检索结果-内蒙古大学图书馆

A New Cybersecurity Approach Enhanced by xAI-Derived Rules to Improve Network Intrusion Detection and SIEM

computers, Materials & Continua 2025年第5期83卷 1607-1621页

作者： Federica Uccello Marek Pawlicki Salvatore D'Antonio RafałKozik MichałChoras Centro Direzionale Department of EngineeringUniversity of Naples‘Parthenope’Isola C4Napoli80133Italy Department of Computer and Information Science Software and SystemsLinköping UniversityLinköping58183Sweden ITTI Sp.z o.o. Pozna´n61-612Poland Faculty of Telecommunications Computer Science and Electrical EngineeringBydgoszcz University of Science and TechnologyBydgoszcz85-796Poland

The growing sophistication of cyberthreats,among others the Distributed Denial of Service attacks,has exposed limitations in traditional rule-based Security information and Event Management *** machine learning–based intrusion detection systems can capture complex network behaviours,their“black-box”nature often limits trust and actionable insight for security *** study introduces a novel approach that integrates Explainable Artificial Intelligence—xAI—with the Random Forest classifier to derive human-interpretable rules,thereby enhancing the detection of Distributed Denial of Service(DDoS)*** proposed framework combines traditional static rule formulation with advanced xAI techniques—SHapley Additive exPlanations and Scoped Rules-to extract decision criteria from a fully trained *** methodology was validated on two benchmark datasets,CICIDS2017 and *** rules were evaluated against conventional Security information and Event Management Systems rules with metrics such as precision,recall,accuracy,balanced accuracy,and Matthews Correlation *** results demonstrate that xAI-derived rules consistently outperform traditional static ***,the most refined xAI-generated rule achieved near-perfect performance with significantly improved detection of DDoS traffic while maintaining high accuracy in classifying benign traffic across both datasets.

关键词： Cybersecurity explainable artificial intelligence intrusion detection system rule-based SIEM distributed denial of service

来源：评论

学校读者我要写书评

暂无评论

Adaptive residual convolutional neural network for moiré image restoration

引用

International Journal of information technology (Singapore) 2025年第2期17卷 783-791页

作者： Malagi, Vindhya P. Naresh, E. Mithra, C. Suresh, B. V. N. V. Krishna Department of AI & amp ML Dayananda Sagar College of Engineering Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Chennai 600062 India Computer Science & amp Engineering KLEF KL University Andhra Pradesh Vaddeswaram India

Restoring Moiré images presents significant challenges due to the complex interference patterns that obscure image details. These patterns often degrade the quality of images, making accurate restoration crucial for various applications. Effective Moiré image restoration requires advanced techniques to overcome the difficulties posed by these intricate artifacts. This study introduces an Adaptive Residual Convolutional Neural Network (RCNN) for Moiré image restoration, augmented with the Zebra Optimization Algorithm (ZOA) to enhance both feature extraction and restoration accuracy. The hybrid model leverages ZOA's capability to balance exploration and exploitation, optimizing network parameters to improve learning efficiency. Tested on the DIV2K dataset, this approach demonstrates significant improvements in handling complex Moiré patterns, as evidenced by enhanced Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values. © The Author(s) 2024.

关键词： Adaptive residual convolutional neural network Moiré images Peak signal-to-noise ratio Structural similarity index measure Zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Few-shot semantic segmentation in complex industrial components

引用

Multimedia Tools and Applications 2025年第2期84卷 1013-1030页

作者： Xu, Caie Wang, Bingyan Gan, Jin Jiang, Jin Wang, Yu Tu, Minglei Zhou, WuJie School of Information and Electronic Engineering Zhejiang University of Science and Technology No.318 Liuhe Road Zhejiang Hangzhou310023 China College of Computer Science and Technology University of California San Diego 9500 Gilman Dr LA JollaCA92093 United States Information Center Liuzhou Traditional Chinese Medicine Hospital No. 32 JieFangBei Road GuangZhou LiuZhou545001 China

In the semantic segmentation of complex industrial parts, it is usually impossible to obtain enough defective industrial parts for training. This paper proposes a few sample semantic segmentation model based on complex industrial components to address this issue. This model adopts a U-shaped structure and skip connections to better learn the detailed features of high-resolution data. To minimize noise interference in this process, we introduce a gated attention module to reduce noise in the fusion of two types of feature information. Meanwhile, we propose an adaptive multi-scale attention module to better extract global information from advanced feature information. Compared with similar methods, the proposed model achieved leading results in small sample industrial datasets and demonstrated its generalization ability through the use of VOC datasets. Specifically, we achieved a performance improvement of 2.5% compared to mainstream segmentation models on a dataset containing limited defect industrial component samples, demonstrating the effectiveness and generalization ability of our model © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of ML Algorithms to Improve Crop Productivity Prediction

A Comparative Analysis of ML Algorithms to Improve Crop Prod...

