Expert Systems with Applications最新文献_第8页

Graph-based approaches for rumor detection in social networks: a systematic review 基于图的社交网络谣言检测方法：系统综述

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-22 DOI: 10.1016/j.eswa.2025.129786

Fatima Al-Thulaia, Seyyed Alireza Hashemi Golpayegani

{"title":"Graph-based approaches for rumor detection in social networks: a systematic review","authors":"Fatima Al-Thulaia, Seyyed Alireza Hashemi Golpayegani","doi":"10.1016/j.eswa.2025.129786","DOIUrl":"10.1016/j.eswa.2025.129786","url":null,"abstract":"<div><div>Increased public anxiety and fear, disrupted decision-making, social instability, and other significant societal challenges are the results of the rapid spread of rumors on social media platforms. The unique characteristics of these platforms contribute to the rapid spread of both verified and unverified information. These pressing issues highlight the need to develop advanced technologies for early detection and prevention of rumors. This paper presents a systematic review of graph-based approaches for rumor detection in social networks, analyzing 53 studies published between 2018 and 2025. The selected studies are comprehensively reviewed with a focus on graph models and the integration of propagation structure, social, temporal, and content features, which enhances detection accuracy. This review critically evaluates the effectiveness of various methods, highlighting their strengths, limitations, and key challenges. The key contributions of this paper include: (i) an in-depth analysis of current graph-based rumor detection approaches (ii) a categorization of graph models and feature extraction strategies, (iii) the identification of major challenges and research gaps, and (iv) recommendations for future research to develop scalable, robust, and accurate early rumor detection systems. The findings of this study provide valuable insights for researchers aiming to advance the state-of-the-art in fighting misinformation on social networks.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129786"},"PeriodicalIF":7.5,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145189737","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

Visual Mamba-CNN for scribble-based segmentation in weakly supervised learning for photoacoustic tomography 光声断层成像弱监督学习中基于涂鸦的视觉Mamba-CNN分割

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-22 DOI: 10.1016/j.eswa.2025.129749

Meng Zhou , Ziyin Ren , Qinlin Tan , Xin Du , Hengrong Lan , Fei Gao , Raymond Kai-Yu Tong

{"title":"Visual Mamba-CNN for scribble-based segmentation in weakly supervised learning for photoacoustic tomography","authors":"Meng Zhou , Ziyin Ren , Qinlin Tan , Xin Du , Hengrong Lan , Fei Gao , Raymond Kai-Yu Tong","doi":"10.1016/j.eswa.2025.129749","DOIUrl":"10.1016/j.eswa.2025.129749","url":null,"abstract":"<div><div>Photoacoustic (PA) imaging is a powerful non-invasive medical imaging technique that combines the high contrast of optical imaging with the deep tissue penetration of ultrasound, offering both structural and functional insights into tissues and organs. Organ-level analysis of photoacoustic tomography (PAT) images enables quantification of specific morphological and functional parameters, making accurate organ segmentation a critical step in PA image-based analysis. However, the limited availability of large-scale annotated datasets remains a major challenge. To address this, we employ cross-modality data augmentation by generating synthetic PA images from MRI scans. To further reduce manual annotation efforts, we propose a weakly supervised learning (WSL) framework that leverages scribble annotations. Since many deep learning models struggle to capture global context from sparse labels, we introduce a novel architecture that combines traditional convolutional neural networks (CNNs) with Visual Mamba, integrating both local and global feature extraction capabilities. This hybrid design improves segmentation performance in weakly supervised settings. We validate our method on a simulated PA abdominal dataset and real in vivo mouse abdominal PAT data, demonstrating notable improvements in segmentation accuracy and robustness.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129749"},"PeriodicalIF":7.5,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221480","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

Differentiable histogram-guided unsupervised Retinex enhancement for paired low-light images 配对低光图像的可微直方图引导无监督视网膜增强

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-22 DOI: 10.1016/j.eswa.2025.129782

