Knowledge-Based Systems最新文献

筛选
英文 中文
Spatial-gate self-distillation network for efficient image super-resolution 高效图像超分辨的空间门自蒸馏网络
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-09 DOI: 10.1016/j.knosys.2025.114398
Yinggan Tang , Mengjie Su , Quansheng Xu
{"title":"Spatial-gate self-distillation network for efficient image super-resolution","authors":"Yinggan Tang ,&nbsp;Mengjie Su ,&nbsp;Quansheng Xu","doi":"10.1016/j.knosys.2025.114398","DOIUrl":"10.1016/j.knosys.2025.114398","url":null,"abstract":"<div><div>The balanced extraction of both non-local and local features represents a critical requirement for effective image super-resolution (SR). While transformer-based self-attention (SA) mechanisms demonstrate superior non-local modeling capabilities, their substantial computational demands limit practical deployment. To address this efficiency-performance trade-off, the Spatial-Gate Self-Distillation Network (SGSDN) implements a dual-capacity architecture combining: an SA-like (SAL) module employing strategically dilated 1D depthwise convolutions in horizontal and vertical orientations for efficient non-local feature extraction, and a lightweight local spatial-gate (LKG) block optimized for local detail preservation. Moreover, the proposed spatial-gate self-distillation block (SGSDB) further enhances performance through an optimized distillation structure that simultaneously processes both feature types while minimizing memory overhead. Experimental results demonstrate SGSDN’s superior performance-complexity balance, with benchmark evaluations showing comparable accuracy to SwinIR-light while requiring only 25% of the computational resources (FLOPs) and 25% of parameters, attributable to its avoidance of computationally intensive matrix operations.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"329 ","pages":"Article 114398"},"PeriodicalIF":7.6,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145057310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Robust label propagation based on prior-guided cross domain data augmentation for few-shot unsupervised domain adaptation 基于先验引导跨域数据增强的鲁棒标签传播,用于少镜头无监督域自适应
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-09 DOI: 10.1016/j.knosys.2025.114432
Peng Zhao , Jiakun Shi , Ping Ye , Huiting Liu , Xia Ji
{"title":"Robust label propagation based on prior-guided cross domain data augmentation for few-shot unsupervised domain adaptation","authors":"Peng Zhao ,&nbsp;Jiakun Shi ,&nbsp;Ping Ye ,&nbsp;Huiting Liu ,&nbsp;Xia Ji","doi":"10.1016/j.knosys.2025.114432","DOIUrl":"10.1016/j.knosys.2025.114432","url":null,"abstract":"<div><div>Few-shot unsupervised domain adaptation (FS-UDA) aims to leverage knowledge from an imbalanced, labeled source domain and apply it to an unlabeled target domain. The primary difficulties of FS-UDA stem from the disparity in data distributions across source and target domains, coupled with uneven class representation in the source data. Label propagation (LP) is commonly used in domain adaptation scenarios. However, in FS-UDA tasks, LP disproportionately favors the normal classes because the source domain suffers from imbalanced class distribution, which results in insufficient feature representation and a large domain gap for the few-shot classes. To tackle these problems, we introduce a new robust LP approach that leverages prior-guided cross-domain data augmentation for FS-UDA. Unlike conventional approaches that solely utilize source domain visual data for few-shot class augmentation, our proposed method employs contrastive language image pretraining-derived semantic priors to supervise visual feature extractor training and optimize few-shot prototypes. It enhances domain-invariant feature learning while mitigating cross-domain distribution mismatches. We introduce the visual information from the target domain to perform data augmentation via style transfer, obtaining more diverse class-specific information. Subsequently, we capture intradomain and interdomain relationships more accurately by constructing intradomain and interdomain graphs independently for all samples (original and augmented) from both domains, which facilitates more effective LP and makes LP robust to few-shot classes. Furthermore, we introduce an adaptive graph regularization loss to dynamically adjust class weights, enhance intraclass compactness within domains, and reduce intraclass distribution discrepancies between different domains. Comprehensive experiments validate that the proposed method achieves superior performance compared to existing state-of-the-art methods across various FS-UDA tasks. The proposed method achieves 77.3 % and 61.7 % average accuracies for few-shot classes on the Office-31 and Office-Home datasets, respectively.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"329 ","pages":"Article 114432"},"PeriodicalIF":7.6,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145057304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Sequential contrastive learning for progressive knowledge tracing 递进式知识追踪的顺序对比学习
