检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Hu, Zheyuan Yang, Zhouhao Wang, Yezhen Karniadakis, George Em Kawaguchi, Kenji Division of Applied Mathematics Brown University ProvidenceRI02912 United States Department of Computer Science National University of Singapore Singapore119077 Singapore Advanced Computing Mathematics and Data Division Pacific Northwest National Laboratory RichlandWA United States

Physics-Informed Neural Networks (PINNs) have triggered a paradigm shift in scientific computing, leveraging mesh-free properties and robust approximation capabilities. While proving effective for low-dimensional partial differential equations (PDEs), the computational cost of PINNs remains a hurdle in high-dimensional scenarios. This is particularly pronounced when computing high-order and high-dimensional derivatives in the physics-informed loss. Randomized Smoothing PINN (RS-PINN) introduces Gaussian noise for stochastic smoothing of the original neural net model, enabling the use of Monte Carlo methods for derivative approximation, which eliminates the need for costly automatic differentiation. Despite its computational efficiency, especially in the approximation of high-dimensional derivatives, RS-PINN introduces biases in both loss and gradients, negatively impacting convergence, especially when coupled with stochastic gradient descent (SGD) algorithms. We present a comprehensive analysis of biases in RS-PINN, attributing them to the nonlinearity of the Mean Squared Error (MSE) loss as well as the intrinsic nonlinearity of the PDE itself. We propose tailored bias correction techniques, delineating their application based on the order of PDE nonlinearity. The derivation of an unbiased RS-PINN allows for a detailed examination of its advantages and disadvantages compared to the biased version. Specifically, the biased version has a lower variance and runs faster than the unbiased version, but it is less accurate due to the bias. To optimize the bias-variance trade-off, we combine the two approaches in a hybrid method that balances the rapid convergence of the biased version with the high accuracy of the unbiased version. In addition to methodological contributions, we present an enhanced implementation of RS-PINN. Extensive experiments on diverse high-dimensional PDEs, including Fokker-Planck, Hamilton-Jacobi-Bellman (HJB), viscous Burgers’, Allen-Cahn, and Sine

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Towards the Integration of Web of Things Applications Based on Service Discovery 20th

Towards the Integration of Web of Things Applications Based ...

引用

1st International Workshop on the Web of Things for Humans, WoT4H 2020, 2nd Semantics and the Web for Transport workshop, Sem4Tra 2020 and 6th International Workshop on Knowledge Discovery on the Web, KDWEB 2020 co-located with 20th International Conference on Web Engineering, ICWE 2020

作者： Criado, Javier Boubeta-Puig, Juan Mena, Manel Llopis, Juan Alberto Ortiz, Guadalupe Iribarne, Luis Applied Computing Group University of Almeria Almería Spain Department of Computer Science and Engineering University of Cadiz Cádiz Spain

ISBN: (纸本)9783030656645

The current state of the technologies related to the Web of Things (WoT) and the Internet of Things (IoT) fosters the creation of service directories gathering resource descriptions. These directories are aimed at enabling the service discovery and supporting providers and consumers with a shared element for their communication and interoperability between the involved agents. This interoperability can be ensured by using the abstract layer of the W3C WoT recommendations. However, many of the existing approaches do not include a service discovery mechanism and those that include a WoT directory lack certain functionalities required by distributed systems specific to the WoT such as a Service-Oriented Architecture (SOA). This paper proposes a federated service discovery approach to support the management of WoT applications which ensures that the integration of the whole system components can be addressed by following a SOA. It is aimed at providing query and storage functionality for WoT resources, but also is intended to be connected to other WoT directories by applying a customizable approach based on recommender systems. Thus, we guarantee a flexible mechanism to obtain sets of ranked WoT resources to be utilized in different kinds of applications and domains. © 2020, Springer Nature Switzerland AG.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Application level performance evaluation of wearable devices for stress classification with explainable AI

