Neurocomputing最新文献

{"title":"TSAD: Temporal–spatial association differences-based unsupervised anomaly detection for multivariate time-series","authors":"Hanbing Zhu,&nbsp;Nan Xiao,&nbsp;Hefei Ling,&nbsp;Zongyi Li,&nbsp;Yuxuan Shi,&nbsp;Chuang Zhao,&nbsp;Hongxu Ji,&nbsp;Ping Li,&nbsp;Hui Liu","doi":"10.1016/j.neucom.2025.130611","DOIUrl":"10.1016/j.neucom.2025.130611","url":null,"abstract":"<div><div>Modern industrial control systems are vast and intricate, requiring the monitoring of data from numerous interconnected sensors and actuators for precise intrusion and anomaly detection. While unsupervised time series anomaly detection methods based on deep learning effectively capture complex nonlinear contextual dependencies, the anomaly metrics employed by current methods lack contextual anomaly information, thereby hindering the distinction between anomalies and normalies. Addressing this issue, a Temporal–Spatial Association Differences-based Anomaly Detection model (TSAD) is proposed. This model introduces temporal association difference learning, capturing the temporal association distribution of normal sequences while considering temporal association loss to calculate temporal association differences. Additionally, it incorporates spatial association difference learning, capturing the spatial association distribution of normal sequences while considering spatial association loss to calculate spatial association differences. By focusing on extracting temporal–spatial association patterns from multivariate time-series data under normal operating conditions, the model aggregates reconstruction errors and temporal–spatial association differences during testing to detect anomalies using a novel anomaly metric. Experimental results on four real-world datasets (SWaT, WADI, PSM, and MSL) demonstrate the state-of-the-art performance of the approach.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130611"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Open set domain adaptation via unknown construction and dynamic threshold estimation","authors":"Yong Zhang ,&nbsp;Qi Zhang ,&nbsp;Wenzhe Liu","doi":"10.1016/j.neucom.2025.130668","DOIUrl":"10.1016/j.neucom.2025.130668","url":null,"abstract":"<div><div>Open set domain adaptation (OSDA) focuses on adapting a model from the source domain to the target domain when their class distributions differ. The goal is to accurately recognize unknown classes while correctly classifying known classes. Existing research has indicated that adversarial networks can be efficient for unknown class recognition, yet threshold setting remains a challenge. We address this challenge by proposing an OSDA method that uses unknown construction and dynamic threshold estimation (UCDTE), which consists of three stages: unknown construction, dynamic threshold estimation, and distribution alignment. In the first stage, known as unknown construction, pseudo-unknown samples are constructed through feature fusion to learn information regarding the unknown class. In the second stage, dynamic threshold estimation, an unknown discriminator is constructed to further explore different semantic information in the unknown classes, and a dynamic threshold is generated for each target sample by combining it with the domain discriminator. Finally, in the distribution alignment stage, the dynamic threshold adversarial network aligns known samples between the source and target domains while reducing the intra-class gap of unknown samples in the target domain. Experiments conducted on three datasets have demonstrated the robustness and effectiveness of our approach in adapting models across different domains.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130668"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Knowledge-based hyper-parameter adaptation of multi-stage differential evolution by deep reinforcement learning","authors":"Mingzhang Han,&nbsp;Mingjie Fan,&nbsp;Xinchao Zhao,&nbsp;Lingjuan Ye","doi":"10.1016/j.neucom.2025.130633","DOIUrl":"10.1016/j.neucom.2025.130633","url":null,"abstract":"<div><div>Differential evolution (DE) is a prominent algorithm in evolutionary computation, with adaptive control mechanisms for its operators and parameters being a critical research focus due to their impact on performance. Existing studies often rely on trial-and-error methods or deep reinforcement learning (DRL) for per-generation adaptive control, yet they inadequately explore adaptive hyper-parameter tuning across different stages of the evolution process. To address this limitation, this paper presents a knowledge-based framework named DRL-HP-* for multi-stage DE hyper-parameter adaptation using DRL. The framework divides the algorithm’s search procedure into multiple equal stages, where a DRL agent determines hyper-parameters in each stage based on five types of states that characterize the evolutionary process. A novel reward function is designed to comprehensively train the agent across all training functions, integrating the performance of the backbone algorithm. This approach results in the development of three new algorithms (DRL-HP-jSO, DRL-HP-LSHADE-RSP, and DRL-HP-EjSO). Experimental evaluations on the CEC’18 benchmark suite demonstrate that the proposed algorithms outperform eight state-of-the-art methods, demonstrating superior optimization performance. Further extensive experiments validate the effectiveness of the designed reward function and the framework’s scalability and robustness, highlighting its contribution to enabling stage-wise adaptive hyper-parameter control.