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

Zero-dynamics attack detection based on data association in feedback pathway

Cognitive Robotics

引用

Cognitive Robotics 2025年 5卷 126-139页

作者： Zhang, Zeyu Li, Hongran Todo, Yuki Division of Electrical Engineering and Computer Science Kanazawa University Ishikawa Kanazawa9201192 Japan School of Computer Engineering Jiangsu Ocean University Jiangsu Lianyungang222005 China Faculty of Electrical Information and Communication Engineering Kanazawa University Ishikawa Kanazawa9201192 Japan

This paper considers the security of non-minimum phase systems, a typical kind of cyber-physical systems. Non-minimum phase systems are characterized by unstable zeros in their transfer functions, making them particularly susceptible to disturbances and attacks. The non-minimum phase systems are more vulnerable to zero-dynamics attack (ZDA) than minimum phase systems. ZDA is a stealthy attack strategy that exploits the internal dynamics of a system, remaining undetectable while causing gradual system destabilization. Recent cyber incidents have demonstrated the increasing risk of such hidden attacks in critical infrastructures, such as power grids and transportation systems. This paper first demonstrates that the existing ZDA has the limitation of falling into local convergence, and then proposes an enhanced zero-dynamics attack (EZDA), which overcomes local convergence by diverging system data. Furthermore, this paper presents an autoregressive model which can build the data association between the original data and the forged data. By observing the fluctuations in state values, the presented model can detect not only ZDA, but also EZDA. Finally, numerical simulations and an application example are provided to verify the theoretical results. © 2025

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A Riccati Matrix Equation Solver Design Based Neurodynamics Method and Its Application

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 15163-15176页

作者： Xiao, Pingdan Fang, Junjie Wei, Zhengmiao Dong, Yu Du, Sichun Wen, Shiping Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China University of Technology Sydney Australian AI Institute Faculty of Engineering and Information Technology UltimoNSW2007 Australia

Riccati matrix equation (RME), a critical nonlinear matrix equation in autonomous driving and deep learning. However, memory-compute separation in traditional solving systems leads to latency and inefficiency when solving nonlinear equations, particularly under real-time requirements. Existing hardware lacks dedicated accelerators for RME, no specialized solvers quick addressing its nonlinear complexity. To address this issue, we propose a novel RME solver based on a memristive array, which leverages the parallel and fast computing advantages of analog circuits to quickly solve any order RME. Inspired by Neurodynamics for non-linear matrix equations, we first introduce an innovative Neurodynamics-based RME solving algorithm specifically designed from an analog circuit perspective. Based on this algorithm, we constructed a pioneering closed-loop analog circuit solver, overcoming bottlenecks in using circuits for such nonlinear matrix equations. Our evaluation demonstrates that the proposed solver achieves over 90% accuracy for a 128th-order parameter Riccati matrix equation. Compared to traditional digital processors, the solver offers significant energy efficiency advantages and is three orders of magnitude faster than CPU. Additionally, the solver successfully accelerates our proposed dung beetle optimizer-linear quadratic control algorithm for vehicle suspension control, achieving high precision while significantly reducing time and energy consumption compared to CPU and GPU. © 2004-2012 IEEE.

关键词： Riccati equations

来源：评论

学校读者我要写书评

暂无评论

A Package Level Regression Test Selection Approach for Java Software Systems

引用

IEEE Access 2025年 13卷 87848-87861页

作者： Al-Refai, Mohammed Hammad, Mahmoud M. Faculty of Computer and Information Technology Computer Science Department Jordan university of science and technology P.O. Box 3030 Irbid 22110 Jordan Ajman University Department of Information Technology Faculty of Engineering and Information Technology Ajman United Arab Emirates Jordan University of Science and Technology Faculty of Computer and Information Technology Software Engineering Department P.O. Box 3030 Irbid 22110 Jordan

