Information Fusion最新文献

{"title":"An information fusion model of mutual influence between focal elements: A perspective on interference effects in Dempster–Shafer evidence theory","authors":"Xiaozhuan Gao ,&nbsp;Lipeng Pan","doi":"10.1016/j.inffus.2025.103286","DOIUrl":"10.1016/j.inffus.2025.103286","url":null,"abstract":"<div><div>Dempster’s rule of combination is a fundamental element of the Dempster–Shafer evidence Theory, which is designed to integrate uncertain information from various independent sources. Its primary goal is to reduce uncertainty and present information of better quality to a decision-making process. Dempster’s rule of combination addresses the conflicts among the pieces of evidence provided by multiple sources. By doing so, the fusion process tends to favor one hypothesis over all others. However, it does not consider the potential interactions between focal elements. This interaction phenomenon is similar to the interference effects observed in quantum theory, where the superposition of different states leads to a redistribution of the state probabilities. In recent years, interference effects have also been studied in various fields, including decision science, quantum machine learning, and autonomous driving. Hence, in this paper, we present a novel interference effects-based combination rule in Dempster–Shafer evidence theory, which accounts for the impact of interference effects arising from potential interactions between focal elements. In proposed method, interference effects in information processing can be attributed to the uncertainty within the mass functions of multiple sources. Therefore, this uncertainty can be utilized to quantify the interference effects. Subsequently, the advantages by considering interference effects in fusion process are detailed and validated through several numerical examples. A similarity analysis and other relevant methods are also conducted to further substantiate these advantages. Finally, we evaluate the performance of new method on real-world classification datasets and compare it with other preprocessing methods in evidence theory. The experimental results of 32 datasets show the superiority of new method in classification accuracy compared to other preprocessing methods.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103286"},"PeriodicalIF":14.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144166767","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}

{"title":"Explicitly fusing plug-and-play guidance of source prototype into target subspace for domain adaptation","authors":"Hao Luo ,&nbsp;Zhiqiang Tian ,&nbsp;Panpan Jiao ,&nbsp;Meiqin Liu ,&nbsp;Shaoyi Du ,&nbsp;Kai Nan","doi":"10.1016/j.inffus.2025.103197","DOIUrl":"10.1016/j.inffus.2025.103197","url":null,"abstract":"<div><div>The commonly used maximum mean discrepancy (MMD) criterion has two main drawbacks when reducing cross-domain distribution gaps: firstly, it reduces the distribution discrepancy in a global manner, potentially ignoring local structural information between domains, and secondly, its performance heavily relies on the often-unstable pseudo-label refinement process. To solve these problems, we introduce two universal plug-and-play modules: dynamic prototype pursuit (DPP) regularization and bi-branch self-training (BST) mechanism. Firstly, DPP introduces a new inter-class perspective to stabilize MMD by assigning a source prototype to each target sample. This allows us to utilize inter-class data structure information for better alignment. Next, BST is a novel non-parametric pseudo-label refinement mechanism that updates pseudo labels of target data using a classifier trained on the same distribution as the target domain. This avoids the distribution gap issue, making BST more likely to generate accurate target pseudo labels. Importantly, DPP and BST are universal plug-and-play modules for shallow domain adaptation methods. To demonstrate this, experiments of 3 MMD-based models incorporated with DPP and BST are conducted on Office-Caltech, Reuters21578, and Berlin-Emovo-Tess datasets. Experimental results show that these models incorporated with DPP and BST generally achieve better results compared to not using DPP and BST in terms of multiple metrics including accuracy, F1-score, MCC, and false positive rates. Code of 3 different DA methods enhanced by the plug-and-play DPP and BST is available at: <span><span>https://github.com/Evelhz/DPP-and-BST</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"123 ","pages":"Article 103197"},"PeriodicalIF":14.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144068084","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}

