检索结果-内蒙古大学图书馆

Validating neural networks for spectroscopic classification on a universal synthetic dataset

npj Computational Materials 2023年第1期9卷 1325-1336页

作者： Jan Schuetzke Nathan J.Szymanski Markus Reischl Institute for Automation and Applied Informatics Karlsruhe Institute of TechnologyKarlsruhe 76131Germany Department of Materials Science&Engineering Lawrence Berkeley National LaboratoryBerkeleyCA 94720USA Department of Materials Science&Engineering UC BerkeleyBerkeleyCA 94720USA

To aid the development of machine learning models for automated spectroscopic data classification,we created a universal synthetic dataset for the validation of their *** dataset mimics the characteristic appearance of experimental measurements from techniques such as X-ray diffraction,nuclear magnetic resonance,and Raman spectroscopy among *** applied eight neural network architectures to classify artificial spectra,evaluating their ability to handle common experimental *** all models achieved over 98%accuracy on the synthetic dataset,misclassifications occurred when spectra had overlapping peaks or *** found that non-linear activation functions,specifically ReLU in the fully-connected layers,were crucial for distinguishing between these classes,while adding more sophisticated components,such as residual blocks or normalization layers,provided no performance *** on these findings,we summarize key design principles for neural networks in spectroscopic data classification and publicly share all scripts used in this study.

关键词： spectroscopic adding classify

来源：评论

学校读者我要写书评

暂无评论

ZeitGeist: A Generic Tool Supporting the Dissemination of Time Series Data Following FAIR Principles 15

ZeitGeist: A Generic Tool Supporting the Dissemination of Ti...

引用

15th International Conference on Knowledge Management and Information Systems, KMIS 2023 as part of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2023

作者： Schmidt, Andreas Koubaa, Mohamad Anis Schweikert, Jan Stucky, Karl-Uwe Süß, Wolfgang Hagenmeyer, Veit Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany Department of Computer Science and Business Information Systems University of Applied Sciences Karlsruhe Germany

ISBN: (纸本)9789897586712

An important point for the widespread dissemination of FAIR-data is the lowest possible entry barrier for preparing and providing data to other scientists according to the FAIR criteria. If scientists have to manually extract, transform and annotate the data according to the FAIR criteria and then export it to make it available to the public, this requires a significant investment of time that does not primarily reward the scientist who prepares and provides the data. The Energy Lab at KIT is running a large cluster of an Influx database management system with energy related time series data being stored in a variety of individual databases over periods of up to 15 years. In order to increase the willingness to make data available to the scientific public, we develop a tool that greatly supports and automates the publication and annotation process of time series data stored in Influx databases. Copyright © 2023 by SCITEPRESS - Science and technology Publications, Lda.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

A comparison of clustering methods for the spatial reduction of renewable electricity optimisation models of Europe

引用

Energy informatics 2022年第1期5卷 1-28页

作者： Frysztacki, Martha Maria Recht, Gereon Brown, Tom Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen Germany Institute of Energy Technology Technical University of Berlin Berlin Germany

Modeling the optimal design of the future European energy system involves large data volumes and many mathematical constraints, typically resulting in a significant computational burden. As a result, modelers often apply reductions to their model that can have a significant effect on the accuracy of their results. This study investigates methods for spatially clustering electricity system models at transmission level to overcome the computational constraints. Spatial reduction has a strong effect both on flows in the electricity transmission network and on the way wind and solar generators are aggregated. Clustering methods applied in the literature are typically oriented either towards preserving network flows or towards preserving the properties of renewables, but both are important for future energy systems. In this work we adapt clustering algorithms to accurately represent both networks and renewables. To this end we focus on hierarchical clustering, since it preserves the topology of the transmission system. We test improvements to the similarity metrics used in the clustering by evaluating the resulting regions with measures on renewable feed-in and electrical distance between nodes. Then, the models are optimised under a brownfield capacity expansion for the European electricity system for varying spatial resolutions and renewable penetration. Results are compared to each other and to existing clustering approaches in the literature and evaluated on the preciseness of siting renewable capacity and the estimation of power flows. We find that any of the considered methods perform better than the commonly used approach of clustering by country boundaries and that any of the hierarchical methods yield better estimates than the established method of clustering with k-means on the coordinates of the network with respect to the studied parameters. © 2022, The Author(s).

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Fast whitespace correction with encoder-only transformers 61

Fast whitespace correction with encoder-only transformers

引用

61st Annual Meeting of the Association for Computational Linguistics, ACL-DEMO 2023

作者： Bast, Hannah Hertel, Matthias Walter, Sebastian University of Freiburg Department of Computer Science Freiburg Germany Karlsruhe Institute of Technology Institute for Automation and Applied Informatics Karlsruhe Germany

ISBN: (纸本)9781959429708

The goal of whitespace correction is to fix space errors in arbitrary given text. For example, given the text whi te space correctio nwithTransf or mers, produce whitespace correction with Transformers. We compare two Transformer-based models, a characterlevel encoder-decoder model and a byte-level encoder-only model. We find that the encoderonly model is both faster and achieves higher quality. We provide an easy-To-use tool that is over 900 times faster than the previous best tool, with the same high quality. Our tool repairs text at a rate of over 200 kB/s on GPU, with a sequence-Averaged F1-score ranging from 87.5% for hard-To-correct text up to 99% for text without any spaces. © ACL-DEMO 2023. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

ON RESILIENCE OF FUTURE DECARBONISED ENERGY SYSTEMS IN EUROPE 8

ON RESILIENCE OF FUTURE DECARBONISED ENERGY SYSTEMS IN EUROP...