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-09 DOI: 10.1016/j.knosys.2025.114413
Yi-Fei Wen , Hang Liang , Carl Yang , Tao Zhou , Jia Liu , Yajun Du , Yan-Li Lee
{"title":"Sequential contrastive learning for progressive knowledge tracing","authors":"Yi-Fei Wen ,&nbsp;Hang Liang ,&nbsp;Carl Yang ,&nbsp;Tao Zhou ,&nbsp;Jia Liu ,&nbsp;Yajun Du ,&nbsp;Yan-Li Lee","doi":"10.1016/j.knosys.2025.114413","DOIUrl":"10.1016/j.knosys.2025.114413","url":null,"abstract":"<div><div>In recent years, knowledge tracing has received significant attention in personalized education. It dynamically assesses users’ knowledge states based on their historical response sequence. User response sequences are central to knowledge tracing. While most studies focus on modeling short-term and long-term dependencies, few consider the order in which interactions occur. A recent study argues that the interaction order has little impact on users’ knowledge states (Lee <em>et al.</em>, The Web Conference, 2022), which contradicts both our intuition and constructivist learning theory. To address this contradiction, we propose a <strong>S</strong>equential Contrastive Learning algorithm for <strong>P</strong>rogressive <strong>K</strong>nowledge <strong>T</strong>racing, termed <strong>SPKT</strong>, to test the effectiveness of order information within the response sequences for assessing users’ knowledge states. SPKT embeds order information into the response sequence representation through a carefully designed contrastive learning module, and captures users’ monotonic memory decay patterns using a carefully designed non-symmetrical augmented view construction method. The enhanced sequence representation is subsequently utilized to decode user behavior with a progressive learning process module. Extensive experiments demonstrate that, on average, SPKT outperforms 10 baselines by up to 14 % in AUC and 8 % in ACC across 6 real-world datasets. Furthermore, the results highlight that the order information in response sequences significantly improves algorithmic performance-sometimes even more than the correctness of the responses themselves. Moreover, SPKT more accurately evaluates users with better academic performance and shorter learning sequences. For the same user, longer response sequences are more helpful in assessing a user’s knowledge state.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"329 ","pages":"Article 114413"},"PeriodicalIF":7.6,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhanced binary particle swarm optimization for mitigating pandemic spread through passenger air traffic management 增强的二元粒子群优化,通过客运空中交通管理减轻大流行的传播
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-09 DOI: 10.1016/j.knosys.2025.114430
Gabriel A. Peña, Antonio Jiménez-Martín, Alfonso Mateos
{"title":"Enhanced binary particle swarm optimization for mitigating pandemic spread through passenger air traffic management","authors":"Gabriel A. Peña,&nbsp;Antonio Jiménez-Martín,&nbsp;Alfonso Mateos","doi":"10.1016/j.knosys.2025.114430","DOIUrl":"10.1016/j.knosys.2025.114430","url":null,"abstract":"<div><div>This study tackles a complex binary multi-objective optimization problem focused on minimizing the risk of pandemic importation through strategic passenger air traffic management. The approach involves determining whether international connections to destination airports within a specified country should be activated or deactivated over a defined time frame, considering epidemiological, economic, and socio-political impacts. We introduce a preliminary decision support system designed to assist decision-makers in the parametrization of the problem and quantify their preferences, thereby facilitating the derivation of a compromise solution via a binary particle swarm optimization (BPSO) metaheuristic. The standard BPSO is prone to particles getting trapped in local optima instead of searching for new solution and does not handle infeasible solutions properly. To overcome these inherent limitations, we propose an enhanced version of the BPSO metaheuristic. This enhanced algorithm incorporates novel mechanisms to promote solution space exploration and a robust strategy for managing infeasible solutions. A rigorous comparative analysis is conducted to evaluate the performance of the enhanced BPSO against both the original BPSO and several established state-of-the-art metaheuristics utilizing three benchmark datasets of a constrained problem. Finally, the effectiveness of the proposed enhanced metaheuristic is demonstrated in the context of the pandemic importation risk reduction problem, where it outperforms the original BPSO.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"329 ","pages":"Article 114430"},"PeriodicalIF":7.6,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multimodal prompting and masking strategy for video-grounded dialogue 基于视频的对话的多模态提示和掩蔽策略
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-08 DOI: 10.1016/j.knosys.2025.114367
Feifei Xu , Wang Zhou , Fumiaoyue Jia