引用

Pervasive and Mobile computing 2022年 87卷

作者： Chalabianloo, Niaz Can, Yekta Said Umair, Muhammad Sas, Corina Ersoy, Cem Department of Computer Engineering Boğaziçi University Istanbul Turkey Faculty of Applied Computer Science Universität Augsburg Augsburg Germany Newcastle University Newcastle Upon Tyne United Kingdom School of Computing and Communications Lancaster University Lancaster United Kingdom

Stress has become one of the most prominent problems of modern societies and a key contributor to major health issues. Dealing with stress effectively requires detecting it in real-time, informing the user, and giving instructions on how to manage it. Over the past few years, wearable devices equipped with biosensors that can be utilized for stress detection have become increasingly popular. Since they come with various designs and technologies and acquire biosignals from different body locations, choosing a suitable device for a particular application has become a challenge for researchers and end-users. This study compares seven common wearable biosensors for stress detection applications. This was accomplished by collecting physiological sensor data during Baseline, Stress, Recovery, and Cycling sessions from 32 participants. Machine learning algorithms were used to classify four stress classes, and the results obtained from all wearables were compared. Following this, a state-of-the-art explainable artificial intelligence method was employed to clarify our models’ predictions and investigate the influence different features have on the models’ outputs. Despite the results showing that ECG wearables perform slightly better than the rest of the devices, adding a second biosignal (EDA) improved the results significantly, tipping the balance toward multisensor wearables. Finally, we concluded that although the output results of each model can be affected by various factors, in most cases, there is no significant difference in the accuracy of stress detection by different wearables. However, the decision to select a particular wearable for stress detection applications must be made carefully considering the trade-off between the users’ expectations and preferences and the pros and cons of each device. © 2022

关键词： Stresses

来源：评论

学校读者我要写书评

暂无评论

Data Assimilation in the Latent Space of a Convolutional Autoencoder 21st

Data Assimilation in the Latent Space of a Convolutional Aut...

引用

21st International Conference on Computational science, ICCS 2021

作者： Amendola, Maddalena Arcucci, Rossella Mottet, Laetitia Casas, César Quilodrán Fan, Shiwei Pain, Christopher Linden, Paul Guo, Yi-Ke Data Science Institute Department of Computing Imperial College London London United Kingdom Department of Earth Science and Engineering Imperial College London London United Kingdom Department of Chemistry University of Cambridge Cambridge United Kingdom Department of Applied Mathematics and Theoretical Physics University of Cambridge Cambridge United Kingdom Department of Computer Science Hong Kong Baptist University Kowloon Hong Kong

ISBN: (纸本)9783030779764

Data Assimilation (DA) is a Bayesian inference that combines the state of a dynamical system with real data collected by instruments at a given time. The goal of DA is to improve the accuracy of the dynamic system making its result as real as possible. One of the most popular technique for DA is the Kalman Filter (KF). When the dynamic system refers to a real world application, the representation of the state of a physical system usually leads to a big data problem. For these problems, KF results computationally too expensive and mandates to use of reduced order modeling techniques. In this paper we proposed a new methodology we called Latent Assimilation (LA). It consists in performing the KF in the latent space obtained by an Autoencoder with non-linear encoder functions and non-linear decoder functions. In the latent space, the dynamic system is represented by a surrogate model built by a Recurrent Neural Network. In particular, an Long Short Term Memory (LSTM) network is used to train a function which emulates the dynamic system in the latent space. The data from the dynamic model and the real data coming from the instruments are both processed through the Autoencoder. We apply the methodology to a real test case and we show that the LA has a good performance both in accuracy and in efficiency. © 2021, Springer Nature Switzerland AG.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Empowering Marketing Management and Gaming Consumer Interaction Through AI and Citizen science

Empowering Marketing Management and Gaming Consumer Interact...

