检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Yan, Chenxu Shao, Haijian Zhai, Patrick Jiang, Yingtao Deng, Xing School of Computer Jiangsu University of Science and Technology Zhenjiang212003 China Department of Electrical and Computer Engineering University of Nevada Las VegasNV89154 United States School of Automation Key Laboratory of Measurement and Control for CSE Ministry of Education Southeast University Jiangsu Nanjing210096 China

Because of the dark atmosphere created by YOLO v3's poor detection accuracy, the photographs obtained in reality usually considerably improve the difficulty of target detection tasks in extremely low light settings. Under extremely low light conditions, the YOLOv3 model is used to suggest a high-discrimination target detection approach. Target detection is an essential task in the field of computer vision, in which the image is the source of input, but the image obtained in reality may make the target detection task in extremely low light conditions because of the dark environment and poor-quality imaging equipment, which increases the difficulty of target detection and affects the accuracy of detection. Therefore, based on the above reasons, this paper proposes a high-discrimination target detection method based on the YOLOv3 model under extremely low light conditions. The low light enhancement algorithm based on dehazing algorithm is improved for restraining the part of the transmission rate less than 0.5 in the pixel, to enhance the contrast of the processed images. The improved low light enhancement algorithm is 5.32% higher based on the evaluation index of target detection than the original images. Coiflet wavelet transform is applied to achieve high-discrimination feature extraction of images and decompose the low-frequency features of image information at different resolutions to obtain high-frequency features in the horizontal, vertical, and diagonal directions. The eventually constructed YOLOv3 network has reduced the negative impact of the detected target on the detection accuracy under the illumination change. The results reveal that the target detection method established in this paper has been enhanced by 40.6% on low light photos when compared to the traditional YOLOv3 model, and it still has considerable advantages in comparison to other benchmark approaches in target detection models. © 2022, The Authors. All rights reserved.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Study on subjective perception of S3D image with regular-texture 9

Study on subjective perception of S3D image with regular-tex...

引用

9th IEEE Joint International Information technology and Artificial Intelligence Conference, ITAIC 2020

作者： Su, Zhibin Liu, Bing Li, Weiwei Ren, Hui Huang, Rui Communication University of China School of Information and Communication Engineering Beijing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism CITVC KEHUA CO.LTD. Technology Service Branch Beijing China

With the rapid development of binocular stereo vision technology, S3D images and videos have been widely used in many aspects. However, there are few researches on the detail perception of comfortable experience and stereo sense based on image content with certain disparity. Considering that texture is an important visual information contained in an image, in this paper, we designed the computer-generated S3D images containing two kinds of parallax based on three types of texture distribution and six regular textures for subjective evaluation. The influence of texture features on visual comfort, depth perception and the region of interest were studied through the related data analysis. For comparison with the content of disparities, the 2D images with same texture were designed and rated for assessment. Experimental results have shown that the texture was an important factor affecting the comfort perception. However, only when the subject and the background had texture at the same time, the texture was an important factor affecting the depth perception. The different texture distribution between the main subject and background would cause the change of area of interest and evaluation result. Overall, the larger the area of the texture, the lower the comfort evaluation results, and the higher the depth perception. Our studies will not only confirm the law of perception on S3D images with certain features, but also provide the guide for multidimensional content production and display, which have practical value for the development of S3D image and video technology. © 2020 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Neutronic and Thermaldynamic Analysis on control Drum Failures Accident in Heat Pipe Cooled Reactors

SSRN

引用

SSRN 2023年

作者： Gao, Tianyu Zhou, Tao Huang, Dongli Xue, Chunhui Lu, Huaichang Tang, Jianyu Department of Nuclear Science and Technology School of Energy and Environment Southeast University Jiangsu Nanjing210096 China Institute of Nuclear Thermal-hydraulic Safety and Standardization Jiangsu Nanjing210096 China National Engineering Research Center of Large Power Generation Equipment Safety Operation and Intelligent Measurement and Control Southeast University Jiangsu Nanjing210096 China

This manuscript analyzed the reactor safety of a heat pipe cooled reactor, determining the accident severity in the control drum failure accidents, by calculating the reactivity insertion and radial power distribution with OpenMC, core temperature distribution and actual power density with COMSOL. In addition, this manuscript provides a universal control drum design scheme by changing the shape of the control drum. Results show that the conventional control drum structure has inherent safety characteristics in the case of single control drum failure. When multiple control drums fail, the maximum temperature of reactor core exceeds the designed upperbound, requiring the insertion of safety rod to emergency shut down. In order to reduce the impact of positive reactivity insertion and mitigate the severity of the accident, the control drum absorber and a part of reflector should be designed integratedly as the cylindrical control drums. © 2023, The Authors. All rights reserved.

