检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Basterrech, Sebastián Clemmensen, Line Rubino, Gerardo Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark INRIA Rennes Bretagne Atlantique Rennes France

Modeling non-stationary data is a challenging problem in the field of continual learning, and data distribution shifts may result in negative consequences on the performance of a machine learning model. Classic learning tools are often vulnerable to perturbations of the input covariates, and are sensitive to outliers and noise, and some tools are based on rigid algebraic assumptions. Distribution shifts are frequently occurring due to changes in raw materials for production, seasonality, a different user base, or even adversarial attacks. Therefore, there is a need for more effective distribution shift detection techniques. In this article, we introduce a self-organized continual learning framework designed for monitoring and detecting distribution changes. We explore the problem in a latent space generated by a bio-inspired self-organizing clustering and statistical aspects of the latent space. In particular, we investigate the projections made by two topology-preserving maps: the Self-Organizing Map and the Scale Invariant Map. Our method can be applied in both a supervised and an unsupervised context. We construct the assessment of changes in the data distribution as a comparison of Gaussian signals, making the proposed method fast and robust. We compare it to other unsupervised techniques, specifically Principal Component Analysis (PCA) and Kernel-PCA. Our comparison involves conducting experiments using sequences of images (based on MNIST and injected shifts with adversarial samples), chemical sensor measurements, and the environmental variable related to ozone levels. The empirical study reveals the potential of the proposed approach. © 2024, CC BY-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An algorithm for distributed time delay identification without a priori knowledge of the kernel

引用

Automatica 2025年 178卷

作者： Ritschel, Tobias K.S. Wyller, John Department of Applied Mathematics and Computer Science Technical University of Denmark DK-2800 Kgs. Lyngby Denmark Department of Mathematics Faculty of Science and Technology Norwegian University of Life Sciences 1432 Å s Norway

Time delays are ubiquitous in industry and nature, and they significantly affect both transient dynamics and stability properties. Consequently, it is often necessary to identify and account for the delays when, e.g., designing a model-based control strategy. However, identifying delays in differential equations is not straightforward and requires specialized methods. Furthermore, existing approaches for identifying distributed time delays in delay differential equations (DDEs) require that the functional form of the involved kernel (also called memory function) is known. In this work, we propose an algorithm for identifying distributed delays, which does not require a priori knowledge of the kernel. Specifically, we 1) approximate the unknown kernel in the DDEs by the probability density function of a mixed Erlang distribution and 2) use the linear chain trick (LCT) to transform the resulting DDEs into ODEs. Finally, the parameters in the kernel approximation are estimated as the solution to a dynamical maximum likelihood problem, and we use a single-shooting approach to approximate this solution. We demonstrate the efficacy of the algorithm using a numerical example that involves a point reactor kinetics model of a molten salt nuclear fission reactor. © 2025 The Author(s)

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Revealing Climate Change from Moon Images with Dimensionality Reduction and Machine Learning 4

Revealing Climate Change from Moon Images with Dimensionalit...

引用

4th International Conference on Sustainable Technologies for Industry 4.0, STI 2022

作者： Thejll, Peter Emerson, Monica Jane Saaduzzaman, D.M. Maruf, Md. Hasan Shihavuddin, ASm Climate Scientist Danish Meteorological Institute Denmark Technical University of Denmark Department for Applied Mathematics and Computer Science Denmark Green University of Bangladesh Eee Department Bangladesh

ISBN: (纸本)9781665490450

Earth's albedo is an important factor governing our planet's energy balance, and accurate measurements can help increase our understanding of the climate system as such, and specifically constrain global climate models. Terrestrial albedo is proportional to the intensity of earthshine, which is the solar radiation reflected off Earth onto the moon. Analyzing pictures of the moon can reveal the Earth's albedo at a lower cost and without the same systematic errors as the classical approach based on satellite images. Our proof-of-concept analysis is conducted in a model-world where realistic lunar images are generated by a geometric model of sunlight scattering between the Earth and the Moon. The analysis presented here is based on 1.2 million synthetically generated images of the Moon at the same phase and, as a consequence the dataset has a low variance suitable for our initial investigations. A random forest machine learning model was trained on the dimension-reduced dataset to predict the albedo and reached the target range of ≤0.3% relative error rate. Several machine learning models and feature extraction algorithms were explored to identify the best possible configuration for this aim and compared in this work. © 2022 IEEE.

