检索结果-内蒙古大学图书馆

data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： Sudheer Reddy Bandi M Anbarasan G Merlin Linda Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai India Department of Computer Science and Engineering Swarna Bharathi Institute of Science and Technology Khammam India

Synthetic Aperture Radar (SAR) and Optical sensors are very popular depending on their strengths and application needs. The ocean surface will be covered with clouds most of the time and optical sensors cannot capture the information as they cannot operate in dust and cloudy conditions. So, SAR sensors come into existence to capture the atmospheric phenomena in those regions. There is a wide range of texture extraction techniques such as traditional-based wavelet analysis, statistical analysis, local pixel-based approaches, and dimensional reduction approaches. However, these approaches have limitations in boundary extraction, high-dimensional feature extraction, and uniformity representation. In recent times, deep learning (DL) approaches to extract features which varies based on the applications, image interpretation, and so on. At the same time, DL approaches are limited in transparency, computation requirements, and hyperparameter tuning. In contrast, the proposed S5ELBP i.e., Supervised SAR image classification using the integration of Support Vector Machine (SVM) and Scale Selective Extended Local Binary Pattern (SSELBP) extraction techniques shall overcome various challenges of existing traditional and DL approaches such as adaptive thresholding, less computational resources, and noise robustness. Hence, the objective of the proposed methodology is to extract the image features from the Scale Selective Extended Local Binary Pattern (SSELBP). Also, the SSELBP features are integrated with SVM to show the strength of the proposed approach in SAR image classification. Additionally, the performance of the present work is enhanced by comparing the extracted results with various classifiers. Finally, the work is concluded by recommending the scope of future work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection using Machine Learning Algorithms

Fake News Detection using Machine Learning Algorithms

引用

New Frontiers in Communication, Automation, Management and Security (ICCAMS), International Conference on

作者： Tina Babu Rekha R Nair Adithya Challa Rahul Srikanth Sri Sai Aravindan Suhas S Department of Computer Science and Engineering Alliance Univerity Bengaluru India Department of Computer Science & Engineering (Data Science) School of Engineering Dayananda Sagar Univerity Bengaluru India Department of Computer Science & Engineering (AI & ML) School of Engineering Dayananda Sagar Univerity Bengaluru India

ISBN: (数字)9798350317060

ISBN: (纸本)9798350317077

The spread of false news threatens news and information sources, especially in Indian politics. We present a machine learning-based strategy to identify false news by vectorizing and tokenizing news headlines using a pre-defined dataset of authentic and fraudulent news items. We want to create a model that can properly identify news stories by textual content, separating propaganda from real news. Our technique is tested on a benchmark dataset of news items. Our suggested technique outperforms various state-of-the-art false news detection algorithms in the literature. Our methodology can prevent false news and safeguard news and information sources in Indian politics. This technique is versatile and successful for identifying and reducing the impact of false news across several topics and languages.

关键词： Machine learning algorithms Limiting Detectors Forestry Graph theory Security Labeling

来源：评论

学校读者我要写书评

暂无评论

Learning Patterns from Biological Networks: A Compounded Burr Probability Model

arXiv

引用

arXiv 2024年

作者： Chakraborty, Tanujit Naik, Shraddha M. Chattopadhyay, Swarup Das, Suchismita Department of Science and Engineering Sorbonne University Abu Dhabi United Arab Emirates Department of Computer Science & Engineering XIM University Odisha Bhubaneswar India Department of Data Science SP Jain School of Global Management Mumbai India

