustrate that the proposed Ti-PMF outperforms the existing ones. Copyright © 2022, The Authors. All rights reserved.

关键词： Light trailers

来源：评论

学校读者我要写书评

暂无评论

A New Deep Learning Model for Semi-supervised Soft-sensing of an Industrial Production Process

A New Deep Learning Model for Semi-supervised Soft-sensing o...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： XuDong Shi ChenYu Tian Qi Kang MengChu Zhou HanQiu Bao Jing An Department of Control Science and Engineering Tongji University Shanghai China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai China School of Internet of Things Engineering Jiangnan University Wuxi China School of Software Dalian University of Technology Liaoning China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA School of Electrical and Electronic Engineering Shanghai Institute of Technology Shanghai China

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Soft sensing offers a promising solution for predicting key quality variables in various production industries. One of the major challenges in developing an effective data-driven soft sensor is the scarcity of labeled data and the obstacle of extracting useful information from unlabeled samples. To address this issue, this work proposes a new deep learning-based soft sensor model called a spatiotemporal deep learning network. It leverages an encoder-decoder structure to explicitly exploit the spatial and temporal information in both labeled and unlabeled data, enabling efficient utilization of the latter to facilitate prediction performance. The encoder realizes more detailed spatiotemporal dependencies extraction by the proposed gated recurrent unit-based attention mechanism and the channel-calibration attention-based one. Finally, the extracted spatiotemporal features are fed to a multi-layer perceptron-based prediction head for soft sensor modeling. A mixed form loss is employed in the decoder to train our proposed model which incorporates both labeled and unlabeled data. Experiments are conducted on a real-life industrial process, demonstrating the feasibility and effectiveness of the proposed method.

关键词： Deep learning Attention mechanisms Accuracy Soft sensors Production Predictive models Feature extraction Data models Spatiotemporal phenomena Data mining

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：