检索结果-内蒙古大学图书馆

A deep reinforcement learning model with plan value network for join order selection

International Journal of Wireless and Mobile Computing 2021年第4期21卷 365-374页

作者： Qiao, Yifan Wei, Shengjie Gao, Ruiwei Han, Nan Qiao, Shaojie Song, Haiquan Chu Kochen Honors College Zhejiang University Zhejiang Hangzhou China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Sichuan Chengdu China School of Software Engineering Chengdu University of Information Technology Sichuan Chengdu China School of Energy Power and Mechanical Engineering North China Electric Power University Baoding Beijing071003 China

The existing optimisers and dynamic programming methods rely on the cardinality estimation and the cost model of the local database. The resulting join plan does not reflect the execution time, and the errors of cardinality estimation will also lead to the join plans with poor quality. We propose a new learning optimiser, called DVJ (Deep reinforcement learning with plan Value networks for Join order selection). Compared with the existing deep reinforcement learning method, DVJ has two improvements: (1) the plan value network is designed to improve the reward mechanism in the existing deep reinforcement learning method, and the join plan generated by DVJ can reflect the latency;(2) applying Deep Q-Network to reduce the optimisation time and increase the chance of finding the best connection plan. Extensive experiments are conducted and the experimental results demonstrate that DVJ outperforms traditional optimisers and the existing deep reinforcement learning methods. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

The Discussion of Construction Method for Minimum Interval Radius-Based Interval Process Model

The Discussion of Construction Method for Minimum Interval R...

引用

International Conference on Applied Nonlinear Dynamics, Vibration and Control, ICANDVC 2024

作者： Yang, Yuxiang Li, Chen Hu, Haixiang Wu, Feng Yan, Jun State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment School of Mechanics and Aerospace Engineering Dalian University of Technology Liaoning Dalian116024 China China Nuclear Power Technology Research Institute Co. Ltd. Beijing518031 China

ISBN: (纸本)9789819633166

In practical engineering, the extensive presence of time-variant uncertainty significantly affects structural safety. To efficiently and accurately describe the time-variant uncertainty variables with few samples and insufficient information, a minimum interval radius-based interval process model (MIR-IPM) is proposed. The construction of MIR-IPM involves establishing the corresponding ellipsoid to envelope all measured samples with the minimum interval radius. Thus, it is equivalent to solving a large-scale optimization problem. This paper further uses the coordinate transformation to reduce the dimension of samples, thereby reducing the number of optimization variables and improving the construction efficiency. At last, numerical experiments have verified the efficiency and accuracy of the proposed method in describing the time-variant uncertainty variables with few samples. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Safety engineering

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Rail Surface Defect Detection Method

Unsupervised Rail Surface Defect Detection Method

引用

International Symposium on Environmentally Conscious Design and Inverse Manufacturing (EcoDesign)

作者： ChenYu Zhao Yi Han Ningkang Ouyang YiFan Zhao School of Artificial Intelligence Zhengzhou Software Vocational and Technical College Zhengzhou China Department of Computer Science and Information Anyang Institute of Technology Engineering Anyang China School of Information Engineering North China University of Water Resources and Electric Power Zhengzhou China

ISBN: (数字)9798350363043

ISBN: (纸本)9798350363050

Railroad travel has become an essential part of modern life, therefore, rail surface defect detection has become a problem that cannot be ignored. However, most of the currently existing methods often require a large number of defect samples for learning, which are labor-intensive and very difficult to obtain. In order to alleviate the data dependence of the detection model, this paper proposes an unsupervised method. Specifically, we use Transformer’s attention mechanism to construct the encoder-decoder structure and train it only on normal samples with the purpose of reconstruction, so that those regions that cannot be reconstructed will be regarded as defects at the time of detection. To prevent the model from generalizing its generalization ability to those unknown defective samples, i.e., to avoid overgeneralization, we introduce a noise perturbation in the training so that the model focuses on the reconstruction of normal features. Experiments show that the proposed unsupervised approach outperforms a host of supervised models with low data requirements and can effectively address the current challenges of track defect detection.

关键词： Rails Surface reconstruction Perturbation methods Noise Transformers Data models Decoding Image reconstruction Unsupervised learning Defect detection

来源：评论

学校读者我要写书评

暂无评论

Achieving Efficient and Accurate Segmentation for Autonomous Driving

Achieving Efficient and Accurate Segmentation for Autonomous...