Regression testing of software systems is an important and critical activity but can be expensive and resource-intensive. An approach to enhance its efficiency is Regression Test Selection (RTS), which selectively re-executes a subset of relevant tests that are impacted by code modifications. Previous studies on static and dynamic RTS for Java software have shown that selecting tests at the class level is more effective than using finer granularities like methods or statements. Nevertheless, RTS at the package level, which is a coarser granularity than class level, has not been thoroughly investigated or evaluated for Java projects. To address this gap, we propose PKRTS, a static package-level RTS approach that utilizes the structural dependencies of the software system under test to construct a package-level dependency graph. PKRTS analyzes dependencies in the graph and identifies relevant tests that can reach modified packages, i.e., packages containing altered classes. In contrast to conventional static RTS techniques, PKRTS implicitly considers dynamic dependencies, such as Java reflection and virtual method calls, among classes belonging to the same package by treating all those classes as a single cohesive node in the dependency graph. We evaluated PKRTS on 885 revisions of 9 open-source Java projects, with its performance compared to Ekstazi, a state-of-the-art dynamic class-level approach, and STARTS, a state-of-the-art static class-level approach. We used Ekstazi as the baseline to measure the safety and precision violations of PKRTS and STARTS. The results indicated that PKRTS outperformed static class-level RTS in terms of safety violation, which measures the extent to which relevant test cases are missed. PKRTS showed an average safety violation of 2.29%, while STARTS recorded 5.94%. Despite this, PKRTS demonstrated lower average precision violation than class-level RTS, as it selected a higher number of irrelevant test cases. The average reduction in te

关键词： Dynamic analysis Java software systems Package-level dependencies Regression test selection Software testing Static analysis

来源：评论

学校读者我要写书评

暂无评论

Intelligent wearable vision systems for the visually impaired in Saudi Arabia

引用

Neural Computing and Applications 2025年第14期37卷 8571-8591页

作者： Talaat, Fatma M. El-Shafai, Walid Soliman, Naglaa F. Algarni, Abeer D. El-Samie, Fathi E. Abd Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Navigating the world with visual impairments presents unique challenges, often limiting independence and safety. This research introduces SafeStride, a novel algorithm designed to empower visually impaired individuals through real-time obstacle detection and navigation assistance. SafeStride functions through five interconnected phases: sensor data acquisition, data preprocessing, obstacle detection, path planning, and feedback and guidance. A combination of ultrasonic sensors, cameras, and inertial measurement units (IMUs) feed comprehensive environmental data into the system, enabling accurate obstacle detection and safe path planning. Evaluating SafeStride's performance involved the MNIST dataset for image recognition and a dedicated indoor object detection dataset. Additionally, comparisons were made against three deep learning models—convolutional neural network (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU). The results showcased SafeStride's high accuracy and effectiveness in both obstacle detection and classification. Beyond its impressive performance, SafeStride represents a significant leap forward in navigation aids for the visually impaired. By offering a comprehensive solution that enhances safety and independence in diverse environments, it holds immense potential to improve the lives of countless individuals. Future efforts will focus on further optimizing the algorithm and testing its real-world capabilities, paving the way for a future where safe and independent navigation becomes a reality for all. All three deep learning models (CNN, LSTM, GRU) excelled in the experiment, achieving high accuracy above 0.98, strong recall and F1-scores near 0.99, and exceptional AUC-ROC scores exceeding 0.9998. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Driver Drowsiness Detection Using Swin Transformer and Diffusion Models for Robust Image Denoising

引用

IEEE Access 2025年 13卷 71880-71907页

作者： El-Nabi, Samy Abd Ibrahim, Ahmed F. El-Rabaie, El-Sayed M. Hassan, Osama F. Soliman, Naglaa F. Ramadan, Khalil F. El-Shafai, Walid Faculty of Computer Science and Engineering Department of Artificial Intelligence Engineering South Sinai 46511 Egypt Menoufia University Faculty of Electronic Engineering Department of Electronics and Electrical Communications Engineering Menouf32952 Egypt Suez Canal University Faculty of Computers and Informatics Information Systems Department Ismailia41522 Egypt Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Computer Science Department Riyadh11586 Saudi Arabia