Liyuan Yin , Pingping Liu , Tongshun Zhang , Hongwei Zhao , Qiuzhan Zhou

{"title":"Differentiable histogram-guided unsupervised Retinex enhancement for paired low-light images","authors":"Liyuan Yin , Pingping Liu , Tongshun Zhang , Hongwei Zhao , Qiuzhan Zhou","doi":"10.1016/j.eswa.2025.129782","DOIUrl":"10.1016/j.eswa.2025.129782","url":null,"abstract":"<div><div>Most existing low-light image enhancement (LIE) methods rely on expensive paired low-light and normal-light datasets, while unsupervised approaches depend on handcrafted priors to design networks or select similar normal-light images as pseudo-references, limiting their generalization and robustness. To address these challenges, we propose a novel differentiable histogram-guided unsupervised Retinex enhancement (DHURE) method, which leverages the distribution of illumination histograms in real-world scenarios to achieve high-fidelity color preservation and refined brightness distribution across diverse extremely low-light images. DHURE avoids reliance on scene-specific features and effectively captures both fine-grained details and overall brightness information. Specifically, our method consists of two key components: 1) The lightweight architecture of DHURE is composed of Retinex decomposition and illumination enhancement. We perform Retinex decomposition on paired low-light images (PRD) and design the Illumination Histogram-guided Enhancement (IHE) module. Both modules employ lightweight architectures. 2) To fully exploit the adaptive priors inherent in paired low-light images, we introduce a self-supervised reflectance map loss that aligns with the Retinex basis loss. Based on the illumination distribution of real-world normal-light images, we define two unsupervised illumination histogram losses, enabling more generalized and robust enhancement. Extensive and diverse experiments demonstrate that our method achieves competitive performance compared to existing unsupervised LIE approaches, showing superior results on most evaluation metrics. The source code is available at <span><span>https://github.com/yoonyin/DHURE-main</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129782"},"PeriodicalIF":7.5,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159092","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

Pareto optimization of two-agent scheduling on parallel batch machines 并行批处理机器上双智能体调度的Pareto优化

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-22 DOI: 10.1016/j.eswa.2025.129637

Cui-Lin Zhang , Guo-Qiang Fan

引用次数: 0

Generating realistic pruning solutions for automated grape vine pruning using graph neural networks 使用图神经网络为自动葡萄藤修剪生成现实的修剪解决方案

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-22 DOI: 10.1016/j.eswa.2025.129778

Jaco Fourie , Jeffrey Hsiao , Oliver Batchelor , Kevin Langbroek , Henry Williams , Richard Green , Armin Werner

{"title":"Generating realistic pruning solutions for automated grape vine pruning using graph neural networks","authors":"Jaco Fourie , Jeffrey Hsiao , Oliver Batchelor , Kevin Langbroek , Henry Williams , Richard Green , Armin Werner","doi":"10.1016/j.eswa.2025.129778","DOIUrl":"10.1016/j.eswa.2025.129778","url":null,"abstract":"<div><div>In our prior work we showed that graph neural networks (GNNs) can be trained to generate pruning solutions that could direct robotic pruning robots to perform automated cane pruning of wine grape vines. That study introduced the feasibility of the technology but also showed that there were many open questions and issues with the research results that needed to be addressed. In this study we address some of these questions. For example, we answer the question of how would a model like this perform on real vine architectures compared with pruning solutions from real experienced pruners. Our most notable contributions include moving away from a per-cane classification model that attempts to define a single <em>perfect</em> pruning solution, to a model that ranks multiple good solutions and picks the best one. We addressed a key limitation of the previous training data by moving away from synthetic vine architectures to realistic ones recorded from real vines and using pruning solutions collected by expert pruners as our ground-truth. Our primary goal was to show that learning by example using a GNN-based model was a viable approach to automated pruning, even when compared with experienced pruners. We showed robust performance from our model by training on a dataset of 90 pruning solutions generated by expert pruners in the 2022 season, and testing our performance on 117 pruning solutions from an independent set of pruners from the 2021 season. The model was able to correctly score all the pruning solutions from the 2021 dataset as <em>good</em> to <em>very good</em> and none of the expert solutions were classified as <em>poor</em>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129778"},"PeriodicalIF":7.5,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158638","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

Exploiting point-language models with dual-prompts for 3D anomaly detection 利用双提示的点语言模型进行三维异常检测

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-21 DOI: 10.1016/j.eswa.2025.129758

Jiaxiang Wang , Haote Xu , Xiaolu Chen , Haodi Xu , Yue Huang , Xinghao Ding , Xiaotong Tu

