Expert Systems with Applications最新文献

筛选
英文 中文
A progressive self-supervised learning framework: From fault diagnosis to electric motor wear prediction 渐进式自监督学习框架:从故障诊断到电机磨损预测
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-15 DOI: 10.1016/j.eswa.2025.127513
Morgane Suhas , Emmanuelle Abisset-Chavanne , Pierre-André Rey
{"title":"A progressive self-supervised learning framework: From fault diagnosis to electric motor wear prediction","authors":"Morgane Suhas ,&nbsp;Emmanuelle Abisset-Chavanne ,&nbsp;Pierre-André Rey","doi":"10.1016/j.eswa.2025.127513","DOIUrl":"10.1016/j.eswa.2025.127513","url":null,"abstract":"<div><div>This paper presents a wear prediction framework for systems based on contrastive self-supervised learning, with a focus on knowledge transfer from fault diagnosis to prognosis. Specifically, the study examines a direct current (DC) electric motor with the aim of predicting the extent of its wear. The methodology includes a pre-training phase using contrastive learning, which extracts temporal features from multivariate time series collected from sensors. These features are constructed using labelled data, creating representations that are correlated across sequences that share the same label. These representations are then used for long-term wear prediction, integrating CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory) layers. This approach effectively discriminates between normal and failed states in an upstream task, thereby facilitating failure prediction in a downstream task. A progressive learning strategy was incorporated into the pretext task to accelerate the convergence of the contrastive loss function, although it remains optional within the methodology. The results show that the Root Mean Square Error (RMSE) of the proposed method is twice as low as that of the same model without the pretext task on extrapolated data, even in the absence of labels (RMSE 0.78 vs. 1.44).</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"281 ","pages":"Article 127513"},"PeriodicalIF":7.5,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838610","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
Collaborative production control and distributor selection via multi-agent reinforcement learning with differentiable communication 基于可微通信的多智能体强化学习的协同生产控制与经销商选择
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-15 DOI: 10.1016/j.eswa.2025.127539
Yang Deng , Guojun Sheng , Andy H.F. Chow , Zhili Zhou , Qinyang Bai , Zicheng Su
{"title":"Collaborative production control and distributor selection via multi-agent reinforcement learning with differentiable communication","authors":"Yang Deng ,&nbsp;Guojun Sheng ,&nbsp;Andy H.F. Chow ,&nbsp;Zhili Zhou ,&nbsp;Qinyang Bai ,&nbsp;Zicheng Su","doi":"10.1016/j.eswa.2025.127539","DOIUrl":"10.1016/j.eswa.2025.127539","url":null,"abstract":"<div><div>Collaborative production control and distributor selection are essential for resource allocation and meeting the core of Industry 5.0’s human-centric vision. However, traditional approaches typically handle these decisions independently, failing to adequately address fluctuating market conditions, demand uncertainty, and varying distributor competencies. This paper integrates production control and distributor selection as a Partially Observable Markov Decision Process (POMDP) in a multi-agent system. Specifically, a production control agent optimizes outputs by balancing inventory levels and opportunity costs, while a distributor selection agent dynamically adjusts allocations considering workforce skill diversity, cost efficiency, and equity. The formulated POMDP is solved using a multi-agent reinforcement learning (MARL) framework featuring a differentiable communication layer and GRU-based recurrent neural networks. Numerical experiments conducted under both stable and highly volatile market conditions demonstrate the proposed system’s enhanced adaptability and responsiveness. In particular, inter-agent messaging communication leading to improved welfare metrics and robust performance under diverse distributor-weight configurations. Notably, the resulting system promotes equitable distributor involvement, aligning with Industry 5.0’s emphasis on sustainable, people-centric supply chain operations.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"282 ","pages":"Article 127539"},"PeriodicalIF":7.5,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143859190","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
Concrete section segmentation with advanced deep learning models and refined labeling approaches 采用先进的深度学习模型和精细的标记方法进行混凝土截面分割
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-15 DOI: 10.1016/j.eswa.2025.127697
Woldeamanuel Minwuye Mesfin , Gun Kim , Hyeong-Ki Kim