{"title":"Multimodal prompting and masking strategy for video-grounded dialogue","authors":"Feifei Xu ,&nbsp;Wang Zhou ,&nbsp;Fumiaoyue Jia","doi":"10.1016/j.knosys.2025.114367","DOIUrl":"10.1016/j.knosys.2025.114367","url":null,"abstract":"<div><div>Video-Grounded Dialogue (VGD) is a challenging vision-language task aimed at engaging in multi-turn dialogues with humans based on video and audio content. Despite significant progress in improving AI-generated responses has been made, several challenges remain: 1) A significant amount of computing resources and time are required during training; 2) Current dominant approaches, utilizing T5 or GPT2 as base models, exhibit limited ability to understand video and audio features due to their text-based pre-training paradigms; 3) Existing studies have not addressed the robustness of models in real-world scenarios where dialog history is often missing. To address these issues, we propose VPM, a Video-Grounded Dialogue framework employing prompt-based tuning and a masking strategy. Firstly, to reduce computation resources, inspired by prompt learning, we are the first to employ prompt-based tuning in Video-Grounded Dialogue task by using only 20 % of the training set while maintaining proximal accuracy. Secondly, to enhance the model’s understanding of video and audio, we propose a slicing-based visual mapping network, integrating learnable visual prompts and video-audio slice features sequentially through a series of operations. Finally, we put forward an exponentially masking strategy for dialogue history to improve cross-modal understanding and robustness. Extensive experiments validate the effectiveness of our proposed framework, achieving state-of-the-art performance on the AVSD@DSTC7 and AVSD@DSTC8 datasets.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"329 ","pages":"Article 114367"},"PeriodicalIF":7.6,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Rethinking interactive image matting as incremental Gaussian process regression problems 重新思考交互式图像抠图作为增量高斯过程回归问题
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-08 DOI: 10.1016/j.knosys.2025.114410
Bingjie Guo, Wenhui Huang
{"title":"Rethinking interactive image matting as incremental Gaussian process regression problems","authors":"Bingjie Guo,&nbsp;Wenhui Huang","doi":"10.1016/j.knosys.2025.114410","DOIUrl":"10.1016/j.knosys.2025.114410","url":null,"abstract":"<div><div>Interactive Image Matting (IIM) aims to predict alpha mattes through user interaction. Traditional methods often depend on user experience to interact at the regions where the alpha matte are inaccurate. However, regions with inaccurate model predictions do not necessarily correspond to areas of high model uncertainty, so these methods are unable to effectively reduce model uncertainty, resulting in low interaction efficiency. To address this issue, we observe a commonality between IIM tasks and Gaussian Process (GP) regression: the former predicts alpha values of unlabeled pixels based on user-labeled information, while the latter predicts observations of unknown data based on known data and provides uncertainty estimation for predictions. Based on this observation, we model IIM as an incremental GP regression problem and propose a novel IIM paradigm, IIM-GP. First, IIM-GP is the first model to incrementally utilize model-predicted uncertainty to guide user interaction and update matting results, significantly enhancing interaction efficiency and prediction reliability. Second, an incremental update strategy is implemented within the GP framework, overcoming traditional GP models’ inefficiency in updating results for IIM tasks. Additionally, IIM-GP employs a strategy of selecting <span><math><mi>p</mi></math></span> inducing points from <span><math><mi>n</mi></math></span> labeled pixels to perform variational inference on GP, reducing computational complexity from <span><math><mrow><mi>O</mi><mo>(</mo><msup><mi>n</mi><mn>3</mn></msup><mo>)</mo></mrow></math></span> to <span><math><mrow><mi>O</mi><mo>(</mo><mi>n</mi><msup><mi>p</mi><mn>2</mn></msup><mo>)</mo></mrow></math></span> (<span><math><mrow><mi>p</mi><mo>≪</mo><mi>n</mi></mrow></math></span>). Comprehensive experiments on five widely-used datasets (Composition-1k, AIM-500, Distinctions-646, HIM2K and AM-2K) demonstrate that IIM-GP achieves competitive performance.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"329 ","pages":"Article 114410"},"PeriodicalIF":7.6,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145057309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Toward efficient digital twin simulation: A causal representation learning approach 迈向高效的数字孪生模拟:一种因果表示学习方法
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-08 DOI: 10.1016/j.knosys.2025.114442
Shuyang Luo , Jiachang Qian , Yunhan Geng , Qi Zhou , Quan Lin