引用

2023 International Conference on Disruptive Technologies, ICDT 2023

作者： Nigam, Anushree Jain, Divyanshu Talan, Manish Singh Singh, S.K. Umrao, Sandhya Galgotias College of Engineering and Technology Dept. of Information Technology Greater Noida India Noida Institute of Engineering and Technology Dept. of Computer Science Engineering Greater Noida India

ISBN: (纸本)9798350323887

According to numerous calculations, the global food output must significantly increase by 2050. Additionally, water levels have been declining, and there is a shortage of usable agricultural land. The first step to introducing smart agriculture in India is good analysis and implementation of machine learning. This research strives to present the best-fit machine learning algorithm to predict crop production in a specific area, state or season. The aim of this research is to make data-driven farming possible. By comparing various regression models namely decision tree, linear regression, XGB regression, and random forest, authors found the most accurate and fast algorithm to process the large volume of agricultural data. The data was visualized to find the top 5 crops produced in India and then the top 3 of them were visualized area-wise, state-wise, and season-wise to give a detailed analysis of crop distribution and production in India. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Security: A Comprehensive Review of Machine Learning Approaches 2

Enhancing Cloud Security: A Comprehensive Review of Machine ...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Safi, Wassim Ghwanmeh, Sameh Mahfuri, Mahmoud Al-Sit, Waleed T. Higher Institute For Applied Sciences And Technology-HIAST Damascus Syria American University In The Emirates Department Of Computer Science United Arab Emirates International University For Science And Technology Computer And Information Technology Department Damascus Syria College Of Engineering Mu'tah University Department Of Computer Engineering Al-karak Jordan Higher Colleges Of Technology Dubai United Arab Emirates

ISBN: (纸本)9798350394962

Cloud Computing (CC) has ushered in a paradigm shift in the provisioning of IT resources, offering users enhanced cost-efficiency and streamlined infrastructure management. However, this growth in CC adoption has also brought forth a myriad of security challenges, encompassing threats to availability, integrity, and confidentiality. To combat these challenges, Cloud Service Providers (CSPs) are increasingly turning to Machine Learning (ML) to diminish the necessity for human intervention in the identification and resolution of security issues. ML's capacity to process extensive datasets and make highly accurate predictions holds the potential to revolutionize CSPs' approach to security. This paper delves into recent advancements in the realm of ML-based security within Cloud Computing. It assesses the attributes and efficacy of various ML algorithms, underscoring their distinctive strengths and possible limitations. Our objective is to present a comprehensive overview of the current landscape of ML in cloud security, illuminating the promising prospects this emerging field holds. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Leaf Guard: Detecting the Diseases in Banana Leaf 5

Leaf Guard: Detecting the Diseases in Banana Leaf

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Yathurshan, K. Barathy, S. Karini, G. Sajitha, P. Abeygunawardhna, Pradeep Rajapakse, Kaushalya Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Engineering Electrical & Electronic Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

This research paper introduces 'Leaf Guard,' a mobile app designed for disease detection and management in banana trees, specifically tailored for Sri Lanka's agricultural landscape. Through the amalgamation of image processing, deep learning, and customized chemical recommendations, this app proficiently identifies early-stage diseases, offering tailored remedies. Catering to farmers and agricultural experts, 'Leaf Guard' provides an intuitive tool, revolutionizing disease management and bolstering sustainable banana cultivation practices. By seamlessly integrating these cutting-edge technologies, this research significantly advances disease detection methods, paving the way for environmentally friendly and economical interventions. The study's findings not only enrich the realm of disease detection technology but also hold promise for future innovations, fostering sustainable approaches to enhance banana cultivation. © 2023 IEEE.

关键词： Cultivation

来源：评论

学校读者我要写书评

暂无评论

Dual-Buffer-Based Optical Datacenter Switch Design

引用

Journal of Optical Communications 2023年第2期44卷 155-162页

作者： Bhattacharya, Pronaya Tiwari, Amod Kumar Singh, Arunendra Dr. A.P.J. Abdul Kalam Technical University Uttar Pradesh Lucknow226031 India Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad382481 India Department of Computer Science and Engineering Rajkiya Engineering College Uttar Pradesh Sonbhadra231216 India Department of Information Technology Pranveer Singh Institute of Technology Uttar Pradesh Kanpur209305 India

The unbounded growth of Cloud-based services and Internet-of-Things (IoT) using Software Defined Networking (SDN) has resulted in bandwidth requirements that have grown enormously over the years. To meet this exponential growth that is currently outpacing Moore's Law, we need Optical Interconnection Networks (OIN) that can satisfy the user's requirements. In a similar direction Arrayed Waveguide Gratings (AWG)-based optical interconnects have been heavily investigated in past and many switch designs have emerged over the period of time. This paper proposes a dual-buffer-based optical switch design where the primary buffer stores the contending packets, while the secondary input buffer stores the contending packets which are blocked by AWG for one slot duration only. Moreover, if a blocked packet is generated on the same node then All-Optical Negative Acknowledgement (AO-NACK) will be used for blocked packets. This paper investigates the various issues related to storage of blocked packets, the analysis is done both at physical and network layers in terms of bit error rate (BER) and packet loss probability, respectively. It is found that with proposed switch design BER is 10 times lower than the earlier design, and the number of re-transmitted packets at the load of 0.8, reduces to 26 from 32 as in earlier switch design. © 2019 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Enhancing Early Detection of Pancreatic Cancer: A Machine Learning Approach with Explainable AI Insights

Enhancing Early Detection of Pancreatic Cancer: A Machine Le...