{"title":"Exploiting point-language models with dual-prompts for 3D anomaly detection","authors":"Jiaxiang Wang , Haote Xu , Xiaolu Chen , Haodi Xu , Yue Huang , Xinghao Ding , Xiaotong Tu","doi":"10.1016/j.eswa.2025.129758","DOIUrl":"10.1016/j.eswa.2025.129758","url":null,"abstract":"<div><div>Anomaly detection (AD) in 3D point clouds is crucial in a wide range of industrial applications, especially in various forms of precision manufacturing. Considering the industrial demand for reliable 3D AD, several methods have been developed. However, most of these approaches typically require training separate models for each category, which is memory-intensive and lacks flexibility. In this paper, we propose a novel <u>P</u>oint-<u>L</u>anguage model with dual-prompts for 3D <u>AN</u>omaly d<u>E</u>tection (PLANE). The approach leverages multi-modal prompts to extend the strong generalization capabilities of pre-trained Point-Language Models (PLMs) to the domain of 3D point cloud AD, achieving impressive detection performance across multiple categories using a single model. Specifically, we propose a dual-prompt learning method, incorporating both text and point cloud prompts. The method utilizes a dynamic prompt creator module (DPCM) to produce instance-specific dynamic prompts, which are then integrated with class-specific static prompts for each modality, effectively driving the PLMs. Additionally, based on the characteristics of point cloud data, we propose a pseudo 3D anomaly generation method (Ano3D) to improve the model’s detection capabilities in the unsupervised setting. Experimental results demonstrate that the proposed method, which is under the multi-class-one-model paradigm, achieves a +8.7 %/+7.0 % gain on anomaly detection and localization performance as compared to the state-of-the-art one-class-one-model methods for the Anomaly-ShapeNet dataset, and obtains +4.3 %/+0.3 % gain for the Real3D-AD dataset. Code will be available upon publication.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129758"},"PeriodicalIF":7.5,"publicationDate":"2025-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220909","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

RSUTrajRec: Multi-granularity trajectory recovery based on roadside units sensing RSUTrajRec：基于路边单元感知的多粒度轨迹恢复

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-20 DOI: 10.1016/j.eswa.2025.129780

Xianjing Wu , Xutao Chu , Jianyu Wang , Shengjie Zhao

{"title":"RSUTrajRec: Multi-granularity trajectory recovery based on roadside units sensing","authors":"Xianjing Wu , Xutao Chu , Jianyu Wang , Shengjie Zhao","doi":"10.1016/j.eswa.2025.129780","DOIUrl":"10.1016/j.eswa.2025.129780","url":null,"abstract":"<div><div>Vehicle mobility trajectories, especially fine-grained trajectories, provide valuable insights for understanding urban dynamics and play a crucial role in intelligent transportation systems and urban planning. Obtaining fine-grained vehicle trajectories can be realized by trajectory recovery, but traditional efforts suffer from defects such as poor privacy protection and low recovery accuracy. To address these issues, we propose a new scenario of trajectory recovery based on roadside unit (RSU) sensing. However, this scenario introduces a significant challenge: recovering high-precision trajectories from the incomplete and unevenly distributed sensing data. To tackle this, we design <em>RSUTrajRec</em>, a multi-granularity trajectory recovery framework that comprises a graph neural network-based module for road information prediction, a Transformer-based module for multi-granularity recovery, and an RSU deployment planning module. Extensive real-world dataset evaluations reveal that <em>RSUTrajRec</em> has a significant advantage in recovering missing vehicle trajectories outside the RSU coverage area. In addition, evaluations also verify that the performance of the trajectory recovery task can be effectively improved by optimizing the RSU deployment plan.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129780"},"PeriodicalIF":7.5,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159218","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

Adaptive gated universal information extraction for Chinese legal texts 中文法律文本自适应门控通用信息提取

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-20 DOI: 10.1016/j.eswa.2025.129801

Yabo Liu , Yatong Zhou , Kuo-Ping Lin

{"title":"Adaptive gated universal information extraction for Chinese legal texts","authors":"Yabo Liu , Yatong Zhou , Kuo-Ping Lin","doi":"10.1016/j.eswa.2025.129801","DOIUrl":"10.1016/j.eswa.2025.129801","url":null,"abstract":"<div><div>Constructing knowledge graphs in legal domains requires simultaneous extraction of entities and relations. To reduce repeated modeling in traditional approaches, we adopt the Universal Information Extraction (UIE) model as a foundation and propose an enhanced variant named Adaptive Gated Universal Information Extraction (AGUIE). This study develops a new decoder based on the Adaptive Focusing Gated Attention Unit (AFGAU). This unit enhances the standard Gated Attention Unit (GAU) by integrating two key components—learnable dynamic convolution and reset/update gating mechanisms. Moreover, the study employs a cross-pointer structure as the output layer to better identify information boundaries. To support this study, we construct a domain specific dataset for extracting key information from legal judgment documents. Systematic comparative analysis and ablation studies demonstrate that AGUIE achieves significant performance gains over baseline UIE, with an F1 score of 85.56% on our legal judgment documents dataset. Additionally, we evaluate the model’s generalization on public datasets such as ACE04, ACE05, and CoNLL04, covering both entity recognition and relation extraction tasks. Experimental results indicate that AGUIE demonstrates competitive results with recent studies on ACE04-Ent and CoNLL04, outperforms them on the ACE05 dataset, achieving F1 scores of 87.19% on ACE05-Ent and 79.29% on ACE05-Rel. In conclusion, AGUIE is a reliable and effective solution for universal information extraction in both legal and general domains.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129801"},"PeriodicalIF":7.5,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118829","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