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130633"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Neural adaptive delay differential equations","authors":"Chao Zhou,&nbsp;Qieshi Zhang,&nbsp;Jun Cheng","doi":"10.1016/j.neucom.2025.130634","DOIUrl":"10.1016/j.neucom.2025.130634","url":null,"abstract":"<div><div>Continuous-depth neural networks, such as neural ordinary differential equations (NODEs), have garnered significant interest in recent years owing to their ability to bridge deep neural networks with dynamical systems. This study introduced a new type of continuous-depth neural network called neural adaptive delay differential equations (NADDEs). Unlike recently proposed neural delay differential equations (NDDEs) that require a fixed delay, NADDEs utilize a learnable, adaptive delay. Specifically, NADDEs reformulate the learning process as a delay-free optimal control problem and leverage the calculus of variations to derive their learning algorithms. This approach enables the model to autonomously identify suitable delays for given tasks, thereby establishing more flexible temporal dependencies to optimize the utilization of historical representations. The proposed NADDEs can reconstruct dynamical systems with time-delay effects by learning true delays from data, a capability beyond both NODEs and NDDEs, and achieve superior performance on concentric and image-classification datasets, including MNIST, CIFAR-10, and SVHN.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130634"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Low-rank tensor recovery via jointing the non-convex regularization and deep prior","authors":"Qing Liu,&nbsp;Huanmin Ge,&nbsp;Xinhua Su","doi":"10.1016/j.neucom.2025.130610","DOIUrl":"10.1016/j.neucom.2025.130610","url":null,"abstract":"<div><div>This paper addresses the low-rank tensor completion (LRTC) and tensor robust principal component analysis (TRPCA), which have broad applications in the recovery of real-world multi-dimensional data. To enhance recovery performance, we propose novel non-convex tensor recovery models for both LRTC and TRPCA by combining low-rank priors with data-driven deep priors. Specifically, we use the tensor <span><math><msubsup><mrow><mi>ℓ</mi></mrow><mrow><mi>r</mi></mrow><mrow><mi>p</mi></mrow></msubsup></math></span> pseudo-norm to effectively capture the low-rank structure of the tensor, providing a more accurate approximation of its rank. In addition, a convolutional neural network (CNN) denoiser is incorporated to learn deep prior information, further improving recovery accuracy. We also develop efficient iterative algorithms for solving the proposed models based on the alternating direction method of multipliers (ADMM). Experimental results show that the proposed methods outperform state-of-the-art techniques in terms of recovery accuracy for both LRTC and TRPCA.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130610"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Learning hierarchical image feature for efficient image rectification","authors":"Nanjun Yuan,&nbsp;Fan Yang,&nbsp;Yuefeng Zhang,&nbsp;Luxia Ai,&nbsp;Wenbing Tao","doi":"10.1016/j.neucom.2025.130646","DOIUrl":"10.1016/j.neucom.2025.130646","url":null,"abstract":"<div><div>Image stitching methods often use single-homography or multi-homography estimation for alignment, resulting in images with undesirable irregular boundaries. To address this, cropping and image inpainting are the common operations but discard image regions or introduce content that differs from reality. Recently, deep learning-based methods improve the content fidelity of the rectified images, while suffering from distortion, artifacts, and discontinuous deformations between adjacent image regions. In this work, we propose an efficient network based on the transformer (Rectformer) for image rectification. Specifically, we propose the Global and Local Features (GLF) module, which consists of the Hybrid Self-Attention module and Dynamic Convolution module to capture hierarchical image features. We further introduce two auxiliary losses for better image rectification, bidirectional contextual (BC) loss and deformation consistency (DC) loss. The bidirectional contextual loss encourages the model to preserve image local structure information. The loss of deformation consistency improves the network’s geometric recovery and generalization capabilities through a self-supervised learning strategy. Finally, extensive experiments demonstrate that our method outperforms the existing state-of-the-art methods for rotation correction and rectangling.