检索结果-内蒙古大学图书馆

A Lightweight Deep Autoencoder Scheme for Cyberattack Detection in the Internet of Things

Computer Systems Science & Engineering 2023年第7期46卷 57-72页

作者： Maha Sabir Jawad Ahmad Daniyal Alghazzawi Information Systems Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah80200Saudi Arabia School of Computing Edinburgh Napier UniversityEdinburgh EH105DYUK

The Internet of things(IoT)is an emerging paradigm that integrates devices and services to collect real-time data from surroundings and process the information at a very high speed to make a *** several advantages,the resource-constrained and heterogeneous nature of IoT networks makes them a favorite target for cybercriminals.A single successful attempt of network intrusion can compromise the complete IoT network which can lead to unauthorized access to the valuable information of consumers and *** overcome the security challenges of IoT networks,this article proposes a lightweight deep autoencoder(DAE)based cyberattack detection *** proposed approach learns the normal and anomalous data patterns to identify the various types of network *** most significant feature of the proposed technique is its lower complexity which is attained by reducing the number of *** optimally train the proposed DAE,a range of hyperparameters was determined through extensive experiments that ensure higher attack detection *** efficacy of the suggested framework is evaluated via two standard and open-source *** proposed DAE achieved the accuracies of 98.86%,and 98.26%for NSL-KDD,99.32%,and 98.79%for the UNSW-NB15 dataset in binary class and multi-class *** performance of the suggested attack detection framework is also compared with several state-of-the-art intrusion detection *** outcomes proved the promising performance of the proposed scheme for cyberattack detection in IoT networks.

关键词： Autoencoder cybersecurity deep learning intrusion detection IoT

来源：评论

学校读者我要写书评

暂无评论

MAPFUNet:Multi-attention Perception-Fusion U-Netfor Liver Tumor Segmentation

引用

Journal of Bionic Engineering 2024年第5期21卷 2515-2539页

作者： Junding Sun Biao Wang Xiaosheng Wu Chaosheng Tang Shuihua Wang Yudong Zhang School of Computer Science and Technology Henan Polytechnic UniversityJiaozuo451460China Department of Biological Sciences Xi’an Jiaotong-Liverpool UniversitySuzhou215123China School of Computing and Mathematical Sciences University of LeicesterLeicesterLE17RHUK Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz University21589JeddahSaudi Arabia

The second-leading cause of cancer-related deaths globally is liver *** treatment of liver cancers depends heavily on the accurate segmentation of liver tumors from CT *** improved method based on U-Net has achieved good perfor-mance for liver tumor segmentation,but these methods can still be *** deal with the problems of poor performance from the original U-Net framework in the segmentation of small-sized liver tumors and the position information of tumors that is seriously lost in the down-sampling process,we propose the Multi-attention Perception-fusion U-Net(MAPFU-Net).We propose the Position ResBlock(PResBlock)in the encoder stage to promote the feature extraction capability of MAPFUNet while retaining the position information regarding liver tumors.A Dual-branch Attention Module(DWAM)is proposed in the skip connections,which narrows the semantic gap between the encoder's and decoder's features and enables the network to utilize the encoder's multi-stage and multi-scale *** propose the Channel-wise ASPP with Atten-tion(CAA)module at the bottleneck,which can be combined with multi-scale features and contributes to the recovery of micro-tumor feature ***,we evaluated MAPFUNet on the LITS2017 dataset and the 3DIRCADB-01 dataset,with Dice values of 85.81 and 83.84%for liver tumor segmentation,which were 2.89 and 7.89%higher than the baseline model,*** experiment results show that MAPFUNet is superior to other networks with better tumor feature representation and higher accuracy of liver tumor *** also extended MAPFUNet to brain tumor segmentation on the BraTS2019 *** results indicate that MAPFUNet performs well on the brain tumor segmentation task,and its Dice values on the three tumor regions are 83.27%(WT),84.77%(TC),and 76.98%(ET),respectively.

关键词： Liver tumor segmentation Small tumors Position information Attention Multi-scale features

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Shallow Convolutional Neural Network in Open-World Chart Image Classification

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第6期48卷 185-198页

作者： Bajić, Filip Habijan, Marija Nenadić, Krešimir University Computing Centre University of Zagreb Zagreb10000 Croatia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek31000 Croatia

Data’s role is pivotal in the era of internet technologies, but unstructured data poses comprehension challenges. Data visualizations like charts have emerged as crucial tools for condensing complex information. Classifying charts and applying various processing techniques are vital to interpreting visual data. Traditional chart image classification methods rely on predefined rules and have limited accuracy. The advent of support vector machines (SVMs) and convolutional neural networks (CNNs) significantly improved the accuracy of these methods. This research evaluates our previously introduced Shallow convolutional neural network (SCNN) architecture for chart image classification, comprising four convolutional layers, two max-pooling layers, and one fully-connected layer. The network achieves state-of-the-art results, requiring smaller datasets and reduced computational resources. When two networks are combined into Siamese SCNN (SSCNN), emphasizing generalization, it achieves high accuracy with small datasets and excels in open-set classification. The evaluation process encompasses the utilization of six publicly available datasets. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