{"title":"Concrete section segmentation with advanced deep learning models and refined labeling approaches","authors":"Woldeamanuel Minwuye Mesfin ,&nbsp;Gun Kim ,&nbsp;Hyeong-Ki Kim","doi":"10.1016/j.eswa.2025.127697","DOIUrl":"10.1016/j.eswa.2025.127697","url":null,"abstract":"<div><div>This study investigates deep learning models for semantic and instance segmentation of construction site images, focusing on concrete sections. A labeling scheme was developed for the image dataset, extending to multiple classes to achieve more detailed segmentation. ResNet-50, Xception, Inception ResNet V2, and Mask R-CNN models were trained and evaluated using key metrics, including accuracy, intersection over union, boundary F1 score, and receiver operating characteristic curves. The influence of hyperparameters, particularly the learning rate, was thoroughly analyzed. The results demonstrated that the optimal learning rate is 0.01, which led to a performance improvement within the studied range. Additionally, the Xception model consistently outperformed the others across most classes, delivering robust accuracy and reliability,with an accuracy value of 94%, an IoU of 88%, and a BFS of 73%. Furthermore, this study examines the impact of practical factors, including brightness, blur, camera rotation, perspective distortion, and illumination, on segmentation performance. The findings reveal that segmentation accuracy declines significantly under extreme conditions, highlighting the necessity of data augmentation and high-quality image acquisition to improve model resilience.”</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"281 ","pages":"Article 127697"},"PeriodicalIF":7.5,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842725","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-modal multi-scale multi-level fusion quadrant entropy for mechanical fault diagnosis 多模态多尺度多级融合象限熵的机械故障诊断
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-14 DOI: 10.1016/j.eswa.2025.127715
Zhenya Wang , Yaming Liu , Rengui Bai , Hui Chen , Jinghu Li , Xu Chen , Ligang Yao , Jingshan Zhao , Fulei Chu
{"title":"Multi-modal multi-scale multi-level fusion quadrant entropy for mechanical fault diagnosis","authors":"Zhenya Wang ,&nbsp;Yaming Liu ,&nbsp;Rengui Bai ,&nbsp;Hui Chen ,&nbsp;Jinghu Li ,&nbsp;Xu Chen ,&nbsp;Ligang Yao ,&nbsp;Jingshan Zhao ,&nbsp;Fulei Chu","doi":"10.1016/j.eswa.2025.127715","DOIUrl":"10.1016/j.eswa.2025.127715","url":null,"abstract":"<div><div>Compared to single-sensor fault diagnosis models, multi-sensor information fusion models utilize potential fault information from various sensors for more precise fault diagnosis. However, most fusion models require many training samples to construct accurate models. Collecting these data is costly and challenging, increasing the time needed to build the training model. These models typically fuse information from multiple vibration sensors, with limited research on multi-modal information fusion, such as combining vibration and acoustic data. Additionally, the generality of existing models is weak, often requiring structural and parameter adjustments for different diagnostic tasks. To address these challenges, this paper proposes a high-accuracy and high-efficiency mechanical fault diagnosis model based on the multi-modal multi-scale multi-level fusion quadrant entropy (MMMFQE) using limited training samples. The proposed MMMFQE theory effectively constructs multi-modal information fusion feature maps across multiple scales and levels. The fusion quadrant entropy is then proposed to accurately characterize the mechanical states by analyzing the complexities of fusion feature maps. Analysis of two industrial datasets shows that the proposed model achieves 100% and 99.46% accuracy with only five training samples per state. Moreover, the accuracy, efficiency, and few-shot ability of the proposed model surpass those of several advanced models.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"281 ","pages":"Article 127715"},"PeriodicalIF":7.5,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848629","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
Social network-based consensus reaching model with rational adjustment allocation for large-scale group decision making 基于社会网络的大规模群体决策合理调整分配共识达成模型
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-14 DOI: 10.1016/j.eswa.2025.127724
Feng Wang , Xiaobing Yu , Yaqi Mao
{"title":"Social network-based consensus reaching model with rational adjustment allocation for large-scale group decision making","authors":"Feng Wang ,&nbsp;Xiaobing Yu ,&nbsp;Yaqi Mao","doi":"10.1016/j.eswa.2025.127724","DOIUrl":"10.1016/j.eswa.2025.127724","url":null,"abstract":"<div><div>Large-scale group decision making (LSGDM) refers to the decision-making process involving a large number of decision makers (DMs). As an extension of group decision-making, it can make full use of multiple resources and give play to complementary advantages of the knowledge structure of the large group, but it faces some problems such as difficult concentration of opinion, long decision-making time and difficult management. In LSGDM, individual optimality and fairness regarding consensus adjustment are concerns for DMs. Many existing consensus models assume that DMs are completely cooperative and aim only at global optimality such as the minimization of the total consensus cost. It will be difficult for DMs to fully accept the resulting adjustment suggestion. Therefore, an LSGDM method based on the cooperative game is proposed. First, a new method of trust propagation is developed to calculate a more reliable indirect trust degree between unacquainted DMs. Next, an adaptive clustering algorithm is devised to more objectively cluster the large group into several subgroups. Then, consensus adjustment optimization models are built from the global and individual perspectives, respectively. The difference in the adjustment amount derived from the two perspectives is viewed as a cooperative surplus, which is fairly allocated through a core-based maximum entropy model. Based on the allocation scheme, an overall consensus optimization model considering personalized adjustment preferences is built to determine the final opinion adjustments. Finally, a practical example is provided to illustrate the decision-making process. Furthermore, the comparative analysis shows the advantages of the proposed method.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"281 ","pages":"Article 127724"},"PeriodicalIF":7.5,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842726","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