Complex biological networks, comprising metabolic reactions, gene interactions, and protein interactions, often exhibit scale-free characteristics with power-law degree distributions. However, empirical studies have revealed discrepancies between observed biological network data and ideal power-law fits, highlighting the need for improved modeling approaches. To address this challenge, we propose a novel family of distributions, building upon the baseline Burr distribution. Specifically, we introduce the compounded Burr (CBurr) distribution, derived from a continuous probability distribution family, enabling flexible and efficient modeling of node degree distributions in biological networks. This study comprehensively investigates the general properties of the CBurr distribution, focusing on parameter estimation using the maximum likelihood method. Subsequently, we apply the CBurr distribution model to large-scale biological network data, aiming to evaluate its efficacy in fitting the entire range of node degree distributions, surpassing conventional power-law distributions and other benchmarks. Through extensive data analysis and graphical illustrations, we demonstrate that the CBurr distribution exhibits superior modeling capabilities compared to traditional power-law distributions. This novel distribution model holds great promise for accurately capturing the complex nature of biological networks and advancing our understanding of their underlying mechanisms. © 2024, CC0.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

MLCardiovascularPrediction: Machine Learning-Based Cardiovascular Disease Prediction 3

MLCardiovascularPrediction: Machine Learning-Based Cardiovas...

引用

3rd International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2023

作者： Abdelminaam, Diaa Salama Madbouly, Magda M. Zeid, Magdy Abd-Elghany Elatif Gomaa, Ibrahim Abd Abualigah, Laith Misr International University Faculty of Computer Science Cairo Egypt Benha University Faculty of Computers and Artificial Intelligence Benha Egypt Alexandria University Faculty of Computer and Data Science Alexandria Egypt Alobour High Institute for Computer and Informatics Computer Science Department Cairo Egypt Lebanese American University Department of Electrical and Computer Engineering Byblos13-5053 Lebanon Al-Ahliyya Amman University Hourani Center for Applied Scientific Research Amman19328 Jordan Middle East University Meu Research Unit Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pinang Pulau11800 Malaysia

ISBN: (纸本)9798350306231

Like most diseases that affect a human's life, car-diovascular disease is dangerous and unwanted for anyone who has heard of it as it brings a high risk of death. In today's world, most deaths are caused by heart disease as it could come from age, heritage, smoking, and many factors that could seem normal, and it doesn't matter what part of the world you are in. There must be a way to know or predict if this person is at high risk of cardiovascular disease. This paper and project talk about six algorithms: K-Nearest-Neighbour (KNN), Decision Tree (DT), Naive Bayes, Neural Network, Logistic Regression, and Support Vector Machine (SVM). The results came between 60% to 70% in one dataset and from 80 % to 90 % in the second. Still, they mostly favor the Neural Network algorithm as it can learn and model around complex relationships. The SVM showed different outputs between the two datasets as one is significantly larger than the other, possibly due to the outliers in both datasets being different and more complex in the larger one. Cardiovascular disease can be very dangerous, but finding and discovering it soon can be a lifesaver. These algorithms also can help find and predict it, as it was shown with not just decent, but good and respectable success rates for each one. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Analysis of Rates Derived from Count data Using Generalized Fused Lasso Poisson Model 15th

Spatio-Temporal Analysis of Rates Derived from Count Data ...

引用

15th International KES Conference on Intelligent Decision Technologies, KESIDT 2023

作者： Yamamura, Mariko Ohishi, Mineaki Yanagihara, Hirokazu Department of Statistics Radiation Effects Research Foundation Hiroshima732-0815 Japan Center for Data-driven Science and Artificial Intelligence Tohoku University Sendai980-8576 Japan Mathematics Program Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Higashi-Hiroshima739-8526 Japan

ISBN: (纸本)9789819929689

We propose a method to statistically analyze rates obtained from count data in spatio-temporal terms, allowing for regional and temporal comparisons. Generalized fused Lasso Poisson model is used to estimate the spatio-temporal effects of the rates;the coordinate descent algorithm is used for estimation. The results of an analysis using data on crime rates in Japan’s Osaka Prefecture from 1995 to 2008 confirm the validity of the approach. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Adaptive fused lasso Coordinate descent algorithm Spatio-temporal proportion data

来源：评论

学校读者我要写书评

暂无评论

Purchase intention of Amazon sustainable brands: a hybrid approach of structural equation modeling and Rasch model

