检索结果-内蒙古大学图书馆

5th international conference on data science, machine learning and Applications

作者： Dasari, Kishorebabu Reddy, Siddharth Shirley, G. Sharon Keshav Mem Inst Technol Hyderabad Telangana India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Nowadays, a major cyber-attack is known as a Distributed Denial of Service (DDoS). It disrupts the legitimate users to access the server or network resources. Server or network resource is unavailable is not a small issue these days, because everything is online. So DDoS attacks detection is the key research area to find the best DDoS attack detection. This study evaluate the Logistic Regression, Naive Bayes, Decision Tree, KNN, Random Forest, Ada Boost, Gradient Boost, Multi-Layer Perceptron classification algorithms in order to detect SSDP DDoS attack. CIC-DDoS2019 dataset is used in this study. Classification algorithms evaluated for SSDP DDoS attack detection with different uncorrelated features subsets selected by different correlation methods of Pearson, Kendall and Spearmanmethods. Classification algorithms evaluated by different metrics of accuracy, Log-loss value, ROC-AUC score, K-Fold cross validation accuracy. MLP, KNN classification algorithms gives the best classification results to detect SSDP DDoS attacks.

关键词： DDoS Attack SSDP attack Correlation methods

来源：评论

学校读者我要写书评

暂无评论

Super-Teaching in machine learning 8th

Super-Teaching in Machine Learning

引用

8th international Symposium on Cyber Security, Cryptology, and machine learning, CSCML 2024

作者： Barak-Pelleg, Dina Berend, Daniel Kontorovich, Aryeh Sami Shamoon College of Engineering Beer Sheva84108 Israel Departments of Mathematics and of Computer Science Ben-Gurion University Beer Sheva84105 Israel Department of Computer Science Ben-Gurion University Beer Sheva84105 Israel

ISBN: (纸本)9783031769337

In machine learning, efficiently leveraging large datasets is essential, particularly when computational resources are limited. Sample compression techniques, which involve using carefully chosen subsets of data to train models, provide significant reductions in runtime and memory requirements while preserving generalization performance. This paper investigates a concept known as "super-teaching," where a knowledgeable teacher selectively provides an optimal subset of training data to a learner, thereby enhancing learning outcomes. Building on the work of Ma et al. (2018), who demonstrated that a teacher with complete knowledge of the data distribution could significantly improve a learner’s performance, our study extends this idea beyond the scenario in their paper. We present a more robust and generalized approach, offering insights into how super-teaching can be effectively applied to a broader range of machine learning problems, potentially leading to better training efficiency and improved generalization. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Direct entanglement detection of quantum systems using machine learning

引用

NPJ QUANTUM INFORMATION 2025年第1期11卷 1-14页

作者： Huang, Yulei Che, Liangyu Wei, Chao Xu, Feng Nie, Xinfang Li, Jun Lu, Dawei Xin, Tao Southern Univ Sci & Technol Shenzhen Inst Quantum Sci & Engn Shenzhen Peoples R China Southern Univ Sci & Technol Dept Phys Shenzhen Peoples R China Shenzhen Univ Inst Quantum Precis Measurement Coll Phys & Optoelect Engn State Key Lab Radio Frequency Heterogeneous Integr Shenzhen Peoples R China Quantum Sci Ctr Guangdong Hong Kong Macao Greater Shenzhen Peoples R China Int Quantum Acad Shenzhen Peoples R China

Entanglement plays a crucial role in advancing quantum technologies and exploring quantum many-body simulations. Here, we introduce a protocol aided by neural networks for measuring entanglement in both equilibrium and non-equilibrium states of local Hamiltonians, with a favorable amount of training data. Our numerical simulations across various Hamiltonian models and qubit configurations reveal that this approach can predict comprehensive entanglement metrics, such as R & eacute;nyi entropy, for up to 100 qubits using only single-qubit and two-qubit Pauli measurements. Excitingly, future entanglement dynamics beyond the measurement window can be predicted based solely on previous single-qubit traces. Experimentally, we utilize a nuclear spin quantum processor and a neural network to measure entanglement in the ground and dynamical states of a one-dimensional spin chain. The results demonstrate the feasibility of our method in practical experiments. Therefore, our approach offers a promising method for experimentally measuring entanglement in systems with dozens to hundreds of qubits.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Research on the Detection Methods for Changes in the Mangroves of Dongzhaigang, Hainan from 2019 to 2023 24

Research on the Detection Methods for Changes in the Mangrov...

