检索结果-内蒙古大学图书馆

HunSum-1: an Abstractive Summarization Dataset for Hungarian

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Barta, Botond Lakatos, Dorina Nagy, Attila Nyist, Milán Konor Ács, Judit Department of Automation and Applied Informatics Budapest University of Technology and Economics Hungary Institute for Computer Science and Control Eötvös Loránd Research Network Hungary

We introduce HunSum-1: a dataset for Hungarian abstractive summarization, consisting of 1.14M news articles. The dataset is built by collecting, cleaning and deduplicating data from 9 major Hungarian news sites through CommonCrawl. Using this dataset, we build abstractive summarizer models based on huBERT and mT5. We demonstrate the value of the created dataset by performing a quantitative and qualitative analysis on the models' results. The HunSum-1 dataset, all models used in our experiments and our code are available open source. © 2023, CC BY.

关键词： Open systems

Best Selection of Generative Adversarial Networks Hyper-Parameters Using Genetic Algorithm

学校读者我要写书评

暂无评论

SN Computer Science 2021年第4期2卷 283页

作者： Alarsan, Fajr Ibrahem Younes, Mamoon Informatics and Decision Supporting Systems Higher Institute for Applied Sciences and Technology Damascus Syrian Arab Republic Faculty of Computer and Automation Engineering Damascus University Damascus Syrian Arab Republic

Generative adversarial networks (GANs) are most popular generative frameworks that have achieved compelling performance. They follow an adversarial approach where two deep models generator and discriminator compete with each other. In this paper, we propose a Generative Adversarial Network with best hyper-parameters selection to generate fake images for digit numbers 1–9 with generator and train discriminator to decide whereas the generated images are fake or true. Genetic algorithm (GA) technique was used to adapt GAN hyper-parameters, the resulted algorithm is named GANGA: generative adversarial network with genetic algorithm. The resulted algorithm has achieved high performance;it was able to get zero value of loss function for the generator and discriminator separately. Anaconda environment with tensorflow library facilitates was used;python as programming language was adapted with needed libraries. The implementation was done using MNIST dataset to validate the work. The proposed method is to let genetic algorithm choose best values of hyper-parameters depending on minimizing a cost function such as a loss function or maximizing accuracy function used to find best values of learning rate, batch normalization, number of neurons and a parameter of dropout layer. © 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Discriminator Generative adversarial networks (GAN) Generator Genetic algorithm Image synthesis MNIST dataset

Composing Power Flow Patterns through Coordinated Dispatch of Energy Packets

学校读者我要写书评

暂无评论

Composing Power Flow Patterns through Coordinated Dispatch o...

IEEE Electronic Power Grid (eGrid)

作者： Dominik Schulz Klemens Schneider Marcel Weßbecher Veit Hagenmeyer Martina Zitterbart Marc Hiller Institute of Electrical Engineering (ETI) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany Institute of Telematics (TM) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany Institute for Automation and Applied Informatics (IAI) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany

The increasing share of distributed renewable generation and electrification poses challenges to the existing power grid and its operation. To address these challenges, the concept of an Energy Packet Grid (EP Grid) has been proposed that uses selected internet design principles for power grids. This paper builds upon the EP Grid architecture and explores the shaping of power flows through a coordinated dispatch of energy packets. It introduces parallel energy packet transfers to maintain constant power over specific durations and to improve the approximation of continuous load or supply curves. A scenario manager is integrated into the architecture to coordinate specified sequences of energy packet transfers. Measurements demonstrate two scenarios of possible energy packet sequences.

关键词：

Dynamic Mapping for Evolutionary Algorithm Based Optimization of Energy Hub Gas Scheduling

学校读者我要写书评

暂无评论

Dynamic Mapping for Evolutionary Algorithm Based Optimizatio...

IEEE International Conference on Smart Energy Grid Engineering (SEGE)

作者： Rafael Poppenborg Katharina Beisswanger Christian Hotz Kevin Förderer Thomas Kolb Veit Hagenmeyer Karlsruhe Institute of Technology (KIT) Institute for Automation and Applied Informatics (IAI) DVGW-Research Center at Engler-Bunte-Institute of Karlsruhe Institute of Technology Karlsruhe Institute of Technology (KIT) Engler-Bunte-Institute Fuel Technology Division (EBI ceb)

To reach the goal for limiting climate change, a large amount of renewable energy sources (RESs) needs to be installed and integrated into the existing electrical grid infrastructure. This leads to an increasing demand for flexibility that can be provided by the promising approach of the Energy Hub Gas (EHG). For intelligently controlling the different components of an EHG enhanced optimization methods are required. Due to the complexity of this optimization task a concept and its evaluation for enhancing the ability of an evolutionary algorithm (EA) to track several objectives is presented. With this concept a dynamic mapping of the objective functions to the fitness value of an EA by calculating a degree of fulfillment (DOF) in relation to the maximum and minimum possible boundary value is enabled. The evaluation of this concept shows a significant improvement of optimization results with increasing the DOF by 10.2%.

关键词：

Nonlinear refractive index and multiphoton absorption measurements of wide bandgap semiconductors materials by femtosecond z-scan method

学校读者我要写书评

暂无评论

Nonlinear refractive index and multiphoton absorption measur...