{"title":"Deep learning for hyperspectral image classification: A comprehensive review and future predictions","authors":"Yongchao Song ,&nbsp;Junhao Zhang ,&nbsp;Zhaowei Liu ,&nbsp;Yang Xu ,&nbsp;Siwen Quan ,&nbsp;Lijun Sun ,&nbsp;Jiping Bi ,&nbsp;Xuan Wang","doi":"10.1016/j.inffus.2025.103285","DOIUrl":"10.1016/j.inffus.2025.103285","url":null,"abstract":"<div><div>Hyperspectral image classification (HSIC) is an important research direction in the field of remote sensing image analysis and computer vision, which is of great practical significance. Hyperspectral imaging (HSI) is widely used in a variety of scenarios with its rich spectral and spatial information, but problems such as high-dimensional data characteristics and scarcity of labeled samples challenge the classification accuracy. Deep learning (DL), with its powerful feature extraction and modeling capabilities, provides an effective means to solve the nonlinear problems in HSIC. In this survey, we systematically review the research progress and applications of DL in HSIC. Firstly, we outline the importance of accurate classification, analyze the features of HSI and the challenges faced by DL in this area. Secondly, we introduce different feature representations of HSI and provide a comprehensive describe of the application of various DL models in HSIC. Meanwhile, we also explore DL methods that can effectively improve the classification performance in the case of insufficient training samples. Finally, we summarize the current research situation, and put forward the future development direction and suggestions.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"123 ","pages":"Article 103285"},"PeriodicalIF":14.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144068224","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}

{"title":"HSE: A plug-and-play module for unified fault diagnosis foundation models","authors":"Qi Li ,&nbsp;Bojian Chen ,&nbsp;Qitong Chen ,&nbsp;Xuan Li ,&nbsp;Zhaoye Qin ,&nbsp;Fulei Chu","doi":"10.1016/j.inffus.2025.103277","DOIUrl":"10.1016/j.inffus.2025.103277","url":null,"abstract":"<div><div>Intelligent Fault Diagnosis (IFD) plays a crucial role in industrial applications, where developing foundation models analogous to ChatGPT for comprehensive fault diagnosis remains a significant challenge. Current IFD methodologies are constrained by their inability to construct unified models capable of processing heterogeneous signal types, varying sampling rates, and diverse signal lengths across different equipment. To address these limitations, we propose a novel Heterogeneous Signal Embedding (HSE) module that projects heterogeneous signals into a unified signal space, offering seamless integration with existing IFD architectures as a plug-and-play solution. The HSE framework comprises two primary components: the Temporal-Aware Patching (TAP) module for embedding heterogeneous signals into a unified space, and the Cross-Dimensional Patch Fusion (CDPF) module for fusing embedded signals with temporal information into unified representations. We validate the efficacy of HSE through two comprehensive case studies: a simulation signal dataset and three distinct bearing datasets with heterogeneous features. Our experimental results demonstrate that HSE significantly enhances traditional fault diagnosis models, improving both diagnostic accuracy and generalization capability. While conventional approaches necessitate separate models for specific signal types, sampling frequencies, and signal lengths, HSE-enabled architectures successfully learn unified representations across diverse signal. The results from bearing fault diagnosis applications confirm substantial improvements in both diagnostic precision and cross-dataset generalization. As a pioneering contribution toward IFD foundation models, the proposed HSE framework establishes a fundamental architecture for advancing unified fault diagnosis systems.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"123 ","pages":"Article 103277"},"PeriodicalIF":14.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099099","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}

