检索结果-内蒙古大学图书馆

Die 18. Fachtagung Bildungstechnologien der Gesellschaft fur Informatik e.V., DELFI 2020 - 18th Conference on Educational Technologies of the German Informatics Society, DELFI 2020

作者： Hoppner, Frank Ostfalia University of Applied Sciences Dept. Computer Science Am Exer 2 Wolfenböttel Germany

ISBN: (纸本)9783885797029

We report about research in progress that aims at generating additional value for programming novices from the collective work of all students in this (and earlier) term(s). We propose live progress reports about the whole course to better estimate the own capabilities. And we propose a solution that autonomously creates hints from other students solutions to support novices in situations where they do not know how to proceed. A plugin integrates the tool seamlessly in the IDE to avoid additional technical burden. We report first results on a small test group. © 2020 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Technology transfer

来源：评论

学校读者我要写书评

暂无评论

Better together: Modern methods plus traditional thinking in NP alignment 12

Better together: Modern methods plus traditional thinking in...

引用

12th International Conference on Language Resources and Evaluation, LREC 2020

作者： Kovács, Ádám Ács, Judit Kornai, András Recski, Gábor BME Dept. of Automation and Applied Informatics SZTAKI Institute of Computer Science Hungary Apollo.AI

ISBN: (纸本)9791095546344

We study a typical intermediary task to Machine Translation, the alignment of NPs in the bitext. After arguing that the task remains relevant even in an end-to-end paradigm, we present simple, dictionary- and word vector-based baselines and a BERT-based system. Our results make clear that even state of the art systems relying on the best end-to-end methods can be improved by bringing in old-fashioned methods such as stopword removal, lemmatization, and dictionaries. © European Language Resources Association (ELRA), licensed under CC-BY-NC

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Lightweight AI and Blockchain Optimization for Enhancing Consumer Electronics Decision-Making

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Byeon, Haewon Alsaadi, Mahmood Keshta, Ismail Ahanger, Tariq Ahamed Safarova, Nodira Aldawsari, Hamad Cascone, Lucia Shabaz, Mohammad Korea University of Technology and Education Convergence Department Cheonan Korea Republic of University of Al Maarif College of Sciences Department of Computer Sciences Al Anbar31001 Iraq AlMaarefa University College of Applied Sciences Computer Science and Information Systems Department Riyadh Saudi Arabia CoBA Prince Sattam Bin Abdulaziz University Department of Management Information Systems Saudi Arabia Tashkent State University of Economics Department of Finance and Financial technologies Tashkent Uzbekistan University of Tabuk Department of Computer Science Haql University College Saudi Arabia University of Salerno Dept. of Computer Science Fisciano Italy Model Institute of Engineering and Technology J and K Jammu India

Under the "dual carbon" background, consumerelectronics consumption has become deeply ingrained in people'sminds. However, consumers often distrust the sustainabilityclaims of consumer electronics products. Artificial intelligence(AI) and blockchain technology can address this trust deficitthrough transparency and traceability mechanisms. This studyintegrates blockchain technology into traditional consumerelectronics supply chains, considering consumers' preferences andtrust in these products. An AI-based game model is proposed toanalyze the interactions among supply chain members before andafter implementing blockchain technology, under varying EdgeComputing-based power structures. This model quantitativelyevaluates emission reduction and pricing strategies, aiming tooptimize consumer surplus and total social welfare. By leveragingLightweight AI and blockchain, smart wholesale and cost-sharingcontracts are designed to establish reasonable ranges for wholesaleprices and optimal cost-sharing ratios, enhancing enterpriseoperational efficiency and achieving supply chain *** demonstrate that when consumers exhibit a strongerpreference for consumer electronics products, the adoption ofLightweight AI and blockchain delivers greater benefits across thesupply chain. Furthermore, as consumer willingness to purchasethese products increases, the advantages become morepronounced. Numerical analysis highlights that smart contractscan better coordinate the supply chain, particularly in retailer-dominated scenarios. Finally, empirical cases validate theeffectiveness of the proposed strategies and models. © 1975-2011 IEEE.

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

AC and DC Electrical Strength of Thermally Conductive Insulating Foils under Various Conditions

AC and DC Electrical Strength of Thermally Conductive Insula...

