检索结果-内蒙古大学图书馆

作者： Bruch, Roman Rudolf, Rüdiger Mikut, Ralf Reischl, Markus Institute of Molecular and Cell Biology Mannheim University of Applied Sciences Mannheim Germany Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany

The analysis of microscopic images from cell cultures plays an important role in the development of drugs. The segmentation of such images is a basic step to extract the viable information on which further evaluation steps are build. Classical image processing pipelines often fail under heterogeneous conditions. In the recent years deep neuronal networks gained attention due to their great potentials in image segmentation. One main pitfall of deep learning is often seen in the amount of labeled data required for training such models. Especially for 3D images the process to generate such data is tedious and time consuming and thus seen as a possible reason for the lack of establishment of deep learning models for 3D data. Efforts have been made to minimize the time needed to create labeled training data or to reduce the amount of labels needed for training. In this paper we present a new semisupervised training method for image segmentation of microscopic cell recordings based on an iterative approach utilizing unlabeled data during training. This method helps to further reduce the amount of labels required to effectively train deep learning models for image segmentation. By labeling less than one percent of the training data, a performance of 90% compared to a full annotation with 342 nuclei can be achieved. © 2020 by Walter de Gruyter Berlin/Boston 2020.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Study on Smart Grid Security Testbeds Using MITRE ATT&CK Matrix 14

Comparative Study on Smart Grid Security Testbeds Using MITR...

引用

14th IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2023

作者： Mumrez, Aneeqa Roomi, Muhammad M. Tan, Heng Chuan Mashima, Daisuke Elbez, Ghada Hagenmeyer, Veit Karlsruhe Institute of Technology Institute for Automation and Applied Informatics Kastel Security Research Labs Germany Singapore

ISBN: (纸本)9781665455541

The increasing use of information and communication technologies has led to increasing threats on critical infrastructure like smart grids. Owing to confidentiality issues and difficulties in experimenting cyberattacks on a real environment, testbeds reflecting the characteristics of smart grids have been developed to enable attack experiments and cybersecurity research. In fact, different implementations of smart grid testbeds exist, each with its own challenges and limitations. The comparative study we present here justifies the usability of each type of testbed for different experiments. We begin our study with a selection of state-of-the-art smart grid testbeds, which can be classified into physical, hybrid, and virtual. We then present an evaluation based upon several qualitative metrics and MITRE ATT&CK matrix to demonstrate the coverage of all tactics and techniques to guide about the selection of testbed according to security needs. Finally, we explain applicable tactics and techniques for one of the testbeds through an attack case study to highlight current cybersecurity challenges faced by smart grids. © 2023 IEEE.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

Validating neural networks for spectroscopic classification on a universal synthetic dataset

引用

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

FedKDC: Consensus-Driven Knowledge Distillation for Personalized Federated Learning in EEG-Based Emotion Recognition

引用

IEEE Journal of Biomedical and Health informatics 2025年 PP卷 PP页

作者： Qiu, Xihang Qiu, Wanyong Zhang, Ye Qian, Kun Li, Chun Hu, Bin Schuller, Bjorn W. Yamamoto, Yoshiharu Beijing100081 China Beijing Institute of Technology School of Automation School of Medical Technology Beijing100081 China Shenzhen MSU-BIT University MSU-BIT-SMBU Joint Research Center of Applied Mathematics Shenzhen518172 China Beijing Institute of Technology School of Mathematics and Statistics Beijing100081 China Imperial College London GLAM – the Group on Language Audio & Music LondonSW7 2AZ United Kingdom Technische Universität München CHI Chair of Health Informatics Munich80333 Germany Germany Educational Physiology Laboratory Graduate School of Education University of Tokyo Tokyo1138654 Japan

Federated learning (FL) has gained prominence in electroencephalogram (EEG)-based emotion recognition because of its ability to enable secure collaborative training without centralized data. However, traditional FL faces challenges due to model and data heterogeneity in smart healthcare settings. For example, medical institutions have varying computational resources, which creates a need for personalized local models. Moreover, EEG data from medical institutions typically face data heterogeneity issues stemming from limitations in participant availability, ethical constraints, and cultural differences among subjects, which can slow model convergence and degrade model performance. To address these challenges, we propose FedKDC, a novel FL framework that incorporates clustered knowledge distillation (CKD). This method introduces a consensus-based distributed learning mechanism to facilitate the clustering process. It then enhances the convergence speed through intraclass distillation and reduces the negative impact of heterogeneity through interclass distillation. Additionally, we introduce a DriftGuard mechanism to mitigate client drift, along with an entropy reducer to decrease the entropy of aggregated knowledge. The framework is validated on the SEED, SEED-IV, SEED-FRA, and SEED-GER datasets, demonstrating its effectiveness in scenarios where both the data and the models are heterogeneous. Experimental results show that FedKDC outperforms other FL frameworks in emotion recognition, achieving a maximum average accuracy of 85.2%, and in convergence efficiency, with faster and more stable convergence. © 2013 IEEE.