关键词： Heat pipes

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv5 Detection Algorithm with Pruning and OpenVINO Quantization

An Improved YOLOv5 Detection Algorithm with Pruning and Open...

引用

Chinese Automation Congress (CAC)

作者： Cheng Chen Yahui Gan Zao Han Huan Gao Ang Li Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University NanJing China Nanjing YingQi Intelligent Technology Co. Ltd. Intel Joint Research Institute on Intelligent Edge Computing NanJing China Nanjing YingQi Intelligent Technology Co. Ltd. Intel Joint Research Institute on Intelligent Edge Computing NanJing China

In order to address the problem of current object detection models being too large to be deployed on robot controllers, this paper proposes improvements to YOLOv5 for real-time detection. The YOLOv5s model is pruned at the Batch Normalization (BN) layer, and further optimized using the OpenVINO tool for quantization. The results demonstrate that our improvements effectively improve the model's inference speed while maintaining its accuracy. Compared to the original YOLOv5 model, the pruned model achieves the same accuracy without degradation, with a 36.6% reduction in parameter count and a 35% reduction in weight storage file size. Furthermore, after optimization with OpenVINO, the final model achieves a FPS of 56.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Auction-Promoted Trading for Multiple Federated Learning Services in UAV-Aided Networks

arXiv

引用

arXiv 2022年

作者： Cheng, Zhipeng Liwang, Minghui Xia, Xiaoyu Min, Minghui Wang, Xianbin Du, Xiaojiang Department of Information and Communication Engineering Xiamen University Xiamen China School of Computer Science The University of Adelaide Adelaide Australia School of Information and Control Engineering China University of Mining and Technology Xuzhou China The Xuzhou First People's Hospital Xuzhou China Department of Electrical and Computer Engineering Western University Ontario Canada Department of Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ United States

Federated learning (FL) represents a promising distributed machine learning paradigm that allows smart devices to collaboratively train a shared model via providing local data sets. However, problems considering multiple co-existing FL services and different types of service providers are rarely studied. In this paper, we investigate a multiple FL service trading problem in Unmanned Aerial Vehicle (UAV)-aided networks, where FL service demanders (FLSDs) aim to purchase various data sets from feasible clients (smart devices, e.g., smartphones, smart vehicles), and model aggregation services from UAVs, to fulfill their requirements. An auction-based trading market is established to facilitate the trading among three parties, i.e., FLSDs acting as buyers, distributed located client groups acting as data-sellers, and UAVs acting as UAV-sellers. The proposed auction is formalized as a 0-1 integer programming problem, aiming to maximize the overall buyers' revenue via investigating winner determination and payment rule design. Specifically, since two seller types (data-sellers and UAV-sellers) are considered, an interesting idea integrating seller pair and joint bid is introduced, which turns diverse sellers into virtual seller pairs. Vickrey-Clarke-Groves (VCG)-based, and one-sided matching-based mechanisms are proposed, respectively, where the former achieves the optimal solutions, which, however, is computationally intractable. While the latter can obtain suboptimal solutions that approach to the optimal ones, with low computational complexity, especially upon considering a large number of participants. Significant properties such as truthfulness and individual rationality are comprehensively analyzed for both mechanisms. Extensive experimental results verify the properties and demonstrate that our proposed mechanisms outperform representative methods significantly. © 2022, CC BY-NC-ND.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Sparsity-enhanced Convolutional Neural Network for IoT Cyberattacks Detection

Sparsity-enhanced Convolutional Neural Network for IoT Cyber...

