检索结果-内蒙古大学图书馆

Data Augmentation and Random Multi-Model Deep Learning for Data Classification

computers, Materials & Continua 2023年第3期74卷 5191-5207页

作者： Fatma Harby Adel Thaljaoui Durre Nayab Suliman Aladhadh Salim EL Khediri Rehan Ullah Khan Computer Science Department Future Academy-Higher Future Institute for Specialized Technological StudiesEgypt Department of Computer Systems Engineering Faculty of Electrical and Computer EngineeringUniversity of Engineering and TechnologyPeshawar25120Pakistan Department of Information Technology College of ComputerQassim UniversityBuraydahSaudi Arabia Department of Computer Sciences Faculty of Sciences of GafsaUniversity of GafsaGafsaTunisia

In the machine learning(ML)paradigm,data augmentation serves as a regularization approach for creating ML *** increase in the diversification of training samples increases the generalization capabilities,which enhances the prediction performance of classifiers when tested on unseen *** learning(DL)models have a lot of parameters,and they frequently ***,to avoid overfitting,data plays a major role to augment the latest improvements in ***,reliable data collection is a major limiting ***,this problem is undertaken by combining augmentation of data,transfer learning,dropout,and methods of normalization in *** this paper,we introduce the application of data augmentation in the field of image classification using Random Multi-model Deep Learning(RMDL)which uses the association approaches of multi-DL to yield random models for *** present a methodology for using Generative Adversarial Networks(GANs)to generate images for data *** experiments,we discover that samples generated by GANs when fed into RMDL improve both accuracy and model *** across both MNIST and CIAFAR-10 datasets show that,error rate with proposed approach has been decreased with different random models.

关键词： Data augmentation generative adversarial networks classification machine learning random multi-model deep learning

来源：评论

学校读者我要写书评

暂无评论

Definitions and (Uniform) Interpolants in First-Order Modal Logic 20

Definitions and (Uniform) Interpolants in First-Order Modal ...

引用

20th International Conference on Principles of Knowledge Representation and Reasoning, KR 2023

作者： Kurucz, Agi Wolter, Frank Zakharyaschev, Michael Department of Informatics King's College London United Kingdom Department of Computer Science University of Liverpool United Kingdom Department of Computer Science and Information Systems Birkbeck University of London United Kingdom

ISBN: (纸本)9781956792027

We first consider two decidable fragments of quantified modal logic S5: the one-variable fragment Q1S5 and its extension S5ALCu that combines S5 and the description logic ALC with the universal role. As neither of them enjoys Craig interpolation or projective Beth definability, the existence of interpolants and explicit definitions of predicates-which is crucial in many knowledge engineering tasks-does not directly reduce to entailment. Our concern therefore is the computational complexity of deciding whether (uniform) interpolants and definitions exist for given input formulas, signatures and ontologies. We prove that interpolant and definition existence in Q1S5 and S5ALCu is decidable in CON2EXPTIME, being 2EXPTIME-hard, while uniform interpolant existence is undecidable. Then we show that interpolant and definition existence in the one-variable fragment Q1K of quantified modal logic K is nonelementary decidable, while uniform interpolant existence is undecidable. © 2023 Proceedings of the International Conference on Knowledge Representation and Reasoning. All rights reserved

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Augmenting Internet of Medical Things Security:Deep Ensemble Integration and Methodological Fusion

引用

computer Modeling in Engineering & sciences 2024年第12期141卷 2185-2223页

作者： Hamad Naeem Amjad Alsirhani Faeiz MAlserhani Farhan Ullah Ondrej Krejcar Faculty of Informatics and Management Center for Basic and Applied ResearchUniversity of Hradec KraloveHradec Kralove50003Czech Republic Department of Computer Science College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Department of Computer Engineering&Networks College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Cybersecurity Center Prince Mohammad Bin Fahd UniversityAl JawharahKhobarDhahran34754Saudi Arabia

