Expert Systems with Applications最新文献

筛选
英文 中文
Selection of high-arm fire trucks for urban emergency preparedness based on evidential linguistic CRITIC-BWM approach 基于证据语言学critical - bwm方法的城市应急准备高臂消防车选择
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.128064
Tao Li , Min Zhong , Liguo Fei
{"title":"Selection of high-arm fire trucks for urban emergency preparedness based on evidential linguistic CRITIC-BWM approach","authors":"Tao Li ,&nbsp;Min Zhong ,&nbsp;Liguo Fei","doi":"10.1016/j.eswa.2025.128064","DOIUrl":"10.1016/j.eswa.2025.128064","url":null,"abstract":"<div><div>This study discusses the selection problem of high-arm fire trucks in urban emergency preparedness and proposes a multi-criteria decision-making (MCDM) model based on the Criteria importance through intercriteria correlation and best worst method (CRITIC-BWM) methods guided by the evidence linguistic term sets (ELTS). The model aims to help fire departments select appropriate high-arm fire trucks to deal with high-rise building fires and improve the city’s fire emergency response capabilities. The MCDM model handles the linguistic preference problem by combining the evidence linguistic term sets and uses the CRITIC-BWM combined weighting method to determine the weight of the decision criteria, thereby reducing subjective bias while comprehensively considering multiple criteria. The effectiveness of the model is verified through specific case analysis. The research results show that the model can not only effectively solve the selection problem of high-arm fire trucks, but also provide guidance for the future performance optimization of high-arm fire trucks. Nevertheless, there are still some limitations in this study, such as the evidence linguistic term sets method needs to be further improved and the universality of the model needs to be verified in more fields. Future research will continue to optimize the model, expand its scope of application, and further verify its reliability and effectiveness in actual decision-making.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"287 ","pages":"Article 128064"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144083675","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
Enhancing short-term solar radiation forecasting with hybrid VMD and GraphCast-based machine learning models 利用混合VMD和基于graphcast的机器学习模型增强短期太阳辐射预报
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.128042
Zihuang Yan , Xianghui Lu , Lifeng Wu , Haina Zhang , Fa Liu , Xulei Wang , Wenhao Xu , Wei Liu
{"title":"Enhancing short-term solar radiation forecasting with hybrid VMD and GraphCast-based machine learning models","authors":"Zihuang Yan ,&nbsp;Xianghui Lu ,&nbsp;Lifeng Wu ,&nbsp;Haina Zhang ,&nbsp;Fa Liu ,&nbsp;Xulei Wang ,&nbsp;Wenhao Xu ,&nbsp;Wei Liu","doi":"10.1016/j.eswa.2025.128042","DOIUrl":"10.1016/j.eswa.2025.128042","url":null,"abstract":"<div><div>Accurate solar radiation forecasting is vital for photovoltaic power, agriculture, and weather prediction but faces complex nonlinear challenges. Recently, with the rapid development of artificial intelligence (AI), AI weather forecasting models based on machine learning (ML) have been proposed. The paper proposes a novel method by utilizing Variational Mode Decomposition (VMD) coupled with the global forecasting system Graph Neural Network model (GraphCast), combined with Support Vector Machine (SVM), Random Forest (RF), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM). The method predicts daily solar radiation under limited meteorological data by leveraging five-fold cross-validation. Furthermore, the integration of GraphCast-based forecast meteorological data with ML technology effectively addresses the gap in GraphCast-based solar radiation forecasting. Using models with station-based meteorological variables as a benchmark, the prediction performance of hybrid ML models based on VMD was compared with that of individual models. Among all models, the VMD-based RF model provided the highest accuracy for solar radiation forecasting. Additionally, when more meteorological variables forecasted by GraphCast were used as model inputs, the VMD-based RF model showed improved prediction performance. The VMD-based RF model emerged as the best-performing predictive model in this study, demonstrating an average coefficient of determination (R<sup>2</sup>) of 0.928, mean absolute error (MAE) of 16.578 (W/m<sup>2</sup>), root mean square error (RMSE) of 24.32 (W/m<sup>2</sup>), and normalized root mean square error (NRMSE) of 5.6 (%) across different input combinations. The RMSE of the VMD-based RF model is 58.73% lower than that of the RF model based on station meteorological variables.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"285 ","pages":"Article 128042"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942551","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 Q-learning guided dual population genetic algorithm for distributed permutation flow shop scheduling problem with machine having fuzzy processing efficiency 针对机器具有模糊处理效率的分布式置换流水车间调度问题,采用q学习引导的对偶种群遗传算法
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.127882