引用

IEEE Games Media Entertainment (GEM)

作者： Celestine Iwendi Chatti Subba Lakshmi Bala Dhandayuthapani Veerasamy Paul Hollins Damilare Adeola Pradeep Hewage Adedapo Paul Aderemi Piyush Kumar Shukla School of Creative Technologies University of Bolton Bolton United Kingdom Department of Computer Science & Engineering Guru Nanak Institutions Technical Campus Hyderabad Telangana India Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Oman Cultural Research Development School of Arts. University of Bolton Bolton United Kingdom Department of Computer Science & Engineering University Institute of Technology Rajiv Gandhi Proudyogiki Vishwavidyalaya (Technological University of Madhya Pradesh) Bhopal Madhya Pradesh India

ISBN: (数字)9798350374537

ISBN: (纸本)9798350374544

There has been a significant revolution seen by AI getting incorporated into the management and customer relations of companies. The research of the present Artificial Intelligence (AI) revolution that influences a variety of fields i.e. video games are the topic of the article. AI systems such as machine learning and data analytics can help brands understand consumer behaviour in much greater detail; hence, companies can better reach and interest potential consumers through personalized marketing plans and campaigns. This is another case of citizen science that can host a large number of artisanal anglers who can together provide data that can make the research wider-reaching. The proposed scheme improves the level of customer accuracy and tackles trends timely as well as creates slight space for real-time communication by applying neighbour-based recommendation techniques, neural networks, and sentiment analysis. Its supremacy over the conventional methods of statistical significance is highlighted through the advent of predictive analytics and dynamic pricing approaches. The advantage of deploying natural language processing (NLP) is that it helps to understand what the customers mean with how they write. Measuring the key performance indicators at the end of this approach can be called the method of adaptation and flexibility which makes digital marketing not just refer only the success but also turn to the happiness of customers.

关键词： Video games Technological innovation Sentiment analysis Neural networks Companies Pricing Market research

来源：评论

学校读者我要写书评

暂无评论

Hutchinson Trace Estimation for High-Dimensional and High-Order Physics-Informed Neural Networks

arXiv

引用

arXiv 2023年

作者： Hu, Zheyuan Shi, Zekun Karniadakis, George Em Kawaguchi, Kenji Department of Computer Science National University of Singapore Singapore119077 Singapore Division of Applied Mathematics Brown University ProvidenceRI02912 United States Advanced Computing Mathematics and Data Division Pacific Northwest National Laboratory RichlandWA United States

Physics-Informed Neural Networks (PINNs) have proven effective in solving partial differential equations (PDEs), especially when some data are available by seamlessly blending data and physics. However, extending PINNs to high-dimensional and even high-order PDEs encounters significant challenges due to the computational cost associated with automatic differentiation in the residual loss function calculation. Herein, we address the limitations of PINNs in handling high-dimensional and high-order PDEs by introducing the Hutchinson Trace Estimation (HTE) method. Starting with the second-order high-dimensional PDEs, which are ubiquitous in scientific computing, HTE is applied to transform the calculation of the entire Hessian matrix into a Hessian vector product (HVP). This approach not only alleviates the computational bottleneck via Taylor-mode automatic differentiation but also significantly reduces memory consumption from the Hessian matrix to an HVP's scalar output. We further showcase HTE's convergence to the original PINN loss and its unbiased behavior under specific conditions. Comparisons with the Stochastic Dimension Gradient Descent (SDGD) highlight the distinct advantages of HTE, particularly in scenarios with significant variability and variance among dimensions. We further extend the application of HTE to higher-order and higher-dimensional PDEs, specifically addressing the biharmonic equation. By employing tensor-vector products (TVP), HTE efficiently computes the colossal tensor associated with the fourth-order high-dimensional biharmonic equation, saving memory and enabling rapid computation. The effectiveness of HTE is illustrated through experimental setups, demonstrating comparable convergence rates with SDGD under memory and speed constraints. Additionally, HTE proves valuable in accelerating the Gradient-Enhanced PINN (gPINN) version as well as the Biharmonic equation. Overall, HTE opens up a new capability in scientific machine learning for tackl

