检索结果-内蒙古大学图书馆

RobustFace: a novel image restoration technique for face adversarial robustness improvement

Multimedia Tools and Applications 2025年第11期84卷 8965-8993页

作者： Sadu, Chiranjeevi Das, Pradip K. Yannam, V Ramanjaneyulu Nayyar, Anand Department of Computer Science and Engineering RGUKT Nuzvid Andhra Pradesh Nuzvid India Department of Computer Science and Engineering IIT Guwahati Assam Guwahati India School of Technology Woxsen University Telangana Hyderabad India Graduate School Faculty of Information Technology Duy Tan University Da Nang550000 Viet Nam

Machine Learning (ML) models, particularly Deep Learning (DL), have made rapid progress and achieved significant milestones across various applications, including numerous safety-critical contexts. However, these models have recently been discovered to be susceptible to adversarial attacks, which are well-crafted input images. The primary objective of this paper is to propose a novel methodology titled "RobustFace", which is based on deep image restoration networks, that significantly improves the facial adversarial robustness of various image-classification models. Adversarial images are created using the Private Fast Gradient Sign Method (P-FGSM), StyleGAN and Fast Landmark Manipulation (FLM) methods. The adversarial images are then enhanced using deep image restoration networks to bring back them into the original space. The encoded weighted local magnitude patterns (WLMP) are extracted and provided to different types of classifiers to detect facial adversarial images from the clean images. The effectiveness of RobustFace has been demonstrated on two real-world datasets and experimental outcomes show that it significantly improves facial adversarial robustness on all evaluating classifiers. It improves the highest classification accuracy from 98.75% to 99.00% on P-FGSM attacks, from 77.94% to 85.25% on adversarial attacks generated by StyleGAN and from 65.52% to 69.50% for FLM attacks. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Novel Cluster Analysis-Based Crop Dataset Recommendation Method in Precision Farming

引用

computer Systems Science & engineering 2023年第9期46卷 3239-3260页

作者： K.R.Naveen Kumar Husam Lahza B.R.Sreenivasa Tawfeeq Shawly Ahmed A.Alsheikhy H.Arunkumar C.R.Nirmala Department of Computer Science&Engineering Bapuji Institute of Engineering&TechnologyDavangereKarnatakaIndia Department of Information Technology Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Information Science&Engineering Bapuji Institute of Engineering&TechnologyDavangereKarnatakaIndia Department of Electrical Engineering Faculty of Engineering at RabighKing Abdulaziz UniversityJeddahSaudi Arabia Department of Electrical Engineering College of EngineeringNorthern Border UniversityArarSaudi Arabia

Data mining and analytics involve inspecting and modeling large pre-existing datasets to discover decision-making *** agriculture uses datamining to advance agricultural *** farmers aren’t getting the most out of their land because they don’t use precision *** harvest crops without a well-planned recommendation *** crop production is calculated by combining environmental conditions and management behavior,yielding numerical and categorical *** existing research still needs to address data preprocessing and crop categorization/***,statistical analysis receives less attention,despite producing more accurate and valid *** study was conducted on a dataset about Karnataka state,India,with crops of eight parameters taken into account,namely the minimum amount of fertilizers required,such as nitrogen,phosphorus,potassium,and pH *** research considers rainfall,season,soil type,and temperature parameters to provide precise cultivation recommendations for high *** presented algorithm converts discrete numerals to factors first,then reduces ***,the algorithm generates six datasets,two fromCase-1(dataset withmany numeric variables),two from Case-2(dataset with many categorical variables),and one from Case-3(dataset with reduced factor variables).Finally,the algorithm outputs a class membership allocation based on an extended version of the K-means partitioning method with lambda *** presented work produces mixed-type datasets with precisely categorized crops by organizing data based on environmental conditions,soil nutrients,and ***,the prepared dataset solves the classification problem,leading to a model evaluation that selects the best dataset for precise crop prediction.