关键词： Climate models

来源：评论

学校读者我要写书评

暂无评论

IIoT-based Predictive Maintenance for Oil and Gas Industry 6

IIoT-based Predictive Maintenance for Oil and Gas Industry

引用

6th International Conference on Electronic Information Technology and computer Engineering, EITCE 2022

作者： Jia, Zhiyang Wang, Jihe Deng, Cheng Department of Computer Science China University of Petroleum-Beijing at Karamay Xinjiang Karamay China Department of Mathematics West Yunnan University of Applied Sciences Yunnan Dali China

ISBN: (纸本)9781450397148

The Industrial Internet of Things (IIoT) promises to provide an expanded awareness of field assets and equipment, access to data from across locations, and actionable insights for maximizing operational performance and safety of the oil and gas industry. Using automation and machine learning, with the application of predictive maintenance, efficiencies can be boosted and problems can be mitigated sooner and more effectively. The proposed system is mainly based on the data collection, processing, analysis, and modeling of an enormous number of historical and real-time data generated during the operation of the equipment on the edge side. The data-driven predictive maintenance used machine learning models and deep learning models to predict the remaining useful life (RUL). Bi-LSTM based prediction model has been trained on the cloud, and deployed onto the edge devices. The predictive maintenance process includes data acquisition, data processing, training of machine learning model, equipment health assessment, remaining useful life prediction, strategy formulation, and strategy execution. The predictive maintenance solution driven by the IIoT helps oil and gas companies make predictions before equipment failures have a significant impact on their company's safety level and profits to improve asset reliability and promote cost savings. © 2022 Association for Computing Machinery.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Predicting the Geometric Location of Critical Edges in Adaptive GDSW Overlapping Domain Decomposition Methods Using Deep Learning 26th

Predicting the Geometric Location of Critical Edges in Adapt...

引用

26th International Conference on Domain Decomposition Methods, 2020

作者： Heinlein, Alexander Klawonn, Axel Lanser, Martin Weber, Janine Faculty of Electrical Engineering Mathematics & Computer Science Delft Institute of Applied Mathematics Delft University of Technology Mekelweg 4 CD Delft72628 Netherlands Department of Mathematics and Computer Science University of Cologne Weyertal 86-90 Köln50931 Germany Center for Data and Simulation Science University of Cologne Köln Germany

ISBN: (纸本)9783030950248

For complex model problems with coefficient or material distributions with large jumps along or across the domain decomposition interface, the convergence rate of classic domain decomposition methods for scalar elliptic problems usually deteriorates. In particular, the classic condition number bounds [1, 12] will depend on the contrast of the coefficient function. As a remedy, different adaptive coarse spaces, e.g. [4, 13], have been developed which are obtained by solving certain generalized eigenvalue problems on local parts of the interface, i.e., edges and/or faces. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Domain decomposition methods

来源：评论

学校读者我要写书评

暂无评论

Neural Bayes estimators for censored inference with peaks-over-threshold models

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 19070-19118页

作者： Jordan Richards Matthew Sainsbury-Dale Andrew Zammit-Mangion Raphaël Huser School of Mathematics and Maxwell Institute for Mathematical Sciences University of Edinburgh Edinburgh UK and Statistics Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia Statistics Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia and School of Mathematics and Applied Statistics University of Wollongong Wollongong Australia School of Mathematics and Applied Statistics University of Wollongong Wollongong Australia Statistics Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

Making inference with spatial extremal dependence models can be computationally burdensome since they involve intractable and/or censored likelihoods. Building on recent advances in likelihood-free inference with neural Bayes estimators, that is, neural networks that approximate Bayes estimators, we develop highly efficient estimators for censored peaks-over-threshold models that use augmented data to encode censoring information in the neural network input. Our new method provides a paradigm shift that challenges traditional censored likelihood-based inference methods for spatial extremal dependence models. Our simulation studies highlight significant gains in both computational and statistical efficiency, relative to competing likelihood-based approaches, when applying our novel estimators to make inference with popular extremal dependence models, such as max-stable, r-Pareto, and random scale mixture process models. We also illustrate that it is possible to train a single neural Bayes estimator for a general censoring level, precluding the need to retrain the network when the censoring level is changed. We illustrate the efficacy of our estimators by making fast inference on hundreds-of-thousands of high-dimensional spatial extremal dependence models to assess extreme particulate matter 2.5 microns or less in diameter (PM2:5) concentration over the whole of Saudi Arabia.