引用

International Conference on Computational Intelligence and Security

作者： Yingyun Kang Yongxin Feng Yongqun Chen Wei Wang School of Information Science and Engineering Shenyang Ligong University Shenyang China Science and Technology on Communication Information Security Control LaboratoryJiaxingChina

ISBN: (纸本)9781665494908

The Internet of Things (IoT) is a collection of interconnected devices that can be linked without the need for human interaction. IoT will have a significant impact on our lives in terms of economics, commerce, and society. IoT network nodes are typically resource-constrained, which makes them attractive targets for cyberattacks. However, due to the unique properties of IoT nodes, current solutions are insufficient to cover the complete security spectrum of IoT networks. A more intelligent IoT network security solution is required. Artificial intelligence is one of the most suited computing paradigms for providing embedded intelligence in IoT and is being used to address various security issues. To detect IoT cyber threats, we introduce a sparsity-enhanced convolutional neural network in this paper. Recently published IoT datasets are used for experiments. The proposed neural network is effective by experimental results and analysis.

关键词： Economics Neurons Network security Convolutional neural networks Internet of Things Computer crime Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Cascade of pressure-driven phase transitions in the topological nodal-line superconductor PbTaSe2

引用

Physical Review B 2022年第6期106卷 L060501-L060501页

作者： Tahir Murtaza Haiyang Yang Jiajia Feng Yi Shen Yongheng Ge Yi Liu Chunqiang Xu Wenhe Jiao Yaokang Lv Christopher J. Ridley Craig L. Bull Pabitra K. Biswas Raman Sankar Wei Zhou Bin Qian Xuefan Jiang Zhenjie Feng Yonghui Zhou Ziming Zhu Zhaorong Yang Xiaofeng Xu Key Laboratory of Quantum Precision Measurement of Zhejiang Province Department of Applied Physics Zhejiang University of Technology Hangzhou 310023 China College of Information Engineering Zhejiang University of Technology Hangzhou 310023 China Anhui Province Key Laboratory of Condensed Matter Physics at Extreme Conditions High Magnetic Field Laboratory Chinese Academy of Sciences Hefei 10 230031 China School of Physics and Key Laboratory of MEMS of the Ministry of Education Southeast University Nanjing 211189 China Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Department of Physics and Synergetic Innovation Center for Quantum Effects and Applications Hunan Normal University Changsha 410081 China College of Chemical Engineering Zhejiang University of Technology Hangzhou 310014 China ISIS Pulsed Neutron and Muon Source STFC Rutherford Appleton Laboratory Harwell Campus Didcot Oxfordshire OX11 0QX United Kingdom School of Chemistry University of Edinburgh David Brewster Road Edinburgh EH9 3FJ United Kingdom Institute of Physics Academia Sinica Nankang Taipei 11529 Taiwan Department of Physics Changshu Institute of Technology Changshu 215500 China Materials Genome Institute Shanghai University Shanghai 200444 China

We report a succession of pressure-tuned structural transitions in the topological nodal-line superconductor PbTaSe2, evidenced from synchrotron x-ray diffraction, elastic neutron scattering, Raman spectroscopy, and electrical transport measurements up to 56 GPa, accompanied by first-principles calculations to uncover the evolution of the underlying electronic structure. In contrast to the previously proposed small shift of the Pb Wyckoff coordinate in the sub-GPa regime, our study reveals that it is rather a transition from P6¯m2 (α phase) to P63mc (β phase), subsequently followed by a transition to P6/mmm (γ phase) at ∼7.5 GPa and to Pmmm (δ phase) at ∼44 GPa. In addition, the first-principles calculations unambiguously demonstrate the multiple types of topological fermions associated with these different pressure-driven structures. Collectively, our results not only present the intriguing structural transitions in this topological PbTaSe2 superconductor, they also provide the impetus to study topological phase transitions and their physical consequences in a broader class of topological materials.

关键词： Phase transitions by order Superconducting phase transition Superconductivity Topological superconductors

来源：评论

学校读者我要写书评

暂无评论

Dynamic space-covered broadcast algorithm based on neighbor-degree in mobile ad hoc wireless networks

Dynamic space-covered broadcast algorithm based on neighbor-...

