检索结果-内蒙古大学图书馆

HTC-HAD: A Hybrid Transformer-CNN Approach for Hyperspectral Anomaly Detection

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 10144-10156页

作者： Zhao, Minghua Zheng, Wen Hu, Jing Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Engineering Xi'an710048 China

Hyperspectral anomaly detection (HAD) identifies anomalies by analyzing differences between anomalies and background pixels without prior information, presenting a significant challenge. Most existing studies leverage the high correlation in spectral and spatial dimensions, primarily focusing on local spectral and spatial information for background reconstruction while neglecting long-range dependencies. This local perception constrains models from fully capturing intrinsic spatial–spectral connections. To address this, we propose a novel hybrid transformer-CNN network for HAD (HTC-HAD). Specifically, HTC-HAD combines CNNs with transformers, where the CNN focuses on local modeling, and the transformer addresses long-range modeling. This dual approach ensures the accurate reconstruction of backgrounds by capturing both local and long-range dependencies. Meanwhile, to reduce model complexity and redundancy among neighboring bands, we incorporate a simplified and effective band selection strategy as preprocessing. In addition, to prevent anomalies from being reconstructed during background estimation, we employ an adaptive weight loss function to suppress them. Experimental results on several real datasets, both qualitatively and quantitatively, demonstrate that our HTC-HAD achieves satisfying detection performance. © 2008-2012 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

CSG_IACO: an efficient stigmergic-based improved ACO routing strategy to determine the effective path based on traffic density in V2V networks

引用

International Journal of Information Technology (Singapore) 2025年第3期17卷 1883-1908页

作者： Kumari, J. Jesy Janet Thangam, S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

Vehicular ad hoc networks (VANETs) are an essential element and building block of the autonomous vehicle system. VANETs, a subcategory of mobile ad hoc networks (MANETs), stand out due to certain predetermined attributes. In VANETs, optimal path routing offers solutions to address issues like traffic density, node mobility, link failure, and bandwidth. Finding the optimal VANET road path between source and destination conditions is difficult. Extensive paths increase network overhead, communication costs, and failure probability, reducing routing efficiency. We present the new traffic density-based stigmergic ant colony optimization routing (CSG_IACO) to improve routing performance. Improved ant colonies stimulate the proposed CSG_IACO, which measures inter-vehicular density. Ant behavior serves as the inspiration for the improved ACO technique, a meta-heuristic methodology. Phase 1 of the CSG_IACO involves using the traffic density to form a cluster among the vehicles. Phase 2 of the suggested approach is Stigmergy-based ant colony optimization, which guides ants to indirectly communicate with each other to act upon the change in the environment to find a best path. This improves protocol efficiency in all aspects. The simulations using NS 2.35 and SUMO indicate that the proposed system considerably reduces obstacles to finding the optimal path compared to existing systems. The simulations show that our suggested scheme performs better than AODV-DATRLD, ACO-DATRLD, and CaCOIoV in terms of performance including the count of delivered packets, throughput, end-to-end delay, the average count of cluster formations per cluster head, and the number of dropped packets. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.

关键词： Ant colony optimization Cluster Optimal path QoS Stigmergy Traffic density VANETs

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 1-14页

作者： Tan, Mingkui Chen, Guohao Wu, Jiaxiang Zhang, Yifan Chen, Yaofo Zhao, Peilin Niu, Shuaicheng South China University of Technology School of Software Engineering China Pazhou Laboratory Guangzhou China XVERSE China National University of Singapore School of Computing Singapore Tencent AI Lab China Nanyang Technological University College of Computing and Data Science Singapore

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important when the test environment changes frequently. Although some recent attempts have been made to handle this task, we still face two key challenges: 1) prior methods have to perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications;2) while existing TTA solutions can significantly improve the test performance on out-of-distribution data, they often suffer from severe performance degradation on in-distribution data after TTA (known as catastrophic forgetting). To this end, we have proposed an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples for test-time entropy minimization. To alleviate forgetting, EATA introduces a Fisher regularizer estimated from test samples to constrain important model parameters from drastic changes. However, in EATA, the adopted entropy loss consistently assigns higher confidence to predictions even when the samples are underlying uncertain, leading to overconfident predictions that underestimate the data uncertainty. To tackle this, we further propose EATA with Calibration (EATA-C) to separately exploit the reducible model uncertainty and the inherent data uncertainty for calibrated TTA. Specifically, we compare the divergence between predictions from the full network and its sub-networks to measure the reducible model uncertainty, on which we propose a test-time uncertainty reduction strategy with divergence minimization loss to encourage consistent predictions instead of overconfident ones. To further re-calibrate predicting confidence on different samples, we utilize the disagreement among predicted labels as an indicator of the data uncertainty. Based on this, we devise a min-max entropy

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust facial expression recognition via lightweight reinforcement learning for rehabilitation robotics

