检索结果-内蒙古大学图书馆

*** — A Julia Package for Polynomial Chaos in Systems and Control

IFAC-PapersOnLine 2020年第2期53卷 7210-7216页

作者： Tillmann Mühlpfordt Frederik Zahn Veit Hagenmeyer Timm Faulwasser Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany

Polynomial chaos expansion (pce) is an increasingly popular technique for uncertainty propagation and quantification in systems and control. Based on the theory of Hilbert spaces and orthogonal polynomials, PCE allows for a unifying mathematical framework to study systems under arbitrary uncertainties of finite variance; we introduce this problem as a so-called mapping under uncertainty. For practical PCE-based applications we require orthogonal polynomials relative to given probability densities, and their quadrature rules. With *** we provide a Julia software package that delivers the desired functionality: given a probability density function, *** offers several numerical routines to construct the respective orthogonal polynomials, and the quadrature rules together with tensorized scalar products. *** is the first PCE-related software written in Julia, a scientific programming language that combines the readability of scripted languages with the speed of compiled languages. We provide illustrating numerical examples that show both PCE and *** in action.

关键词： polynomial chaos expansion uncertainties stochastic optimal control Julia

来源：评论

学校读者我要写书评

暂无评论

Design-for-manufacture of high-resolution 3D printed rotation optics

Design-for-manufacture of high-resolution 3D printed rotatio...

引用

Freeform Optics, Freeform 2019 - Part of Optical Design and Fabrication 2019

作者： Sieber, Ingo Moser, Daniel Gengenbach, Ulrich Karlsruhe Institute of Technology Institute for Automation and Applied Informatics Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen76344 Germany

Design and manufacture of a novel varifocal freeform optics by means of high-resolution 3D printing are presented. Tuning of its focal length is achieved by mutually rotating two lens bodies around the optical axis. &... 详细信息

ISBN: (纸本)9781943580606

关键词： Lenses

来源：评论

学校读者我要写书评

暂无评论

Annotation Efforts in Image Segmentation can be Reduced by Neural Network Bootstrapping

Annotation Efforts in Image Segmentation can be Reduced by N...

引用

作者： Rettenberger, Luca Schilling, Marcel Reischl, Markus Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen76344 Germany

Modern medical technology offers potential for the automatic generation of datasets that can be fed into deep learning systems. However, even though raw data for supporting diagnostics can be obtained with manageable effort, generating annotations is burdensome and time-consuming. Since annotating images for semantic segmentation is particularly exhausting, methods to reduce the human effort are especially valuable. We propose a combined framework that utilizes unsupervised machine learning to automatically generate segmentation masks. Experiments on two biomedical datasets show that our approach generates noticeably better annotations than Otsu thresholding and k-means clustering without needing any additional manual effort. Using our framework, unannotated datasets can be amended with pre-annotations fully unsupervised thus reducing the human effort to a minimum. © 2022 by Walter de Gruyter Berlin/Boston.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Optimization of Energy Pulsation and Power Dissipation in Modular Multilevel Converters (MMCs) 65

Multiobjective Optimization of Energy Pulsation and Power Di...

引用

65th IEEE Annual International Scientific Conference on Power and Electrical Engineering of Riga Technical University, RTUCON 2024

作者： Kappenstein, Simon T. Hagenmeyer, Veit Groll, Lutz Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen76344 Germany

ISBN: (纸本)9798350365771

This paper introduces a multiobjective optimization strategy for minimizing both energy pulsation and power dissipation in modular multilevel converters (MMCs). The occurrence of energy pulsation and power dissipation in MMCs has the negative potential to lead to a reduction in efficiency, to an increase in thermal stress, and to reliability issues. A Pareto front analysis shows that simultaneous improvement of both objectives is not possible. Analytical function optimization provides an exact solution for the case where only energy dissipation is considered. By optimizing the tradeoffs between minimizing energy pulsation and reducing power losses, this work offers a comprehensive solution to enhance the performance of MMCs. © 2024 IEEE.

关键词： Power converters

来源：评论

学校读者我要写书评

暂无评论

Interactive Evolution of Facial Composites

引用

IFAC-PapersOnLine 2017年第1期50卷 11776-11781页

作者： Zahradnikova, Barbora Sutova, Zuzana Schreiber, Peter Institute of Applied Informatics Automation and Mechtronics Faculty of Materials Science and Technology Slovak University of Technology Paulinska 16 Trnava Slovakia

Facial composite is a tool used in criminal investigation to identify an unknown person, usually a suspect of a crime. Traditionally, it is created by a forensic artist on the basis of a detailed description provided by one or several eye witnesses. Due to the subjectivity and low efficiency of the composition process, facial composite has not been considered to be a reliable evidence until recently. Despite expectations, replacing traditional drawing by computer-driven systems did not result in improved identification rates. Therefore, the research of the last decades has been oriented on developing a method more compatible with the human way of perceiving faces. In this paper, we present a system developed as a result of deep psychological research on human face perception and recall. The proposed approach enables automatic generation of facial images and their presenting to a witness, resembling the process of line-up identification. Besides providing information on computational model of a face, the primary goal of the paper is to discuss the applied evolutionary strategies in terms of individual parameter settings and evolutionary operator choice and to evaluate the strategies with regard to the construction time, operator usability and composite accuracy. Besides, we summarize the procedures recommended for further improving the efficiency of the composition process. © 2017

关键词： Crime Efficiency Evolutionary algorithms Criminal investigation crossover Evolutionary system Facial composites mutation

来源：评论

学校读者我要写书评

暂无评论

User interaction interface for Energy Management in Smart Homes

User interaction interface for Energy Management in Smart Ho...