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130646"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Attributed graph clustering with multi-scale weight-based pairwise coarsening and contrastive learning","authors":"Binxiong Li ,&nbsp;Yuefei Wang ,&nbsp;Binyu Zhao ,&nbsp;Heyang Gao ,&nbsp;Benhan Yang ,&nbsp;Quanzhou Luo ,&nbsp;Xue Li ,&nbsp;Xu Xiang ,&nbsp;Yujie Liu ,&nbsp;Huijie Tang","doi":"10.1016/j.neucom.2025.130796","DOIUrl":"10.1016/j.neucom.2025.130796","url":null,"abstract":"<div><div>This study introduces the Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning (MPCCL) model, a novel approach for attributed graph clustering that effectively bridges critical gaps in existing methods, including long-range dependency, feature collapse, and information loss. Traditional methods often struggle to capture high-order graph features due to their reliance on low-order attribute information, while contrastive learning techniques face limitations in feature diversity by overemphasizing local neighborhood structures. Similarly, conventional graph coarsening methods, though reducing graph scale, frequently lose fine-grained structural details. MPCCL addresses these challenges through an innovative multi-scale coarsening strategy, which progressively condenses the graph while prioritizing the merging of key edges based on global node similarity to preserve essential structural information. It further introduces a one-to-many contrastive learning paradigm, integrating node embeddings with augmented graph views and cluster centroids to enhance feature diversity, while mitigating feature masking issues caused by the accumulation of high-frequency node weights during multi-scale coarsening. By incorporating a graph reconstruction loss and KL divergence into its self-supervised learning framework, MPCCL ensures cross-scale consistency of node representations. Experimental evaluations reveal that MPCCL achieves a significant improvement in clustering performance, including a remarkable 15.24 % increase in NMI on the ACM dataset and notable robust gains on smaller-scale datasets such as Citeseer, Cora and DBLP. In the large-scale Reuters dataset, it significantly improved by 17.84 %, further validating its advantage in enhancing clustering performance and robustness. These results highlight MPCCL’s potential for application in diverse graph clustering tasks, ranging from social network analysis to bioinformatics and knowledge graph-based data mining. The source code for this study is available at <span><span>https://github.com/YF-W/MPCCL</span><svg><path></path></svg></span></div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130796"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 dynamic hybrid expert framework with encoder–decoder interaction for robust image enhancement in train environment perception","authors":"Xin Liu ,&nbsp;Hongping Wang ,&nbsp;Linsen Song ,&nbsp;Yiwen Zhang ,&nbsp;Xiaoxu Zhang ,&nbsp;Chunbo Liu ,&nbsp;Xiao Shang ,&nbsp;Jingru Liu ,&nbsp;Yuanting Yang ,&nbsp;Xinming Zhang","doi":"10.1016/j.neucom.2025.130650","DOIUrl":"10.1016/j.neucom.2025.130650","url":null,"abstract":"<div><div>Train environment perception technology is one of the critical factors in ensuring safe train operations, particularly in challenging conditions such as foggy, rainy weather, and poorly lit environments like tunnels. The clarity of images directly influences the accuracy of obstacle detection and decision-making processes during train operation. However, existing image restoration methods are typically tailored to single scenarios, making them inadequate for the diverse and complex environmental variations encountered during train operations. Most of these methods lack specificity, rendering them ineffective in handling complex textures and fine details, resulting in suboptimal image quality under adverse conditions, often plagued by blurriness and noise interference. To address these challenges, we propose a dynamic hybrid expert image restoration framework specifically designed for train environment perception. This framework integrates multiple expert modules and a dynamic weight generation mechanism, enabling flexible adaptation to various environmental characteristics. Specifically, the framework comprises multiple expert modules, each focusing on distinct feature extraction tasks, thereby enhancing image clarity and detail restoration in challenging conditions such as foggy weather, low-light situations, and tunnels. The system dynamically generates weights based on the input image characteristics, allowing for the seamless integration of features extracted by each expert, which significantly improves image clarity and detail restoration. Additionally, the interaction between encoder–decoder attention mechanisms enhances the fusion of global and local information, ensuring robust image restoration in complex environments. Experimental results demonstrate that our method performs exceptionally well across various train operating conditions, particularly in foggy image enhancement and low-light image restoration in tunnels. Compared to existing methods, our approach achieves superior restoration quality and efficiency. Our method significantly enhances the image processing capabilities of train environment perception systems, providing a robust safeguard for safe train operations.