引用

SN Business and Economics 2023年第12期3卷 1-29页

作者： Santos, Luiz Diego Vidal Holanda, Francisco Sandro Rodrigues de Santana Oliveira, Catuxe Varjão Pedrotti, Alceu de Menezes, Pedro Vinícius Bertulino Villwock, Ana Paula Schervinski Graduate Program in Intellectual Property Science Universidade Federal de Sergipe-UFS Sergipe São Cristóvão Brazil Agronomy Engineering Department Universidade Federal de Sergipe-UFS Sergipe São Cristóvão Brazil Computer Science Department Instituto Federal de Sergipe-UFS Sergipe Lagarto Brazil

This article conducts a comprehensive examination of brand-based equity closely linked to environmental sustainability in the Amazon Rainforest. The research is primarily dedicated to identifying the factors that influence consumers’ willingness to purchase products from sustainable brands within six categories: cosmetics, tourism, clothing, accessories, and food. The central aim of this study is to investigate how brand equity constructs, rooted in environmental sustainability within the Amazon Rainforest, impact consumer loyalty and purchase intention. To accomplish this objective, a mixed-methodology approach was employed, combining structural equation modeling with item response theory. This study involved 535 potential consumers, and data from eight selected brands served as the basis for the analysis. Within the framework of Purchase Intention (PI), the following variables were regarded as formative constructs: Strategic Brand Positioning (SBP), Perceived Brand Quality (PBQ), Retail Innovation (RI), and Brand Authenticity (BA). The results obtained from the structural equation models underscore the statistical significance and substantial impact of all pathways. Notably, SBP emerged as the most significant contributor to the effect on PI, as hypothesized. Brand equity and environmental sustainability were found to indirectly affect behavioral PI. Consumers exhibited a high level of latent trait (θ), with items consistently reflecting elevated values, confirming their acceptance of products, except brand differentiation. Overall, the findings highlight the effectiveness of branding strategies rooted in environmental sustainability in enhancing the brand equity of small forest companies. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023.

关键词： Amazon Rainforest Brands Entrepreneurship Microenterprises Sustainability performance Sustainable development

来源：评论

学校读者我要写书评

暂无评论

A lightweight and efficient raw data collection scheme for IoT systems

引用

Journal of Information and Intelligence 2024年第3期2卷 209-223页

作者： Yixuan Huang Yining Liu Jingcheng Song Weizhi Meng School of Computer and Information Security Guilin University of Electronic TechnologyGuilin 541004China School of Data Science and Artificial Intelligence Wenzhou University of TechnologyWenzhou 325027China School of Computer Science&Engineering LinYi UniversityLinyi 276000China Department of Aplied Mathematics and Computer Science Technical University of DenmarkKongens Lyngby 2800Denmark

With the prevalence of Internet of Things(loT)devices,data collection has the potential to improve people's lives and create a significant ***,it also exposes sensitive information,which leads to privacy *** approach called N-source anonymity has been used for privacy preservation in raw data collection,but most of the existing schemes do not have a balanced efficiency and *** this work,a lightweight and efficient raw data collection scheme is *** proposed scheme can not only collect data from the original users but also protect their ***,the proposed scheme can resist user poisoning attacks,and the use of the reward method can motivate users to actively provide *** and simulation indicate that the proposed scheme is safe against poison ***,the proposed scheme has better performance in terms of computation and communication overhead compared to existing *** efficiency and appropriate incentive mechanisms indicate that the scheme is practical for IoT systems.

