检索结果-内蒙古大学图书馆

Gender-Based Analysis of User Reactions to Facebook Posts

Big Data Mining and Analytics 2024年第1期7卷 75-86页

作者： Yassine El Moudene Jaafar Idrais Rida El Abassi Abderrahim Sabour Mathematical Engineering and Computer Science Laboratory Faculty of SciencesIbn Zohr UniversityAgadir 8706Morocco Department of Computer Science Mathematical−High School of Technology Ibn Zohr UniversityAgadir 8706Morocco

Online Social Networks(OSNs)are based on the sharing of different types of information and on various interactions(comments,reactions,and sharing).One of these important actions is the emotional reaction to the *** diversity of reaction types available on Facebook(namely FB)enables users to express their feelings,and its traceability creates and enriches the users’emotional identity in the virtual *** paper is based on the analysis of 119875012 FB reactions(Like,Love,Haha,Wow,Sad,Angry,Thankful,and Pride)made at multiple levels(publications,comments,and sub-comments)to study and classify the users’emotional behavior,visualize the distribution of different types of reactions,and analyze the gender impact on emotion *** of these can be achieved by addressing these research questions:who reacts the most?Which emotion is the most expressed?

关键词： profiling knowledge extraction data mining emotion mining social media data crawling Facebook reactions gender

来源：评论

学校读者我要写书评

暂无评论

The Security of Using Large Language Models:A Survey With Emphasis on ChatGPT

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 1-26页

作者： Wei Zhou Xiaogang Zhu Qing-Long Han Lin Li Xiao Chen Sheng Wen Yang Xiang the School of Science Computing and Engineering Technologies Swinburne University of Technology IEEE the School of Computer and Mathematical Sciences the University of Adelaide Adelaide the Faculty of Science and Engineering Southern Cross University the School of Information and Physical Sciences the University of Newcastle

ChatGPT is a powerful artificial intelligence(AI)language model that has demonstrated significant improvements in various natural language processing(NLP) tasks. However, like any technology, it presents potential security risks that need to be carefully evaluated and addressed. In this survey, we provide an overview of the current state of research on security of using ChatGPT, with aspects of bias, disinformation, ethics, misuse,attacks and privacy. We review and discuss the literature on these topics and highlight open research questions and future *** this survey, we aim to contribute to the academic discourse on AI security, enriching the understanding of potential risks and mitigations. We anticipate that this survey will be valuable for various stakeholders involved in AI development and usage, including AI researchers, developers, policy makers, and end-users.

关键词： Artificial intelligence (AI) ChatGPT large language models (LLMs) security

来源：评论

学校读者我要写书评

暂无评论

Power Evaluation of Some Tests for Inverse Rayleigh Distribution

引用

Annals of Data science 2025年第2期12卷 739-755页

作者： Ahrari, Vahideh Hasanalipour, Parisa Department of Computer Science Shahrekord University Shahrekord Iran Department of Statistics Faculty of Mathematical Sciences Ferdowsi University of Mashhad Mashhad Iran

The Inverse Rayleigh distribution has many applications in the area of reliability studies. It is regarded as a model for a lifetime random variable. It is essential to develop an efficient goodness-of-fit test for this distribution. In this paper, the problem of the goodness-of-fit test for the Inverse Rayleigh distribution based on different statistics is studied. Each method is described, and the corresponding test statistics are constructed. The critical values and power comparisons are also obtained using Monte Carlo computations. The results are discussed and interpreted separately. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

New logarithmic step size for stochastic gradient descent

引用

Frontiers of computer science 2025年第1期19卷 109-118页

作者： Mahsa Soheil SHAMAEE Sajad Fathi HAFSHEJANI Zeinab SAEIDIAN Department of Computer Science Faculty of Mathematical ScienceUniversity of KashanKashan 87317-53153Iran Department of Applied Mathematics Shiraz University of TechnologyShiraz 13876-71557Iran Department of Mathematical Sciences University of KashanKashan 87317-53153Iran

In this paper, we propose a novel warm restart technique using a new logarithmic step size for the stochastic gradient descent (SGD) approach. For smooth and non-convex functions, we establish an O(1/√T) convergence rate for the SGD. We conduct a comprehensive implementation to demonstrate the efficiency of the newly proposed step size on the FashionMinst, CIFAR10, and CIFAR100 datasets. Moreover, we compare our results with nine other existing approaches and demonstrate that the new logarithmic step size improves test accuracy by 0.9% for the CIFAR100 dataset when we utilize a convolutional neural network (CNN) model.