引用

Electrical Insulation Conference and Electrical Manufacturing & Coil Winding Conference

作者： Martin Scheler Lukas Reiß enweber Sabrina Hetzel Tobias Fischer Michael Rossner Alexander Stadler Wilhelm Pohl Dept. of Electrical Engineering and Computer Science Coburg University of Applied Sciences and Arts Coburg Germany HALA Contec GmbH &amp Co. KG Ottobrunn Germany

ISBN: (数字)9781665480239

ISBN: (纸本)9781665480246

In this work we present the results of AC and DC breakdown voltage measurements on thermally conductive insulating foil sheets. The aim is to derive suitable voltage values for a nondestructive electrical strength test. The voltages are as high as possible without producing too many rejects. From the different test methods for breakdown measurements, we choose the method that delivers the lowest breakdown voltages. The effect of different voltage rise rates is investigated and a suitable rise rate is derived. The thickness and area dependency of the foils to the breakdown voltage is investigated and discussed. Rectangular electrode surfaces are preferred for testing sheets. Therefore, we investigate the difference between circular and rectangular electrode geometries on the breakdown results. Furthermore, we propose a method for scaling the obtained test voltages to different foil sheet dimensions which is based on the enlargement law. The prerequisite is that breakdowns with extensive random samples are performed on a known arrangement. Because the enlargement law is not valid in all cases, it is necessary to perform breakdown measurements on the scaled arrangement for referencing. For a small number of samples, the method delivers low probability breakdown voltages more accurate than performing statistical analysis on the scaled arrangement.

关键词： Electrodes Breakdown voltage Voltage measurement Electric breakdown Statistical analysis Probability Thermal conductivity

来源：评论

学校读者我要写书评

暂无评论

Nondestructive 100 Percent Electrical Strength Test Method for Thermally Conductive Insulating Foils

Nondestructive 100 Percent Electrical Strength Test Method f...

引用

Electrical Insulation Conference and Electrical Manufacturing & Coil Winding Conference

作者： Lukas Reiß enweber Martin Scheler Sabrina Hetzel Tobias Fischer Michael Rossner Alexander Stadler Wilhelm Pohl Dept. of Electrical Engineering and Computer Science Coburg University of Applied Sciences and Arts Coburg Germany HALA Contec GmbH &#x0026 Co. KG Ottobrunn Germany

ISBN: (数字)9781665480239

ISBN: (纸本)9781665480246

In this work we present a method to test thermally conductive insulating foils nondestructive for their AC and DC electrical strength. The term 100 % test method is intended to summarize two aspects: the AC and DC electrical strength, respectively, is tested for a specific voltage amplitude, and the electric field is applied to the entire foil dimension. The test method meets several requirements. Firstly, insulating foils are tested in form of sheets, which may have different thicknesses and areas. Secondly, the test voltage (AC, DC) is as high as possible without producing too many rejected sheets. Thirdly, high cycle rates (tested sheets per hour) are realized. Investigations are performed to exclude short-time degradation caused by the test method. Possible long-term degradation effects are not considered. To meet the requirements, suitable test voltages considering the foil dimensions are determined based on breakdown tests. A suitable test time for AC and DC is derived for the nondestructive test method. To avoid flashovers during the test, the foil sheet must protrude over the electrodes. The protruded area is considered as not tested and is removed afterwards. An optimum electrode contour is designed to reduce the edge field strength and to avoid large radii. An automatic test stand is presented and discussed for testing foil sheets of variable dimensions. The contact pressure is kept constant regardless of the electrode weight. Foil sheets are tested with the test stand and the 100 % method is applied. The results are discussed.

关键词： Electrodes Degradation Breakdown voltage Insulation Electric breakdown High-voltage techniques Thermal conductivity

来源：评论

学校读者我要写书评

暂无评论

On the Exploitation of Deepfake Model Recognition

On the Exploitation of Deepfake Model Recognition

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Luca Guarnera Oliver Giudice Matthias Nieß ner Sebastiano Battiato Department of Mathematics and Computer Science University of Catania Italy IT Dept. Banca d&#x2019 Italia Applied Research Team Rome Italy Technical University of Munich Germany

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487405

Despite recent advances in Generative Adversarial Networks (GANs), with special focus to the Deepfake phenomenon there is no a clear understanding neither in terms of explainability nor of recognition of the involved models. In particular, the recognition of a specific GAN model that generated the deepfake image compared to many other possible models created by the same generative architecture (e.g. StyleGAN) is a task not yet completely addressed in the state-of-the-art. In this work, a robust processing pipeline to evaluate the possibility to point-out analytic fingerprints for Deepfake model recognition is presented. After exploiting the latent space of 50 slightly different models through an in-dept. analysis on the generated images, a proper encoder was trained to discriminate among these models obtaining a classification accuracy of over 96%. Once demonstrated the possibility to discriminate extremely similar images, a dedicated metric exploiting the insights discovered in the latent space was introduced. By achieving a final accuracy of more than 94% for the Model Recognition task on images generated by models not employed in the training phase, this study takes an important step in countering the Deepfake phenomenon introducing a sort of signature in some sense similar to those employed in the multimedia forensics field (e.g. for camera source identification task, image ballistics task, etc).