引用

2020 International Conference on Machine Learning and Intelligent Systems, MLIS 2020

作者： Lou, Qiaoqiao Zhao, Zhijin School of Telecommunication Engineering Hangzhou Dianzi University China State Key Lab of Information Control Technology in Communication System of No.36 Research Institute China Electronic Technology Corporation China

ISBN: (纸本)9781643681368

Broadcast is an important link in mobile ad hoc wireless networks (MANETs). In order to improve broadcast coverage, reduce forwarding probability and broadcast collision, a dynamic space-covered broadcast algorithm based on neighbor-degree in MANETs is proposed. The concepts of neighbor-degree, available-angel and available-distance are introduced. The neighbor-degree is used to generate the initial forwarding probability of a node. Based on the available-angle and available-distance, the node weight is proposed to calculate the final forwarding probability, thereby realizing the dynamic selection of forwarding node and reflecting the dynamic space-covered of node. The forwarding strategy is proposed to reduce broadcast collision. Simulation results show that, compared with dynamic probability broadcast and node location based space-covered broadcast, proposed broadcast algorithm reduces the broadcast collision, improves the broadcast coverage, and reduces the forwarding probability when the number of nodes is large. © 2020 The authors and IOS Press.

关键词： Probability

来源：评论

学校读者我要写书评

暂无评论

Short Interval Solar Power Prediction for Energy Harvesting with Low Computation Cost on Edge Computation Network

Short Interval Solar Power Prediction for Energy Harvesting ...

引用

IEEE Annual Computing and communication Workshop and Conference (CCWC)

作者： Yue Chen Xing Cheng Yanxin Yao Bei Wan School of Information and Communication Engineering Beijing Information Science and Technology University Beijng China Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument Beijing Information Science & Technology University Advanced Equipment Intelligent Perception and Control Beijing International Cooperation Base for Science and Technology Beijing Information Science & Technology University

ISBN: (数字)9781665414906

ISBN: (纸本)9781665430586

Solar energy forecasting methods including artificial neural network (ANN) are mostly for planning large or medium scale grid connected photovoltaic (PV) systems. The small prediction step will cause expensive computational cost with ANN. Using the concept of edge computing (EC), the paper proposes an effective short time step PV energy predicting model I based on ANN and wavelet transformation to reduce the computation costs. Sparse coefficients, which are tried by both different wavelet types and similar day classification, and a few forecast meteorological data are used as inputs to reduces the scale of ANN sharply. The simulation results demonstrate that, when the proposed method processes the whole year data, the proposed ANN model I has low computation complexity and superior precision.

关键词： Training Photovoltaic systems Computational modeling Artificial neural networks Solar energy Predictive models Wavelet coefficients

来源：评论

学校读者我要写书评

暂无评论

The role of attribute ranker using classification for software defect-prone data-sets model: An empirical comparative study 14

The role of attribute ranker using classification for softwa...

引用

14th Annual IEEE International Systems Conference, SYSCON 2020

作者： Malik, Maaz Rasheed Yining, Liu Shaikh, Salahuddin Dept. Information and Communication Engineering Guilin University of Electronics Technology Guilin China Dept. School of Control and Computer Engineering North China Electric Power University Beijing China

ISBN: (纸本)9781728153650

Feature selection, is an issue firmly identified with size decrease of data-sets model. The target of feature selection is to recognize features in the data-set as significant, and dispose of some other feature as unimportant and repetitive data. Since feature selection diminishes the dimensionality of the data-sets model, it holds out the probability of increasingly successful and quick activity of data mining algorithm which can be worked quicker and all the more adequately by utilizing feature selection. In this research paper we will investigate feature extraction Principal Component Analysis (PCA) with attribute ranker search technique. In practice, Principal Component Analysis with attribute ranker search strategy isn't just used to improve extra storage space or the computational accuracy and efficiency of the classification algorithm, however can likewise enhance the prescient presentation by diminishing the scourge of dimensionality - particularly on the off chance that we are working with software defect-prone or non-defected data-sets models. We have used 10 datasets models, these datasets models basically REPOSITORY model of NASA which contain binary class defected and non-defected datasets models. We have also used 6 classifiers for comparatively analysis between objective model and real datasets model. We illustrated the comparatively analysis between PCA Ranker Search method with No-PCA. We have also compared classifiers efficiency with each other. The most efficient and useful classifier are the Bagging and Multilayer Perceptron at all attribute ranking search method. But the comparatively analysis between the classifiers that Naïve bayes and MultiLayer Perceptron have well increased the correctly classified instances percentage in overall software fault forecast. One more comparison between the PCA Ranker Search Method and No-PCA that is attribute ranker search method is really good for increasing accuracy and efficiency for software fault forecast

关键词： Defects

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：