引用

International Symposium on Environmentally Conscious Design and Inverse Manufacturing (EcoDesign)

作者： Ningkang Ouyang Jie Dong Yi Han ChenYu Zhao School of Information Engineering North China University of Water Resources and Electric Power Zhengzhou China Department of Computer Science and Information Anyang Institute of Technology Engineering Anyang China School of Artificial Intelligence Zhengzhou Software Vocational and Technical College Zhengzhou China

ISBN: (数字)9798350363043

ISBN: (纸本)9798350363050

Autonomous driving technology, as a mainstream trend in today’s technological development, holds significant commercial value. Semantic segmentation, a core technology in this field, faces challenges with current mainstream models due to their complex structures, large numbers of parameters, and the need for high-performance hardware. These issues hinder their application in mobile devices. Therefore, this paper proposes a road scene semantic segmentation algorithm based on dynamic asymmetric convolution and capsule networks, named Asymmetric Capsule Convolutional Networks (ACCN). Specifically, the algorithm uses dynamic asymmetric convolution to construct a baseline network that combines dynamic convolution and capsule dynamic routing algorithms to enhance the model’s representational capabilities. Additionally, a dispersed attention module is built to strengthen the dependency between features to achieve more adaptable network weights. Experiments demonstrate that ACCN achieves a good balance between segmentation accuracy and detection speed. On the CamVid and Cityscapes test datasets, the proposed method in this paper achieved an average Intersection over Union (mIoU) of $\mathbf{8 0. 8\%}$ at 55.2 fps, showcasing better trade-offs in segmentation accuracy and efficiency. The experimental results indicate the effectiveness of our method.

关键词： Accuracy Convolution Heuristic algorithms Semantic segmentation Roads Routing Hardware Mobile handsets Vehicle dynamics Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Designing a Model for Predicting Asthma in Adolescent Using Map Reduce and Federated Learning

Designing a Model for Predicting Asthma in Adolescent Using ...

引用

Science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Raphael Henshaw Ekpo Victor Chukwudi Osamor Ambrose A. Azeta Kayode Akindeji Adeyinka Elizabeth Orelaja Department of Computer and Information Sciences Covenant University Ota Ogun State Nigeria Department of Software Engineering Namibia University of Science and Technology Windhoek Namibia Department of Electrical Power Engineering Faculty of Engineering and The Built Environment Durban University of Technology South Africa Department of Computer Science and Quantitative Methods Clarksville Tennesse U.S.A

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

This study aims at designing Map Reduce and federated learning-based asthma prediction model for adolescent to provide answers to the problems associated with the existing asthma prediction model for adolescent. This study leveraged on two diverse datasets: the Nigerian Hospital Asthma dataset and the National Survey of Children Health dataset for benchmarking purposes. Symmetrical uncertainty and normalization interaction were employed for feature selection. The model was trained using Federated Artificial Intelligence (AI) technology Enabler (FATE) and complemented with XGBoost model and one central server for federated algorithm averaging. The study was implemented with python programming language on Google Collaboratory environment. The results of the analysis showed considerable high accuracy of 0.98, precision (0.98%), recall (0.98%) and F1-socre (0.99%) for the asthmatic class and precision of 0.98%, recall of 0.98%, as well as F1-score of 0.99% for the non-asthmatic class. The implemented model was benchmark with the existing asthma prediction models in the literature. Simulated attack was also performed using implemented model with and without Map Reduce. This study concludes that the researchers’ model has the potentials to outperform some of the existing machine learning models on asthma prediction in adolescent, thereby facilitating collaborative sharing of the model with other hospitals, protect the patient information from leakage, meeting the criteria of healthcare data protection regulation as well as beneficial for enhancing the security of the dataset.

关键词： Surveys Pediatrics Hospitals Computational modeling Predictive models Benchmark testing Data models

来源：评论

学校读者我要写书评

暂无评论

Fusionngfpe: An Image Fusion Approach Driven by Non-Global Fuzzy Pre-Enhancement Framework

SSRN

引用

SSRN 2024年

作者： Zhang, Xiangbo Liu, Gang Li, Mingyi Ren, Qin Tang, Haojie Bavirisetti, Durga Prasad School of Automation Engineering Shanghai University of Electric Power Shanghai201306 China School of Environmental Science and Engineering Southwest Jiaotong University Chengdu610000 China School of Software and Microelectronics Peking University Beijing100000 China Department of Computer Science Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Trondheim7034 Norway

The majority of prevailing image fusion methods employ a global strategy, often resulting in a reduction of contrast. In this study, we propose an image fusion approach (FusionNGFPE), specifically tailored to the structural characteristics of infrared (IR) imagery. We introduce a contrast equalization algorithm based on the Fourth-order Partial Differential Equation (FPDE) to effectively enhance background regions. Recognizing the inherent disparities between IR and visible (VIS) images, we devise a hybrid fusion strategy leveraging the Expectation Maximization algorithm (EM) and Principal Component Analysis algorithm (PCA). Comparative analysis against state-of-the-art fusion methods demonstrates the superior performance of our proposed algorithm in both qualitative and quantitative assessments. Additionally, to assess the practical applicability of FusionNGFPE, we integrate the fusion framework into the RGBT target tracking task utilizing the VOT-RGBT and OTCBVS datasets. Through comprehensive comparative experiments, we ascertain that the FusionNGFPE framework seamlessly integrates with the tracking task, significantly enhancing tracking accuracy across diverse scenarios. © 2024, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Residual resampling-based physics-informed neural network for neutron diffusion equations

arXiv

引用

arXiv 2024年

作者： Zhang, Heng He, Yun-Ling Liu, Dong Hang, Qin Yao, He-Min Xiang, Di Chongqing University of Posts and Telecommunications Chongqing400065 China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China CNNC Engineering Research Center of Nuclear Energy Software and Digital Reactor Chengdu610213 China