关键词： stochastic gradient descent logarithmic step size warm restart technique

来源：评论

学校读者我要写书评

暂无评论

A Diamond-based approximation algorithm for the shortest link scheduling in wireless networks under SINR model 8

A Diamond-based approximation algorithm for the shortest lin...

引用

8th International Conference on Smart Cities, Internet of Things and Applications, SCIoT 2024

作者： Mohammadi, Neda Bigham, Bahram Sadeghi Alzahra University Faculty of Mathematical Sciences Department of Computer Science Tehran Iran

ISBN: (纸本)9798350374674

The Internet of Things (IoT) is an important technology that is increasingly used in various new applications such as smart cities, smart transportation, mobile healthcare, etc. Link scheduling can effectively reduce latency, improve Quality-of-Service (QoS) and save energy consumption of devices in these networks. In this paper, we study the fundamental problem of shortest link scheduling (SLS) in wireless networks with uniform power assignment and under the Signalto- Interference-plus-Noise-Ratio (SINR) interference model. We propose an O ( log1+∈(dlmax/dlmin) ) Diamond-based SLS (DSLS) algorithm, where ∈ lmax and dlmin are the length of the longest and shortest link, respectively. We partition the link set into disjoint classes and for each class, schedule the links by partitioning the link deployment plane into small diamonds. Theoretical analysis and simulation results show the correctness and efficiency of the DSLS algorithm. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Semi-Self-Supervised Learning for Semantic Segmentation in Images with Dense Patterns

引用

Plant Phenomics 2023年第2期5卷 149-163页

作者： Keyhan Najafian Alireza Ghanbari Mahdi Sabet Kish Mark Eramian Gholam Hassan Shirdel Ian Stavness Lingling Jin Farhad Maleki Department of Computer Science University of SaskatchewanSaskatoonSaskatchewanCanada Mathematics Department Faculty of SciencesUniversity of QomQomIran Department of Mathematics Faculty of Mathematical ScienceShahid Beheshti UniversityTehranIran Department of Computer Science University of CalgaryCalgaryAlbertaCanada

Deep learning has shown potential in domains with large-scale annotated ***,manual annotation is expensive,time-consuming,and ***-level annotations are particularly costly for semantic segmentation in images with dense irregular patterns of object instances,such as in plant *** this work,we propose a method for developing high-performing deep learning models for semantic segmentation of such images utilizing little manual *** a use case,we focus on wheat head *** synthesize a computationally annotated dataset—using a few annotated images,a short unannotated video clip of a wheat field,and several video clips with no wheat—to train a customized U-Net *** the distribution shift between the synthesized and real images,we apply three domain adaptation steps to gradually bridge the domain *** using two annotated images,we achieved a Dice score of 0.89 on the internal test *** further evaluated on a diverse external dataset collected from 18 different domains across five countries,this model achieved a Dice score of *** expose the model to images from different growth stages and environmental conditions,we incorporated two annotated images from each of the 18 domains to further fine-tune the *** increased the Dice score to *** result highlights the utility of the proposed approach in the absence of large-annotated *** our use case is wheat head segmentation,the proposed approach can be extended to other segmentation tasks with similar characteristics of irregularly repeating patterns of object instances.

关键词： instance utilizing consuming

来源：评论

学校读者我要写书评

暂无评论

AN ITERATIVE TWO-GRID METHOD FOR STRONGLY NONLINEAR ELLIPTIC BOUNDARY VALUE PROBLEMS

引用

Journal of Computational Mathematics 2025年第3期43卷 673-689页

作者： Jiajun Zhan Lei Yang Xiaoqing Xing Liuqiang Zhong School of Computer Science and Engineering Faculty of Innovation EngineeringMacao University of Science and TechnologyMacao SAR 999078China School of Mathematical Sciences South China Normal UniversityGuangzhou 510631China

We design and analyze an iterative two-grid algorithm for the finite element discretizations of strongly nonlinear elliptic boundary value problems in this *** propose an iterative two-grid algorithm,in which a nonlinear problem is first solved on the coarse space,and then a symmetric positive definite problem is solved on the fine *** main contribution in this paper is to establish a first convergence analysis,which requires dealing with four coupled error estimates,for the iterative two-grid *** also present some numerical experiments to confirm the efficiency of the proposed algorithm.