Bragg Gratings, Photosensitivity and Poling in Glass Waveguides and Materials, BGPP 2022

作者： Karatodorov, Stefan Shehadi, Mariam Stoychev, Lyubomir Yankov, Georgi Tsankov, Docho Shivachev, Boris Petrov, Todor Institute of Solid State Physics Bulgarian Academy of Sciences 72 Tsarigradsko Chaussee Sofia1784 Bulgaria Department of Electrical Motion Automation Systems Faculty of Automatics Technical University of Sofia Bulgaria Institute of Mineralogy and Crystallography Bulgarian Academy of Sciences Sofia1113 Bulgaria Department of Applied Physics Faculty of Applied Mathematics and Informatics Technical University of Sofia Bulgaria

We studied the nonlinear properties of some of the most promising nonlinear media for microelectronic applications - AlN and GaN. The nonlinear refractive index n2 and the multiphoton absorption β of the media are me... 详细信息

ISBN: (纸本)9781957171166

关键词： Aluminum nitride

ALDI++: Automatic and parameter-less discord and outlier detection for building energy load profiles

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Quintana, Matias Stoeckmann, Till Park, June Young Turowski, Marian Hagenmeyer, Veit Miller, Clayton Singapore Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Germany Department of Civil Engineering University of Texas Arlington United States

Data-driven building energy prediction is an integral part of the process for measurement and verification, building benchmarking, and building-to-grid interaction. The ASHRAE Great Energy Predictor III (GEPIII) machine learning competition used an extensive meter data set to crowdsource the most accurate machine learning workflow for whole building energy prediction. A significant component of the winning solutions was the pre-processing phase to remove anomalous training data. Contemporary pre-processing methods focus on filtering statistical threshold values or deep learning methods requiring training data and multiple hyper-parameters. A recent method named ALDI (Automated Load profile Discord Identification) managed to identify these discords using matrix profile, but the technique still requires user-defined parameters. We develop ALDI++, a method based on the previous work that bypasses user-defined parameters and takes advantage of discord similarity. We evaluate ALDI++ against a statistical threshold, variational auto-encoder, and the original ALDI as baselines in classifying discords and energy forecasting scenarios. Our results demonstrate that while the classification performance improvement over the original method is marginal, ALDI++ helps achieve the best forecasting error improving 6% over the winning's team approach with six times less computation time. © 2022, CC BY.

关键词： Matrix algebra

Probabilistic Forecasting of Day-Ahead Electricity Prices and their Volatility with LSTMs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Trebbien, Julius Pütz, Sebastian Schäfer, Benjamin Nygård, Heidi S. Gorjão, Leonardo Rydin Witthaut, Dirk Forschungszentrum Jülich Jülich Germany Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen Germany Faculty of Science and Technology Norwegian University of Life Sciences Ås Norway

Accurate forecasts of electricity prices are crucial for the management of electric power systems and the development of smart applications. European electricity prices have risen substantially and became highly volatile after the Russian invasion of Ukraine, challenging established forecasting methods. Here, we present a Long Short-Term Memory (LSTM) model for the German-Luxembourg day-ahead electricity prices addressing these challenges. The recurrent structure of the LSTM allows the model to adapt to trends, while the joint prediction of both mean and standard deviation enables a probabilistic prediction. Using a physics-inspired approach – superstatistics – to derive an explanation for the statistics of prices, we show that the LSTM model faithfully reproduces both prices and their volatility. Copyright © 2023, The Authors. All rights reserved.

关键词： Long short-term memory

Classification of Bundle Branch Blocks with QRS Templates Extracted from 12-lead ECGs

学校读者我要写书评

暂无评论

Classification of Bundle Branch Blocks with QRS Templates Ex...

作者： Welle, Hannes Nagel, Claudia Loewe, Axel Mikut, Ralf Dössel, Olaf Institute of Biomedical Engineering KIT Fritz-Haber-Weg 1 Karlsruhe Germany Institute for Automation and Applied Informatics KIT Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen Germany

Being non-invasive, cheap and widely available, the 12-lead electrocardiogram (ECG) is a standard method to assess cardiac function. Still, its reliable interpretation requires specialized knowledge and experience, rendering a second opinion valuable. We evaluated the performance of machine learning based classification of 11,705 healthy and bundle branch block 12-lead ECGs from 3 open databases. For each lead of the ECG signal, a representative QRS-complex template was extracted automatically. Principal component analysis (PCA) was applied to the concatenated, normalized and rescaled QRS signals to reduce their dimensionality. Multilayer perceptron and support-vector machine classifiers were trained using the principal components of weighted and non-weighted QRS template signals as input data. Classifiers achieved F1 scores between 0.92 and 0.96 on the test set for different input configurations. Anomaly based weighting slightly improved the performance of the classifiers. Neither class-wise PCA for feature extraction nor adding information on sex, gender and electrical heart axis to the input data yielded considerable improvement of the F1 scores. The achieved classification accuracy is similar to deep learning classifier performances and should generalize robustly to other ECG datasets. Our results suggest that this simple and well interpretable approach based on morphological signal characteristics is suitable for automatically and non-invasively identifying bundle branch block pathologies in clinical or smart electronics contexts. © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Electrocardiograms

A novel criterion for global incremental stability of dynamical systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Vrabel, Robert Slovak University of Technology in Bratislava Institute of Applied Informatics Automation and Mechatronics Bottova 25 Trnava917 01 Slovakia

In this paper, we establish the sufficient conditions guaranteeing global uniform exponential stability, or at least global asymptotic stability, of all solutions for nonlinear dynamical systems, also known as global incremental stability (GIS) of the systems. We provide here an alternative approach for assessment of GIS in terms of logarithmic norm under which the stability becomes a topological notion and also generalize both horizontally and vertically the well-known Demidovich criterion for GIS of dynamical systems. Convergence of all solutions to the origin x = 0, which is not assumed to be an equilibrium state of system, is also analyzed. Theory is illustrated by a simulation *** Codes 93C10, 34D23 © 2022, CC BY.

关键词： Nonlinear dynamical systems