The neutron diffusion equation plays a pivotal role in the analysis of nuclear reactors. Nevertheless, employing the Physics-Informed Neural Network (PINN) method for its solution entails certain limitations. Traditional PINN approaches often utilize fully connected network (FCN) architecture, which is susceptible to overfitting, training instability, and gradient vanishing issues as the network depth increases. These challenges result in accuracy bottlenecks in the solution. In response to these issues, the Residual-based Resample Physics-Informed Neural Network(R2-PINN) is proposed, which proposes an improved PINN architecture that replaces the FCN with a Convolutional Neural Network with a shortcut(S-CNN), incorporating skip connections to facilitate gradient propagation between network layers. Additionally, the incorporation of the Residual Adaptive Resampling (RAR) mechanism dynamically increases sampling points, enhancing the spatial representation capabilities and overall predictive accuracy of the model. The experimental results illustrate that our approach significantly improves the model’s convergence capability, achieving high-precision predictions of physical fields. In comparison to traditional FCN-based PINN methods, R2-PINN effectively overcomes the limitations inherent in current methods, providing more accurate and robust solutions for neutron diffusion equations. Copyright © 2024, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation of Substation Scenes Using Attention-Based Model 4

Semantic Segmentation of Substation Scenes Using Attention-B...

引用

4th IEEE International Conference on Electronics technology, ICET 2021

作者： Chen, Qian Zhang, Changhua Li, Hao Wan, Naijia Wang, Donghui Xu, Bin University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China University of Electronic Science and Technology of China School of Mechanical and Electrical Engineering Chengdu China Nuclear Power Institute of China Science and Technology on Reactor System Design Technology Laboratory Chengdu China

ISBN: (纸本)9781728176734

Inspection robots are widely used in transformer substation for inspection tasks. In order to complete the task, the robots need to understand and recognize road scenes. However, the transformer substation contains lots of similar and small equipment, which are difficult to recognize. To address this problem, we propose a semantic segmentation model to recognize road scenes. Specifically, our proposed model discriminates the equipment by leveraging multi-view method. We use attention mechanism to strengthen the relationship between pixels that belong to an individual category. Compared with previous methods, our approach achieves a good performance in a new dataset from a transformer substation and shows robustness in recognizing equipment of transformer substation. © 2021 IEEE.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Recognition Method of Metamorphic Relation Identification 13

A Dynamic Recognition Method of Metamorphic Relation Identif...

引用

13th International Conference on Reliability, Maintainability, and Safety, ICRMS 2022

作者： Hong, Jie Zhang, Jie Qiu, Qi Ma, Angang Li, Meng Yan, Shiyu Gong, Helin School of Computing University of South China Hunan Hengyang China Engineering and Technology Research Center Software Evaluation and Testing for Intellectual Equipment of Hunan Province Hunan Hengyang China CNNC Key Laboratory on High Trusted Computing Hunan Hengyang China Nuclear Power Institute of China Science and Technology on Reactor System Design Technology Laboratory Chengdu China

ISBN: (数字)9781665486903

ISBN: (纸本)9781665486903

Metamorphic testing is one of the effective methods to alleviate the test oracle problem. Metamorphic relation is the core of metamorphic testing, and there is no effective automatic identification technology. This paper transforms the metamorphic relation recognition issue into a symbolic expression regression problem. The test input pairs are generated using the preset input pattern, and the output pattern is mined by gene expression programming. After reduction and verification, a valid metamorphic relation is obtained. Experiments show that this method can identify the relation obtained by static analysis and a more significant number. At the same time, compared with existing technologies, it has apparent advantages in effectiveness, reliability, and performance. © 2022 IEEE.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Underwater Image Super-Resolution and Enhancement 4

An Improved Method for Underwater Image Super-Resolution and...

引用

4th IEEE International Conference on Electronics technology, ICET 2021

作者： Li, Hao Zhang, Changhua Wan, Naijia Chen, Qian Wang, Donghun Song, Danrong University of Electronic Science and Technology of China School of Mechanical and Electrical Engineering Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China Technology Laboratory Nuclear Power Institute of China Science and Technology on Reactor System Design Chengdu China

ISBN: (纸本)9781728176734

Underwater object detection and recognition are still challenging because of the degradation caused by the complex underwater imaging environment and lighting conditions. Aiming at the problems of the simultaneous enhancement and super-resolution (SESR), a method with single image super-resolution and enhancement of underwater imagery is proposed. Firstly, an underwater image super-resolution algorithm is proposed to remove blurring, and then an end-to-end underwater image enhancement network is used to compensate for color casts and produce natural color enhancement images. In addition, we verify the effectiveness of the proposed model through qualitative analysis and quantitative experiments and compare the performance with several state-of-the-art models, which show that the proposed method performs better. © 2021 IEEE.

关键词： Image enhancement

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：