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Score-fPINN: Fractional Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker-Planck-Lévy Equations

arXiv

引用

arXiv 2024年

作者： Hu, Zheyuan Zhang, Zhongqiang Karniadakis, George Em Kawaguchi, Kenji Department of Computer Science National University of Singapore Singapore119077 Singapore Department of Mathematical Sciences Worcester Polytechnic Institute WorcesterMA01609 United States Division of Applied Mathematics Brown University ProvidenceRI02912 United States Advanced Computing Mathematics and Data Division Pacific Northwest National Laboratory RichlandWA United States

We introduce an innovative approach for solving high-dimensional Fokker-Planck-Lévy (FPL) equations in modeling non-Brownian processes across disciplines such as physics, finance, and ecology. We utilize a fractional score function and Physical-informed neural networks (PINN) to lift the curse of dimensionality (CoD) and alleviate numerical overflow from exponentially decaying solutions with dimensions. The introduction of a fractional score function allows us to transform the FPL equation into a second-order partial differential equation without fractional Laplacian and thus can be readily solved with standard physics-informed neural networks (PINNs). We propose two methods to obtain a fractional score function: fractional score matching (FSM) and score-fPINN for fitting the fractional score function. While FSM is more cost-effective, it relies on known conditional distributions. On the other hand, score-fPINN is independent of specific stochastic differential equations (SDEs) but requires evaluating the PINN model's derivatives, which may be more costly. We conduct our experiments on various SDEs and demonstrate numerical stability and effectiveness of our method in dealing with high-dimensional problems, marking a significant advancement in addressing the CoD in FPL equations. © 2024, CC BY.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Encryption with Image Steganography Based Data Hiding Technique in IIoT Environment

引用

computers, Materials & Continua 2022年第7期72卷 1323-1338页

作者： Mahmoud Ragab Samah Alshehri Hani A.Alhadrami Faris Kateb Ehab Bahaudien Ashary SAbdel-khalek Information Technology Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Centre of Artificial Intelligence for Precision Medicines King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Mathematics Faculty of ScienceAl-Azhar UniversityNaser City11884CairoEgypt Department of Pharmacy Practice Faculty of PharmacyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Medical Laboratory Technology Faculty of Applied Medical SciencesKing Abdulaziz UniversityJeddah21589Saudi Arabia Molecular Diagnostic Lab King Abdulaziz University HospitalKing Abdulaziz UniversityJeddah21589Saudi Arabia Special Infectious Agent Unit King Fahd Medical Research CenterKing Abdulaziz UniversityJeddah21589Saudi Arabia Electrical and Computer Engineering Department Faculty of EngineeringKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Mathematics Faculty of ScienceTaif UniversityTaif21944Saudi Arabia Department of Mathematics Faculty of ScienceSohag UniversitySohag82524Egypt

Rapid advancements of the Industrial Internet of Things(IIoT)and artificial intelligence(AI)pose serious security issues by revealing secret ***,security data becomes a crucial issue in IIoT communication where secrecy needs to be guaranteed in real ***,AI techniques can be utilized to design image steganographic techniques in *** addition,encryption techniques act as an important role to save the actual information generated from the IIoT devices to avoid unauthorized *** order to accomplish secure data transmission in IIoT environment,this study presents novel encryption with image steganography based data hiding technique(EISDHT)for IIoT *** proposed EIS-DHT technique involves a new quantum black widow optimization(QBWO)to competently choose the pixel values for hiding secrete data in the cover *** addition,the multi-level discrete wavelet transform(DWT)based transformation process takes ***,the secret image is divided into three R,G,and B bands which are then individually encrypted using Blowfish,Twofish,and Lorenz Hyperchaotic *** last,the stego image gets generated by placing the encrypted images into the optimum pixel locations of the cover *** order to validate the enhanced data hiding performance of the EIS-DHT technique,a set of simulation analyses take place and the results are inspected interms of different *** experimental outcomes stated the supremacy of the EIS-DHT technique over the other existing techniques and ensure maximum security.