关键词： Data mining crop prediction k-prototypes k-means cluster machine learning

来源：评论

学校读者我要写书评

暂无评论

Predicting software vulnerability based on software metrics: a deep learning approach

引用

Iran Journal of computer Science 2024年第4期7卷 801-812页

作者： Agbenyegah, Francis Kwadzo Asante, Micheal Chen, Jinfu Akpaku, Ernest Department of Computer Science Kwame Nkrumah University of Science and Technology Kumasi Ghana School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Department of Information Technology Faculty of Computing and Information Systems Ghana Communication Technology University Accra Ghana

The security of IT systems is the topmost priority of software developers. Software vulnerabilities undermine the security of computer systems. Lately, there have been a lot of reported issues of software vulnerabilities recorded in individuals and corporate systems. Software metrics-based techniques have been used and found to be effective due to low false positives and false negatives. However, there are software metrics that have not been investigated and could have an impact on the performance of the predictive model. In this study, we developed an ensemble deep learning algorithm made of LSTM, CNN, and MLP models with the non-investigated metrics as a feature to learn the latent representation of code metrics to predict anomalies in source code effectively. We trained the proposed model on the SySeVR datasets and compared the model's performance against five deep learning algorithms and four state-of-the-art SVPs. The proposed model performs better than the other deep learning with a classification accuracy of 96.17%, and a precision of 97.72%. The model's classification accuracy is 4.98% higher than that of the five deep learning models and 1.71% lower in precision than the state-of-the-art SVP. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Deep learning Machine learning Software metrics Software security Software vulnerabilities

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural Computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A decision-making model for self-driving vehicles based on GPT-4V, federated reinforcement learning, and blockchain

引用

Neural Computing and Applications 2024年第34期36卷 21545-21560页

作者： Alam, Tanweer Gupta, Ruchi Ahamed, N. Nasurudeen Ullah, Arif Department of Computer Science Faculty of Computer and Information Systems Islamic University of Madinah P.O.Box. 170 Madinah42351 Saudi Arabia Department of Information Technology Ajay Kumar Garg Engineering College Ghaziabad Abdul Kalam Technical University Lucknow India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Department of Computer Science Faculty of Computing and Artificial Intelligence Air University Islamabad Pakistan

Decision-making is crucial in fully autonomous vehicle operations and is expected to greatly influence future transportation systems. Observing the current driving status of autonomous vehicles is vital for its decision-making process. The autonomous connected vehicles on the road send significant data about their movements to the server to maintain continuous training. With the Proof of Authority (PoA) consensus process, blockchain technology provides a valid, decentralised and secure option to improve transactions throughput and minimise delay. The limited computational capacity of vehicles poses a challenge in achieving high accuracy and low latency while training self-driving algorithms. GPT-4V surpassed challenging autonomous systems in scene interpretation and causal thinking. GPT-4V has ability to navigate circumstances without access to database, interpret intentions, and make sound decisions in real-world driving scenarios. The reward function and different driving conditions are organised to allow an optimal search to find the most efficient driving style while ensuring safety. The consequences of the Blockchain-enabled decision-making model (DMM) for Self-Driving Vehicles (SDV) primarily based on GPT-4V and Federated Reinforcement Learning (FRL) would, likely, upgrades in decision-making accuracy, operational performance, statistics integrity, and potentially enhanced learning skills in SDV. Integrating blockchain technology, superior language modelling GPT-4V and FRL may lead to multiplied safety, reliability, and decision-making ability in SDV. This study utilised the Simulation of Urban MObility (SUMO) simulator to assess the ability of SDV to maintain its desired speed consistently and securely in a highway setting using proposed DMM. This study indicates that the suggested DMM, utilising the driving state evaluation approach for SDV, can help these vehicles operate safely and effectively. The performance of the proposed model, such as CPU utilisation

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Medical Image Analysis for Personalized Medicine 65

Deep Learning in Medical Image Analysis for Personalized Med...

引用

65th International Symposium ELMAR, ELMAR 2023

作者： Galic, Irena Habijan, Marija Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek31000 Croatia

ISBN: (纸本)9798350325126

Deep learning (DL) has transformed the field of medical image processing, enabling unprecedented accuracy and efficiency in various applications. It has been widely utilized for medical image analysis of different anatomical regions. In this article, we provide an overview of commonly used deep learning methods, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs). We briefly overview their applications in medical image analysis, such as image classification, object detection/localization, segmentation, generation, and registration. We also highlight the strengths and limitations of each method and identify the challenges that still need to be addressed, including the limited availability of annotated data, variability in medical images, and the interpretability issue. Finally, we discuss future research directions, including developing explainable deep learning methods and integrating multi-modal data. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Deploying Testbed Docker-based application for Encryption as a Service in Kubernetes 32

Deploying Testbed Docker-based application for Encryption as...

