检索结果-内蒙古大学图书馆

34th European Modeling and Simulation Symposium, EMSS 2022

作者： Zwettler, Gerald A. Ono, Yuta Stradner, Michael Praschl, Christoph Research Group Advanced Information Systems and Technology Research and Development Department University of Applied Sciences Upper Austria Graduate School of Software and Information Science Iwate Prefectural University Japan Department of Software Engineering School of Informatics Communications and Media University of Applied Sciences Upper Austria

Historical and current aerial photographs are only of great value if the geolocation or address of the photographed areas is also available. In Western Europe, especially Austria, Germany and Czech Republic, there is a market for the sale of aerial photographs of one’s own private residential building. Automated geolocation is a feasible way to enable the sales agents to assign the addresses for the sale more quickly. In the course of this research work, a process chain is modeled that allows the assignment of aerial photographs to residential addresses using machine vision. After model-based rectifying the aerial images to compensate for perspective distortions, larger image blocks get assembled using image stitching. The assignment to a 2D reference map, such as satellite imagery via Google Maps, is done by applying a U-Net CNN after extracting durable image features such as roads or buildings. The mapping of aerial imagery to two-dimensional cartography is either automated via registration approaches or based on manually placed corresponding landmarks and homography. Test runs on imagery between the years 1969 and 2020 show that the labor-intensive process of geolocation of aerial imagery can be solved by the proposed process model in a hybrid way. © 2022 The Authors.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Data-informativity conditions for structured linear systems with implications for dynamic networks

arXiv

引用

arXiv 2024年

作者： Van den Hof, Paul M.J. Shi, Shengling Fonken, Stefanie J.M. Ramaswamy, Karthik R. Hjalmarsson, Håkan Dankers, Arne G. Control Systems Group Department of Electrical Engineering Eindhoven University of Technology Netherlands Department of Chemical Engineering Massachusetts Institute of Technology United States ASML Veldhoven Netherlands Division of Decision and Control Systems Royal Institute of Technology Stockholm Sweden Department of Electrical and Software Engineering University of Calgary Canada

When estimating models of a multivariable dynamic system, a typical condition for consistency is to require the input signals to be persistently exciting, which is guaranteed if the input spectrum is positive definite for a sufficient number of frequencies. In this paper it is investigated how such a condition can be relaxed by exploiting prior structural information on the multivariable system, such as structural zero elements in the transfer matrix or entries that are a priori known and therefore not parametrized. It is shown that in particular situations the data-informativity condition can be decomposed into different MISO (multiple input single output) situations, leading to relaxed conditions for the MIMO (multiple input multiple output) model. When estimating a single module in a linear dynamic network, the data-informativity conditions can generically be formulated as path-based conditions on the graph of the network. The new relaxed conditions for data-informativity will then also lead to relaxed path-based conditions on the network graph. Additionally the new expressions are shown to be closely related to earlier derived conditions for (generic) single module identifiability. © 2024, CC BY-NC-ND.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5-Based Method for Tiny Defect Detection on Steel Plate

Improved YOLOv5-Based Method for Tiny Defect Detection on St...

引用

International Conference on Intelligent Control and Information Processing (ICICIP)

作者： Jiwei Yu Zhihang Ji Yang Yu Muhua Liu Lin Wang Xuhui Zhao Ruijuan Zheng School of Information Engineering Henan University of Science and Technology Luoyang China Longmen Laboratory 360 Digital Security Technology Group Co. Ltd Luoyang China School of Software Henan University of Science and Technology Luoyang China

In this paper, a novel detection method based YOLOv5 is proposed, which is suitable for detecting tiny defects on steel plate. First, we introduce the Bi-Level Routing Attention (BRA) module to learn global and local detail features in the im age simultaneously, which can more efficiently extract tiny defect feature information. Second, a feature enhancement module, Spatial Context Pyramid, is designed to enhance the tiny defect feature by contrasting the spatial context information obtained from feature fusion procedure. Extensive experimental results show that our method achieves comparable performance on the NEU-DET dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Stealthy Backdoor Attack Method Based on Generative Adversarial Networks

A Stealthy Backdoor Attack Method Based on Generative Advers...

引用

Image Processing, Electronics and Computers (IPEC), Asia-Pacific Conference on

作者： Yayue Tan Gao Yu Yaqi Zhang Yongqing Tang College of Computer and Information Science School of Software Southwest University Chongqing China Department of Payment Platform Technology Payment core platform Ant Group Co. Ltd Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350374407

ISBN: (纸本)9798350374414

Deep neural networks have been widely and successfully applied to many critical tasks, such as image pattern recognition, natural language processing and autonomous driving, and large amounts of training data and increasing computational power are key factors in their success. Many studies in recent years have shown that deep neural network models face many practical security threats, such as adversarial attacks and backdoor attacks, which can have very serious consequences in the real world. Aiming at the problems of stealth, backdoor trigger design and universality of current backdoor attack methods, a novel method of invisible backdoor attack based on generative adversarial network is proposed. As a backdoor attack method based on data poisoning, inspired by image steganography, this method trains an encoder to generate poisoned samples through generative adversarial network to implement backdoor attack. The secret image used to guide the generation of backdoor triggers does not need to be carefully designed, and the encoder has good generalization ability across datasets. These features not only make its attack effective and stealthy, but also greatly reduce the cost of backdoor. Extensive experimental and analytical results show that the proposed backdoor attack method is effective, stealthy, sustainable and universal.