When it comes to smart healthcare business systems,network-based intrusion detection systems are crucial for protecting the system and its networks from malicious network *** protect IoMT devices and networks in healthcare and medical settings,our proposed model serves as a powerful tool for monitoring IoMT *** study presents a robust methodology for intrusion detection in Internet of Medical Things(IoMT)environments,integrating data augmentation,feature selection,and ensemble learning to effectively handle IoMT data *** rigorous preprocessing,including feature extraction,correlation removal,and Recursive Feature Elimi-nation(RFE),selected features are standardized and reshaped for deep learning *** using the BAT algorithm enhances dataset *** deep learning models,Transformer-based neural networks,self-attention Deep Convolutional Neural Networks(DCNNs),and Long Short-Term Memory(LSTM)networks,are trained to capture diverse data *** predictions form a meta-feature set for a subsequent meta-learner,which combines model *** classifiers validate meta-learner features for broad algorithm *** comprehensive method demonstrates high accuracy and robustness in IoMT intrusion *** were conducted using two datasets:the publicly available WUSTL-EHMS-2020 dataset,which contains two distinct categories,and the CICIoMT2024 dataset,encompassing sixteen *** results showcase the method’s exceptional performance,achieving optimal scores of 100%on the WUSTL-EHMS-2020 dataset and 99%on the CICIoMT2024.

关键词： Cyberattack ensemble learning feature selection intrusion detection smart cities machine learning BAT augmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient Computation Offloading of IoT-Based Workflows Using Discrete Teaching Learning-Based Optimization

引用

computers, Materials & Continua 2022年第11期73卷 3685-3703页

作者： Mohamed K.Hussein Mohamed H.Mousa Department of Computer Science Faculty of Computers and InformaticsSuez Canal UniversityIsmailiaEgypt Department of Information Technology College of Computer Science at AlKamilUniversity of JeddahJeddahSaudi Arabia

As the Internet of Things(IoT)and mobile devices have rapidly proliferated,their computationally intensive applications have developed into complex,concurrent IoT-based workflows involving multiple interdependent *** exploiting its low latency and high bandwidth,mobile edge computing(MEC)has emerged to achieve the high-performance computation offloading of these applications to satisfy the quality-of-service requirements of workflows and *** this study,we propose an offloading strategy for IoT-based workflows in a high-performance MEC *** proposed task-based offloading strategy consists of an optimization problem that includes task dependency,communication costs,workflow constraints,device energy consumption,and the heterogeneous characteristics of the edge *** addition,the optimal placement of workflow tasks is optimized using a discrete teaching learning-based optimization(DTLBO)*** experimental evaluations demonstrate that the proposed offloading strategy is effective at minimizing the energy consumption of mobile devices and reducing the execution times of workflows compared to offloading strategies using different metaheuristics,including particle swarm optimization and ant colony optimization.

关键词： High-performance computing internet of things(IoT) mobile edge computing(MEC) workflows computation offloading teaching learning-based optimization

来源：评论

学校读者我要写书评

暂无评论

Deep learning approaches and data augmentation for melanoma detection

引用

Neural Computing and Applications 2024年 1-14页

作者： Alzamel, Mai Iliopoulos, Costas Lim, Zara Computer Science Department College of Computer and Information Sciences King Saud University P.O. Box 145111 Riyadh Saudi Arabia Department of Informatics King’s College London 30 Aldwych LondonWC2B 4BG United Kingdom

Skin cancer is one of the most common and dangerous forms of cancer. Diagnosis in the preliminary stages plays a significant role in determining the probability of getting cured, particularly for cancers associated with a higher risk such as melanoma. Traditional examination procedures are surgical treatments that cause significant soreness and scarring. Consequently, there is a rising need for an automatic, painless and accurate skin cancer detection. Machine learning (ML) and deep learning (DL) techniques have shown a promising results in prediction and classification tasks. This study has two primary contributions: Firstly, we developed four deep learning models for skin cancer detection using Convolutional Neural Networks (CNNs) including: ResNetv2, VGG16, EfficientNet-B5 and EfficientNet-B7. Secondly, we highlight the importance of handling data imbalance for supervised classification of medical images, by applying image data augmentation with Generative Adversarial Network (GANs). We compare the obtained results with the state of art which shows the efficiency of the CNN for skin cancer detection. Furthermore, we demonstrate the performance of an ML model, namely Support Vector Machine (SVM), against the CNN model results. The proposed classification system was evaluated using the International Skin Imaging Collaboration (ISIC) Archive which is a large public skin lesion dataset. The results show that the four CNN models outperform the SVM in accuracy, precision, recall and F1 score. The F1 scores for the CNN classifiers were 84.22%, 80.42%, 80.01% and 80.98% for EfficientNet-B7, EfficientNet-B5, ResNet50V2 and VGG16, respectively. On the other hand, the F1 score for the SVM classifier was 69.56%. Data augmentation increased the F1 scores performance to 86.08%, 83.79%, 84.16%, 82.46% and 73.52% for EfficientNet-B7, EfficientNet-B5, ResNet50V2 and VGG16, SVM, respectively. Overall, the results show that EfficientNet-B7 outperformed the other proposed CNN models

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Key Management in Lightweight Cryptography: A New Hashing-Based Approach 8

Efficient Key Management in Lightweight Cryptography: A New ...

