检索结果-内蒙古大学图书馆

2nd international conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Nakerakanti, Sravan Kumar Chirraiahgari, Gokul Krishna Reddy Athilakshmi, R. Department of Computational Intelligence SRM Institute of Science and Technology Faculty of Engineering and Technology KTR campus Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Faculty of Engineering and Technology KTR campus Chennai India

ISBN: (纸本)9798350340235

The COVID-19 pandemic has had a profound impact on societies across the globe. Prioritizing the goal of achieving herd immunity is crucial for reducing the spread of the virus, and thus, this research places a strong emphasis on this objective. This study aims to emphasize the importance of understanding and predicting herd immunity levels for COVID-19 using advanced machine learning algorithms to ensure high-quality predictions that are easily accessible. By leveraging various data sources such as vaccination data, population statistics, and daily COVID-19 case counts, this research study has developed predictive models to estimate the threshold required for herd immunity. Our approach involves employing a range of machine-learning techniques, including regression analysis, and ensemble methods along with an Explainable and Susceptible-Infectious-Recovered (SIR) Forecasting model, to capture the complex interactions between infection rates, vaccination campaigns, and population demographics. The performance of our models has been rigorously evaluated and validated against COVID-19 data. The proposed model combines the interpretability of the SIR model with the predictive power of machine learning and Explainable-AI, providing a transparent and reliable framework for herd immunity estimation. The findings highlight the importance of explainable AI in public health decision-making and provide valuable insights into herd immunity dynamics for COVID-19. © 2023 IEEE.

关键词： Corona Virus Disease 2019 (COVID-19) Explainable Artificial Intelligence (XAI) Herd Immunity Susceptible Infectious Recovered (SIR) model

来源：评论

学校读者我要写书评

暂无评论

A Review of Malware Detection Applications and Research 2nd

A Review of Malware Detection Applications and Research

引用

2nd international conference on Network Simulation and Evaluation, NSE 2023

作者： Bai, Youming Li, Shudong Han, Weihong Wu, Xiaobo Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China Department of New Networks Peng Cheng Laboratory Shenzhen518000 China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China

ISBN: (纸本)9789819745210

Malware, as one of the main threats to computer systems and network security, is constantly evolving and growing, causing serious impacts on individual users, business organizations, and national security. This review summarizes and sorts out the current research status in the field of malware detection, focusing on the file structure, common types of malware, malware camouflage techniques, common analysis methods and techniques for malware detection, including feature based static analysis, dynamic analysis, machine learning methods, etc. Furthermore, this article discusses the methods and applications of malware detection, and analyzes some methods and ideas for detecting malware based on different features. Through the review of this article, readers can comprehensively understand the current status and development trends of malware detection, providing reference and guidance for improving network security protection capabilities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Stateful MapReduce Framework for mRMR Feature Selection Using Horizontal Partitioning 1

引用

9th international conference on Pattern Recognition and machine Intelligence (PReMI)

作者： Yelleti, Vivek Prasad, P. S. V. S. Sai Univ Hyderabad Sch Comp & Informat Sci Hyderabad 500046 Telangana India

ISBN: (数字)9783031127007

ISBN: (纸本)9783031126994;9783031127007

Feature selection (FS) is an important pre-processing step in building machine learning models. minimum Redundancy and Maximum Relevance (mRMR) approach has emerged as one of the successful algorithms in obtaining irredundant feature subset involving only bivariate computations. In the current digital age, owing to the prevalence of very large scale datasets, an imminent need has arisen for scalable solutions using distributed/parallel algorithms. MapReduce solutions are proven to be one of the best approaches to design fault-tolerant and scalable solutions. This work analyses the existing Horizontal MapReduce approaches for mRMR feature selection and identifies the limitations thereof. It is observed that existing approaches involve redundant and repetitive computations and lacks a metadata framework to diminish them. This motivated us to propose Horizontal partitioning based MapReduce solutions namely HMR_mRMR, is an Iterative MapReduce algorithms and is designed under Apache Spark. Appropriate usage of metadata framework and solution formulation optimizes the computations in the proposed approaches. The comparative experimental study is conducted with existing approaches to establish the importance of HMR_mRMR.

关键词： Feature Selection mRMR Big data Horizontal partitioning MapReduce Iterative MapReduce

来源：评论

学校读者我要写书评

暂无评论

Deep Inception V5 Convolution Neural Network to detect and prevent the propagation of deepfake information in Social Media Applications and Research databases 8

Deep Inception V5 Convolution Neural Network to detect and p...