关键词： IIoT security data hiding technique image steganography encryption secure communication

来源：评论

学校读者我要写书评

暂无评论

Tackling the Curse of Dimensionality in Fractional and Tempered Fractional PDEs with Physics-Informed Neural Networks

arXiv

引用

arXiv 2024年

作者： Hu, Zheyuan Kawaguchi, Kenji Zhang, Zhongqiang Em Karniadakis, George Department of Computer Science National University of Singapore 119077 Singapore Department of Mathematical Sciences Worcester Polytechnic Institute WorcesterMA01609 United States Division of Applied Mathematics Brown University ProvidenceRI02912 United States Advanced Computing Mathematics and Data Division Pacific Northwest National Laboratory RichlandWA United States

Fractional and tempered fractional partial differential equations (PDEs) are effective models of long-range interactions, anomalous diffusion, and non-local effects. Traditional numerical methods for these problems are mesh-based, thus struggling with the curse of dimensionality (CoD). Physics-informed neural networks (PINNs) offer a promising solution due to their universal approximation, generalization ability, and mesh-free training. In principle, Monte Carlo fractional PINN (MC-fPINN) estimates fractional derivatives using Monte Carlo methods and thus could lift CoD. However, this may cause significant variance and errors, hence affecting convergence;in addition, MC-fPINN is sensitive to hyperparameters. In general, numerical methods and specifically PINNs for tempered fractional PDEs are under-developed. Herein, we extend MC-fPINN to tempered fractional PDEs to address these issues, resulting in the Monte Carlo tempered fractional PINN (MC-tfPINN). To reduce possible high variance and errors from Monte Carlo sampling, we replace the one-dimensional (1D) Monte Carlo with 1D Gaussian quadrature, applicable to both MC-fPINN and MC-tfPINN. We validate our methods on various forward and inverse problems of fractional and tempered fractional PDEs, scaling up to 100,000 dimensions. Our improved MC-fPINN/MC-tfPINN using quadrature consistently outperforms the original versions in accuracy and convergence speed in very high dimensions. © 2024, CC BY.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Glioma/Glioblastoma Detection in Brain MRI using Pre-trained Deep-Learning Scheme 3

Glioma/Glioblastoma Detection in Brain MRI using Pre-trained...

引用

3rd International Conference on Intelligent computing, Instrumentation and Control Technologies, ICICICT 2022

作者： Rajinikanth, Venkatesan Kadry, Seifedine Damasevicius, Robertas Sujitha, R. Angel Balaji, Gangadharam Mohammed, Mazin Abed Noroff University College Faculty of Applied Computing and Technology Kristiansand94612 Norway Vytautas Magnus University Department of Applied Informatics Kaunas44404 Lithuania St. Joseph's College of Engineering Department of Electronics and Instrumentation Engineering Omr Chennai600119 India M/S Tata Consultancy Services Limited Tcsl Siruseri Sez Unit Sipcot I.T. Park TN Chennai603103 India University of Anbar College of Computer Science and Information Technology Ramadi31001 Iraq

ISBN: (数字)9781665410052

ISBN: (纸本)9781665410052

Convolutional Neural Network (CNN) supported medicinal image examination is extensively accepted due to its reputation and improved accuracy. The investigational outcome obtained with DLS along with a chosen classifier helps to achieve better detection results than the traditional and machine-learning methods. The proposed research examines the performance of pre-trained VGG16 and VGG19 schemes in detecting the brain tumour (Glioma/Glioblastoma) grade using different pooling methods. The classification is performed using SoftMax with five-fold cross-validation, and the products are compared and presented. The brain tumour images considered in this study are collected from The Cancer Imaging Archive (TCIA) dataset. This work considered 2000 images (1000 Glioma and 1000 Glioblastoma) of axial-plane with dimension of 224×224×3 pixels for the assessment, and the attained results are compared. The experimental outcome achieved with Python® confirms that the VGG16 with average-pooling provides a better classification accuracy (>99%) with Decision Tree (DT) compared with other methods considered. © 2022 IEEE.

关键词： Python

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：