引用

8th international conference on Electronic Information Technology and Computer Engineering, EITCE 2024

作者： Zhang, Xianyao Lu, Huajun Qiu, Shuailong Liu, Lijin Wu, Zhongqiang School of Information Science and Technology Hainan Normal University Hainan Haikou China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen China

ISBN: (纸本)9798400710094

This study introduces the research methods for detecting changes in the mangroves of Dongzhaigang, Hainan from 2019 to 2023. Mangrove ecosystems play a crucial role in providing habitats and have ecological and economic value, but in recent years, they have faced degradation and management issues. In order to effectively monitor mangrove changes, researchers have utilized remote sensing techniques and machine learning methods for mangrove cover information extraction and classification. The paper describes the methods of estimating mangrove cover using remote sensing satellite imagery and spectral indices and explores the applications of clustering, decision trees, support vector machines, and deep learning in mangrove change detection. The research results indicate that the support vector machine algorithm performs well in classifying mangrove and non-mangrove areas. This study provides a basis for the management and decision-making of Dongzhaigang Mangrove Nature Reserve in Hainan Province and highlights the future research potential in the application of multi-source and multi-resolution data and deep learning techniques. © 2024 Copyright held by the owner/author(s).

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing DDoS Attack Detection Using machine learning 2

Optimizing DDoS Attack Detection Using Machine Learning

引用

2nd international conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Aggarwal, Saransh Behera, Bhagrajyoti Singh, Murari Kumar Sharma, Ajeet Kumar School of Computing Science and Engineering Sharda University Greater Noida India School of Computer Science and Engineering Sharda University Greater Noida India

ISBN: (纸本)9798331530389

The increase in the Distributed Denial of Service attack (DDoS) leads to a significant threat to the network security. Inability to timely and accurately detect DDoS attacks disrupts services offered by companies and the government causing financial losses. Additionally, prolonged DDoS attacks can spoil user experience and degrade company reputation. The recent literature reveals various techniques for detecting DDoS attacks, including pre-trained machine learning and deep learning algorithms. This research paper addresses this challenge by tweaking random forest algorithms for maximum accuracy using CICDDoS2019 dataset. The methodology includes collecting of dataset, data processing, feature scaling and training multiple machine learning algorithms to identify maximum accuracy for detecting DDoS attacks. The result shows improvement of accuracy and precision of machine learning models used. Future work may include training the model for other types of attacks, real time implementation of the model developed, developing a hybrid approach for detection and protection from DDoS attack. © 2025 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Predicting System Performance and Resource Exhaustion with machine learning: Tackling Class Imbalance 1

Predicting System Performance and Resource Exhaustion with M...

引用

1st international conference on Advances in Computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Swati, Shipra Kumar, Naween Dubey, Ankit Saini, Vaibhav Sharma, Subham Pranav, Ayushman Bennett University SCSET U.P. Greater Noida India

ISBN: (纸本)9798331518578

This study introduces a robust machine learning pipeline for event classification, utilizing a large-scale dataset from eight Google Borg compute clusters (May 2019) available via Google Big- Query. The dataset includes detailed job submissions, scheduling decisions, and resource usage data, with enhancements such as 5-minute CPU usage histograms, shared resource reservations, and job-parent relationships critical for MapReduce task analysis. data preprocessing involves imputation for missing values, label encoding for categorical data, and SMOTE to address the class imbalance. Feature scaling using StandardScaler and dimensionality reduction via Principal Component Analysis (PCA) retained 95% of the variance. The dataset was divided into training and testing sets, preserving class distribution. Seven machine learning models were evaluated, spanning linear, non-linear, ensemble, and neural network approaches. The Support Vector machine (SVM) achieved exceptional performance, with 98.0% accuracy, 97.5% cross-validation score, 98.2% precision, 97.8% recall, and 98.0% F1-score. This study highlights the evolution of workloads and resource usage patterns, contributing to developing scalable and efficient event classification frameworks in cloud computing. © 2025 IEEE.

关键词： Cloud computing Event classification Google Borg clusters machine learning Principal component analysis (PCA) Resource usage patterns Synthetic minority oversampling technique (SMOTE)

来源：评论

学校读者我要写书评

暂无评论

Scalable and Interpretable learning Tool Development within Game-based learning Environment: A Case Study of Mission HydroSci 25

Scalable and Interpretable Learning Tool Development within ...

引用

2025 ACM international conference on Supporting Group Work, GROUP Companion 2025

作者： Lu, Wenyi Computer Science University of Missouri ColumbiaMO United States

ISBN: (纸本)9798400711879

This research develops scalable and interpretable learning tools—stealth assessment and a teacher dashboard—using a sophisticated logging system within the Mission HydroSci game-based learning environment. By integrating existing frameworks with customized approaches, the system captures in-game behaviors critical to understanding learning processes. A stealth assessment pipeline, combined with advanced machine learning, and a data-enriched dashboard, is being developed to enhance teacher-student communication. This study contributes a scalable framework for learning tools across diverse game contexts, offering valuable insights for educators, researchers, and game designers to improve both learning and educational game design in classroom settings. © 2025 Copyright held by the owner/author(s).