{"title":"Towards efficient RGB-T semantic segmentation via feature generative distillation strategy","authors":"Shenlu Zhao ,&nbsp;Jingyi Wang ,&nbsp;Qiang Zhang ,&nbsp;Jungong Han","doi":"10.1016/j.inffus.2025.103282","DOIUrl":"10.1016/j.inffus.2025.103282","url":null,"abstract":"<div><div>Recently, multimodal knowledge distillation-based methods for RGB-T semantic segmentation have been developed to enhance segmentation performance and inference speeds. Technically, the crux of these models lies in the feature imitative distillation-based strategies, where the student models imitate the working principles of the teacher models through loss functions. Unfortunately, due to the significant gaps in the representation capability between the student and teacher models, such feature imitative distillation-based strategies may not achieve the anticipatory knowledge transfer performance in an efficient way. In this paper, we propose a novel feature generative distillation strategy for efficient RGB-T semantic segmentation, embodied in the Feature Generative Distillation-based Network (FGDNet), which includes a teacher model (FGDNet-T) and a student model (FGDNet-S). This strategy bridges the gaps between multimodal feature extraction and complementary information excavation by using Conditional Variational Auto-Encoder (CVAE) to generate teacher features from student features. Additionally, Multimodal Complementarity Separation modules (MCS-L and MCS-H) are introduced to separate complementary features at different levels. Comprehensive experimental results on four public benchmarks demonstrate that, compared with mainstream RGB-T semantic segmentation methods, our FGDNet-S achieves competitive segmentation performance with lower number of parameters and computational complexity.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"123 ","pages":"Article 103282"},"PeriodicalIF":14.7,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144068226","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}

{"title":"Registration-aware cross-modal interaction network for optical and SAR images","authors":"Zhong Chen ,&nbsp;Xiaolei Zhang ,&nbsp;Xueru Xu ,&nbsp;Hanruo Chen ,&nbsp;Xiaofei Mi ,&nbsp;Jian Yang","doi":"10.1016/j.inffus.2025.103278","DOIUrl":"10.1016/j.inffus.2025.103278","url":null,"abstract":"<div><div>The registration of optical and synthetic aperture radar (SAR) images is valuable for exploration due to the inherent complementarity of optical and SAR imagery. However, the substantial radiation and geometric differences between the two modalities present a major obstacle to image registration. Specifically, images from optical and SAR require integration of precise local features and registration-aware global features, and features within and across modalities need to be interacted with efficiently to achieve accurate registration. To tackle this problem, we build a Robust Quadratic Net (RQ-Net) based on the paradigm of describe-then-detect, which is of dual-encoder–decoder design, the first encoder is responsible for encoding local features within each modality through vanilla convolutional operators, while the other is an elaborated Multilayer Cross-modal Registration-aware (MCR) encoder specialized in building global relationships both inner- and inter-modalities, which is conducted effectively at various scales to extract informative features for registration. Furthermore, to cooperate with the network’s training for more well-suited registration feature descriptors, we propose a reconsider loss to review whether the least similar positive feature pairs are matchable and make the RQ-Net achieve a higher matching capability. Through extensive qualitative and quantitative experiments on three paired optical and SAR datasets, RQ-Net has been validated as superior in extracting sufficient features for matching and improving image success registration rates while maintaining low registration errors.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"123 ","pages":"Article 103278"},"PeriodicalIF":14.7,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143941126","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}