Guanzhong Zuo, Zhiyang Jia, Zongyang Wu, Jiawei Shi, Gang Wang
{"title":"A Q-learning guided dual population genetic algorithm for distributed permutation flow shop scheduling problem with machine having fuzzy processing efficiency","authors":"Guanzhong Zuo,&nbsp;Zhiyang Jia,&nbsp;Zongyang Wu,&nbsp;Jiawei Shi,&nbsp;Gang Wang","doi":"10.1016/j.eswa.2025.127882","DOIUrl":"10.1016/j.eswa.2025.127882","url":null,"abstract":"<div><div>The emergence of Industry 5.0 has shifted the focus of research towards green manufacturing, flexible and digitalized production, particularly emphasizing human–machine collaboration and distributed manufacturing systems. Such a transition introduces increasingly complex and dynamic challenges for manufacturing enterprises, resulting in heightened uncertainties in production scheduling where traditional scheduling approaches often exhibit limited capability in handling multi-objective trade-offs. To overcome these limitations, a <span><math><mi>Q</mi></math></span>-learning guided dual-population genetic algorithm (QGGA) is proposed in the current study, featuring two key innovations: (1) a cooperation pool with dual-population knowledge sharing that stores non-dominated solutions from both populations while maintaining their evolutionary independence, (2) a state-dependent action adaptation mechanism that dynamically selects actions from nine heuristic rules using <span><math><mi>Q</mi></math></span>-learning. The cooperation pool enables synergistic optimization by storing non-dominated solutions from both populations to enable knowledge exchange while preserving their independent optimization processes. The <span><math><mi>Q</mi></math></span>-learning component continuously optimizes action selection based on solution diversity metric and convergence metric. Experimental results demonstrate that the proposed method achieves 19.1% improvement in Hypervolume (HV) and 65.5% reduction in inverted Generational Distance (IGD) compared to NSGA-II, outperforms PPO by 24.8% HV, and achieves an 90.4%better IGD than MOEA/D, achieving superior balance between solution robustness and computational efficiency. This advancement provides a new methodological framework for addressing Industry 5.0 scheduling challenges under uncertainty.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"285 ","pages":"Article 127882"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143941842","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
Constructing high-quality health indicators from multi-source sensor data for predictive maintenance applications 从多源传感器数据构建用于预测性维护应用的高质量运行状况指示器
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.127870
Chuang Chen , Mengchen Li , Jiantao Shi , Dongdong Yue , Ge Shi , Cuimei Bo
{"title":"Constructing high-quality health indicators from multi-source sensor data for predictive maintenance applications","authors":"Chuang Chen ,&nbsp;Mengchen Li ,&nbsp;Jiantao Shi ,&nbsp;Dongdong Yue ,&nbsp;Ge Shi ,&nbsp;Cuimei Bo","doi":"10.1016/j.eswa.2025.127870","DOIUrl":"10.1016/j.eswa.2025.127870","url":null,"abstract":"<div><div>Prognostics and health management are critical for ensuring the reliability, safety, and economic efficiency of modern industrial equipment. However, with the growing volume and diversity of multi-source sensor data, effectively processing these data and extracting valuable information to accurately assess equipment health remains an urgent challenge. In response, this paper proposes a novel prognostics and health management approach based on health indicator construction. By integrating the nonlinear feature extraction capability of kernel principal component analysis and the deep representation learning strength of deep autoencoders, significantly enhancing the expressiveness of the constructed health indicators. Furthermore, a stochastic degradation model based on the Wiener process is incorporated with the health indicators to provide dynamic, uncertainty-aware estimation of the remaining useful life. Based on the predicted remaining useful life distribution, a cost-driven maintenance decision-making strategy is proposed to optimize maintenance timing. Experimental results obtained on the C-MAPSS dataset demonstrate significant improvements in prediction accuracy and provide a robust decision-making framework for predictive maintenance. These findings highlight the potential of the proposed method to enhance industrial reliability while reducing maintenance costs.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"285 ","pages":"Article 127870"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942549","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
MMVAD: A vision–language model for cross-domain video anomaly detection with contrastive learning and scale-adaptive frame segmentation MMVAD:基于对比学习和尺度自适应帧分割的跨域视频异常检测的视觉语言模型
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.127857
Debojyoti Biswas, Jelena Tesic