关键词： censored data convolutional neural network likelihood-free inference neural estimation spatial extremes threshold exceedance

来源：评论

学校读者我要写书评

暂无评论

An Improved Evolutionary Algorithm for Data Mining and Knowledge Discovery

引用

computers, Materials & Continua 2022年第4期71卷 1233-1247页

作者： Mesfer Al Duhayyim Radwa Marzouk Fahd N.Al-Wesabi Maram Alrajhi Manar Ahmed Hamza Abu Sarwar Zamani Department of Natural and Applied Sciences College of Community-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversitySaudi Arabia Department of Mathematics Faculty of ScienceCairo UniversityGiza 12613Egypt Department of Computer Science Faculty of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Information Systems Faculty of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlkharjSaudi Arabia

Recent advancements in computer technologies for data processing,collection,and storage have offered several chances to improve the abilities in production,services,communication,and *** mining(DM)is an interdisciplinary field commonly used to extract useful patterns from the *** the same time,educational data mining(EDM)is a kind of DM concept,which finds use in educational ***,artificial intelligence(AI)techniques can be used for mining a large amount of *** the same time,in DM,the feature selection process becomes necessary to generate subset of features and can be solved by the use of metaheuristic optimization *** this motivation,this paper presents an improved evolutionary algorithm based feature subsets election with neuro-fuzzy classification(IEAFSS-NFC)for data mining in the education *** presented IEAFSS-NFC model involves data pre-processing,feature selection,and ***,the Chaotic Whale Optimization Algorithm(CWOA)is used for the selection of the highly related feature subsets to accomplish improved classification ***,Neuro-Fuzzy Classification(NFC)technique is employed for the classification of education *** IEAFSS-NFC model is tested against a benchmark Student Performance DataSet from the UCI *** simulation outcome has shown that the IEAFSS-NFC model is superior to other methods.

关键词： Educational data mining feature selection whale optimization classification

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory-based Models for Sleep Quality Prediction from Wearable Device Time Series Data

引用

Procedia computer science 2023年 227卷 1062-1069页

作者： Alam Ahmad Hidayat Arif Budiarto Bens Pardamean Mathematics Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Several studies suggest that sleep quality is associated with physical activities. Moreover, deep sleep time can be used to determine the sleep quality of an individual. In this work, we aim to find the association between physical activities and deep sleep time by modeling the time series data such as heart rate and a number of steps captured from a commercial wearable device. Our previous study demonstrates that deep learning-based time series modeling is well suited for our problem since the temporal patterns in the two physical parameters need to be captured to obtain more accurate results. We first preprocess our series data to have a time-step size of 10 minutes. To improve our previous effort in this modeling, we compare four different variants of Long Short-Term Memory (LSTM)-based models, ranging from single input to dual input models. Our result shows that the simple stacked LSTM model performs better for our data because the remaining models suffer from overfitting due to a larger number of the trained parameters.

关键词： deep learning forecasting sleep quality time series wearable devices

来源：评论

学校读者我要写书评

暂无评论

ZERO DISTRIBUTIONS OF DERIVATIVES OF POLYNOMIAL FAMILIES CENTERING ON A SET

arXiv

引用

arXiv 2023年

作者： Christian, Henriksen Lunde, Petersen Carsten Eva, Uhre Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Department of Science and Environment Roskilde University Denmark

Suppose C ⊂ ℂ is compact. Let qk be a sequence of polynomials of degree nk → ∞, such that the locus of roots of all the polynomials is bounded, and the number of roots of qk in any closed set L not meeting C is uniformly bounded. Supposing that (qk)k has an asymptotic root distribution µ we provide conditions on C and µ assuring the sequence of mth derivatives (Equation presented) also has asymptotic root distribution µ for any m ≥ 1. This complements recent results of Totik, [17].MSC Codes 30C15 (Primary) 37F10, 42C05 (Secondary) Copyright © 2023, The Authors. All rights reserved.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Indonesian Agricultural-crops Classification Using Transfer Learning Model

引用

Procedia computer science 2023年 227卷 128-136页

作者： Mahmud Isnan Alam Ahmad Hidayat Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Department of Mathematics School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Classification of Indonesian crops is a critical task in developing farming and getting more understanding of agriculture. However, there is no clear task in classifying types of crops in Indonesia. Transfer learning has been used successfully in a variety of image classification applications. Thus, in this paper, we collected images of Indonesian crops from the internet randomly and proposed a classification by using transfer learning of deep learning with four pre-trained models: EffficientNet- B0, ResNet18, VGG19, and AlexNet. In the experiment, augmentation techniques such as random horizontal flip, random vertical flip, and random affine were utilized to prevent the network from overfitting. The result found that EfficientNet-B0 outperformed other models with an accuracy of 82.55. Then, the model struggled to distinguish between crops in the same family. According to the results, although transfer learning can work well to classify images of Indonesian agricultural crops, some improvements are still required to address existing issues.

关键词： Agriculture Classification Crop Deep Learning Transfer learning

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：