关键词： Federated learning

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

A Spatial Decomposition Method for Solving the Security-Constrained Unit Commitment Problem 7

A Spatial Decomposition Method for Solving the Security-Cons...

引用

7th IEEE International Humanitarian Technologies Conference, IHTC 2024

作者： Madhusoodhanan, Arjun Kumar Giuntoli, Marco Schmitt, Susanne Harjunkoski, Iiro Poland, Jan Leibfried, Thomas Karlsruhe Institute of Technology Institute of Automation and Applied Informatics Karlsruhe Germany Karlsruhe Institute of Technology Institute for Electrical Energy Systems and High Voltage Technology Karlsruhe Germany Hitachi Energy Research Mannheim Germany

ISBN: (纸本)9798350354645

Today, we are experiencing exponential growth in distributed energy sources and storage systems, such as Battery Energy Storage Systems (BESS), which participate in the day-ahead energy market. Moreover, the need for energy market coupling to ensure social welfare maximization and grid security makes the Security-Constrained Unit Commitment (SCUC) problem more challenging due to the increasing problem size. This work proposes a novel approach for solving the SCUC problem in a distributed manner by decomposing the grid into multiple areas connected by tie-lines. The solution leverages the Alternating Direction Method of Multipliers (ADMM) to solve the problem efficiently. The proposed Spatially Decomposed SCUC method significantly reduces the computational burden arising from the combinatorial nature of the problem. The speed-up and optimality of the proposed method is validated on the IEEE 118-bus and RTE 6468-bus systems. © 2024 IEEE.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

MPC-DICE: An open-source Matlab implementation of receding horizon solutions to DICE

引用

IFAC-PapersOnLine 2018年第5期51卷 120-125页

作者： Faulwasser, Timm Kellett, Christopher M. Weller, Steven R. Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen76344 Germany School of Electrical Engineering and Computing University of Newcastle CallaghanNew South Wales2308 Australia

The most widely used integrated assessment model for studying the economics of climate change is the Dynamic Integrated model of Climate and Economy (DICE). DICE is a nonlinear, time-varying discrete-time system whereby important quantities are calculated by solving an associated optimal control problem. Here, we describe an open-source Matlab implementation of the DICE model which uses Model Predictive Control (MPC) to approximately solve the DICE optimal control problem. © 2018

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

Assessment of a scheduling strategy for dispatching prosumption of an industrial campus

Assessment of a scheduling strategy for dispatching prosumpt...

引用

Internationaler ETG-Kongress 2019: Das Gesamtsystem im Fokusder Energiewende - International ETG Congress 2019: The Overall System in the Focus of the Energy Turnaround

作者： Appino, Riccardo Remo González Ordiano, Jorge Ángel Munzke, Nina Mikut, Ralf Faulwasser, Timm Hagenmeyer, Veit Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen76344 Germany Institute of Electrotechnical Engineering Karlsruhe Institute of Technology Eggenstein-Leopoldshafen76344 Germany

ISBN: (纸本)9783800749553

Effective scheduling of the power exchange with an external grid is of interest for clusters of devices (including consumption, generation and storage) that aim to participate in energy markets. Scheduling is often performed by means of optimization-based algorithms considering uncertain forecasts of inflexible generation and consumption. In this paper, we assess the performance of a previously proposed scheduling algorithm—based on non-parametric probabilistic forecasts both in terms of power and energy—in a realistic industrial campus setting. Simulation results using real data from the KIT north campus underpin the applicability of the proposed algorithm. © VDE VERLAG GMBH Â Berlin Â Offenbach

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

New feature based on influence lines for anomaly detection in bridge monitoring 12th

New feature based on influence lines for anomaly detection i...

引用

12th International Conference on Bridge Maintenance, Safety and Management, IABMAS 2024

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)9781032770406

Bridge monitoring using displacement, strain, acceleration or rotation measurements during normal operation can be a good supplement to conventional manual bridge inspections. In order to detect damage from the measured signal, features must be extracted from the signal that are primarily damage-sensitive. In recent years, features based on the influence lines have been increasingly investigated. The influence line represents the simplified signal that can be measured with a sensor at a fixed position when a single vehicle crosses the bridge. In this paper, we present the new feature normalised integrated influence lines (niil). We show that niil is sensitive to damage, independent of vehicle geometry, velocity, sampling rate, deviation from ideal lane and robust against noise using the analytical bending beam and strain data from a real bridge that has been successively damaged. niil can be calculated based on the curvature, rotation or displacement influence lines. © 2024 The Author(s).

关键词： Anomaly detection

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：