引用

32nd International Conference on Software, Telecommunications and computer Networks, SoftCOM 2024

作者： Javadpour, Amir Ja'fari, Forough Taleb, Tarik Benzaid, Chafika Rosa, Luis Tomas, Pedro Cordeiro, Luis Ictficial Oy Espoo Finland Sharif University of Technology Department of Computer Engineering Iran Ruhr University Bochum Faculty of Electrical Engineering and Information Technology Bochum Germany University of Oulu Faculty of Information Technology and Electrical Engineering Oulu Finland OneSource Coimbra Portugal

ISBN: (纸本)9789532901382

The scalability of today's networking infrastructures, such as Kubernetes, has increased the demand for everything-as-a-service concepts, including encryption services. This paper details deploying an Encryption as a Service (EaaS) framework on Kubernetes. In our current implementation, a web platform is dedicated to the subscription processes and managing the requested services. Service providers subscribe to receive encryption and decryption services for their clients, and a token is assigned to them. The client, or better to say, the devices covered by that service provider, can use encryption/decryption to specify that token. As our implemented web platform is written in Django, through this paper, we have discussed the deployment of Django applications on Kubernetes and the role of two other services (i.e., Database and Nginx) to make it available. The services are executed on Docker containers and deployed on Kubernetes pods. We have also explained the steps to build Docker containers, including the details of Dockerfiles. We have deployed this framework on both local and remote Kubernetes environments. The former deployment was performed by setting up a local Minikube cluster, while the latter assumes a remote Kubernetes cluster, and we are connecting to it through a VPN. We have tested the availability and accuracy of the encryption/decryption services and checked the logs to ensure that these services work correctly. We aim to present this article to assist researchers wishing to conduct effective testing or a Testbed in the real world. © 2024 University of Split, FESB.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Deep Learning-Based Model for Tomato Leaf Disease Classification

引用

computers, Materials & Continua 2023年第12期77卷 3969-3992页

作者： Naeem Ullah Javed Ali Khan Sultan Almakdi Mohammed S.Alshehri Mimonah Al Qathrady Eman Abdullah Aldakheel Doaa Sami Khafaga Department of Software Engineering University of Engineering and TechnologyTaxila4400Pakistan Department of Computer Science Faculty of PhysicsEngineeringand Computer ScienceUniversity of HertfordshireHatfieldAL109ABUK Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Departments of Information Systems College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

Tomato leaf diseases significantly impact crop production,necessitating early detection for sustainable *** Learning(DL)has recently shown excellent results in identifying and classifying tomato leaf ***,current DL methods often require substantial computational resources,hindering their application on resource-constrained *** propose the Deep Tomato Detection Network(DTomatoDNet),a lightweight DL-based framework comprising 19 learnable layers for efficient tomato leaf disease classification to overcome *** Convn kernels used in the proposed(DTomatoDNet)framework is 1×1,which reduces the number of parameters and helps in more detailed and descriptive feature extraction for *** proposed DTomatoDNet model is trained from scratch to determine the classification success rate.10,000 tomato leaf images(1000 images per class)from the publicly accessible dataset,covering one healthy category and nine disease categories,are utilized in training the proposed DTomatoDNet *** specifically,we classified tomato leaf images into Target Spot(TS),Early Blight(EB),Late Blight(LB),Bacterial Spot(BS),Leaf Mold(LM),Tomato Yellow Leaf Curl Virus(YLCV),Septoria Leaf Spot(SLS),Spider Mites(SM),Tomato Mosaic Virus(MV),and Tomato Healthy(H).The proposed DTomatoDNet approach obtains a classification accuracy of 99.34%,demonstrating excellent accuracy in differentiating between tomato *** model could be used on mobile platforms because it is lightweight and designed with fewer *** farmers can utilize the proposed DTomatoDNet methodology to detect disease more quickly and easily once it has been integrated into mobile platforms by developing a mobile application.