{"title":"Joint content-aware and difference-transform lightweight network for remote sensing images semantic change detection","authors":"Jindou Zhang ,&nbsp;Ruiqian Zhang ,&nbsp;Xiao Huang ,&nbsp;Zhizheng Zhang ,&nbsp;Bowen Cai ,&nbsp;Xianwei Lv ,&nbsp;Zhenfeng Shao ,&nbsp;Deren Li","doi":"10.1016/j.inffus.2025.103276","DOIUrl":"10.1016/j.inffus.2025.103276","url":null,"abstract":"<div><div>Advancements in Earth observation technology have enabled effective monitoring of complex surface changes. Semantic change detection (SCD) using high-resolution remote sensing images is crucial for urban planning and environmental monitoring. However, existing deep learning-based SCD methods, which combine semantic segmentation (SS) and binary change detection (BCD), face challenges in lightweight design and consistency between semantic and change results, limiting their accuracy and applicability. To overcome these limitations, we propose the Joint Content-Aware and Difference-Transform Lightweight Network (CDLNet). CDLNet features a lightweight architecture, skip connections, and a multi-task decoding mechanism. The Temporal-Spatial Content-Aware Fusion module (TSAF) in the SS decoding branch incorporates change information to improve semantic classification accuracy within change regions. The Multi-Type Temporal Difference-Transform module (MTDT) in the BCD decoding branch enhances change localization for accurate SCD through efficient transformation of temporal difference features. Experiments on the SECOND, HiUCD mini, MSSCD, and Landsat-SCD datasets demonstrate that CDLNet outperforms thirteen state-of-the-art methods, achieving average improvements of 1.41%, 1.53% and 1.49% in the <span><math><mrow><mi>F</mi><msub><mrow><mn>1</mn></mrow><mrow><mi>s</mi><mi>c</mi><mi>d</mi></mrow></msub></mrow></math></span>, <span><math><mrow><mi>I</mi><mi>o</mi><mi>U</mi><mi>c</mi></mrow></math></span> and <span><math><mrow><mi>S</mi><mi>c</mi><mi>o</mi><mi>r</mi><mi>e</mi></mrow></math></span> metrics, respectively. Ablation studies confirm the effectiveness of the TSAF and MTDT modules and the rationality of multi-task loss weight configuration. Furthermore, CDLNet utilizes only 20% of the parameters (12.88M) and 7.5% of the FLOPs (30.11G) of the leading model, achieving an inference speed of 41 FPS, which underscores its superior lightweight characteristics. The results indicate that CDLNet offers excellent detection performance, generalization, and robustness within a lightweight framework. The code of our paper is accessible at: <span><span>https://github.com/zjd1836/CDLNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"123 ","pages":"Article 103276"},"PeriodicalIF":14.7,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144068227","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}

{"title":"A self-supervised data augmentation strategy for EEG-based emotion recognition","authors":"Yingxiao Qiao,&nbsp;Qian Zhao","doi":"10.1016/j.inffus.2025.103279","DOIUrl":"10.1016/j.inffus.2025.103279","url":null,"abstract":"<div><div>Due to the scarcity problem of electroencephalogram (EEG) data, building high-precision emotion recognition models using deep learning faces great challenges. In recent years, data augmentation has significantly enhanced deep learning performance. Therefore, this paper proposed an innovative self-supervised data augmentation strategy, named SSDAS-EER, to generate high-quality and various artificial EEG feature maps. Firstly, EEG feature maps were constructed by combining differential entropy (DE) and power spectral density (PSD) features to obtain rich spatial and spectral information. Secondly, a masking strategy was used to mask part of the EEG feature maps, which prompted the designed generative adversarial network (GAN) to focus on learning the unmasked feature information and effectively filled in the masked parts. Meanwhile, the elaborated GAN could accurately capture the distribution characteristics of spatial and spectral information, thus ensuring the quality of the generated artificial EEG feature maps. In particular, this paper introduced a self-supervised learning mechanism to further optimize the designed classifier with good generalization ability to the generated samples. This strategy integrated data augmentation and model training into an end-to-end pipeline capable of augmenting EEG data for each subject. In this study, a systematic experiment was conducted on the DEAP dataset, and the results showed that the proposed method achieved an average accuracy of 97.27% and 97.45% on all subjects in valence and arousal, respectively, which was 1.46% and 1.39% higher compared to the time before the strategy was applied. Simultaneously, the similarity between the generated EEG feature maps and the original EEG feature maps was verified. These results indicated that SSDAS-EER had significant performance improvement in EEG emotion recognition tasks, demonstrating its great potential in improving the efficiency of EEG data utilization and emotion recognition accuracy.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"123 ","pages":"Article 103279"},"PeriodicalIF":14.7,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084094","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}