引用

2024 IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2024

作者： Pattanashetti, Neeraj V Mayur, R. Prakash, Adarsh Adiga, Tryambaka B Kodipalli, Ashwini Rao, Trupthi Global Academy of Technology Dept. of Computer Science & Engineering Karnataka Bangalore India Global Academy of Technology Dept. of Information Science & Engineering Karnataka Bangalore India Global Academy of Technology Dept. of Artificial Intelligence & Data Science Karnataka Bangalore India

ISBN: (纸本)9798350376876

Among the most deadly and complex illnesses in the world, pancreatic cancer is typified by its early asymptomatic stage and subsequent discovery of the disease when it has progressed to an advanced stage. Getting the patients in a correct treatment path at the earliest point is important for suitable intervention and patient outcomes in the long run. We utilized advanced algorithms and model prediction techniques includes, feature extraction, hyperparameter tuning and explainability methods which aims to enhance both the comprehension and predictive accuracy of models employed. The goal is to assess patient health status and diagnose pancreatic diseases (cancer vs. non-cancer) by developing a learning algorithm. We obtained a dataset containing demographic information and urine biomarkers to start the investigation. First stage of our analysis employs a single classifier and later we apply bagging and boosting algorithms to achieve ensemble models. Hyperparameter fine-tuning has got a positive outcome, which has Gradient Boosting and Cat Boosting as its top performing models. The ensemble model produced excellent results (92.02 %), demonstrating the usefulness of the suggested approach. LIME and SHAP techniques play the key role in model outcome interpretability providing an insight of algorithmic decision-making process. Such a wide range of combinations of biomarkers have a potential of pancreatic cancer detection in early stages and thus will help shape diagnostics strategies in near future. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

On Parameterized Picture Fuzzy Discriminant information Measure in Medical Diagnosis Problem 1

引用

3rd International Conference on Emergent Converging Technologies and Biomedical Systems, ETBS 2023

作者： Monika Sharma, Aman Bajaj, Rakesh Kumar Department of Mathematics Jaypee University of Information Technology Himachal Pradesh Waknaghat Solan173234 India Department of Computer Science and Engineering Jaypee University of Information Technology Himachal Pradesh Waknaghat Solan173234 India

ISBN: (数字)9789819986460

ISBN: (纸本)9789819986453

Decision-making processes related to the problems of pattern recognition, clustering, and expert and knowledge-based systems contain a lot of uncertainty in the form of imprecise, incomplete, and inexact information with partial contents where the notions of entropy, discriminant measure and similarity measure play a crucial role. In the present communication, a very recently proposed doubly-parameterized information tool is suitably applied for picture fuzzy sets. This bi-parameterized discriminant measure would give diversification in handling the inexact/incomplete information in terms of obtaining the degree of association and closeness in the data of various applications. Further, the introduced bi-parametric measure has been successfully applied in the principle of minimum discriminant information with the help of some illustrative discussions in the applied fields, e.g., "medical diagnosis". Additionally, for the validity and efficacy of the presented work, necessary characteristic comparison along with important remarks has been done. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Sign to Speak: Real-time Recognition for Enhance Communication 3

Sign to Speak: Real-time Recognition for Enhance Communicati...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Baghavathi Priya, S. Rao, P V R Subba Madeswaran, TamilSelvi Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India University of Technology and Applied Sciences Department of Information Technology Nizwa Oman

ISBN: (纸本)9798350375190

Recent developments in the area of research on sign language recognition have led to making use of deep learning techniques with the goal to assist the self-learning transition of sign language from one language to another. In order to detect and classify characters from photographs in multiple sign languages, a number of deep-learning models, have been deployed. SLR is a prominent area of study and technology that aims to mitigate speaking barriers for individuals who unable to talk and listen. This involves the development of tools capable of understanding and deciphering sign language movements, hence facilitating a wider range of interactions for those who are difficult of listening and speaking. This paper demonstrates a novel model called CNN Inception Net, which is a neural network based on convolution. The use of an Indian sign dataset enables the achievement of a notable performance rate of 98.9%, enabling precise recognition of actions in the language of signs. © 2024 IEEE.

关键词： Deep 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：