引用

8th international conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Kirubanandham, K. Suriyaprakash, S. Sabareeswaran, G. Sanjay, P. Shalini, A. Karpagam Academy of Higher Education Computer Science and Engineering Coimbatore India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376425

Online social media application and research databases are witnessing an exponential growth of deep cloned and deepfake information due to AI tools like ChatGPT. Online social media application and Research databases has been envisioned as knowledge sharing medium among the researchers and subscribers. Especially many plagiarism detection tools using machine learning architectures has devised to mitigate the submission of the duplicate and similar content but still leads to numerous challenges in managing cloned and optimized information by Artificial intelligence tools. In this article, a novel objective is set to design a quality assessment tool for research article and information uploaded to the social media and research databases. In order to achieve that objective, deep learning architecture entitled deep inception V5 convolution Neural Network is designed to detect and prevent propagation of the deep cloned and AI optimized content in research databases and social media. To perform the model training and testing, twitter dataset and Scopus dataset in the specified area during years from 2019 to 2024 has been extracted. Initially data preprocessing is carried out to normalize and annotate the sentences. Latent discriminant analysis approach is applied to extract the concept drift and vocabulary edited features from the pre-processed sentences. Those features are represented as word embedding vector. Embedding vector is projected to the deep inception V5 Convolutional Neural Network to generate feature map through inception layers. Further fully connected layer composed of the activation function incorporating ReLu approach, Softmax function incorporating the random forest classifier is to detect the deep cloned content and loss function incorporating the cross entropy is to eliminate over fitting and underfitting issues. Next, testing data is applied to trained model to evaluate the effectiveness of the detection approach using cross fold validation. Experimen

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep learning and IoT for COVID Detection and Health Monitoring 3

Deep Learning and IoT for COVID Detection and Health Monitor...

引用

3rd international conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Devi, D.Rukmani Kingslin, M.Theodore Josphine, C.Vimala Manivannan, Kirankumar Rajavel, A. Ramalakshmi, R. R.M.D Engineering College Department of Electronics and Communication Engineering Chennai India R.M.K College of Engineering College & Technology Department of Electronics and Communication Engineering India R.M.K Engineering College Department of Artificial Intelligence and Data Science Chennai India Easwari Engineering College Department of Electronics and Communication Engineering India Electronics and Instrumentation Engineering Kamaraj College of Engineering and Technology Virudhunagar India Ramco Institute of Technology Department of Electronics and Communication Engineering Rajapalayam India

ISBN: (纸本)9798350343632

Covid-19 has been spreading globally since 2019, and the significant death toll from delayed detection has been a consequence. One way to solve this issue is to use AI to swiftly identify Covid-19 without having to deal with problems like a shortage of testing kits. To this end, this study has developed a system that uses both deep learning and machine learning techniques to detect the presence of Covid-19 in lung X-ray images. While the KNN method is used in machine learning to classify the image and detect COVID-19, DF-Net is used in deep learning to optimize the image and provide more clarity. Because DL and ML algorithms work together, this method combines the advantages of a high degree of accuracy with a shorter training period. This study also integrated a health monitoring system that uses Internet of Things (IoT) sensors to take a patient's temperature and heart rate;the data is updated on the cloud. © 2023 IEEE.

关键词： Deep learning (DL) DF-Net Global Monitoring (GM) K-Nearest Neighbors (KNN) machine learning (ML)

来源：评论

学校读者我要写书评

暂无评论

Contribution-based Federated learning client selection

引用

international JOURNAL OF INTELLIGENT SYSTEMS 2022年第10期37卷 7235-7260页

作者： Lin, Weiwei Xu, Yinhai Liu, Bo Li, Dongdong Huang, Tiansheng Shi, Fang South China Univ Technol Sch Comp Sci & Engn Guangzhou Peoples R China Pengcheng Lab Shenzhen Peoples R China South China Normal Univ Sch Comp Sci Guangzhou Peoples R China

Federated learning (FL), as a privacy-preserving machine learning paradigm, has been thrusted into the limelight. As a result of the physical bandwidth constraint, only a small number of clients are selected for each round of FL training. However, existing client selection solutions (e.g., the vanilla random selection) typically ignore the heterogeneous data value of the clients. In this paper, we propose the contribution-based selection algorithm (Contribution-Based Exponential-weight algorithm for Exploration and Exploitation, CBE3), which dynamically updates the selection weights according to the impact of clients' data. As a novel component of CBE3, a scaling factor, which helps maintain a good balance between global model accuracy and convergence speed, is proposed to improve the algorithm's adaptability. Theoretically, we proved the regret bound of the proposed CBE3 algorithm, which demonstrates performance gaps between the CBE3 and the optimal choice. Empirically, extensive experiments conducted on Non-Independent Identically Distributed data demonstrate the superior performance of CBE3-with up to 10% accuracy improvement compared with K-Center and Greedy and up to 100% faster convergence compared with the Random algorithm.

关键词： client contribution-based EXP3 Federated learning global models Non-Independent Identically Distributed

来源：评论

学校读者我要写书评

暂无评论

Energy Harvesting Design for Cooperative Reconfigurable Intelligent Surface with Multi-Agent Deep Reinforcement learning 10

Energy Harvesting Design for Cooperative Reconfigurable Inte...