{"title":"Toward efficient digital twin simulation: A causal representation learning approach","authors":"Shuyang Luo ,&nbsp;Jiachang Qian ,&nbsp;Yunhan Geng ,&nbsp;Qi Zhou ,&nbsp;Quan Lin","doi":"10.1016/j.knosys.2025.114442","DOIUrl":"10.1016/j.knosys.2025.114442","url":null,"abstract":"<div><div>In recent years, digital twin (DT) technology has emerged as a focal point in the field of shaft system prognostics and health management. To reduce simulation time cost and computational overhead, data-driven intelligent data generation algorithms have been employed as surrogates for traditional finite element simulations. However, such algorithms are typically constrained to generating in-distribution data within known operational domains and fail to generalize to out-of-distribution data under unseen conditions, which significantly hindering the development of DT model under variable operating scenarios. To address this limitation, this paper proposes a novel causal factorization–recombination network (CFRN) for generating shaft vibration responses under previously unseen operating conditions. Firstly, the structural causal model (SCM) for shaft vibration response is constructed to encode the causal mechanisms linking two critical operational parameters with vibration responses. Based on the SCM, a dual-encoder architecture is developed. By optimizing causal consistency loss, causal independence loss, and reconstruction loss, the model identifies latent mediators associated with the two causal factors. Additionally, a novel bidirectional cross-attention mechanism is introduced to equitably integrate mediators corresponding to different combinations of causal factors, enabling robust feature representation under unseen operational conditions. Finally, the recombined features are utilized to synthesize vibration response data. The proposed CFRN is validated using a shaft system simulation dataset. Extensive comparative experiments demonstrate that the generated data under unseen conditions by CFRN achieves 98.06% accuracy on crucial frequency. The proposed approach offers a novel paradigm for accelerating simulation response in DT frameworks.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"329 ","pages":"Article 114442"},"PeriodicalIF":7.6,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Utility and occupancy driven pattern analysis for processing dynamic data streams in damped window control 阻尼窗口控制中处理动态数据流的效用和占用驱动模式分析
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-08 DOI: 10.1016/j.knosys.2025.114453
Taewoong Ryu , Doyoung Kim , Seungwan Park, Seongbin Park, Myungha Cho, Hanju Kim, Junyoung Park, Hyeonmo Kim, Unil Yun
{"title":"Utility and occupancy driven pattern analysis for processing dynamic data streams in damped window control","authors":"Taewoong Ryu ,&nbsp;Doyoung Kim ,&nbsp;Seungwan Park,&nbsp;Seongbin Park,&nbsp;Myungha Cho,&nbsp;Hanju Kim,&nbsp;Junyoung Park,&nbsp;Hyeonmo Kim,&nbsp;Unil Yun","doi":"10.1016/j.knosys.2025.114453","DOIUrl":"10.1016/j.knosys.2025.114453","url":null,"abstract":"<div><div>Data analysis is suitable for data control systems by discovering hidden knowledge that is difficult for humans to perceive from huge and complex data. In various data analysis methods, high utility occupancy pattern analysis considers the utility occupancy of each pattern in the corresponding transaction in addition to the profit and quantity of patterns, which is effective for data control systems, including data science fields. However, recent data holds more insightful knowledge when processing real-time generated data. Previous occupancy-based approaches do not handle the relative significance of the latest data. To overcome the limitation, we introduce a new method for discovering high utility occupancy patterns from dynamic data streams where time-sensitive data consistently occurs. The proposed method assigns relative importance to each pattern by considering the temporal aspect of each transaction. Advanced constructing and restructuring processes are utilized in the proposed method for efficiently controlling data according to the time flow of each pattern in dynamic environments. In the pattern expansion process, a new upper bound adopting the decaying factor is suggested to efficiently reduce unnecessary searches for unpromising patterns. Experimental results demonstrate that the proposed method has superior runtime and scalability performance compared to state-of-the-art methods with comparable memory usage. The ablation study underscores how the proposed components contribute to the overall effectiveness of the proposed method. Additional evaluations indicate that the proposed method analyzes insightful result patterns compared to state-of-the-art methods, and a case study demonstrates its applicability to real-time dynamic data control systems.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"329 ","pages":"Article 114453"},"PeriodicalIF":7.6,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimized task offloading with energy efficient communication and optimal offloading network: a mobility and energy-efficient approach for augmented reality in mobile edge computing 具有节能通信和最佳卸载网络的优化任务卸载:移动边缘计算中增强现实的移动性和节能方法
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-08 DOI: 10.1016/j.knosys.2025.114431
Anitha Jebamani Soundararaj, Godfrey Winster Sathianesan