{"title":"MMVAD: A vision–language model for cross-domain video anomaly detection with contrastive learning and scale-adaptive frame segmentation","authors":"Debojyoti Biswas,&nbsp;Jelena Tesic","doi":"10.1016/j.eswa.2025.127857","DOIUrl":"10.1016/j.eswa.2025.127857","url":null,"abstract":"<div><div>Video Anomaly Detection (VAD) is crucial for public safety and detecting abnormalities in risk-prone zones. However, detecting anomalies from weakly labeled datasets has been very challenging for CCTV surveillance videos. The challenge is more intense when we involve high-altitude drone videos for VAD tasks. Very few works have been done on drone-captured VAD, and even the existing CCTV VAD methods suffer from several limitations that hinder their optimal performance. Previous VAD works mostly used single modal data, <em>e.g.</em>, video data, which was insufficient to understand the context of complex scenes. Moreover, the existing multimodal systems use the traditional linear fusion method to capture multimodal feature interaction, which does not address the misalignment issue from different modalities. Next, the existing work relies on fixed-scale video segmentation, which fails to preserve the fine-grained local and global context knowledge. Also, it was found that the feature magnitude-based VAD does not correctly represent the anomalous events. To address these issues, we present a novel vision–language-based video anomaly detection for drone videos. We use adaptive long-short-term video segmentation (ALSVS) for local–global knowledge extraction. Next, we propose to use a shallow yet efficient attention-based feature fusion (AFF) technique for multimodal VAD (MMVAD) tasks. Finally, for the first time, we introduce feature anomaly learning based on a saliency-aware contrastive algorithm. We found contrastive anomaly feature learning is more robust than the magnitude-based loss calculation. We performed experiments on two of the latest drone VAD datasets (Drone-Anomaly and UIT Drone), as well as two CCTV VAD datasets (UCF crime and XD-Violence). Compared to the baseline and closest SOTA, we achieved at least a +3.8% and +3.3% increase in AUC, respectively, for the drone and CCTV datasets.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"285 ","pages":"Article 127857"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942552","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
SpectMamba: Remote sensing change detection network integrating frequency and visual state space model spectrmamba:结合频率和视觉状态空间模型的遥感变化检测网络
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.127902
Zhiwei Dong, Dapeng Cheng, Jinjiang Li
{"title":"SpectMamba: Remote sensing change detection network integrating frequency and visual state space model","authors":"Zhiwei Dong,&nbsp;Dapeng Cheng,&nbsp;Jinjiang Li","doi":"10.1016/j.eswa.2025.127902","DOIUrl":"10.1016/j.eswa.2025.127902","url":null,"abstract":"<div><div>In recent years, the fusion of Convolutional Neural Network (CNNs) and Transformer models, which can simultaneously leverage the former’s efficiency in local feature extraction and the latter’s advantage in capturing long-range dependencies, has achieved complementary strengths and demonstrated superior modeling potential. However, some of the high-frequency subtle changes and periodic structural changes (e.g., regularly arranged clusters of reconstructed buildings) in multispectral remote sensing images are often difficult to detect in the spatial domain; at the same time, the high computational complexity of the Transformer model restricts its practical application. Recently, the state-space model-based Mamba architecture has performed well in the RSCD task, efficiently learning image global information with linear complexity. Based on this, this study hypothesizes that a strategy combining spectral layers with visual state space (VSS) modules can more efficiently parse these challenges in dense prediction tasks. Specifically, we propose the frontier strategy of using a spectral layer for the initial layer and a VSS layer for the deeper layer and verify its effectiveness through extensive experiments. At the same time, we identify and optimize the limitations of VSS in independently processing the high-frequency information output from the spectral layer, and develop Conv-VSS. These techniques are integrated and extended into a network called SpectMamba, which fuses the spectral layer and Conv-VSS to more appropriately capture feature representations by analyzing the feature images in both the frequency domain and spatial features while avoiding the complexity associated with high-dimensional matrix operations in self-attention. Extensive experimental results on three publicly available datasets show that SpectMamba significantly outperforms existing techniques on several performance metrics.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"287 ","pages":"Article 127902"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144083674","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
Trust-based core social graph convolution: An innovative framework for location recommendation 基于信任的核心社交图卷积:一个创新的位置推荐框架
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.127899
Tianyu Xie , Yunliang Chen , Yong Wu , Ningning Cui , Haofeng Chen , Xuanyu Lu , Xiaohui Huang , Yuewei Wang , Jianxin Li