关键词： data privacy Raw data collection loT systems Unlinkability

来源：评论

学校读者我要写书评

暂无评论

SPARQL Generation with Entity Pre-trained GPT for KG Question Answering

arXiv

引用

arXiv 2024年

作者： Bustamante, Diego Takeda, Hideaki Department of Computer Science PUC Santiago Chile Millenium Institute for Foundational Research on Data Santiago Chile Tokyo Japan

Knowledge Graphs popularity has been rapidly growing in last years. All that knowledge is available for people to query it through the many online databases on the internet. Though, it would be a great achievement if non-programmer users could access whatever information they want to know. There has been a lot of effort oriented to solve this task using natural language processing tools and creativity encouragement by way of many challenges. Our approach focuses on assuming a correct entity linking on the natural language questions and training a GPT model to create SPARQL queries from them. We managed to isolate which property of the task can be the most difficult to solve at few or zero-shot and we proposed pre-training on all entities (under CWA) to improve the performance. We obtained a 62.703% accuracy of exact SPARQL matches on testing at 3-shots, a F1 of 0.809 on the entity linking challenge and a F1 of 0.009 on the question answering *** Codes 68P20, 68T50 © 2024, CC0.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Urdu Fake News Detection using TF-IDF Features and TextCNN 13

Urdu Fake News Detection using TF-IDF Features and TextCNN

引用

Working Notes of FIRE - 13th Forum for Information Retrieval Evaluation, FIRE-WN 2021

作者： Ilyas, Muhammad Abdullah Shahzad, Khurram Department of Computer Science University of the Punjab Lahore Pakistan Department of Data Science University of the Punjab New Campus Lahore Pakistan

Social media platforms are widely to exchange ideas and sharing news with each other. Consequently, any idea, post, or new posted on social media is likely to become viral in a short span of time. However, if a fake news becomes viral it can have consequences for the society. Therefore, the detection and eradication of fake news is desired. Recognizing the need for fake news detection, several studies have been conducted for this task in English and Western languages. However, the research in Urdu fake news detection has merely commenced. To promote research and development in this area, the second time in two years, Forum for Information Retrieval Evaluation 2021 has dedicated a track for fake news detection task for Urdu, called UrduFake’21. In this study, we have used three deep learning techniques for Urdu fake news detection, including the state-of-the-art Text CNN with three types of word embeddings, as well as TF-IDF features. The results of the experiments has shown that TextCNN with TF-IDF is the most effective technique that achieved an accuracy of 0.716 and macro average F1 score of 0.663. Furthermore, according to the results released by the organizers of UrduFake’21 our approach is ranked 2nd among the 19 submissions. © 2021 Copyright for this paper by its authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Diagnostic Framework for Mumps Based on Deep Learning with Enhanced Mayfly Optimization Algorithm 1

Diagnostic Framework for Mumps Based on Deep Learning with E...

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Mercy, S. Sudha Madhavi, S. Keerthika, A. Prathima, Ch Prabhu, R.T. R.M.K Engineering College Department of Computer Science & Design Chennai India Vel Tech Multi Tech Dr.Rangarajan Dr Sakunthala Engineering College Department of It Chennai India Aarupadai Veedu Institute of Technology Department of Ece Chennai India Department of Data Science Tirupati India Saveetha School of Engineering Simats Department of Ece Chennai India

ISBN: (纸本)9798350316469

The mumps virus causes a very infectious sickness. The enlargement of the parotid salivary glands can be quite uncomfortable. Mumps treatment centers on symptom management. The illness must take its natural course. While most people experience very moderate symptoms, some develop severe consequences. The mumps virus can be avoided with the use of the MMR vaccination. In this research, we employ a convolutional neural network (CNN) technique to better automate mumps detection. In order to automate mumps detection, the authors of this research suggest a convolutional neural network (CNN) trained using XGBoost Classifier data. Incorporating machine learning (ML) technique comparisons. A mumps dataset consisting of 50×50 RGB picture patches served as the basis for all the models. Quantitative findings from each approach were put through validation testing based on their respective effectiveness metrics. To improve the efficiency of the model, the Mayfly Optimization Algorithm is implemented. Results show that the suggested method is effective, with 97% accuracy, suggesting that it might help decrease diagnostic errors caused by human error. And the suggested system we've developed is so precise that it outperforms the CNN model, which only gets around 92% of the time. Consequently, the suggested method is 5% more accurate than the CNN Model. © 2023 IEEE.

关键词： Convolutional Neural Network Mayfly Optimization Algorithm Mumps Classification XGBoost Classifier

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：