With the rapid development of intelligent transportation systems and growing emphasis on driver safety, real-time detection of driver drowsiness has become a critical area of research. This study presents a robust and scalable driver drowsiness detection framework that integrates a Swin Transformer-based deep learning model with a diffusion model for image denoising. While conventional convolutional neural networks (CNNs) are effective in standard vision tasks, they often suffer performance degradation in real-world driving scenarios due to noise, poor lighting, motion blur, and adversarial attacks. To address these challenges, the proposed model focuses on eye-state detection, specifically, prolonged eye closure, as a primary indicator of driver disengagement and fatigue. Our system introduces a novel preprocessing stage using a denoising diffusion model built on a U-Net encoder-decoder architecture, effectively mitigating the impact of Gaussian noise and adversarial perturbations. Additionally, we incorporate adversarial training with Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks, demonstrating significant improvements in classification accuracy and resilience. Evaluations are conducted on two benchmark datasets, Eye-Blink and Closed Eyes in the Wild (CEW), under both clean and noisy conditions. Comparative experiments show that the proposed system outperforms several state-of-the-art models, including ViT, ResNet50V2, InceptionV3, MobileNet, DenseNet169, and VGG19, in terms of accuracy (up to 99.82%), PSNR (up to 41.61 dB), and SSIM (up to 0.984), while maintaining competitive inference times suitable for practical deployment. Moreover, a detailed sensitivity analysis of data augmentation strategies reveals that techniques such as rotation and horizontal flip substantially enhance the model’s generalization across variable visual inputs. The system also demonstrates improved robustness under real-world black-box scenarios and adver

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

UltraSegNet:A Hybrid Deep Learning Framework for Enhanced Breast Cancer Segmentation and Classification on Ultrasound Images

引用

computers, Materials & Continua 2025年第5期83卷 3303-3333页

作者： Suhaila Abuowaida Hamza Abu Owida Deema Mohammed Alsekait Nawaf Alshdaifat Diaa Salama Abd Elminaam Mohammad Alshinwan Department of Computer Science Faculty of Prince Al-Hussein Bin Abdallah II for Information TechnologyAl Al-Bayt UniversityMafraq25113Jordan Medical Engineering Department Faculty of EngineeringAl-Ahliyya Amman UniversityAmman19328Jordan Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Faculty of Computers Science Misr International UniversityCairo11800Egypt Jadara Research Center Jadara UniversityIrbid21110Jordan

Segmenting a breast ultrasound image is still challenging due to the presence of speckle noise,dependency on the operator,and the variation of image *** paper presents the UltraSegNet architecture that addresses these challenges through three key technical innovations:This work adds three things:(1)a changed ResNet-50 backbone with sequential 3×3 convolutions to keep fine anatomical details that are needed for finding lesion boundaries;(2)a computationally efficient regional attention mechanism that works on high-resolution features without using a transformer’s extra memory;and(3)an adaptive feature fusion strategy that changes local and global featuresbasedonhowthe image isbeing *** evaluation on two distinct datasets demonstrates UltraSegNet’s superior performance:On the BUSI dataset,it obtains a precision of 0.915,a recall of 0.908,and an F1 score of *** the UDAIT dataset,it achieves robust performance across the board,with a precision of 0.901 and recall of ***,these improvements are achieved at clinically feasible computation times,taking 235 ms per image on standard GPU ***,UltraSegNet does amazingly well on difficult small lesions(less than 10 mm),achieving a detection accuracy of *** is a huge improvement over traditional methods that have a hard time with small-scale features,as standard models can only achieve 0.63–0.71 *** improvement in small lesion detection is particularly crucial for early-stage breast cancer *** from this work demonstrate that UltraSegNet can be practically deployable in clinical workflows to improve breast cancer screening accuracy.

关键词： Breast cancer ultrasound image segmentation classification deep learning

来源：评论

学校读者我要写书评

暂无评论

A Study of Predicting Social Networking Sites(SNS) Media Disorder Survey Data Using a Machine Learning Approach

A Study of Predicting Social Networking Sites(SNS) Media Dis...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Munia, Jerin Akther Tahmiduzzaman, K.B.M. Saad, Izazul Haque Islam, Md Mynul Akash, Abdul Hady Zumma, Md. Thoufiq Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh University of Technology Sydney Faculty of Engineering and Information Technology Sydney Australia University of Asia Pacific Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331509828