关键词： CNN deep learning DTomatoDNet tomato leaf disease classification smart agriculture

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Unanswered Python-Related Questions on Stack Overflow

An Empirical Study of Unanswered Python-Related Questions on...

引用

2024 International Conference on information technology Research and Innovation, ICITRI 2024

作者： Nugroho, Yusuf Sulistyo Halim, Salsabil Aisyah Abdul Islam, Syful Kurniawan, Yogiek Indra Erlina, Tati Universitas Muhammadiyah Surakarta Informatics Engineering Faculty of Communication and Informatics Surakarta Indonesia BSMRSTU Computer Science and Engineering Faculty of Engineering Gopalganj Bangladesh Universitas Jenderal Soedirman Informatics Engineering Faculty of Engineering Purwokerto Indonesia Universitas Andalas Computer Engineering Faculty of Information Technology Padang Indonesia

ISBN: (纸本)9798350376210

As a high-level programming language, Python supports user-friendly coding and system integration. It is not only used for data analytics but is also applied in software development. Although it has several benefits, users have various issues while running Python code. When programmers face issues, they often use Stack Overflow (SO) to get assistance for their problems. However, many Pythonrelated questions on SO are not responded to and remain unanswered. Thus, in this paper, we analyzed these unanswered questions to identify potential weaknesses of user and discussion characteristics. We applied a mixed-methods approach, including quantitative and qualitative analysis of user reputation, question types, and discussion topics. Our analysis shows that unanswered questions are mostly from low-reputation users (72.52%), followed by mid-reputation users (17.93%), and high-reputation users (9.5 5%). The distribution of the unanswered question types shows that low-reputation users ask more 'how' type of question (38.90%) followed by mid and high-reputation users. In contrast, the 'what' and 'why' questions are mostly posted by high-reputation users, followed by mid and low-reputation users. Our word-cloud analysis suggests a correlation between user reputation and the question topics. We acknowledge that there are limitations in our study, include potential misclassifications due to the time of posting and biases in manual labeling, which may affect the accuracy of our findings. This study provides insights into unanswered questions posted by the community, open up potential areas for future work such as improving support mechanisms and community engagement. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

A novel U-net model for brain tumor segmentation from MRI images

引用

Alexandria engineering Journal 2025年 126卷 220-230页

作者： Obayya, Marwa Alshuhail, Asma Mahmood, Khalid Alanazi, Meshari H. Alqahtani, Mohammed Aljehane, Nojood O. Almansour, Hamad Al-Hagery, Mohammed Abdullah Department of Biomedical Engineering College of Engineering Princess Nourah bint Abdulrahman University PO Box 84428 Riyadh11671 Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal university Saudi Arabia Department of Information Systems Applied College at Mahayil King Khalid University Saudi Arabia Department of Computer Science College of Sciences Northern Border University Arar Saudi Arabia Department of Information System and Cyber Security College of Computing and Information Technology University of Bisha Bisha61922 Saudi Arabia Department of Computer Science Faculty of Computers and Information Technology University of Tabuk Tabuk Saudi Arabia Applied Collage Najran University Najran Saudi Arabia Department of Computer Science College of Computer Qassim University Saudi Arabia

Segmentation of brain tumors aids in diagnosing the disease early, planning treatment, and monitoring its progression in medical image analysis. Automation is necessary to eliminate the time and variability associated with traditional segmentation methods. Convolutional neural networks (CNNs) and U-Net architectures have demonstrated their efficiency and effectiveness in segmenting brain tumors from MRI images using deep learning techniques. The paper presents an improved U-Net-based segmentation algorithm that integrates nested skip paths to improve encoder-decoder feature fusion. The performance of segmentation was optimized by utilizing a variety of activation functions and loss functions, including Dice Loss and Intersection over Union (IoU). A high level of accuracy was demonstrated in the proposed model when it was evaluated using the LGG Segmentation Dataset. The proposed approach for segmenting medical images has been shown to be both robust and efficient in a comparative analysis. © 2025 The Authors

关键词： Convolutional neural networks

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：