{"title":"Optimized task offloading with energy efficient communication and optimal offloading network: a mobility and energy-efficient approach for augmented reality in mobile edge computing","authors":"Anitha Jebamani Soundararaj,&nbsp;Godfrey Winster Sathianesan","doi":"10.1016/j.knosys.2025.114431","DOIUrl":"10.1016/j.knosys.2025.114431","url":null,"abstract":"<div><div>Mobile edge computing enables the efficient execution of compute-intensive tasks by offloading them to edge servers. However, frequent user mobility in 5 G urban networks leads to increased latency, energy consumption, and resource wastage due to continuous handovers. To address these challenges, Energy Efficient Communication and Optimal Offloading Network, a framework is proposed that combines user mobility prediction and hybrid optimization for task offloading. Energy Efficient Communication and Optimal Offloading Network utilizes a modified Long Short-Term Memory model to predict user movement with high accuracy, achieving an accuracy improvement from 65 % to 95 % over ten iterations. Additionally, a Hybrid Grey Wolf Optimization Algorithm optimizes task allocation, resulting in a 30 % reduction in energy consumption and a 25 % improvement in server utilization compared to baseline methods. The framework achieves latency as low as 5 milliseconds for augmented reality tasks while maintaining scalability in high-traffic 5 G environments. The proposed model also outperforms baseline approaches in terms of task completion time, throughput, and communication efficiency, and it achieves a 94.5 % offloading success rate and 98 % augmented reality delay compliance. The proposed model provides a scalable and useful solution for real-time Augmented Reality by combining energy-constrained task allocation with mobility-aware predictions.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114431"},"PeriodicalIF":7.6,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
TSH-FCNet: Triple-source heterogeneous remote sensing images fusion classification network based on feature propagation and perception TSH-FCNet:基于特征传播与感知的三源异构遥感图像融合分类网络
IF 7.6 1区 计算机科学
Knowledge-Based Systems Pub Date : 2025-09-08 DOI: 10.1016/j.knosys.2025.114370
Wei Cheng , Yining Feng , Yuting Zhao , Xianghai Wang
{"title":"TSH-FCNet: Triple-source heterogeneous remote sensing images fusion classification network based on feature propagation and perception","authors":"Wei Cheng ,&nbsp;Yining Feng ,&nbsp;Yuting Zhao ,&nbsp;Xianghai Wang","doi":"10.1016/j.knosys.2025.114370","DOIUrl":"10.1016/j.knosys.2025.114370","url":null,"abstract":"<div><div>With the diversification of remote sensing (RS) sensor types, the accessibility and availability of various RS data types are continuously improving. The collaborative use of multi-source RS data can comprehensively and effectively improve the accuracy of RS for earth observation. However, current research on multi-source RS image fusion classification primarily focuses on only two types of RS data. The heterogeneous characteristics of three or more types of RS data significantly complicate the data fusion process. In particular, how to effectively explore the correlations among the inherent characteristics of three or more heterogeneous RS data remains a critical challenge that has not been effectively addressed. This greatly affects the accuracy of RS land classification and other earth observation tasks. To address this issue, a TSH-FCNet based on feature propagation and perception for collaborative classification of hyperspectral (HS), multispectral (MS), and radar images is proposed. This network thoroughly explores the intrinsic correlations among the three heterogeneous data sources and employs an innovative feature interaction mechanism to leverage their complementary advantages. It overcomes the interference of heterogeneous characteristics between different data sources on fusion, effectively enhancing the final classification accuracy. Specifically, a distance similarity attention guides the mutual perception and fusion of triple-source RS information, promoting the flow of complementary features among the triple-source and improving the final classification accuracy. Additionally, the shared information from the triple-source RS data is injected into the features to be fused through a domain alignment mechanism, enhancing the spatial and semantic consistency of the features, thereby strengthening the classification model’s ability to recognize complex surface features. We tested the algorithm on three triple-source RS datasets. The experimental results indicate that the proposed algorithm achieves significant improvements over existing mainstream methods, exhibiting greater stability and reliability when handling highly heterogeneous and diverse data sources. The implementation code of this algorithm will be available from <span><span>https://github.com/cwlnnu/TSH-FCNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"329 ","pages":"Article 114370"},"PeriodicalIF":7.6,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信