引用

8th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2024

作者： Al-Mahmood, Haider H. Alsaad, Saad N. Informatics Institute for Postgraduate Studies Iraqi Commission for Computers and Informatics Baghdad Iraq University of Mustansiriyah Department of Computer Science College of Science Baghdad Iraq

ISBN: (纸本)9798350354423

Lightweight encryption methods are introduced to overcome the challenges of high-power consumption and high memory usage in the traditional cryptography system. The primary goal of the lightweight encryption technique is to make it suitable for use in devices provided with lower power and small memories. The importance of lightweight cryptosystem is its ability to provide suitable security for data encryption without consuming high level of power and without need for big memories. As the devices with lower battery life and supplied low memory become widespread, encryption key management problems start to emerge. This may lead to a high possibility of an attack on the encryption key and break the encryption system. In this context, this paper proposes a novel hashing- based approach for key generation in lightweight cryptography. The approach involves generating significant hash digits from a seed input to the hashing system, and then using hash code slicing to select different characters and numbers that can be used as a seed for the key generating system. The practical results, which demonstrate that a small seed length can effectively generate a large key length, are a testament to the effectiveness of the proposed approach. These results can be used in the encryption process to reduce the initial total bits, thereby enhancing the efficiency of the system. © 2024 IEEE.

关键词： Cryptographic Algorithms Encryption Key Management Hashing Techniques IoT Security Lightweight Cryptography

来源：评论

学校读者我要写书评

暂无评论

Intelligent Cybersecurity Classification Using Chaos Game Optimization with Deep Learning Model

引用

computer systems science & Engineering 2023年第4期45卷 971-983页

作者： Eatedal Alabdulkreem Saud S.Alotaibi Mohammad Alamgeer Radwa Marzouk Anwer Mustafa Hilal Abdelwahed Motwakel Abu Sarwar Zamani Mohammed Rizwanullah Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh 11671Saudi Arabia Department of Information Systems College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Computer Science and Bioinformatics Singhania UniversityPacheri BariJhnujhunuRajasthanIndia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh 11671Saudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Cyberattack detection has become an important research domain owing to increasing number of cybercrimes in recent *** Machine Learning(ML)and Deep Learning(DL)classification models are useful in effective identification and classification of *** addition,the involvement of hyper parameters in DL models has a significantly influence upon the overall performance of the classification *** this background,the current study develops Intelligent Cybersecurity Classification using Chaos Game Optimization with Deep Learning(ICC-CGODL)*** goal of the proposed ICC-CGODL model is to recognize and categorize different kinds of attacks made upon ***,ICC-CGODL model primarily performs min-max normalization process to normalize the data into uniform *** addition,Bidirectional Gated Recurrent Unit(BiGRU)model is utilized for detection and classification of ***,CGO algorithm is also exploited to adjust the hyper parameters involved in BiGRU model which is the novelty of current work.A wide-range of simulation analysis was conducted on benchmark dataset and the results obtained confirmed the significant performance of ICC-CGODL technique than the recent approaches.

关键词： Deep learning chaos game optimization cybersecurity chaos game optimization cyberattack

来源：评论

学校读者我要写书评

暂无评论

Research on Key Technologies of Automated Instructional Design for Engineering Education Courses 5

Research on Key Technologies of Automated Instructional Desi...

引用

5th International Conference on computer science and Technologies in Education, CSTE 2023

作者： Zeng, Ling Liang, Zaoqing Liang, Yun Huang, Peijie College of Mathematics and Informatics Department of Computer Science and Technology SCAU Guangzhou China

ISBN: (纸本)9798350325720

An Automated Instructional Design (AID) solution for engineering education courses instructional design is proposed in this research. By limiting the Domain of AID to engineering education courses, and limiting the course objectives to the graduate attributes and professional competence of engineering education programme, as well as limiting the instructional methods to task-And-Activity-based methods, and applying the evaluation vocabulary regularly used in the field of engineering education, a complete set of instructional design vocabulary related to the instructional design domain can be abstracted. Using the Unified Modeling Language (UML) Profile mechanism, the complete set of instructional design vocabulary can be represented by a designed visual model language, which provide a complete instructional design description language, named Instructional Design Visual Model Language (IDVML), dedicated to the field of engineering education for AID tool implementation. Then the existed Model-Driven Architecture (MDA) tools can be applied to design IDVML-related Platform Independent Model (PIM) and various Platform Specific Model (PSM) meta-models, and the conversion templates from PIM to various PSM, as well as various conversion templates from PSM to executable code, database table, Web page, course Ontology, etc., so as to realize the conversion from IDVML to program code directly. Finally, using the Meta-model Object Facility (MOF), an independent AID can be implemented. This AID can help the teacher to design the teaching objectives, content, tasks and activities, evaluation of engineering education related courses which meet the requirements of engineering education accreditation. At the same time, the course Ontology can be generated to provide Ontology basis for the subsequent construction of individualized learning system. © 2023 IEEE.