引用

Optoelectronics Letters 2025年第2期21卷 97-104页

作者： CHEN Yifan FAN Weiming GAO Hongwei YU Jiahui JU Zhaojie School of Computing University of PortsmouthPO13HEUK School of Automation and Electrical Engineering Shenyang Ligong UniversityShenyang 110159China Department of Biomedical Engineering Zhejiang UniversityHangzhou 310027China

This paper proposes a lightweight reinforcement network (LRN) and auxiliary label distribution learning (ALDL)based robust facial expression recognition (FER) *** designed representation reinforcement (RR) network mainly comprises two modules,i.e.,the RR module and the auxiliary label space construction (ALSC) *** RR module highlights key feature messaging nodes in feature maps,and ALSC allows multiple labels with different intensities to be linked to one ***,LRN has a more robust feature extraction capability when model parameters are greatly reduced,and ALDL is proposed to contribute to the training effect of LRN in the condition of ambiguous training *** tested our method on FER-Plus and RAF-DB datasets,and the experiment demonstrates the feasibility of our method in practice during rehabilitation robots.

关键词： rehabilitation lightweight auxiliary

来源：评论

学校读者我要写书评

暂无评论

Endoscopy-assisted lightweight diagnosis system based on transformers for colon polyp detection

引用

Optoelectronics Letters 2025年第1期21卷 57-64页

作者： FAN Weiming YU Jiahui JU Zhaojie School of Automation and Electrical Engineering Shenyang Ligong UniversityShenyang 110159China Department of Biomedical Engineering Zhejiang UniversityHangzhou 310058China School of Computing University of PortsmouthPO13HEUK

The integration of endoscopy has significantly propelled the diagnosis and treatment of gastrointestinal diseases,with colonoscopy establishing itself as the primary method for early diagnosis and preventive care in colorectal cancer(CRC).Although deep learning holds promise in mitigating missed polyp rates,modern endoscopy examinations pose additional challenges,such as image blurring and *** study explores lightweight yet powerful attention mechanisms,introducing the spatial-channel transformer(SCT),an innovative approach that leverages spatial channel relationships for attention weight *** method utilizes rotation operations for inter-dimensional dependencies,followed by residual transformation,encoding inter-channel and spatial information with minimal computational *** experiments on the CVC-Clinic DB polyp detection dataset,addressing endoscopy pitfalls,underscore the superiority of our SCT over other state-of-the-art *** proposed model maintains high performance,even in challenging scenarios.

关键词： diagnosis utilize holds

来源：评论

学校读者我要写书评

暂无评论

Simulating Social Pressure: Evaluating Risk Behaviors in Construction Using Augmented Virtuality

引用

IEEE Transactions on Visualization and Computer Graphics 2025年第5期31卷 2494-2503页

作者： Pooladvand, Shiva Hasanzadeh, Sogand Takahashi, George Park, Kenneth Jongwon Marroquin, Jacob School of Sustainable Engineering and the Built Environment Arizona State University United States Lyles School of Civil and Construction Engineering Purdue University United States Rosen Center for Advanced Computing Purdue University United States

Drawing on social influence and behavioral intention theories, coworkers' risk-taking serves as an "extra motive" —an exogenous factor—for risk-taking behaviors among workers in the workplace. Social influence theories have shown that social factors, such as social pressure and coworker risk-taking, may predict risk-taking behaviors and significantly affect decision-making. While immersive technologies have been widely used to create close-to-real simulations for construction safety-related studies, there is a paucity of research considering the impact of social presence in evaluating workers' risk decision-making within immersive environments. To bridge this gap, this study developed a state-of-the-art Augmented Virtuality (AV) environment to investigate roofers' risk-taking behaviors when exposed to social stressors (working alongside a safe/unsafe peer). In this augmented virtuality environment, a virtual peer with safe and unsafe behaviors was simulated in order to impose peer pressure and increase participants' sense of social presence. Participants were asked to install asphalt shingles on a physical section of a roof (passive haptics) while the rest of the environment was projected virtually. During shingle installation, participants' cognitive and behavioral responses were captured using psychophysiological wearable technologies and self-report measures. The results demonstrated that the developed AV model could successfully enhance participants' sense of presence and social presence while serving as an appropriate platform for assessing individuals' decision-making orientations and behavioral changes in the presence of social stressors. Such information shows the value of immersive technologies to examine the naturalistic responses of individuals without exposing them to actual risks. © 1995-2012 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Leveraging Blockchain-Enabled Digital Twins for Building Commissioning

Leveraging Blockchain-Enabled Digital Twins for Building Com...