引用

10TH international conference ON INTELLIGENT data AND SECURITY (IDS)

作者： Tao, Yihang Wu, Jun Pan, Qianqian Chen, Xiuzhen Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China Waseda Univ Grad Sch Informat Prod & Syst Fukuoka Japan Univ Tokyo Sch Engn Dept Syst Innovat Tokyo Japan

ISBN: (纸本)9798350389487;9798350389494

Cooperative reconfigurable intelligent surface (Cooperative-RIS)-assisted communication systems have been proven to provide more smart computing and communication ability than single-RIS or multi-distributed-RIS systems regarding beamforming gain and channel diversity. However, the increased number of deployed RISs brings heavier energy consumption, which makes the cooperative-RIS system less sustainable. The majority of previous works mainly study energy harvesting (EH) for single-RIS systems which cannot be directly applied to the cooperative-RIS systems. In this paper, we study the EH for cooperative-RIS-assisted communication systems. Specifically, we first model the cooperative beamforming and EH optimization as a non-convex problem. Besides, we propose a multi-agent deep deterministic policy gradient (MADDPG)-based EH efficiency maximization scheme for cooperative RISs while satisfying an acceptable sum rate. Finally, experimental results show the effectiveness of our proposed scheme.

关键词： smart communication reconfigurable intelligent surface energy harvesting cooperative beamforming multi-agent deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

BU MET ABA Program to Quantitative Trading in Energy Market 19th

BU MET ABA Program to Quantitative Trading in Energy Market

引用

19th EAI international conference on Computer science and Education in Computer science, CSECS 2023

作者： Yu, Hanbo Department of Administrative Sciences Boston University Metropolitan College BostonMA02215 United States

ISBN: (纸本)9783031446672

This paper presents a study conducted by the author during his enrollment in the applied Business Analytics program at BU Metropolitan College from September 2019 to January 2021. Equipped with the acquired techniques and skills, the author subsequently joined a high-tech energy company and engaged in quantitative trading to capitalize on the financial opportunities presented by the DART spread. The paper provides an overview of the New England wholesale energy market, including an explanation of how the DALMP and RTLMP are settled, highlights extreme market events, and discusses the market's chaotic nature. The author further describes the qualitative and quantitative approaches employed, such as machine learning, statistical analysis, and data mining, which enabled him to achieve an impressive annual rate of return of 25.52% and a peak daily rate of return of 334.87% (translating to net earnings of $100,462.36 within a single day) through quant trading. © ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering 2023.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Prediction of Heart Disease Severity Using Hierarchically-Structured machine-learning Models with Feature Space Reduction

Prediction of Heart Disease Severity Using Hierarchically-St...

引用

17th international Joint conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2024

作者： Kiuchi, Ayami Fujita, Tomoya Yamana, Hayato Department of Computer Science and Engineering Waseda University Tokyo Japan Department of Computer Science and Communications Engineering Waseda University Tokyo Japan Faculty of Science and Engineering Waseda University Tokyo Japan

Heart disease is the primary cause of death worldwide according to the 2019 statistics published by the World Health Organization (WHO), with roughly 8.9 million people dying annually. Predicting the likelihood and severity of this disease leads to earlier detection and helps reduce the workload of medical professionals. Previous studies have adopted a one-time classification that is insufficient to predict heart disease severity. This study proposes a novel classification method to enhance the prediction accuracy of heart disease by using: 1) a hierarchical binary-classification technique to classify the severity in order from the lowest level and 2) a data-preprocessing technique to transform continuous values into binary values based on medical knowledge and statistics information to decrease the feature space. An experimental evaluation of the heartdisease dataset from the UC Irvine (UCI) machine-learning repository confirms that the proposed method achieves the highest accuracy at 100% in predicting the presence of heart disease and at 93.13% in its severity level. In addition, the proposed method achieved 96.67%, 91.25%, 90.59%, and 93.64% accuracy for severity prediction in the Cleveland, Hungarian, Long-Beach-VA, and Switzerland datasets, respectively. © 2024 by SCITEPRESS–science and Technology Publications, Lda.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Selection via Multi-Structure learning and Indicator Matrix

Unsupervised Feature Selection via Multi-Structure Learning ...

引用

2024 international conference on New Trends in Computational Intelligence, NTCI 2024

作者： Hu, Zebiao Gao, Xiaoyu Bian, Ziwei Wang, Jian Ablameyko, Sergey V. Qingdao China Qingdao China Belarusian State University Faculty of Applied Mathematics and Computer Science Minsk Belarus

ISBN: (纸本)9798331517021

Traditional feature selection methods usually only consider a specific geometric structure of the original data, which cannot reveal the most essential underlying structure of the data. Apart from this, a regularization constraint with sparsity is often imposed on the mapping matrix, which inevitably leads to additional parameter setting issues. To address these challenges, a novel unsupervised feature selection via multi-structure learning and indicator matrix (UFSMI) is proposed in this study. More concretely, we construct a unified framework that incorporates multi-structure learning and feature selection. UFSMI first explores the global and local geometric structure of high dimensional data in subspace to excavate the intrinsic structure of data, effectively reducing the interference of redundant features. Then, an indicator matrix for feature selection that can explicitly indicate which features should be selected is in-troduced without imposing any regularization constraints. Finally, the most useful subset of features can be obtained based on the indices of the non-zero elements in the indicator matrix. A series of experiments are conducted to demonstrate the effectiveness and superiority of the proposed method on nine real-word high dimensional datasets by comparing with existing state-of-the-art feature selection methods. © 2024 IEEE.

关键词： Unsupervised 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：