A novel fuzzy clustering approach with transition matrix for explainable evaluation of social media-based digital literacy interventions 基于社交媒体的数字素养干预的可解释评价：一种新的模糊聚类方法与转移矩阵

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-20 DOI: 10.1016/j.eswa.2025.129769

Rustam , Diana Noor Anggraini , Koredianto Usman , Loveleen Gaur

{"title":"A novel fuzzy clustering approach with transition matrix for explainable evaluation of social media-based digital literacy interventions","authors":"Rustam , Diana Noor Anggraini , Koredianto Usman , Loveleen Gaur","doi":"10.1016/j.eswa.2025.129769","DOIUrl":"10.1016/j.eswa.2025.129769","url":null,"abstract":"<div><div>Assessing the effectiveness of digital literacy interventions often relies on raw score comparisons or hard classifications, which may obscure nuanced changes in conceptual understanding and provide limited interpretability. Traditional approaches fail to capture the probabilistic and fuzzy nature of learning progression and do not support transparent analysis of how learners transition across conceptual clusters over time. This study proposes an explainable evaluation framework that integrates fuzzy clustering with a fuzzy transition matrix to model the redistribution of aggregated membership values between pretest and posttest conceptual clusters. The framework applies Fuzzy C-Means (FCM) to derive soft cluster memberships and constructs a transition matrix that represents probabilistic learning progression in a linguistically interpretable form. Unlike conventional methods, this approach enables the analysis of gradual transitions across levels of proficiency rather than binary outcomes. The model was applied to real-world educational data from control and experimental classes, the latter of which received a social media-based instructional intervention. Results indicate that the control class exhibited downward or stagnant patterns, particularly among high-performing learners, while the experimental class showed more coherent upward cluster transitions among low- and moderate-level learners. By enabling interpretable modeling of pre–post cluster transition patterns, the proposed framework contributes to the advancement of explainable machine learning in education. It also highlights the potential of social computing platforms to foster scalable, data-driven digital literacy development.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129769"},"PeriodicalIF":7.5,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159097","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

Dynamic graph structure correction with nonadjacent correlations for multivariate time series forecasting 多元时间序列预测的非相邻相关动态图结构校正

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-09-20 DOI: 10.1016/j.eswa.2025.129768

Dandan He , Yueyang Wang , Chaoli Lou , Gang Tan , Qingyu Xiong , Guodong Sa

{"title":"Dynamic graph structure correction with nonadjacent correlations for multivariate time series forecasting","authors":"Dandan He , Yueyang Wang , Chaoli Lou , Gang Tan , Qingyu Xiong , Guodong Sa","doi":"10.1016/j.eswa.2025.129768","DOIUrl":"10.1016/j.eswa.2025.129768","url":null,"abstract":"<div><div>Effectively modeling the relations between variables in multivariate time series is of utmost importance for accomplishing accurate predictions. In real-world scenarios, in addition to sequential correlations, the evolution of relations between variables also exhibits nonadjacent correlations at different scales. However, existing methods primarily focus on constructing dynamic graph structures at each time step using temporal features extracted by continuous temporal models, which cannot capture above latent dependencies. In this study, we introduce the Dynamic Graph Structure Correction (DGC) model, leveraging a multi-scale framework with dilated convolution. To take full advantage of nonadjacent correlations in the evolution of relations between variables, we adaptively select history-related graph structures to correct initial graph structure constructed by Gate Recurrent Units. In addition, we design a time-decay-based attention mechanism to address the influence of time intervals between history-related and current time steps. Finally, the evolved graph structures are fed into graph neural networks to handle the multi-scale and complex structural relations. Our proposed model achieves superior performance compared to state-of-the-art methods in multivariate time series forecasting, as evidenced by the evaluation results on four widely used benchmark datasets.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129768"},"PeriodicalIF":7.5,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159093","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