检索结果-内蒙古大学图书馆

Session-Guided Attention in Continuous Learning with Few Samples

IEEE Transactions on Image Processing 2025年 34卷 2654-2666页

作者： Pan, Zicheng Yu, Xiaohan Gao, Yongsheng Griffith University Institute for Integrated and Intelligent Systems Australia Macquarie University School of Computing Australia

Few-shot class-incremental learning (FSCIL) aims to learn from a sequence of incremental data sessions with a limited number of samples in each class. The main issues it encounters are the risk of forgetting previously learned data when introducing new data classes, as well as not being able to adapt the old model to new data due to limited training samples. Existing state-of-the-art solutions normally utilize pre-trained models with fixed backbone parameters to avoid forgetting old knowledge. While this strategy preserves previously learned features, the fixed nature of the backbone limits the model's ability to learn optimal representations for unseen classes, which compromises performance on new class increments. In this paper, we propose a novel SEssion-Guided Attention framework (SEGA) to tackle this challenge. SEGA exploits the class relationships within each incremental session by assessing how test samples relate to class prototypes. This allows accurate incremental session identification for test data, leading to more precise classifications. In addition, an attention module is introduced for each incremental session to further utilize the feature from the fixed backbone. As the session of the testing image is determined, we can fine-tune the feature with the corresponding attention module to better cluster the sample within the selected session. Our approach adopts the fixed backbone strategy to avoid forgetting the old knowledge while achieving novel data adaptation. Experimental results on three FSCIL datasets consistently demonstrate the superior adaptability of the proposed SEGA framework in FSCIL tasks. © 1992-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Algorithms for Minimizing the Kirchhoff Index via Adding Edges

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3342-3355页

作者： Zhou, Xiaotian Zehmakan, Ahad N. Zhang, Zhongzhi Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China School of Computing Australian National University CanberraACT2601 Australia Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China

The Kirchhoff index, which is the sum of the resistance distance between every pair of nodes in a network, is a key metric for gauging network performance, where lower values signify enhanced performance. In this paper, we study the problem of minimizing the Kirchhoff index by adding edges. We first provide a greedy algorithm for solving this problem and give an analysis of its quality based on the bounds of the submodularity ratio and the curvature. Then, we introduce a gradient-based greedy algorithm as a new paradigm to solve this problem. To accelerate the computation cost, we leverage geometric properties, convex hull approximation, and approximation of the projected coordinate of each point. To further improve this algorithm, we use pre-pruning and fast update techniques, making it particularly suitable for large networks. Our proposed algorithms have nearly-linear time complexity. We provide extensive experiments on ten real networks to evaluate the quality of our algorithms. The results demonstrate that our proposed algorithms outperform the state-of-the-art methods in terms of efficiency and effectiveness. Moreover, our algorithms are scalable to large graphs with over 5 million nodes and 12 million edges. © 2025 IEEE.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

A Transfer Learning-Based Approach for Fatigue Detection Through the Fusion of Physiological Signals

引用

IEEE Sensors Journal 2025年第9期25卷 15750-15760页

作者： Kakhi, Kourosh Asgharnezhad, Hamzeh Khosravi, Abbas Alizadehsani, Roohallah Rajendra Acharya, U. Institute for Intelligent Systems Research and Innovation Deakin University Waurn PondsVIC3216 Australia University of Southern Queensland School of Mathematics Physics and Computing ToowoombaQLD4350 Australia

The improvement of road safety and the reduction of accident occurrences globally necessitates the detection of driver fatigue. This article explores the current research gap in identifying the most effective physiological signals for fatigue detection. Through a comprehensive analysis, physiological signals are converted into images and processed using pretrained deep neural networks (DNNs) to detect patterns indicative of fatigue. This research stands as a pioneering effort in fatigue detection, examining various combinations of physiological signals, pretrained DNNs, and classification methods within a dataset. Our thorough evaluation demonstrates that multiple classifiers using ECG signals can achieve near-perfect performance metrics (accuracy, area under the curve, precision, and recall) on test sets. These highlight the transformative potential of artificial intelligence (AI) technologies in redefining current systems for monitoring driver fatigue, marking a significant leap forward in the application of AI for ensuring driver safety and preventing accidents caused by fatigue. The findings reinforce the critical role of incorporating advanced AI techniques into driver-assistance systems to develop more reliable and efficient fatigue detection solutions. © 2001-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Explainable Artificial Intelligence Driven Segmentation for Cervical Cancer Screening