This study uses survey data and machine learning algorithms to forecast social media disorder in people. A total of 600 individuals answered questions on their social media usage patterns, internet habits, demographics, and signs of social media disorder. This dataset was used to train a number of machine learning models, such as Gaussian Naive Bayes (GaussianNB), Random Forest, K-Nearest Neighbors (KNN), Decision Tree, and Support Vector Machine (SVM). According to the findings, the GaussianNB model had the greatest accuracy of 97%, followed by SVM (94%), Random Forest (91%), Decision Tree (92%), and KNN (90%). These results demonstrate how well machine learning can identify those who may be at risk for social media disorder. In order to improve prediction performance, future research will concentrate on increasing feature size, diversifying datasets, and refining models. Furthermore, incorporating these models into user-friendly apps and intervention programs may offer useful resources for the early diagnosis and treatment of social media illness. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Review of IoT-Driven Innovations in Supply Chain Management 3

A Review of IoT-Driven Innovations in Supply Chain Managemen...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Chandankhede, Arpit Gourshettiwar, Palash Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Sawangi Meghe Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Computer Science and Engineering Sawangi Meghe Maharashtra Wardha442001 India

ISBN: (纸本)9798331509675

Supply Chain Management (SCM) worldwide makes major advancements through the Internet of Things (IoT) by enabling real-time monitoring and prediction analytics and automatic decision capabilities in worldwide deliver chains. Through IoT technology integration with Artificial Intelligence (AI) and blockchain and cloud computing the supply chain solves major operational problems including monitoring difficulties and waste reduction and regulatory compliance requirements and operation leadership deficits. The implementation of IoT for supply chain management encounters major adoption barriers from high installation costs combined with security risks and operability complications as well as limited scalability capacity that affects especially small to medium enterprises (SMEs) and developing markets. The evaluation paper examines the shifting impact of IoT in supply chain management which enhances performance metrics and brings greater clarity and strengthens supply chain resilience. A scientist studied existing papers and case studies to reveal several essential advantages which include better inventory management, predictive analysis systems and more effective supply-chain collaborations. The analysis emphasizes effective solutions for security privacy and moral and environmental issues to guarantee sustainable expanded IoT adoption. This paper delivers practical knowledge alongside best practices to help organizations adopt IoT systems which create adaptable efficient deliver chains with sustainability at their core thus achieving long-term market benefits in today's complex global marketplace. © 2025 IEEE.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

The Internet of Things in Elderly Healthcare Applications: A Systematic Review and Future Directions

引用

IEEE Access 2025年 13卷 71335-71373页

作者： Shirvanian, Naser Shams, Maryam Masoud Rahmani, Amir Lansky, Jan Mildeova, Stanislava Hosseinzadeh, Mehdi Islamic Azad University Department of Computer Engineering Science and Research Branch Tehran14778-93855 Iran Kurdistan University Department of Physics Faculty of Basic Science Sanandaj66177-15175 Iran National Yunlin University of Science and Technology Future Technology Research Center Douliu64002 Taiwan University of Finance and Administration Department of Computer Science and Mathematics Faculty of Economic Studies Prague101 00 Czech Republic Duy Tan University School of Computer Science Da Nang550000 Viet Nam Jadara University Jadara Research Center Irbid21110 Jordan

The increase in the elderly population globally and the prevalence of chronic diseases among the elderly have resulted in rising healthcare costs worldwide. Utilizing the Internet of Things (IoT) and smart sensors to reduce healthcare costs and enhance the quality of life for the elderly is a highly effective and valuable solution. Effective monitoring can improve resource management in IoT-based healthcare systems. We conducted a systematic literature review (SLR) for elderly healthcare on the IoT to evaluate its various facets and key areas. The taxonomy of elderly healthcare studies in the IoT comprises six categories: smart homes, security and privacy, remote healthcare system, wearable devices, smartphone, healthcare and healthcare costs. Management of chronic diseases has the highest percentage of evaluation statistics in the field of smart homes, at 61%. In addition, 26% of smart homes in healthcare are devoted to behavioral characteristics and 13% to biological characteristics. Finally, this study highlights the visions and challenges of elderly healthcare articles and future work. © 2013 IEEE.

关键词： Medical services Internet of Things Older adults Security Monitoring Diseases Costs Privacy Biomedical monitoring Smart homes

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：