引用

2012 IEEE PES Innovative Smart Grid Technologies, ISGT 2012

作者： Becker, Birger Kellerer, Anna Schmeck, Hartmut Institute of Applied Informatics and Formal Description Methods Karlsruhe Institute of Technology Germany

ISBN: (纸本)9781457721588

The growing share of fluctuating power generation by renewable resources and the increasing distribution of battery electric vehicles require the integration of intelligent Energy Management Systems (EMS) into the electrical power grid. Smart Homes will be equipped with controllable consumers, suppliers and storages to realize a flexible consumption and supply of thermal and electrical energy. In this challenge, the interactive integration of the smart home's resident is essential to reduce comfort losses to a minimum. In this paper, we present a generic Energy Management Panel (EMP) providing the connection between the resident and the EMS and its integration into the EMS of a real smart home. The integrated approach considers thermal and electrical energy flows concurrently. In this way, the EMP provides an efficient operation of the EMS complying with the individual constraints of the resident. © 2012 IEEE.

关键词： Energy management systems

来源：评论

学校读者我要写书评

暂无评论

Direct Window-to-Wall Ratio Prediction Using Deep Learning Approaches

Direct Window-to-Wall Ratio Prediction Using Deep Learning A...

引用

2023 Joint Urban Remote Sensing Event, JURSE 2023

作者： Zhuo, Xiangyu Tian, Jiaojiao Hafele, Karl-Heinz Remote Sensing Technology Institute German Aerospace Center Weßling Germany Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen Germany

ISBN: (纸本)9781665493734

A building's window-to-wall ratio (WWR) plays a critical role in estimating heat loss, solar gain and daylighting levels, and is therefore essential for building energy modeling applications. Typically, an accurate WWR estimation corresponds to an accurate window segmentation result, which requires high quality rectified and annotated façade images. In this paper, we propose a novel end-to-end regression model that directly predicts the invisible building attribute, the WWR, from façade imagery. For comparison, we have adopted the latest proposed semantic segmentation of windows from façade images and calculate the WWR based on the result of the semantic segmentation. These two approaches are performed and compared on three public façade benchmarks. The experimental results demonstrate that the direct prediction of invisible building attributes is feasible. Furthermore, the regression-based approach can achieve similar WWR accuracy as the segmentation-based method when they use the same backbone. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Using weather data in energy time series forecasting: the benefit of input data transformations

引用

Energy informatics 2023年第1期6卷 44页

作者： Neumann, Oliver Turowski, Marian Mikut, Ralf Hagenmeyer, Veit Ludwig, Nicole Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Hermann-von-Helmholtz-Platz 1 Baden-Wuerttemberg Karlsruhe76344 Germany Cluster of Excellence Machine Learning University of Tübingen Maria-von-Linden Str. 6 Baden-Wuerttemberg Karlsruhe76344 Germany

Renewable energy systems depend on the weather, and weather information, thus, plays a crucial role in forecasting time series within such renewable energy systems. However, while weather data are commonly used to improve forecast accuracy, it still has to be determined in which input shape this weather data benefits the forecasting models the most. In the present paper, we investigate how transformations for weather data inputs, i. e., station-based and grid-based weather data, influence the accuracy of energy time series forecasts. The selected weather data transformations are based on statistical features, dimensionality reduction, clustering, autoencoders, and interpolation. We evaluate the performance of these weather data transformations when forecasting three energy time series: electrical demand, solar power, and wind power. Additionally, we compare the best-performing weather data transformations for station-based and grid-based weather data. We show that transforming station-based or grid-based weather data improves the forecast accuracy compared to using the raw weather data between 3.7 and 5.2%, depending on the target energy time series, where statistical and dimensionality reduction data transformations are among the best. © 2023, The Author(s).

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

4.3 towards classification of technical sound events with deep learning models

4.3 towards classification of technical sound events with de...

引用

2019 Knowledge Management in Digital Work Environments State-of-the-Art and Outlook, WM 2019

作者： Rieder, Constantin Germann, Markus Scherer, Klaus Peter Karlsruhe Institute of Technology Institute for Automation and Applied Informatics Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen76344 Germany Ibidem

ISBN: (纸本)9783885796978

Sounds of machines and mechanical systems contain a lot of information about the observed object and its state. Experienced engineers and technical service staff can often identify or classify a certain technical object with state via its sound. An equivalent automated system with such capabilities is difficult to realise because of noisy unknown surroundings. In this paper, we show an approach to implement the mentioned characteristics with deep learning methods and enhance the power of a technical assistance system. © 2020 Gesellschaft fur Informatik (GI). 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

Automated fabrication of multi-layer printed electronic circuits using a novel vector ink-jet printing process control and surface mounting of discrete components

引用

IFAC-PapersOnLine 2019年第15期52卷 609-614页

作者： Ulrich Gengenbach Martin Ungerer Liane Koker Klaus-Martin Reichert Peter Stiller Chengyuan Huang Veit Hagenmeyer Institute for Automation and Applied Informatics Karlsruhe Institute of Technology 76021 Karlsruhe Germany

Printed electronics offer great potential for new applications such as Internet of Things devices and wearables. A methodology for integration of design and process assessment based on a stepwise transfer of the circuit to be printed from printed circuit board test vehicles to the final printed substrate is introduced. A multi-layer vector ink-jet printing process with three functional inks is presented using the example of the fabrication of a demonstrator circuit. This fabrication is realized using a newly set up printing system as enabling technology: Integration of a piezo print head into the path planning of the printing system and its control as virtual stepper axis enable highly precise vector printing yielding printed functional elements with low tolerances. Finally, process improvements for assembly of surface mounted devices on printed foil substrates are outlined.

关键词： Functional Printing printed circuits process automation systems design iterative improvement transcoders piezo print head as virtual stepper axis

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：