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Development and Validation of Risk Assessment Model for Pelvic Organ Prolapse Based on A Retrospective Study with machine learning Algorithms

引用

international UROGYNECOLOGY JOURNAL 2025年 1-9页

作者： Mei, Ling Gao, Linbo Wang, Tao Yang, Dong Chen, Weixing Niu, Xiaoyu Sichuan Univ West China Univ Hosp 2 Dept Obstet & Gynecol Chengdu 610041 Peoples R China Sichuan Univ West China Univ Hosp 2 Ctr Translat Med Key Lab Birth Defects & Related Dis Women & Childr Chengdu 610041 Peoples R China Sichuan Univ West China Univ Hosp 2 Lab Metabol & Gynecol Dis Res Chengdu 610041 Peoples R China Guangzhou AID Cloud Technol Co Ltd Dept Data Sci Guangzhou 510663 Peoples R China

Introduction and HypothesisWe aimed to develop and validate a clinically applicable risk assessment model for identifying women at a high risk of pelvic organ prolapse (POP) based on a retrospective *** study enrolled patients with and without POP between January 2019 and December 2021. Clinical data were collected and machine learning models were applied, such as multilayer perceptron, logistic regression, random forest (RF), light gradient boosting machine and extreme gradient boosting. Two datasets were constructed, one comprising all variables and the other excluding physical examination variables. Two versions of the machine learning model were developed. One was for professional doctors, and the other was for community-health providers. The area under the curve (AUC) and its confidence interval (CI), accuracy, F1 score, sensitivity, and specificity were calculated to evaluate the model's performance. The Shapley Additive Explanations method was used to visualize and interpret the model *** total of 16,416 women were recruited, with 8,314 and 8,102 in the POP and non-POP groups respectively. Eighty-seven variables were recorded. Among all candidate models, the RF model with 13 variables showed the best performance, with an AUC of 0.806 (95% CI 0.793-0.817), accuracy of 0.723, F1 of 0.731, sensitivity of 0.742, and specificity of 0.703. Excluding the physical examination variables, the RF model with 11 variables showed an AUC, accuracy, F1 score, sensitivity, and specificity of 0.716, 0.652, 0.688, 0.757, and 0.545 *** constructed a clinically applicable risk warning system that will help clinicians to identify women at a high risk of POP.

关键词： machine learning Pelvic organ prolapse Risk assessment model Shapley additive explanations method

来源：评论

学校读者我要写书评

暂无评论

Understanding Stroke Risk Profiles in Middle-Aged Adults: A Genetic Algorithm-Based Feature Selection Aproach

Understanding Stroke Risk Profiles in Middle-Aged Adults: A ...

引用

18th international Joint conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Gonçalves, Ligia Ferreira de Carvalho Fiorini, Caio Davi Rabelo Franca, Daniel Rocha Noronha, Marta Dias Moreira Song, Mark Alan Junho Galvez, Luis Enrique Zárate Data Science and Artificial Intelligence Pontifícia Universidade Católica de Minas Gerais Rua Claudio Manuel Belo Horizonte Brazil Computer Science Pontifícia Universidade Católica de Minas Gerais Rua Claudio Manuel Belo Horizonte Brazil Institute of Exact Sciences and Computer Science Pontifícia Universidade Católica de Minas Gerais Rua Claudio Manuel Belo Horizonte Brazil

data mining and machine learning techniques have been widely used in the knowledge extraction process of medical databases, one highlight being their use to improve diagnostic systems. Decision trees are supervised black box machine learning models that, although simple, are easy to interpret. In this work, we propose the use of these techniques to describe the profile of middle-aged adults (40-59) diagnosed with stroke, a disease that in Brazil was one of the main causes of death in previous years. The genetic algorithm was applied to extract the best characteristics so that the Decision Tree algorithm could then be used in the database provided by the 2019 National Health Survey to obtain the most comprehensive rules and identify the most relevant attributes for describing the profile of these individuals. The conclusions indicate that the rules generated for middle-aged adults are mainly about routine habits, such as work or salt consumption. © 2025 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Adversarial learning of Summary Statistics for Approximate Bayesian Computation 24

Adversarial Learning of Summary Statistics for Approximate B...

引用

8th international conference on Advances in Artificial Intelligence, ICAAI 2024

作者： Adel, Tameem Cambridge United Kingdom

ISBN: (纸本)9798400718014

Estimating influential parameters in real-world applications can be challenging, especially in problems where the model likelihood is intractable. To perform inference, the machine learning model should be able to understand the underlying phenomena and conditions which have led to the observations in hand. Estimating the posterior distribution of the influential parameters given observations (the inverse problem) can therefore be onerous, especially when the likelihood is intractable. The Approximate Bayesian Computation (ABC) paradigm is the standard statistical methodology to address such likelihood-free problems. In a nutshell, ABC methods establish a proxy for the likelihood based on data simulations. Two main bottlenecks of any ABC technique are the comparisons between observed and simulated datasets, and the manner via which data must be summarized in order to make the eventual data comparisons optimally fit for the inference purpose. We propose an ABC algorithm that learns how to perform data summarization in a data-driven manner, which is not based on pre-selecting summary statistics a priori. The proposed ABC algorithm is based on a neural network which is trained via adversarial learning. We show how the proposed ABC algorithm can infer the posterior distributions of parameters with high fidelity, and with low bias and variance. We apply the algorithm to two different applications and demonstrate its efficacy and robustness with respect to parameter inference. © 2024 Copyright held by the owner/author(s).

关键词： Adversarial machine 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：