{"title":"Trust-based core social graph convolution: An innovative framework for location recommendation","authors":"Tianyu Xie ,&nbsp;Yunliang Chen ,&nbsp;Yong Wu ,&nbsp;Ningning Cui ,&nbsp;Haofeng Chen ,&nbsp;Xuanyu Lu ,&nbsp;Xiaohui Huang ,&nbsp;Yuewei Wang ,&nbsp;Jianxin Li","doi":"10.1016/j.eswa.2025.127899","DOIUrl":"10.1016/j.eswa.2025.127899","url":null,"abstract":"<div><div>With the increasing popularity of location-based social networks (LBSNs), recommendation based on LBSNs has attracted wide attention in academic and industrial domains. Traditional recommendation systems face critical challenges in handling data sparsity and underutilized social trust. Existing traditional models particularly struggle to incorporate both trust-level differences and implicit relationships effectively within large-scale personalized recommendations. This limitation directly leads to aggravated data sparsity, further exacerbating cold-start scenarios and significantly reducing recommendation accuracy for long-tail items. Existing widely-adopted deep learning models, such as graph convolutional networks (GCNs), apply equal propagation weights to all neighbor nodes, which not only causes feature convergence between high-trust and ordinary users (over-smoothing) but also incurs substantial computational overhead. We propose the Trust-Based Core Graph Collaborative Filtering (TCGCF) framework, integrating trust-weighted core graph analysis with trust-constrained graph convolution. TCGCF captures both explicit and implicit trust relationships, enhances personalization, and mitigates over-smoothing. Our trust-weighted core graph analysis identifies influential users in information propagation, while the trust-constrained convolution scheme enables precise, differentiated information flow. Experiments on real-world datasets demonstrate that TCGCF improves recommendation accuracy and computational efficiency, outperforming existing models in precision, recall, and suitability for large-scale applications.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"285 ","pages":"Article 127899"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143941862","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
Multi-objective optimal design of an optimal fuzzy fractional order PID controller for fractional order hydraulic turbine regulating system 分数阶水轮机调节系统最优模糊分数阶PID控制器的多目标优化设计
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.127904
Shiyu Xi , Zhihuan Chen
{"title":"Multi-objective optimal design of an optimal fuzzy fractional order PID controller for fractional order hydraulic turbine regulating system","authors":"Shiyu Xi ,&nbsp;Zhihuan Chen","doi":"10.1016/j.eswa.2025.127904","DOIUrl":"10.1016/j.eswa.2025.127904","url":null,"abstract":"<div><div>The hydraulic turbine regulating system (HTRS) is a crucial component of the energy dispatch of hydropower plants. To achieve precise control of the HTRS output speed under variable working conditions, this paper explores the benefits of multi-objective optimization in the control field. A multi-objective optimization problem is established for an optimal fuzzy fractional order PID (OFFOPID) controller, tailored for fractional order HTRS working under both unload and load conditions. By introducing fractional order calculus operators and specifically optimizing the gains, rule bases, and membership functions, the OFFOPID controller enhances the traditional fuzzy PID controller and provides greater flexibility. In this multi-objective optimization problem, steady-state error (SSE), integral square error (ISE), and overshoot percentage (OP) are selected as the objective functions to ensure precise control accuracy, rapid response, and smooth transient behavior. To obtain the optimal Pareto frontier, the Pareto local search-nondominated sorting genetic algorithm III (PLS-NSGAIII) is proposed, with hybrid coding for population individuals specific to the OFFOPID framework. In this algorithm, the improved individual selection, crossover, and mutation operators enhance global search, while individual local search, conducted based on Pareto optimality, improves local search capabilities. Experiments show that the OFFOPID controller provides rapid and accurate responses for highly inertial HTRS, outperforming traditional controllers. Compared to three other multi-objective optimization algorithms on benchmark test functions and HTRS applications, the PLS-NSGAIII achieves lower GD and IGD values and higher HV values, demonstrating its effectiveness in solving HTRS problem.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"286 ","pages":"Article 127904"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072178","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
Environmental impact assessment for renewable energy investments through integrated reinforcement learning and molecular fuzzy-based decision-making algorithm 基于集成强化学习和分子模糊决策算法的可再生能源投资环境影响评价
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.128051
Hasan Dinçer , Serkan Eti , Yaşar Gökalp , Serhat Yüksel