关键词： Training Measurement Deepfakes Analytical models Image recognition Forensics Pipelines

来源：评论

学校读者我要写书评

暂无评论

Maximum Likelihood Uncertainty Estimation: Robustness to Outliers

arXiv

引用

arXiv 2022年

作者： Nair, Deebul S. Hochgeschwender, Nico Olivares-Mendez, Miguel A. Dept. of Computer Science Bonn-Rhein-Sieg University of Applied Sciences Germany Institute for Software Technology Germany SpaceR Research Group University of Luxembourg Luxembourg

We benchmark the robustness of maximum likelihood based uncertainty estimation methods to outliers in training data for regression tasks. Outliers or noisy labels in training data results in degraded performances as well as incorrect estimation of uncertainty. We propose the use of a heavy-tailed distribution (Laplace distribution) to improve the robustness to outliers. This property is evaluated using standard regression benchmarks and on a high-dimensional regression task of monocular dept. estimation, both containing outliers. In particular, heavy-tailed distribution based maximum likelihood provides better uncertainty estimates, better separation in uncertainty for out-of-distribution data, as well as better detection of adversarial attacks in the presence of outliers. © 2022, CC BY-SA.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

On the Exploitation of Deepfake Model Recognition

arXiv

引用

arXiv 2022年

作者： Guarnera, Luca Giudice, Oliver Nießner, Matthias Battiato, Sebastiano Department of Mathematics and Computer Science University of Catania Italy Banca d’Italia Applied Research Team IT Dept. Rome Italy Technical University of Munich Germany

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images

arXiv

引用

arXiv 2022年

作者： Guarnera, Luca Giudice, Oliver Battiato, Sebastiano Department of Mathematics and Computer Science University of Catania Italy iCTLab Spinoff of University of Catania Italy Applied Research Team IT Dept. Banca d'Italia Italy

Most recent style-transfer techniques based on generative architectures are able to obtain synthetic multimedia contents, or commonly called deepfakes, with almost no artifacts. Researchers already demonstrated that synthetic images contain patterns that can determine not only if it is a deepfake but also the generative architecture employed to create the image data itself. These traces can be exploited to study problems that have never been addressed in the context of deepfakes. To this aim, in this paper a first approach to investigate the image ballistics on deepfake images subject to style-transfer manipulations is proposed. Specifically, this paper describes a study on detecting how many times a digital image has been processed by a generative architecture for style transfer. Moreover, in order to address and study accurately forensic ballistics on deepfake images, some mathematical properties of style-transfer operations were investigated. Copyright © 2022, The Authors. All rights reserved.

关键词： Ballistics

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Recognition Using Different CNN Models

Plant Disease Recognition Using Different CNN Models

引用

International Conference on Confluence The Next Generation Information Technology Summit (Confluence)

作者： Shivam Gupta Shrey Gilotra Shivam Rathi Tanupriya Choudhury Ketan Kotecha School of Computer Science University of Petroleum and Energy Studies Dehradun India CSE Dept. Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune Maharashtra India Symbiosis Centre for Applied Artificial Intelligence Symbiosis Institute of Technology Symbiosis International University Pune India

The research paper highlights the remarkable threats that plant diseases pose to global agricultural productivity and food security. The early detection and accurate recognition of these diseases are crucial for the effective management of plants. Deep learning models, such as CNN, Resnet34, Resnet50, and VGG16, have shown propitious results in computer vision tasks, including plant disease recognition. The study explores the effectiveness of these models using a comprehensive dataset consisting of images of healthy and diseased plants. The pretrained versions of the models are fine-tuned using transfer learning techniques with performance evaluation based on metrics like accuracy, precision, recall and f1 score. Comparative analysis also identifies each model's strengths and weaknesses in classifying plant diseases, considering factors like model architecture dept. and complexity. The overall findings of this research contribute towards the development of automated plant disease recognition systems integrated into real-time monitoring systems.

关键词：

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：