关键词： Training Steganography Costs Toxicology Computational modeling Training data Artificial neural networks Passwords Generative adversarial networks Security

来源：评论

学校读者我要写书评

暂无评论

Tamper-Proof Storage of User Movement Logs in Smart Parks 7

Tamper-Proof Storage of User Movement Logs in Smart Parks

引用

7th International Conference on Communication, Image and Signal Processing, CCISP 2022

作者： Niu, Yiru Jiang, Hong Huang, Xiaobing Zhao, Qi Xiang, Hong Xia, Xiaofeng Zhao, Yue Science and Technology on Communication Security Laboratory No.30 Research Institute of China Electronics Technology Group Corporation Chengdu610041 China No.30 Research Institute of China Electronics Technology Group Corporation Chengdu610041 China Qianghua Times Technology Co Ltd. Chengdu610041 China School of Big Data and Software Engineering Chongqing University Chongqing400044 China

ISBN: (数字)9781665459594

ISBN: (纸本)9781665459594

With the introduction of the smart city concept and the rapid development of various emerging technologies such as cloud computing, Internet of Things, big data and artificial intelligence, traditional parks have also ushered in new opportunities and are developing in a smarter direction. Since the park is an open area with frequent movement of people and equipment, it is prone to security problems. At this point, logs will be a good aid for incident accountability. In this paper, we mainly use Merkle hash tree and distributed storage for secure storage of logs. Meanwhile, to ensure the non-repudiation of logs, the signatures of users and log-generating devices are required when generating logs. After analysis, the scheme proposed in this paper can achieve tamper-proof and traceability of logs. © 2022 IEEE.

关键词： Parks

来源：评论

学校读者我要写书评

暂无评论

Towards an Automated System for Reverse Geocoding of Aerial Photographs 30

Towards an Automated System for Reverse Geocoding of Aerial ...

引用

30th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2022

作者： Praschl, Christoph Stradner, Michael Ono, Yuta Zwettler, Gerald Research Group Advanced Information Systems and Technology Research and Development Department University of Applied Sciences Upper Austria Austria Graduate School of Software and Information Science Iwate Prefectural University Japan Department of Software Engineering School of Informatics Communications and Media University of Applied Sciences Upper Austria Austria

ISBN: (纸本)9788086943336

Aerial photographs of buildings are often used as memorabilia sold by trading companies. Such photographs come with an issue regarding the address of the shown buildings, since the recording location of the camera may be known, but shows a spatial distance to the actual subject of the image. In addition to that, also this recording location is often not known in detail but only roughly in the form of the flight route/area. To address this problem, a methodology for reverse geocoding is proposed, allowing to identify the position of buildings that are photographed from aerial vehicles. This is done using a process for extending recording locations and a second process based on the registration of invariant features within aerial shots compared to maps. © 2022 University of West Bohemia. All rights reserved.

关键词： Aerial photography

来源：评论

学校读者我要写书评

暂无评论

Identification of leek diseases based on deep learning algorithms

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 14349-14364页

作者： Xu, Laixiang Ning, Shiyuan Zhang, Wenbo Xu, Peng Zhao, Fengjie Cao, Bingxu Hou, Xiangguan School of Information and Communication Engineering Hainan University Haikou570228 China Department of Software Information The 36th Research Institute of China Electronics Technology Group Corporation Jiaxing314033 China Department of Asphalt Fiber Xinjiang Central Section Hesheng Silicon Industry Co. Ltd Fukang831500 China Shangqiu First People’s Hospital Henan Suixian People’s Hospital of The First Affiliated Hospital of Zhengzhou University Shangqiu476000 China School of Information Engineering Luohe Vocational Technology College Luohe462000 China Department of Research and Development Shanghai OFILM Smart Car Link Technology Co. Ltd Shanghai200120 China