A TreeSoft Set with Interval Valued Neutrosophic Set in the era of Industry 4.0

引用

Neutrosophic Sets and Systems 2024年 64卷 170-184页

作者： Alqazzaz, Ali Sallam, Karam M. Department of Information Systems and Cybersecurity College of Computing and Information Technology University of Bisha P.O. Box 344 Bisha61922 Saudi Arabia School of IT and Systems Faculty of Science and Technology University of Canberra Canberra Australia

The introduction of Industry 4.0 has brought about a significant shift in the manufacturing and supply chain management sectors, requiring supplier selection procedures to be adjusted to this rapidly changing technical environment. This study aims to improve supplier selection in Industry 4.0. This selection contains various criteria, so multi-criteria decision-making (MCDM) is used to deal with these criteria. The interval-valued neutrosophic sets (IVNSs) are used to deal with uncertainty in the evaluation process. The IVNSs are integrated with the TreeSoft Set. The TOPSIS method is an MCDM method used to rank the alternatives. The results show that the economic criterion is the most important, and supplier 7 is the best. © (2023), (University of New Mexico). All Rights Reserved.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Improving the Performance of Bully Algorithm for Leader Election in Distributed Systems 1

Improving the Performance of Bully Algorithm for Leader Elec...

引用

1st International Conference on Emerging Technologies for Dependable Internet of Things, ICETI 2024

作者： Alkohali, Ebrahim A. Algabri, Malek Abdullah, Monir Faculty of Computer & Information Technology Sana’a University Sana’a Yemen College of Computing and Information Technology University of Bisha Bisha Saudi Arabia

ISBN: (纸本)9798331533557

Leader election is a classical problem in distributed systems in which the selection a coordinator node to perform tasks is necessary. However, coordinator can fail and this requires performing a leader election operation to choose a new coordinator. This study focuses on the Bully algorithm which uses a lot of messages and higher network traffic which are considered the main drawback. This paper provides a simple and adaptable adaptive bully algorithm that lowers the messages passing used and is simple and flexible. The algorithm utilizes only one node, called responsibility for the election, and a time span, where a time span is set for each node. These two procedures minimize leader election operations especially discovering failures from multiple processes in the system and messages passing. According to the results, the enhanced algorithm is better than the algorithm bully. It reduces the complexity of message passing during leader election operations. © 2024 IEEE.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

A classification-based privacy-preserving decision-making for secure data sharing in Internet of Things assisted applications

引用

Digital Communications and Networks 2022年第4期8卷 436-445页

作者： Alaa Omran Almagrabi A.K.Bashir Department of Information Systems Faculty of Computing and Information Technology(FCIT)King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computing and Mathematics Manchester Metropolitan UniversityManchesterUK

The introduction of the Internet of Things(IoT)paradigm serves as pervasive resource access and sharing platform for different real-time *** resource availability,access,and allocation provide a better quality of user experience regardless of the application type and ***,privacy remains an open issue in this ubiquitous sharing platform due to massive and replicated data *** this paper,privacy-preserving decision-making for the data-sharing scheme is *** scheme is responsible for improving the security in data sharing without the impact of replicated resources on communicating *** this scheme,classification learning is used for identifying replicas and accessing granted resources *** on the trust score of the available resources,this classification is recurrently performed to improve the reliability of information *** user-level decisions for information sharing and access are made using the classification of the resources at the time of *** proposed scheme is verified using the metrics access delay,success ratio,computation complexity,and sharing loss.

关键词： Classification learning Data mining IoT Privacy-preserving Resource replication

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Sustainable Waste Valorization using TreeSoft Set with Neutrosophic Sets

引用

Neutrosophic Sets and Systems 2024年 65卷 151-160页

This study proposed a neutrosophic set framework with TreeSoft Set for sustainable waste valorization selection. The neutrosophic set is used to overcome uncertainty and vague information in the evaluation process. The neutrosophic set has three membership degrees: truth, indeterminacy, and falsity. The multi-criteria decision-making (MCDM) methodology deals with various criteria to evaluate waste valorization. The VIKOR method is an MCDM method used to rank the alternatives. The numerical example was created with 12 criteria and 10 alternatives. Three decision-makers and experts are invited to evaluate the requirements and options. We used the bipolar neutrosophic numbers to replace the opinions of experts. © (2023), (University of New Mexico). All Rights Reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

SafeChurn: Assessing Adversarial Attacks AgainstChurn Prediction Model and Defense

SafeChurn: Assessing Adversarial Attacks AgainstChurn Predic...