{"title":"FSVS-Net: A few-shot semi-supervised vessel segmentation network for multiple organs based on feature distillation and bidirectional weighted fusion","authors":"Yuqun Yang ,&nbsp;Jichen Xu ,&nbsp;Mengyuan Xu ,&nbsp;Xu Tang ,&nbsp;Bo Wang ,&nbsp;Kechen Shu ,&nbsp;Zheng You","doi":"10.1016/j.inffus.2025.103281","DOIUrl":"10.1016/j.inffus.2025.103281","url":null,"abstract":"<div><div>Accurate 3D vessel mapping is essential for surgical planning and interventional treatments. However, the conventional manual slice-by-slice annotation in CT scans is extremely time-consuming, due to the complexity of vessels: sparse distribution, intricate 3D topology, varying sizes, irregular shapes, and low contrast with the background. To address this problem, we propose a few-shot semi-supervised vessel segmentation network (FSVS-Net) applicable to multiple organs. It can leverage a few annotated slices to segment vessel regions in unannotated slices, enabling efficient semi-supervised processing of the entire CT sequences. Specifically, we propose a feature distillation module for FSVS-Net to enhance vessel-specific semantic representations and suppress irrelevant background features. In addition, we design a bidirectional weighted fusion strategy that propagates information from a few annotated slices to unannotated ones in both opposite directions of the CT sequence, effectively modeling 3D vessel continuity and reducing error accumulation. Extensive experiments on three datasets (hepatic vessels, pulmonary vessels, and renal arteries) demonstrate that FSVS-Net achieves state-of-the-art performance in few-shot vessel segmentation task, significantly outperforming existing methods. We collected and annotated three vessel datasets, including clinical data from Tsinghua Changgung Hospital and public sources (e.g., MSD08), for this study. In practice, it reduces the average annotation time from 2 h to 0.5 h per volume, improving efficiency by 4<span><math><mo>×</mo></math></span>. We release three organ-specific vessel datasets and the implementation code at: <span><span>https://github.com/YqunYang/FSVS-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"123 ","pages":"Article 103281"},"PeriodicalIF":14.7,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071140","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}

{"title":"General pre-trained inertial signal feature extraction based on temporal memory fusion","authors":"Yifeng Wang,&nbsp;Yi Zhao","doi":"10.1016/j.inffus.2025.103274","DOIUrl":"10.1016/j.inffus.2025.103274","url":null,"abstract":"<div><div>Inertial sensors are widely used in smartphones, robotics, wearables, aerospace systems, and industrial automation. However, extracting universal features from inertial signals remains challenging. Inertial signal features are encoded in abstract, unreadable waveforms, lacking the visual intuitiveness of images, which makes semantic extraction difficult. The non-stationary nature and complex motion patterns further complicate the feature extraction process. Moreover, the lack of large-scale annotated inertial datasets limits deep learning models to learn universal features and generalize them across expansive applications of inertial sensors. To this end, we propose a Topology Guided Feature Extraction (TG-FE) approach for general inertial signal feature extraction. TG-FE fuses time-series information into graph representations, constructing a Memory Graph by emulating the complex network characteristics of human memory. Guided by small-world network principles, this graph integrates local and global information while sparsity constraints emphasize critical feature interactions. The Memory Graph preserves nonlinear relationships and higher-order dependencies, enabling the model to generalize across scenarios with minimal task-specific tuning. Furthermore, a Cross-Graph Feature Fusion mechanism integrates information across stacked TG-FE modules to enhance representation ability and ensure stable gradient flow. With self-supervised pre-training, the TG-FE modules require only minimal fine-tuning to adapt to various hardware configurations and task scenarios, consistently outperforming comparison methods across all evaluations. Compared to the current state-of-the-art method, our TG-FE achieves 11.7% and 20.0% error reduction in attitude and displacement estimation tasks. Notably, TG-FE achieves an order-of-magnitude advantage in stability evaluations, maintaining robust performance even under 20% noise conditions where competing methods degrade significantly. Overall, this work offers a solution for general inertial signal feature extraction and opens new avenues for applying graph-based deep learning to capture and represent sequential signal features.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"123 ","pages":"Article 103274"},"PeriodicalIF":14.7,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936280","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}