关键词： Iterative two-grid method Convergence Strongly nonlinear elliptic problems

来源：评论

学校读者我要写书评

暂无评论

Exploring Social Ties in Informal Conversations about ASD and ADHD: A Graph-Based Approach

Exploring Social Ties in Informal Conversations about ASD an...

引用

2023 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2023

作者： Jamali, Naghmeh Nesari, Mobin Rezvani, Zahra Iran Department of Computer Sciences Iran School of Computer Science Faculty of Mathematical Sciences Alzahra University Tehran Iran

ISBN: (纸本)9798350346473

Studying society from a network perspective involves examining the relationships and interactions among individuals within a society. Informal conversations about medical issues especially in children's neurodevelopmental disorders (NDD) can build a strong relationship that comes from a common problem. This study assesses the ability of novel graph-based approaches to explore how informal conversations about NDD in question-Answering forums can create and grow a substantial dynamic of flows. After preparing and cleaning our dataset, called PerSNA, the network is built based on the questions and answers exchanged. The various features of graphs were extracted based on graph theory. The results indicated that although the number of nodes and edges in these networks is increasing quadratically, the networks are becoming islanded. The utilization of a graph-based analysis technique to examine informal discussions surrounding prevalent topics such as neurodevelopmental disorders represents a novel and promising approach for investigating community behaviors. This analytical method has the potential to facilitate our research efforts and offer a visual means for evaluating the data. Our study followed rigorous protocols to protect the privacy of participants during both data collection and analysis. Our dataset is private but codes are available at https://***/orgs/Persian-SNA/repositories © 2023 IEEE.

关键词： Flow graphs

来源：评论

学校读者我要写书评

暂无评论

Robust WCET Estimation via Ensemble Learning with Fractional-Order Legendre Function Kernels 5

Robust WCET Estimation via Ensemble Learning with Fractional...

引用

5th National and the 1st International Conference on Applied Research in Electrical Engineering, AREE 2025

作者： Monfared, Amir Hussein Ataei Moghaddam, Mahdi Movahedian Sharif-Bakhtiar, Sheedeh Parand, Kourosh Borna, Keivan Kharazmi University Faculty of Mathematics and Computer Science Department of Computer Science Tehran Iran Shahid Beheshti University Faculty of Mathematical Sciences Department of Computer and Data Sciences Tehran Iran Institute for Cognitive and Brain Sciences Shahid Beheshti University Department of Cognitive Modeling Tehran Iran

ISBN: (纸本)9798350377170

Estimating Worst-Case Execution Time (WCET) as a regression problem has become increasingly challenging due to the complexity of modern hardware and software systems. Traditional statistical methods often fall short of providing accurate and reliable estimates. To address these limitations, ensemble learning methods have emerged as a promising approach for capturing edge cases in execution scenarios. This paper proposes a novel ensemble model that integrates fractional-order Legendre functions (FLF) to enrich feature representation. This integration reduces correlations between individual models within the ensemble, enhancing generalization capabilities. Our method achieves significant reductions in Mean Squared Error (MSE) for WCET estimates while maintaining high levels of safeness. Specifically, the proposed model maintained an error below one across most benchmarks, with safeness levels of %100 in 13 out of 16 benchmarks. These findings underscore the efficacy of our approach and its potential to provide robust and accurate WCET estimates for complex systems. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Speech Enhancement 7

Generative Adversarial Networks for Speech Enhancement

引用

7th International Conference on Signal Processing and Information Security, ICSPIS 2024

作者： Hamdan, Mohammad Punjabi, Prateek Yarmouk University Faculty of IT Department of Computer Science Jordan Heriot Watt University School of Mathematical and Computer Sciences Dubai United Arab Emirates

ISBN: (纸本)9798350368673

Speech is the fundamental form of communication among humans. Speech Enhancement is a technique that helps in improving the quality of speech. The most common method used for enhancing speech is the removal of background noise. However, speech is now being used as an input for text-based applications (such as Speech-to-Text), conferencing systems (such as Microsoft Teams), etc. A baseline GAN model is constructed to find out the inefficiencies that are present in the current GAN based approaches for speech enhancement. We propose an improved lightweight novel GAN model for speech enhancement that uses the self-attention layer adapted from non-local attention coupled with the convolutional layers in the discriminator network to improve its performance. The proposed model is evaluated on an independent and unseen test set. The audio generated by the model confirm the viability of the model. © 2024 IEEE.

关键词： Generative adversarial 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：