{"title":"Environmental impact assessment for renewable energy investments through integrated reinforcement learning and molecular fuzzy-based decision-making algorithm","authors":"Hasan Dinçer ,&nbsp;Serkan Eti ,&nbsp;Yaşar Gökalp ,&nbsp;Serhat Yüksel","doi":"10.1016/j.eswa.2025.128051","DOIUrl":"10.1016/j.eswa.2025.128051","url":null,"abstract":"<div><div>Environmental impact assessment is a significant component of renewable energy project planning. However, the identification of key environmental performance indicators remains underexplored. In the literature, most existing studies do not adequately prioritize these environmental factors. This situation creates a significant research gap in the renewable energy literature. This study addresses this gap by proposing a novel hybrid decision-making model to identify the most effective investment strategies for improving the environmental performance of renewable energy projects. First, the balanced expert dataset has been constructed by Q-learning algorithm. The second stage is related to the evaluation of the criteria with molecular fuzzy (MF) Bayesian networks (BANEW)-based weighting. Finally, alternatives are ranked by MF multi-objective particle swarm optimization (MOPSO). This study fills an important gap in the literature on increasing the environmental sustainability of renewable energy investments by integrating molecular geometry-based fuzzy decision-making techniques and Q-learning supported expert weighting method in prioritizing environmental impacts. The use of molecular geometry and fuzzy multi-criteria decision-making analysis together reduces the uncertainty in the solution process of complex problems more effectively. The use of the Q-learning algorithm in the model reduces subjectivity in the decision-making process by providing a dynamic structure based on learning in the weighting of expert opinions. The findings show that biodiversity is the most effective environmental impact of renewable energy investments is mostly on biodiversity. On the other side, it is also identified that the most optimal option for assessing the environmental impact of renewable energy investments is life cycle assessment.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"285 ","pages":"Article 128051"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928645","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
An adaptive auto fusion with hierarchical attention for multimodal fake news detection 基于层次关注的自适应自动融合多模态假新闻检测
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-05-08 DOI: 10.1016/j.eswa.2025.127930
Alex Munyole Luvembe , Weimin Li , Shaohua Li , Guiqiong Xu , Xing Wu , Fangfang Liu
{"title":"An adaptive auto fusion with hierarchical attention for multimodal fake news detection","authors":"Alex Munyole Luvembe ,&nbsp;Weimin Li ,&nbsp;Shaohua Li ,&nbsp;Guiqiong Xu ,&nbsp;Xing Wu ,&nbsp;Fangfang Liu","doi":"10.1016/j.eswa.2025.127930","DOIUrl":"10.1016/j.eswa.2025.127930","url":null,"abstract":"<div><div>The phenomenon of fake news often relies on diverse multimodal evidence to deceive readers and achieve widespread popularity. While existing fusion methods aim to enhance feature interaction, they typically rely on concatenation or attention mechanisms that struggle to model nuanced dynamics of multimodal information due to missing data and modality heterogeneity. To overcome these limitations, we propose an <strong>A</strong>daptive <strong>A</strong>uto <strong>F</strong>usion with <strong>H</strong>ierarchical <strong>A</strong>ttention <strong>(AAFHA)</strong> framework for multimodal fake news detection. AAFHA integrates image captions directly into the fusion pipeline to strengthen cross-modal learning, unlike prior approaches that treat them as siloed inputs. We first design a multi-level interaction for text and captions by incorporating hierarchical encoding to capture both local and global dependencies, allowing the model to detect subtle cross-modal associations. Then, a sparse weighting technique, guided by hierarchical attention, further refines these interactions by dynamically allocating attention across modalities. This guided focus is implemented through a constrained SoftMax function, improving contextual alignment and reducing isolated feature modeling. To enable adaptive semantic integration, we introduce an Auto-Fusion module that supports dynamic end-to-end training. The model optimizes a learned similarity measure in a shared representation space, aligning textual, caption, and image features to adaptively capture semantic associations. Additionally, sparse training with contrastive loss is incorporated to preserve semantic consistency and enhance class separability during fusion. Experimental results demonstrate that AAFHA outperforms existing baselines, yielding accuracy improvements of 0.094%, 0.198%, and 0.001% on the PolitiFact, Gossip, and Pheme datasets, respectively. These findings demonstrate the model’s effectiveness in identifying multimodal fake news.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"285 ","pages":"Article 127930"},"PeriodicalIF":7.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143941840","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:481959085
Book学术官方微信