引用

International Conference of Sustainable Development and Smart Built Environments, SDSBE 2024

作者： Adu-Amankwa, Nana Akua Rahimian, Farzad School of Computing Engineering and Digital Technologies Teesside University Middlesbrough United Kingdom

ISBN: (纸本)9789819640508

This paper delves into the potential integration of Blockchain (BC) and Digital Twins (DT) into Building Commissioning (BCx). Through a combination of literature review and semi-structured interviews with experts in academia and industry, the study highlights the perceived role of BC-enabled DT in ensuring effective management of BCx activities. BCx often encounter issues related to manual data handling and inconsistencies in data representation, which can lead to errors, data loss, fragmented and inaccurate information, and poor decision-making. Thus, the study’s findings underscore the unique features of BC-enabled DT in supporting real-time decision-making, improving information access among stakeholders, and enhancing data security. These findings are supported by evidence from literature, demonstrating that DTs can leverage data for reliable decision-making while BC can ensure data integrity in a decentralised peer-to-peer framework. Furthermore, the study delves into the technological considerations for the effective use of a BC-enabled DT approach to BCx. The study sheds light on the approach’s relevance and significantly contributes to the advancement of the industry’s digital transformation strategies. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

CL3: A Collaborative Learning Framework for the Medical Data Ensuring Data Privacy in the Hyperconnected Environment 25th

CL3: A Collaborative Learning Framework for the Medical Da...

引用

25th International Conference on Web Information Systems engineering, WISE 2024

作者： Parvez, Mohammad Zavid Islam, Rafiqul Islam, Md Zahidul School of Computing Mathematics and Engineering Charles Sturt University BathurstNSW Australia

ISBN: (纸本)9789819605729

In a hyperconnected environment, medical institutions are particularly concerned with data privacy when sharing and transmitting sensitive patient information due to the risk of data breaches, where malicious actors could intercept sensitive information. A collaborative learning framework, including transfer, federated, and incremental learning, can generate efficient, secure, and scalable models while requiring less computation, maintaining patient data privacy, and ensuring an up-to-date model. This study aims to address the detection of COVID-19 using chest X-ray images through a proposed collaborative learning framework called CL3. Initially, transfer learning is employed, leveraging knowledge from a pre-trained model as the starting global model. Local models from different medical institutes are then integrated, and a new global model is constructed to adapt to any data drift observed in the local models. Additionally, incremental learning is considered, allowing continuous adaptation to new medical data without forgetting previously learned information. Experimental results demonstrate that the CL3 framework achieved a global accuracy of 89.99% when using Xception with a batch size of 16 after being trained for six federated communication rounds. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Dual-Task Deep Reinforcement Learning and Domain Transfer Architecture for Bootstrapping Swarming Collective Motion Skills

引用

IEEE Systems Journal 2025年第1期19卷 327-338页

作者： Abpeikar, Shadi Garratt, Matt Anavatti, Sreenatha Ghanem, Reda Kasmarik, Kathryn University of New South Wales School of Engineering Technology CanberraACT2600 Australia University of New South Wales School of Systems Computing CanberraACT2600 Australia

Recent research has shown it is possible for groups of robots to automatically "bootstrap" their own collective motion behaviors, particularly movement in a group. However, existing work has primarily provided proof of concept in regular, open arenas without obstacles. For practical applications on real robots, multiple collective motion skills are required. This article proposes a novel, multitask deep reinforcement learning algorithm and domain transfer architecture permitting multiple collective motion skills to be bootstrapped automatically and applied to real robots. The proposed approach is tested for tuning two collective motion skills for grouped movement and obstacle avoidance, without requiring a map of the environment. We show that our approach can tune obstacle avoidance parameters while maintaining high-quality swarming collective behavior when an obstacle is detected. Furthermore, learned collective motion skills can be transferred from a point mass simulation onto real mobile robots using our domain transfer architecture, without loss of quality. Transferability is comparable to that of an evolutionary algorithm run in a high-fidelity simulator. © 2007-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

When Embodied AI Meets Industry 5.0:Human-Centered Smart Manufacturing

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 485-501页

作者： Jing Xu Qiyu Sun Qing-Long Han Yang Tang IEEE the Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology the School of Science Computing and Engineering Technologies Swinburne University of Technology

As embodied intelligence(EI), large language models(LLMs), and cloud computing continue to advance, Industry5.0 facilitates the development of industrial artificial intelligence(Ind AI) through cyber-physical-social systems(CPSSs) with a human-centric focus. These technologies are organized by the system-wide approach of Industry 5.0, in order to empower the manufacturing industry to achieve broader societal goals of job creation, economic growth, and green production. This survey first provides a general framework of smart manufacturing in the context of Industry 5.0. Wherein, the embodied agents, like robots, sensors, and actuators, are the carriers for Ind AI, facilitating the development of the self-learning intelligence in individual entities, the collaborative intelligence in production lines and factories(smart systems), and the swarm intelligence within industrial clusters(systems of smart systems). Through the framework of CPSSs, the key technologies and their possible applications for supporting the single-agent, multi-agent and swarm-agent embodied Ind AI have been reviewed, such as the embodied perception, interaction, scheduling, multi-mode large language models, and collaborative training. Finally, to stimulate future research in this area, the open challenges and opportunities of applying Industry 5.0 to smart manufacturing are identified and discussed. The perspective of Industry 5.0-driven manufacturing industry aims to enhance operational productivity and efficiency by seamlessly integrating the virtual and physical worlds in a human-centered manner, thereby fostering an intelligent, sustainable, and resilient industrial landscape.

关键词： Embodied AI human-centered manufacturing Industry 5.0 internet of things large multi-mode language models

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：