检索结果-内蒙古大学图书馆

ELLIPTIC EQUATION WITH CRITICAL EXPONENT AND DIPOLE POTENTIAL: EXISTENCE AND DECAY ESTIMATES

Acta Mathematica Scientia 2025年第2期45卷 636-658页

作者： Yu SU Zhisu LIU Senli LIU School of Mathematics and Big Data Anhui University of Science and TechnologyHuainan 232001China School of Mathematics and Physics China University of GeosciencesWuhan 430074China Institute for Advanced Marine Research China University of GeosciencesGuangzhou 511462China College of Mathematics and Computing Science Hunan University of Science and TechnologyXiangtan 411201China

The paper is concerned with a class of elliptic equation with critical exponent and Dipole *** precisely,we make use of the refined Sobolev inequality with Morrey norm to obtain the existence and decay properties of n... 详细信息

关键词： Dipole potential decay estimation Hardy Sobolev critical exponent Henon Sobolev critical exponent

来源：评论

学校读者我要写书评

暂无评论

On convergence of covariance matrix of empirical Bayes hyper-parameter estimator

引用

Control Theory and Technology 2024年第2期22卷 149-162页

作者： Yue Ju Biqiang Mu Tianshi Chen School of Data Science and Shenzhen Research Institute of Big Data The Chinese University of Hong KongShenzhenShenzhen518172GuangdongChina Division of Decision and Control Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of Technology10044StockholmSweden Key Laboratory of Systems and Control Institute of Systems ScienceAcademy of Mathematics and System ScienceChinese Academy of SciencesBeijing100190China

Regularized system identification has become the research frontier of system identification in the past *** related core subject is to study the convergence properties of various hyper-parameter estimators as the sample size goes to *** this paper,we consider one commonly used hyper-parameter estimator,the empirical Bayes(EB).Its convergence in distribution has been studied,and the explicit expression of the covariance matrix of its limiting distribution has been ***,what we are truly interested in are factors contained in the covariance matrix of the EB hyper-parameter estimator,and then,the convergence of its covariance matrix to that of its limiting distribution is *** general,the convergence in distribution of a sequence of random variables does not necessarily guarantee the convergence of its covariance ***,the derivation of such convergence is a necessary complement to our theoretical analysis about factors that influence the convergence properties of the EB hyper-parameter *** this paper,we consider the regularized finite impulse response(FIR)model estimation with deterministic inputs,and show that the covariance matrix of the EB hyper-parameter estimator converges to that of its limiting ***,we run numerical simulations to demonstrate the efficacy of ourtheoretical results.

关键词： Regularized system identification Hyper-parameter estimator Empirical Bayes Convergence of covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Strong Overall Error Analysis for the Training of Artificial Neural Networks Via Random Initializations

引用

Communications in Mathematics and Statistics 2024年第3期12卷 385-434页

作者： Arnulf Jentzen Adrian Riekert School of Data Science and Shenzhen Research Institute of Big Data The Chinese University of Hong KongShenzhenPeople’s Republic of China Applied Mathematics:Institute for Analysis and Numerics University of MünsterMünsterGermany

Although deep learning-based approximation algorithms have been applied very successfully to numerous problems,at the moment the reasons for their performance are not entirely understood from a mathematical point of ***,estimates for the convergence of the overall error have been obtained in the situation of deep supervised learning,but with an extremely slow rate of *** this note,we partially improve on these *** specifically,we show that the depth of the neural network only needs to increase much slower in order to obtain the same rate of *** results hold in the case of an arbitrary stochastic optimization algorithm with *** initializations.

关键词： Deep learning Artificial intelligence Empirical risk minimization Optimization

来源：评论

学校读者我要写书评

暂无评论

ML-driven Emotion Identification for Feedback Analysis in E-learning Platforms

ML-driven Emotion Identification for Feedback Analysis in E-...

引用

2024 OPJU International Technology Conference on Smart computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Chitteti, Chengamma Kopparam, Runvika Ganesh, B.V.S.S. Sutraya, Sukerthi Kamakshi, V. Jangam, Shiridinath School of Computing Dept. of Data Science Tirupati India Dept. of Csse Tirupati India G. Narayanamma Institute of Technology and Science for Women Dept. of Data Science Hyderabad India

ISBN: (纸本)9798350373783

With an emphasis on the cognitive and emotional effects of e-learning platforms, this study fills a research gap concerning user experience studies. The study suggests a nonintrusive technique to evaluate the psychological impacts of e-learning platforms by considering feedback data of users in the form of videos and analyzes emotions from video and decides the user feedback level. This process automates the understanding of feedback in a short amount of time for anyone, without requiring specific knowledge of the system. Feedback analysis for E-Learning platforms using deep learning methods for facial expression analysis is proposed in this work. Convolutional Neural Networks (CNNs), a category of deep learning, has become increasingly popular for its ability to precisely analyze and comprehend emotions from facial photos. These models may efficiently learn and extract essential features by being trained on large datasets of tagged facial expression photos. This application takes video feedback as input for various E-learning platforms and analyzes emotions and displays the predicted emotions on video. A publicly accessible dataset is used to test the proposed technique, and the results show that it achieves 90.3% accuracy. This indicates that the approach is highly effective in accurately recognizing facial emotions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Phylogenetic-Informed Generative Adversarial Network for Predicting Mutations in SARS-CoV-2 2