引用

2023 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2023

作者： Kaleem, Amani Mauroof, Aaisha Kalam, Hasna Rupasinghe, Lakmal Liyanapathirana, Chethana Sri Lanka Institute of Information Technology Faculty of Computing Colombo Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9798350341072

Numerous fields including the telecom industry's ability to predict customer churn, have been transformed by neural network models. However, these models' vulnerability to adversarial attacks pose questions about their security and reliability. In this study, we test the robustness of a neural network model created for the classification of telecom churn data by measuring how well it performs under three different adversarial attacks: The Projected Gradient Descent (PGD), Boundary attack, and Carlini Wagner attacks. We first created a convolutional neural network model specifically designed for the telecom churn dataset. A large dataset containing pertinent customer attributes, past usage trends, and churn labels is used to train the model. The models functionality is enhanced to precisely classify customer churn by utilizing appropriate strategies. The trained neural network model undergoes three distinct adversarial attacks. The PGD attack looks for perturbations that maximize themodel's loss function within a given - bound. The Boundary attack crosses decision boundaries in order to provide adversarial cases that result in misclassification. The Carlini attack uses an optimization-based methodology to produce the fewest possible model-fooling perturbations. In this research compare the accuracy of the neural network model before and after each adversarial attack to determine the impact of these attacks. We investigate range of defense mechanisms designed especially for telecom churn data categorization in order to increase the model's resistance to these attacks. By implementing these strategies, our aim is to mitigate the impact of adversarial perturbations and increase the model's resistance to attacks from adversaries. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Predicting Energy Consumption Using Stacked LSTM Snapshot Ensemble

引用

Big Data Mining and Analytics 2024年第2期7卷 247-270页

作者： Mona Ahamd Alghamdi Abdullah S.A.L-Malaise AL-Ghamdi Mahmoud Ragab Information Systems Department Faculty of Computing and Information Technology(FCIT)King Abdulaziz University(KAU)Jeddah 21589Kingdom of Saudi Arabia Information Systems Department FCITKAUJeddah 21589Kingdom of Saudi Arabiaand also with School of EngineeringComputing and DesignDar Al-Hekma UniversityJeddah 22246Kingdom of Saudi Arabia Information Technology Department FCITKAUJeddah 21589Kingdom of Saudi Arabiaand also with Mathematics DepartmentFaculty of ScienceAl-Azhar UniversityNaser City 11884Egypt

The ability to make accurate energy predictions while considering all related energy factors allows production plants,regulatory bodies,and governments to meet energy demand and assess the effects of energy-saving *** energy consumption falls within normal parameters,it will be possible to use the developed model to predict energy consumption and develop improvements and mitigating measures for energy *** objective of this model is to accurately predict energy consumption without data limitations and provide results that are easily *** proposed model is an implementation of the stacked Long Short-Term Memory(LSTM)snapshot ensemble combined with the Fast Fourier Transform(FFT)and *** and Berard’s Individual Household Electric-Power Consumption(IHEPC)dataset incorporated with weather data are used to analyse the model’s accuracy with predicting energy *** model is trained,and the results measured using Root Mean Square Error(RMSE),Mean Absolute Error(MAE),Mean Absolute Percentage Error(MAPE),and coefficient of determination(R^(2))metrics are 0.020,0.013,0.017,and 0.999,*** stacked LSTM snapshot ensemble performs better than the compared models based on prediction accuracy and minimized *** results of this study show that prediction accuracy is high,and the model’s stability is high as *** model shows that high levels of accuracy prove accurate predictive ability,and together with high levels of stability,the model has good interpretability,which is not typically accounted for in ***,this study shows that it can be inferred.

关键词： energy consumption prediction Artificial Intelligence(AI) Deep Learning(DL) snapshot ensemble

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Jellyfish Classification: A Study Using YOLOv8 and Pre-trained Models

Comparative Analysis of Jellyfish Classification: A Study Us...

引用

2024 International Research Conference on Smart computing and Systems Engineering, SCSE 2024

作者： Nawarathne, U.M.M.P.K. Kumari, H.M.L.S. Kumari, H.M.N.S. Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka University of Peradeniya Computing Centre Faculty of Engineering Peradeniya Sri Lanka

ISBN: (纸本)9798350375688

Jellyfish classification holds significant importance due to its implications in environmental monitoring, marine conservation, and public safety. Understanding the distribution and characteristics of jellyfish populations can provide valuable insights into the health of marine ecosystems, helping to manage fisheries, protect biodiversity, and mitigate potential ecological imbalances. Therefore, this study experimented with deep learning models for jellyfish classification, ranging from traditional convolutional neural networks (CNNs) such as DenseNet, InceptionV3, MobileNet, MobileNetV2, and NASNet Mobile and as well as the newly introduced YOLO architecture, YOLOv8. The dataset was comprised of six different types of jellyfish images. Notably, YOLOv8 stands out with an impressive accuracy of 99.5%, demonstrating its efficacy in accurately detecting and classifying jellyfish instances. Other models, such as DenseNet and MobileNet, also yield high accuracy scores, emphasizing the versatility of deep learning models in handling complex image classification tasks. The robust methodologies employed in training these models, combined with the achieved high accuracies, pave the way for enhanced understanding and monitoring of jellyfish populations, contributing to the sustainable management of marine ecosystems. In conclusion, jellyfish classification using YOLOv8 architecture is a crucial tool for marine researchers, environmentalists, and policymakers © 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：