引用

8th International Hybrid Power Plants and Systems Workshop, HYB 2024

作者： Lotze, Jonas Moser, Massimo Hagenmeyer, Veit Department of Strategic Grid Planning TransnetBW GmbH Stuttgart Germany Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen Germany

ISBN: (纸本)9781837241521

The general scope the present model-based research is to analyse climate-neutral scenarios for Europe and to assess the respective resilience of the energy system. Two scenarios are therefore examined, one with an unrestricted global hydrogen market and the other with improved European energy resilience that limits pipeline imports of hydrogen from non-European countries. Key findings include increasing electrification of the heat and transport sectors, widespread use of Power-to-X appliances and, as a result, a doubling of total electricity consumption in Europe. On the power generation side, there is a need for massive expansion of renewables such as wind and photovoltaics. The analysis shows that a more resilient energy system will require additional electrolysis capacity, hydrogen storage and hydrogen grid capacity. The marginal cost of hydrogen will also increase as a result, and a higher price level will subsequently reduce the demand for hydrogen. The overall conclusion is that a transition from fossil fuels to renewables will, in any case, make the energy system much less dependent on imports and thus more resilient. © Energynautics GmbH.

关键词： Carbon capture and utilization

来源：评论

学校读者我要写书评

暂无评论

Ratio-based features for bridge damage detection based on displacement influence line and curvature influence line 11th

Ratio-based features for bridge damage detection based on di...

引用

11th International Conference on Bridge Maintenance, Safety and Management, IABMAS 2022

作者： Döring, A. Vogelbacher, M. Schneider, O. Müller, J. Hinz, S. Matthes, J. Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany Büro für Strukturmechanik Coburg Germany Institute of Photogrammetry and Remote Sensing Karlsruhe Institute of Technology Karlsruhe Germany

ISBN: (纸本)9781032345314

Bridges are getting older and older in Germany. This leads to a high demand of maintenance in the future. Stuctural health monitoring can be a helpful tool for bridge assessment in identifying bridge damage in the early stages. Our goal is a system that is non-invasive, mobile and can be retrofitted on existing bridges under ongoing operation of traffic. The conventional methods of bridge assessment and monitoring use strain measurements and acceleration sensors and are based on modal properties-such as natural frequencies, modal damping and displacement modes or curvature/strain modes-which are prone to environmental changes such as temperature and vehicles. Recent papers introduce features based on the curvature influence line. Some of the introduced features are based on ratios and single vehicle crosses. The advantage of ratio-based features is the reduction of the unknown load. The results show promising results for strain based signals. The question now arises how well the ratio-based features for strain signals can be transferred to the displacement signals measured by an interferometric radar. The advantage of using radar over strain sensors is that the radar is non-invasive and mobile. We compare here the performance of ratio-based features using the displacement influence line with the same features using the curvature/strain influence line for damage detection. In addition to the ratio-based features, we investigate for the comparison other features like peak position and maximum value. We assess the performance of the features with supervised machine learning with various combinations of damage position and damage severity. The considerations are made with an analytical stepped continuous Euler-Bernoulli beam. © 2022 the Author(s).

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

On the Development of a Reconfigurable Platform for the Control of Multiple Collaborative Robots from a Software Engineering Perspective 1

引用

8th Future Technologies Conference, FTC 2023

作者： Salem, Mahmoud Elkaseer, Ahmed Müller, Tobias Scholz, Steffen Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen76344 Germany Karlsruhe Nano Micro Facility Karlsruhe Institute of Technology Eggenstein-Leopoldshafen76344 Germany

ISBN: (数字)9783031474545

ISBN: (纸本)9783031474538

The development of an efficient method to control multiple robots is a critical step to realizing collaborative tasks which, in the era of Industry 4.0, play a significant role in smart flexible manufacturing systems (FMS). In current literature, there have been several attempts to control collaborative robots, but the large majority of the reported works are based on complex and expensive control models. The remainder tend to have approached the problem from the less expensive software engineering perspective. To the best of the authors’ knowledge, most of the studies following the latter approach have been simulations, omitting practical real-world validation. This paper reports the findings obtained while addressing this problem utilizing two strategies, a simulation-based technique and a native software method. Following the systematic implementation of both scenarios, a native algorithm-based platform was developed to control multiple Panda robots in independent, dependent and collaborative ways. The developed platform has demonstrated its capability to control four collaborative Panda robots along with their "OnRobot" grippers in both a synchronized and an asynchronous manner to perform challenging assembly tasks. In addition, the platform is capable of acquiring and transmitting the real-time states of the robots, i.e., joints angle values during motion, to a third-party systems or database for visualization and future corrective actions. Additionally, the robot can recover from collision errors via a software reset without the need for a hard-reset. Finally, it is worth stating that the developed platform is reconfigurable and able to incorporate additional types and numbers of robots into the existing smart flexible system. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Flexible manufacturing systems