Phylogenetic-Informed Generative Adversarial Network for Pre...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Chandar, Vijay Nair, Vishnu G. Rajeswari, D. SRM Institute of Science and Technology School of Computing College of Engineering and Technology Department of Data Science and Business Systems Chennai603203 India

ISBN: (纸本)9798350365269

In the pursuit of developing more effective vaccines against viruses like SARS-CoV-2, understanding their potential mutations is crucial. In order to generate protein sequences, this study presents a unique framework that synergistically blends phylogenetic data with Generative Adversarial Networks (GANs). The proposed method combines the strengths of two models: TEMPO, a transformer-based model proficient in leveraging phylogenetic data for mutation detection in SARS-CoV-2, and MutaGAN, a GAN-based model adept in generating synthetic protein sequences. The phylogenetic data from TEMPO is used in this novel design as the input for the MutaGAN generator, replacing the conventional random noise input used in GANs. The generator may now create synthetic protein sequences that are impacted by the evolutionary past included in the phylogenetic data resulting in the creation of artificial protein sequences that are more biologically significant and lifelike. The discriminator portion of the model, similar to MutaGAN, is still in charge of determining whether or not the input sequences comprise a valid parent-child pair and uses sequences produced by the first GAN as extra negative cases. This prevented the model from going too far off its planned route. Additional investigation into this fascinating confluence of bioinformatics and AI may be possible as a result of this study's conclusions. This approach has tremendous promise in many applications, such as the production of more powerful vaccinations, protein engineering, medication design, and improving our knowledge of biological systems, by forecasting how SARS-CoV-2 could change. A precision of 0.662 and an accuracy of around 0.671, together with a Matthews Correlation Coefficient (MCC) score of 0.313, show that the framework performs very well. These scores show that the framework performs better than a number of cutting-edge baseline techniques. The synthetic protein sequences generated by the framework not only bea

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Herbal Remedies on Autism Spectrum Disorder Using AGLSTM Analysis

Exploring the Impact of Herbal Remedies on Autism Spectrum D...

引用

2023 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Bagiyalakshmi, N. Veeramakali, T. SRM Institute of Science and Technology School of Computing Department of Data Science and Business Systems Kattankulathur India

ISBN: (纸本)9798350319200

Autism is a personality disorder that can cause significant emotional, intellectual, and behavioral deficits. Autism is recognized as an illness on the spectrum because, while certain kids might have mild symptoms, others may have extensive life-challenging abnormalities. However, autistic people have unique characteristics and health goals and may react differently to conventional or herbal therapy than others. Herbal medications might be a possible approach to helping autistic people's bodies and brains. However, further research is needed to determine whether herbal therapy is useful for autistic individuals. To gain insight into how people think regarding herbal medication for autism, data must be processed promptly as it is generated, which may be accomplished using sentiment assessment, which analyzes polarization in writings. This paper proposes the AGLSTM Model, a hybrid model that solves the sentiment evaluation issue by combining LSTM with agglomerative clustering. The suggested system signifies text data into numerical vectors that illustrate text features such as the frequency of words and embeddings of phrases using the TF-IDF technique and the word2vec model. Every word becomes assigned to a cluster using a method known as clustering based on how similar it is to the cluster nucleus or other texts in the region. The outcome of the experiment is a set of clusters composed of sentences with comparable emotional content. The LSTM framework can detect long-term correlations between word patterns and classify feedback as positive or negative. © 2023 IEEE.

关键词： AGLSTM Autism Clustering Herbal medicine

来源：评论

学校读者我要写书评

暂无评论

Evolution of Consensus Algorithms in Blockchain Technology

Evolution of Consensus Algorithms in Blockchain Technology

引用

2023 International Conference on Intelligent Systems for Communication, IoT and Security, ICISCoIS 2023

作者： Harshini Poojaa, K. Ganesh Kumar, S. School of Computing SRM Institute of Science and Technology Department of Data Science and Business Systems Chengalpattu India

ISBN: (纸本)9798350335835

Blockchain being a decentralised, distributed ledger, has attracted industries to implement the solutions on blockchain. The transactions are agreed in a deterministic manner because of the availability of consensus algorithms. The state of the machine is concluded based on the agreement generated by the consensus algorithm. The performance of the blockchain system can be increased to the order of magnitude when the right consensus is used. In this paper, the limitations and performance of various consensus algorithms have been reviewed along with the characteristics of the same. In addition to that, this paper compares the consensus algorithms based on various parameters such as speed, double-spending, 51% attack and many more. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Exploring Sentiment Detection in Healthcare: An Exhaustive Analysis