Vegetable diseases and pests continue to be a major threat to food security. Manual identification is time-consuming and labor-intensive due to the wide variety of diseases and pests, and it is also prone to errors. In this paper, a novel and integrated deep learning framework based on convolutional neural networks was proposed for leek disease identification using an improved Cycle-GAN network, gated recurrent units, and recurrent convolutional auto-encoders. We collected healthy and diseased leek leaves under realistic conditions for the experimental implementation. We concentrated on the identification of five leek diseases: virus, rust, blight, sclerotium rolfsii, and botrytis cinerea. It is discovered that the proposed method’s evaluation metrics produce an accuracy of 99.58%, a specificity of 99.62%, a sensitivity of 97.96%, a precision of 99.77%, and an f1-score of 98.19%, which is significantly higher than other cutting-edge deep learning models such as ShuffleNet-V3, Inception-V4, and Efficient-B7. Many aspects of the proposed model implementation provide competitive advantages, such as high recognition precision, strong adaptive ability, and good generalization. In conclusion, the proposed system can accurately classify leek diseases, which is very beneficial in increasing the efficiency of plant pathology image analysis. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Vegetables

来源：评论

学校读者我要写书评

暂无评论

A XGBoost Method Based on Telecom Customer Satisfaction Enhancement Strategy 5

A XGBoost Method Based on Telecom Customer Satisfaction Enha...

引用

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Gou, Haosong Su, Ling Zhang, Gaoyi Huang, Wei Rao, Yunbo Yang, Yang Sichuan Co. Ltd. China Mobile Communications Group Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China Sichuan Institute of Computer Sciences Chengdu China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

Customer satisfaction is critical for the telecom operators to gain competitive advantages, and the customer satisfaction index is used to evaluate the customers how satisfied with the services, such as network experience and after-sales service. In this paper, we aim to find the internal relationship between customer satisfaction index and network experience by adopting XGBoost machine learning algorithm to help operators predict the satisfaction score to enhance customer satisfaction. We train a better model by selecting key factors, model training, validating and testing. The final experiment shows our trained model achieves much better performance than usual linear regression model. © 2022 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

The Optimization of Multi-classifier Ensemble Method Based on Dynamic Weighted Voting

The Optimization of Multi-classifier Ensemble Method Based o...

引用

2021 International Conference on Advanced Technologies and Applications of Modern Industry, ATAMI 2021

作者： Yang, Ping Fang, Jian Xu, Junting Jin, Guanghao Song, Qingzeng School of Software Tian Gong University Tianjin China Beijing Gongmei Group Beijing China School of Computer Science and Technology Tian Gong University Tianjin China School of Telecommunication Engineering Beijing Polytechnic Beijing China

Generally, on the same data set, different deep learning classification models will achieve different performances. The existing weighted voting method can combine the results of models, which can improve the performance of classification. On the other side, its classification accuracy is affected by the accuracy of all models. In this paper, we proposed a dynamic weighted voting method. Our method dynamically selects models on different data sets, and integrates them according to their weights, thereby improving the classification accuracy. We evaluated the methods on three data sets of CIFAR10, CIFAR100 and Existing, which increased the accuracy about 0.65%, 0.91%, and 0.78% respectively compared with the existing weighted voting method. © Published under licence by IOP Publishing Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Overview of 3D Human Pose Estimation

引用

Computer Modeling in engineering & Sciences 2023年第3期134卷 1621-1651页

作者： Jianchu Lin Shuang Li Hong Qin Hongchang Wang Ning Cui Qian Jiang Haifang Jian Gongming Wang Huaiyin Institute of Technology Huai’an223000China Jiangsu Outlook Shenzhou Big Data Technology Co. Ltd.Nanjing210002China Institute of Semiconductors Chinese Academy of SciencesBeijing100083China Center of Materials Science and Optoelectronics Engineering&School of Integrated Circuits University of Chinese Academy of SciencesBeijing100049China Inspur Software Group Company Ltd.Jinan250104China China GreatWall Industry Corporation Beijing100054China China GreatWall Industry Corporation Navigation Co. Ltd.Beijing100144China

3D human pose estimation is a major focus area in the field of computer vision,which plays an important role in practical *** article summarizes the framework and research progress related to the estimation of monocular RGB images and *** overall perspective ofmethods integrated with deep learning is *** image-based and video-based inputs are proposed as the analysis *** this viewpoint,common problems are *** diversity of human postures usually leads to problems such as occlusion and ambiguity,and the lack of training datasets often results in poor generalization ability of the *** methods are crucial for solving such *** image-based input,the multi-view method is commonly used to solve occlusion ***,the multi-view method is analyzed *** referring to video-based input,the human prior knowledge of restricted motion is used to predict human *** addition,structural constraints are widely used as prior ***,weakly supervised learningmethods are studied and discussed for these two types of inputs to improve the model generalization *** problem of insufficient training datasets must also be considered,especially because 3D datasets are usually biased and ***,emerging and popular datasets and evaluation indicators are *** characteristics of the datasets and the relationships of the indicators are explained and ***,this article can be useful and instructive for researchers who are lacking in experience and find this field *** addition,by providing an overview of 3D human pose estimation,this article sorts and refines recent studies on 3D human pose *** describes kernel problems and common useful methods,and discusses the scope for further research.

关键词： 3D human pose estimation monocular camera deep learning multi-view indicator

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：