来源：评论

学校读者我要写书评

暂无评论

MEMS LiDAR Sensor Simulation for Autonomous Driving: A Novel Framework Using Open-source Tools 56

MEMS LiDAR Sensor Simulation for Autonomous Driving: A Novel...

引用

56th International Symposium on Robotics, ISR Europe 2023

作者： Berens, Felix Elser, Stefan Reischl, Markus Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe76344 Germany Institute for Artificial Intelligence Ravensburg-Weingarten University of Applied Sciences Weingarten88250 Germany

ISBN: (纸本)9783800761418

Sensor data is essential for the development of methods in autonomous driving like object detection, odometry, or SLAM. MEMS LiDAR sensors can be very valuable for autonomous vehicles because they are less prone to shock and wear compared to motorized optomechanical LiDAR sensors. Recording real-world data is complicated and expensive. An alternative is simulated data, but for MEMS LiDAR sensors there is no publicly available software to simulate this type of sensor. With this paper, we introduce a method to simulate data recorded by a MEMS LiDAR sensor like the Blickfeld Cube 1 (and other MEMS LiDAR sensors as well). For this, we use the open-source autonomous driving simulation environment CARLA. Our method can be used to generate a large amount of MEMS LiDAR data faster and cheaper than it would be possible using real-world sensors). We compare our synthetic point cloud with a real-world point cloud and evaluate the similarity. Moreover, we demonstrate the application of our method on the problem of the optimal sensor configuration. © VDE VERLAG GMBH Berlin Offenbach.

关键词： Autonomous Driving MEMS LiDAR Simulate Data

来源：评论

学校读者我要写书评

暂无评论

Boost short-term load forecasts with synthetic data from transferred latent space information

引用

Energy informatics 2022年第1期5卷 1-20页

作者： Heidrich, Benedikt Mannsperger, Lisa Turowski, Marian Phipps, Kaleb Schäfer, Benjamin Mikut, Ralf Hagenmeyer, Veit Karlsruhe Institute of Technology Institute for Automation and Applied Informatics Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen76344 Germany

Sustainable energy systems are characterised by an increased integration of renewable energy sources, which magnifies the fluctuations in energy supply. Methods to to cope with these magnified fluctuations, such as load shifting, typically require accurate short-term load forecasts. Although numerous machine learning models have been developed to improve short-term load forecasting (STLF), these models often require large amounts of training data. Unfortunately, such data is usually not available, for example, due to new users or privacy concerns. Therefore, obtaining accurate short-term load forecasts with little data is a major challenge. The present paper thus proposes the latent space-based forecast enhancer (LSFE), a method which combines transfer learning and data augmentation to enhance STLF when training data is limited. The LSFE first trains a generative model on source data similar to the target data before using the latent space data representation of the target data to generate seed noise. Finally, we use this seed noise to generate synthetic data, which we combine with real data to enhance STLF. We evaluate the LSFE on real-world electricity data by examining the influence of its components, analysing its influence on obtained forecasts, and comparing its performance to benchmark models. We show that the Latent Space-based Forecast Enhancer is generally capable of improving the forecast accuracy and thus helps to successfully meet the challenge of limited available training data. © 2022, The Author(s).

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Framework for Semantic Segmentation of Biomedical Images

A Lightweight Framework for Semantic Segmentation of Biomedi...

引用

作者： Rieken Munke, Friedrich Rettenberger, Luca Reischl, Markus Popova, Anna Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen Germany Institute of Biological and Chemical Systems-Functional and Molecular Systems Karlsruhe Institute of Technology Eggenstein-Leopoldshafen Germany

We introduce a lightweight framework for semantic segmentation that utilizes structured classifiers as an alternative to deep learning methods. Biomedical data is known for being scarce and difficult to label. However, this framework provides a lightweight, easy-to-apply, and fast-to-train approach that can be adapted to changes in image material though efficient retraining. Moreover, the framework is able to adapt to various input sizes making it robust against changes in resolution and is not tied to specialized hardware, which allows efficient application on standard laptops or desktops without GPUs. We benchmark two distinct models, a single structured classifier and an ensemble of structured classifiers, against a U-Net, evaluating overall performance and training speed. The framework is versatile and can be applied to multi-class semantic segmentation. Our study shows that the proposed framework can effectively compete with established deep learning methods on diverse datasets in terms of performance while reducing training time immensely. © 2023 the author(s), published by Walter de Gruyter Berlin/Boston.

关键词： Semantic Segmentation

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：