Exploring Sentiment Detection in Healthcare: An Exhaustive A...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Bagiyalakshmi, N. Veeramakali, T. Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798350305708

In our daily lives, sentiment analysis is essential. People usually make decisions after seeking advice from others. We used to rely on our judgments before the internet on the advice of our friends and relatives. But now, we have high-performance source sentiment analysis, which collects and analyses opinions from a variety of channels, including social media. To correctly represent emotion in a phrase, we must concentrate on idioms, sarcasm, negations, and context terms. A range of deep learning and machine learning techniques can be used to overcome the aforementioned issues. The aforementioned parameter will be used by the algorithm to identify the polarity of a statement. This study proposal covers the problems with sentiment analysis as well as its numerous levels. The review talks about the challenges and particularities of sentiment analysis. These have to do with issues like textual information, peculiarities of language, emotional vocabulary relevant to particular domains, and security and confidentiality of data. The report also emphasizes how sentiment analysis might promote public healthcare initiatives, boost pharmaceutical methods for making choices, as well as improve patient care. © 2023 IEEE.

关键词： Deep Learning Healthcare Machine learning Recommendation system Sentiment Analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive sail fish optimizer based optimized region selection for robust video steganography

引用

International Journal of Information Technology (Singapore) 2025年第4期17卷 2417-2427页

作者： Babu, J. Suresh Niranjana, G. Ramana, Kadiyala Department of Computing Science & Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur Chengalpattu India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Chengalpattu India Department of Artificial Intelligence and Data Science Chaitanya Bharathi Institute of Technology (Autonomous) Hyderabad India

Securing data transmission in a digital era is a difficult one due to the broad application of the Internet, personal computers, and mobile phones for communication. Traditional video steganography techniques sometimes fail to identify the best pixels for encoding hidden data, resulting in lowerquality and robustness. To solve this issue, this article proposes an innovative steganography technique that improves the security and quality of data hiding. The proposed method takes cover video and secret images as input. The Structural Similarity Index Measurement (SSIM) first collects key frames from the input video. The adaptive sailfish optimizer (ASFO) is then used to find the best regions within these keyframes to insert the secret data in. To improve security, the discrete wavelet transform (DWT) is applied to the specified region, and the LL band is used for the hiding process. The secret image is encrypted by Adaptive elliptical curve cryptography (AECC) and transformed to binary bits, which then get embedded in the chosen band. This method leads to the construction of a stego-video. The extraction procedure is repeated using the same approach, which ensures secure and robust data transmission. Performance metrics, including PSNR, BER, NAE, TAF, and NC are analyzed to compare each method's efficacy. © Bharati Vidyapeeth's institute of Computer Applications and Management 2025.

关键词： Adaptive elliptical curve cryptography And stego-video Discrete wavelet transform Structural similarity index measurement Video steganography

来源：评论

学校读者我要写书评

暂无评论

QRCODE: Quasi-Residual Convex Deep Network for Fusing Misaligned Hyperspectral and Multispectral Images

引用

IEEE Transactions on Geoscience and Remote Sensing 2024年 62卷 1-15页

作者： Lin, Chia-Hsiang Hsu, Chih-Chung Young, Si-Sheng Hsieh, Cheng-Ying Tai, Shen-Chieh National Cheng Kung University Department of Electrical Engineering Miin Wu School of Computing Tainan70101 Taiwan Institute of Data Science Miin Wu School of Computing National Cheng Kung University Tainan70101 Taiwan National Cheng Kung University Institute of Computer and Communication Engineering Department of Electrical Engineering Tainan70101 Taiwan Institute of Data Science National Cheng Kung University Tainan70101 Taiwan

Considering that hyperspectral image (HSI) is often of lower spatial resolution when compared to multispectral image (MSI), an economical approach for obtaining a high-spatial-resolution (HSR) HSI is to fuse the acquired HSI and MSI, thereby greatly facilitating the subsequent material identification and classification in satellite remote sensing. As satellite-acquired HSI and MSI are often misaligned, the proposed deep neural network does not require the input HSI/MSI to be spatially co-registered, making the challenging fusion network design even more difficult. In this study, we propose a streamlined and efficient convex model integrated into the subnetwork, which obviates the need for complex network structures in learning spatial-spectral relationships, effectively guiding the quasi-residual learning task in our alignment-free fusion network. The convex subnetwork is a low-rank model that leverages the convex geometric structure implicitly embedded in the hyperspectral signature space. To address the misalignment between HSI and MSI effectively, we introduce a novel shifted window attention module (SWAM) that exploits the neighboring correlation in the feature domain, significantly enhancing the performance and stability of the fusion task. Capitalizing on the redundancy among spectrums, we employ grouped convolution to decrease the computational complexity without causing additional performance degradation. The proposed quasi-residual convex deep (QRCODE) network demonstrates the state-of-the-art performance in alignment-free HSI/MSI fusion tasks. © 1980-2012 IEEE.

关键词： Deep neural networks

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：