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130650"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Spatial-frequency dual-domain Kolmogorov–Arnold networks for multimodal medical image fusion","authors":"Lewu Lin ,&nbsp;Jiaxin Xie ,&nbsp;Yingying Wang ,&nbsp;Jialing Huang ,&nbsp;Rongjin Zhuang ,&nbsp;Xiaotong Tu ,&nbsp;Xinghao Ding ,&nbsp;Na Shen ,&nbsp;Qing Lu","doi":"10.1016/j.neucom.2025.130661","DOIUrl":"10.1016/j.neucom.2025.130661","url":null,"abstract":"<div><div>Multimodal Medical Image Fusion (MMIF) can significantly enhance the efficiency and accuracy of clinical diagnosis and treatment by integrating medical images from different modalities into a single image with rich information. Recent advancements in Kolmogorov–Arnold Networks (KAN) have demonstrated significant potential in nonlinear fitting, owing to their ability to decompose complex multivariate functions into simpler univariate functions while maintaining high accuracy and interpretability. While most existing methods focus on developing increasingly complex architectures, addressing MMIF from a frequency analysis perspective and leveraging both spatial and frequency domains for interpretable and effective cross-modal fusion through KAN remains an underexplored frontier in prior research. To address this gap, we introduce Spatial-Frequency Dual-domain KAN (SFDKAN), a novel framework for MMIF. Initially, we apply a Hierarchical Wavelet Decomposition strategy to decompose the input modality into different frequency bands and introduce the powerful nonlinear mapping capability of KAN into the sub-bands of varying frequencies. This approach refines unimodal feature extraction and enhances the retention of high-frequency details and structural integrity. Next, we design a Spatial-Frequency Integration KAN (SFIKAN), leveraging complementary information from both spatial and frequency domains to facilitate effective cross-modality feature interaction and fusion. The Spatial KAN effectively focuses on critical regions in the fusion result, while ignoring irrelevant areas and suppressing redundant information. Meanwhile, the Frequency KAN overcomes the local limitations of the spatial domain, effectively handling long-range dependencies and enhancing global feature representation, thereby enabling more efficient cross-modality feature fusion. Extensive experiments on CI-MRI, PET-MRI, and SPECT-MRI datasets demonstrate the superiority of our method over state-of-the-art (SOTA) medical image fusion algorithms in both quantitative metrics and visual quality. The code will be available at <span><span>https://github.com/xiejiaaax/SFDKAN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130661"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"fRAKI: k-space deep learning with offline data-universal and online scan-specific priors","authors":"Jing Pan ,&nbsp;Xiaohan Liu ,&nbsp;Yiming Liu ,&nbsp;Xuebin Sun ,&nbsp;Yanwei Pang","doi":"10.1016/j.neucom.2025.130663","DOIUrl":"10.1016/j.neucom.2025.130663","url":null,"abstract":"<div><div>Sampling a limited number of phase-encoding lines followed by estimating missing lines is an efficient method for shortening scan time of MRI. GeneRalized Autocalibarating Partial Parallel Acquisition (GRAPPA) is such a classical method and is widely used in clinical MRI. As a non-linear method, Robust Artificial-neural-networks for K-space Interpolation (RAKI) is a break-through of GRAPPA in the sense of much higher estimation accuracy. However, RAKI takes much longer estimation time because it requires online training a network for each receiving coil. To overcome the low-efficiency problem, we propose a fast version of RAKI (called fRAKI). fRAKI is roughly 26 times faster and can obtain much higher estimation accuracy compared with RAKI. The high efficiency of fRAKI is due to two properties: (1) A single network is shared to estimate missing lines of all the coils. (2) The online training of fRAKI can converge after a smaller number of iterations. Fast convergency is obtained by using a pre-trained model for initializing learnable parameters. High accuracy benefits from that the pre-train model contains data-universal prior and is also used as a sub-network of fRAKI so that the online training subnetwork can focus on learning scan-specific prior without the risk of overfitting the scan-specific data. Experimental results on the NYU fastMRI knee and brain datasets demonstrate the efficiency and accuracy of the proposed fRAKI.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"648 ","pages":"Article 130663"},"PeriodicalIF":5.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144364897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}