引用

IEEE Access 2025年 13卷 71306-71322页

作者： Sritharan, Niruthikka Gnanavel, Nishaanthini Inparaj, Prathushan Meedeniya, Dulani Yogarajah, Pratheepan University of Moratuwa Department of Computer Science and Engineering Moratuwa10400 Sri Lanka Ulster University School of Computing Engineering and Intelligent Systems LondonderryBT48 7JL United Kingdom

Cervical cancer remains an important global health challenge among women. Early and accurate identification of abnormal cervical cells is crucial for effective treatment and improved survival rates. This paper addresses the development of a novel weakly supervised segmentation framework that combines binary classification, Explainable Artificial Intelligence (XAI) techniques, and GraphCut to automate cervical cancer screening. Unlike traditional segmentation methods that rely on pixel-level annotations of medical images, which are costly, laborious, and require expertise in medical imaging, our approach leverages classification-driven insights to segment the nucleus, cytoplasm, and background regions. A key innovation of our framework is the use of XAI techniques such as Grad-CAM++ and LRP combined with GraphCut, to enable annotation-free segmentation using only classification-level labels. This represents a pioneering application of explainability techniques in the context of cervical cancer screening. Among the classification models explored, including fine-tuned variants of VGGNet and XceptionNet, VGG16-Adapted128 achieved the highest performance, marked by an accuracy of 0.94, precision of 0.94, recall of 0.94, and an F1 score of 0.94. This novel segmentation framework employed LRP and GradCAM++ as XAI techniques to gain insight into the decision-making process of classification models, with GradCAM++ demonstrating greater effectiveness. The performance of these XAI methods was assessed through both visual inspection and quantitative metrics, including entropy and pixel flipping. This innovative approach to segmentation is formally introduced through two algorithms detailed in this paper. The weakly supervised segmentation framework achieved a Dice Similarity Coefficient (DSC) of 62.05% and an Intersection over Union (IoU) of 61.89%. In addition, it has received high satisfaction ratings from expert evaluations and has been seamlessly integrated into a user-frie

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Utility-Adjustable Reverse Auction Mechanism for UAV Data Collection Task Allocation 20th

A Utility-Adjustable Reverse Auction Mechanism for UAV Data...

引用

20th IFIP WG 10.3 International Conference on Network and Parallel computing, NPC 2024

作者： Chen, Peng Zhang, Jixian School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

ISBN: (纸本)9789819628636

Due to their low cost, easy deployment, and high flexibility, unmanned aerial vehicles(UAV) have become widely utilized for various data collection tasks across different fields. In particular, virtual service providers(VSP) recruit UAVs to collect data in their regions of interest(ROI), and leverage this data to offer a range of services, such as metaverse, traffic management, etc. To attract UAV owners to participate in the recruitment activities, VSP need to provide participating users with payments as rewards to motivate their participation. However, the recruitment demands of different VSPs for UAVs can vary significantly. For instance, time-sensitive tasks require timely recruitment of sufficient UAVs to ensure prompt completion of data collection tasks, necessitating higher payments to increase user enthusiasm. Conversely, in other types of tasks, the VSP’s objective might be to maximize its own utility. However, designing a general incentive mechanism for VSPs with different tasks that satisfies incentive compatibility(IC) and individual rationality(IR) to address the issues of UAV task allocation and payment is challenging. If VSP offer insufficient payments to users, it will be difficult to attract enough users to share their UAVs;conversely, offering excessive payments to users will harm the VSP’ profits. To address this problem, we propose a utility-adjustable reverse auction mechanism based on reverse Vickrey-Clarke-Groves(VCG) auction and affine maximizer auction(AMA) theory to cope with different task scenarios. This incentive mechanism can maximize social welfare while flexibly adjusting the utility allocation between VSP and users, ensuring non-negative utility for both parties. Experimental results show that the mechanism has excellent performance. © IFIP International Federation for Information Processing 2025.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

引用

Neural computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Comparison of Segmentation Algorithms for Extraction of Stone from Kidney X-ray Image 4th

Comparison of Segmentation Algorithms for Extraction of Ston...