关键词： Engineering education

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Mesh Segmentation

引用

computer Modeling in Engineering & sciences 2023年第5期135卷 1745-1763页

作者： Abubakar Sulaiman Gezawa Qicong Wang Haruna Chiroma Yunqi Lei Department of Computer Science School of InformaticsXiamen UniversityXiamen361005China Shenzen Research Institute Xiamen UniversityShenzen518000China College of Computer Science and Engineering University of Hafr Al BatinHafr Albatin39524Saudi Arabia

In the shape analysis community,decomposing a 3D shape intomeaningful parts has become a topic of interest.3D model segmentation is largely used in tasks such as shape deformation,shape partial matching,skeleton extraction,shape correspondence,shape annotation and texture *** approaches have attempted to provide better segmentation solutions;however,the majority of the previous techniques used handcrafted features,which are usually focused on a particular attribute of 3Dobjects and so are difficult to *** this paper,we propose a three-stage approach for using Multi-view recurrent neural network to automatically segment a 3D shape into visually meaningful *** first stage involves normalizing and scaling a 3D model to fit within the unit sphere and rendering the object into different *** viewpoints,on the other hand,might not have been associated,and a 3D region could correlate into totally distinct outcomes depending on the *** address this,we ran each view through(shared weights)CNN and Bolster block in order to create a probability boundary *** Bolster block simulates the area relationships between different views,which helps to improve and refine the *** stage two,the feature maps generated in the previous step are correlated using a Recurrent Neural network to obtain compatible fine detail responses for each ***,a layer that is fully connected is used to return coherent edges,which are then back project to 3D objects to produce the final *** on the Princeton Segmentation Benchmark dataset show that our proposed method is effective for mesh segmentation tasks.

关键词： Deep learning mesh segmentation 3D shape shape features

来源：评论

学校读者我要写书评

暂无评论

Selective feature-based ovarian cancer prediction using MobileNet and explainable AI to manage women healthcare

引用

Multimedia Tools and Applications 2024年 1-22页

作者： Almujally, Nouf Abdullah Alzahrani, Abdulrahman Hakeem, Abeer M. Attiah, Afraa Umer, Muhammad Alsubai, Shtwai Polsinelli, Matteo Ashraf, Imran Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer Science and Engineering College of Computer Science and Engineering University of Hafr Al Batin Hafr Al Batin39524 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Computer Science The Islamia University of Bahawalpur Bahawalpur Pakistan Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University P.O. Box 151 Al-Kharj11942 Saudi Arabia Department of Management & amp Innovation Systems University of Salerno Fisciano84084 Italy Department of Information and Communication Engineering Yeungnam University Gyeongsan38541 Korea Republic of

Ovarian cancer is a global health concern due to the unavailability of an effective screening strategy and is often diagnosed at a late stage with approximately 70% of the case which reduces the survival chances of patients. Initial diagnosis is challenging due to inconspicuous symptoms in its initial stages which complicate its timely diagnosis. Regular screenings, such as pelvic exams, ultrasounds, and blood tests targeting specific biomarkers can be helpful for early diagnosis. In addition, the use of machine learning models can help automate this process thereby assisting medical experts for accurate diagnosis. This study aims at timely and accurate detection of ovarian cancer using a transfer learning approach that uses the MobileNet model. Moreover, the Chi-square technique is used to extract the most impactful features for better accuracy. For experiments, the Soochow University ovarian cancer dataset is employed. Extensive experiments are performed using all features from the dataset, as well as, using Chi-square-based selective features. The best accuracy of 90.88% is achieved with the Xception model when all features are used. Experimental results show a substantial increase when selective features are used indicating a 98.49% accuracy using the MobileNet model with 20 most important features. In addition, precision, recall, and F1 scores of 99.13%, 99.27%, and 99.20% are obtained showing the model’s robustness and generalization. This study also employs Shapley additive explanations to explain the importance of various features toward the model’s output thereby providing transparency for the model’s decision-making process. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Diagnosis

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：