引用

4th International Conference on Smart IoT systems: Innovations and computing, SSIC 2023

作者： Nisha, N. Dhaka, Vijaypal Singh Sinwar, Deepak Department of Computer and Communication Engineering Manipal University Jaipur Jaipur India Director of School of Computing and Intelligent Systems Department of Computer and Communication Engineering Manipal University Jaipur Jaipur India Department of IoT and Intelligent Systems Manipal University Jaipur Jaipur India

ISBN: (纸本)9789819751990

Healthcare systems are gaining popularity because of the advancement of new technology aiding healthcare professional for diagnosis of disease from medical modalities. The detection and classification of disease using AI and its technologies are active research areas in the last decade. Radiologist usually detects stone from the kidney using different imaging like CT scan, MRI scan, and X-ray. For the detection of stone in kidney X-ray images, various segmentation and classification methods are used. These different classification and segmentation methods are used to reduce errors and time of healthcare professional in diagnosis of stone in X-ray image. In this paper, comparison of different algorithms like thresholding algorithm, contour-based algorithm, deep learning algorithms like U-Net, U-Net++, V-Net, V-Net++, and Transformer Net are used for segmentation of stone from kidney X-ray images. The thorough comparison of different deep learning architectures in diagnosing stone from kidney X-ray images is also made in this paper. Most of the papers work on classification of stone from different medical modalities before segmentation which cause data leakage problem. In this research paper, comparisons of different segmentation algorithms help in achieving higher accuracy and reduce the data leakage problem. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Malware Detection and Analysis in Android Applications with Mobile Security Framework (MobSF) Using a Permission-Based Approach 12th

Malware Detection and Analysis in Android Applications with ...

引用

12th International Conference on Frontiers of intelligent computing: Theory and Applications, FICTA 2024

作者： Kizito, Mark Homayounvala, Elaheh Kazemian, Hassan Araujo, Istteffanny Intelligent Systems Research Group School of Computing and Digital Media London Metropolitan University 166-220 Holloway Rd LondonN7 8DB United Kingdom

ISBN: (纸本)9789819601424

This paper examines security concerns in Android applications arising from violations to the principle of least privilege. Using mobile security framework (MobSF), static and dynamic analysis techniques were used in evaluating how non-essential permission groups that are not core to application functions greatly increase risks of unauthorized system access by attackers, data breaches and privacy concerns, enlarged attack surfaces, and hijacking system resources among others. A permission-based approach systematically identifies malware and highlights dangerous permission groups that magnify security risks. The findings of this research study emphasis on meticulous auditing of permissions to prevent security threats in Android applications and to safeguard user-sensitive data. The conducted experiments compared essential core permissions to non-essential ones regarding application functionality and overall system security. It was also noted that background permissions potentially pose a great deal of risk to security when granted without proper rationale as this increases attack surfaces within the application itself. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

Seeing through Dense Fog with an intelligent Adaptive Dehazing System

引用

IEEE Sensors Journal 2025年第10期25卷 17696-17705页

作者： Chen, Pengyun Cao, Ning Xu, Ziqin Cui, Shuang Jin, Shaohui Liu, Hao Xu, Mingliang Zhengzhou University School of Computer Science and Artificial Intelligence Zhengzhou450001 China National University of Defense Technology College of Advanced Interdisciplinary Studies Changsha410073 China Ministry of Education Engineering Research Center of Intelligent Swarm Systems Zhengzhou450001 China National Super-computing Center Zhengzhou450001 China

Most existing image dehazing methods are mainly suitable for synthetic datasets and often perform poorly in real-world, complex hazy scenarios. To address this issue, this paper proposes an intelligent adaptive dehazing system that integrates range-gated imaging with deep learning, combining image acquisition and restoration for enhanced dehazing performance. The range-gated imaging system reduces scattered light interference. However, our approach primarily focuses on enhancing image quality through advanced dehazing methods. Specifically, we introduce the MSCENAFormer dehazing network, which achieves high-quality reconstruction of target scenes in dense fog by effectively removing fog and improving visibility. The core modules of MSCENAFormer include the multi-scale enhanced neighborhood attention module (MSENA) and the comprehensive attention refinement module (CARM). MSENA is designed to capture rich local information in harsh environment, improving the dehazing effect and enhancing image details. CARM integrates the local and global information to optimize the visual effect further. In addition, the adaptive feature mixing module (AFM) is used to fuse multi-scale features for better performance. To validate the performance of our method, we utilize our lab-collected non-homogeneous haze real dataset, O-ITDF, along with the public datasets NH-HAZE, NTIRE2021 and NTIRE2023. Experimental results demonstrate that our proposed MSCENAFormer outperforms many methods. We share our code at https://***/NingCao-zzu/MSCENAFormer. © 2001-2012 IEEE.

关键词： Light interference

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：