LSBT-Net: A lightweight framework for fault diagnosis of bearings based on an interpretable spatial-temporal model lbt - net:基于可解释时空模型的轴承故障诊断轻量级框架
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-14 DOI: 10.1016/j.eswa.2025.127718
Yicheng Duan , Tongguang Yang , Chenlin Wang , Yongjian Zhang , Qingkai Han , Shuangping Guo
{"title":"LSBT-Net: A lightweight framework for fault diagnosis of bearings based on an interpretable spatial-temporal model","authors":"Yicheng Duan ,&nbsp;Tongguang Yang ,&nbsp;Chenlin Wang ,&nbsp;Yongjian Zhang ,&nbsp;Qingkai Han ,&nbsp;Shuangping Guo","doi":"10.1016/j.eswa.2025.127718","DOIUrl":"10.1016/j.eswa.2025.127718","url":null,"abstract":"<div><div>Intelligent fault diagnosis based on deep learning has emerged as a research focus in mechanical equipment due to its adaptive feature extraction capability. However, current models struggle with low accuracy, high computational costs, and poor interpretability when detecting faults in insulated bearings. To address these challenges, this paper proposes a novel lightweight spatiotemporal model-based intelligent diagnostic framework, named LSBT-Net, which aims to identify motor insulating bearing faults in practical engineering applications more accurately. Specifically, this research breaks the conventional thinking of “learning fault data feature information” by innovatively developing a spatiotemporal information fusion module. This module is cleverly integrated into the LSBT-Net framework, enabling the extraction of both local and global high-dimensional fault feature information from insulating bearings. At the same time, based on a lightweight design, it significantly reduces the total number of parameters and computational resources required by the framework, thus lowering its computational complexity. The t-SNE algorithm is introduced into the LSBT-Net framework to achieve local or global interpretability. Furthermore, by calculating the gradient information of the LSBT-Net framework on the fault types of insulating bearings through backpropagation, the interpretability of the framework with respect to the physical information is enhanced. Using insulating bearings and typical fault experiments as examples, the LSBT-Net framework demonstrates excellent diagnostic capability and generalization performance compared to other advanced methods.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"281 ","pages":"Article 127718"},"PeriodicalIF":7.5,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143833955","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
Ordinal regression for preference learning in wearables using sensor data 基于传感器数据的可穿戴设备偏好学习的有序回归
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-14 DOI: 10.1016/j.eswa.2025.127616
Simón Weinberger , Jairo Cugliari , Aurélie Le Cain
{"title":"Ordinal regression for preference learning in wearables using sensor data","authors":"Simón Weinberger ,&nbsp;Jairo Cugliari ,&nbsp;Aurélie Le Cain","doi":"10.1016/j.eswa.2025.127616","DOIUrl":"10.1016/j.eswa.2025.127616","url":null,"abstract":"<div><div>Wearable technology makes it increasingly common to obtain successive measurements of a variable that changes over time. A key challenge in various fields is understanding the relationship between a time-dependent variable and a scalar response. In this context, we focus on active frames equipped with electrochromic lenses, currently in development. These lenses allow users to adjust the tint at will, choosing from four different levels of darkness. Our goal to train an ordinal regression model to predict the preferred tint level using ambient light data collected by an Ambient Light Sensor (ALS) to deploy it on electrochromic frames, which would control the tint in a personalized way. We approach this as an ordinal regression problem with a functional predictor. To tackle the complexities of the task, we use an adaptation of the classical ordinal model to include functional covariates. We explore the use of wavelets and B-splines functional basis, as well as regularization techniques such as lasso or roughness penalty. In two datasets with data issued from wearable devices, these functional ordinal regression models outperform LSTM and FCN networks, being up to 10% more accurate while remaining interpretable.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"281 ","pages":"Article 127616"},"PeriodicalIF":7.5,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842724","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
Taming deep reinforcement learning-based conflict resolution in air traffic control using geometric technique 基于几何技术的基于深度强化学习的空中交通管制冲突解决
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-14 DOI: 10.1016/j.eswa.2025.127579
Lei Wang , Hongyu Yang , Yunxiang Han , Suwan Yin , Yuankai Wu
{"title":"Taming deep reinforcement learning-based conflict resolution in air traffic control using geometric technique","authors":"Lei Wang ,&nbsp;Hongyu Yang ,&nbsp;Yunxiang Han ,&nbsp;Suwan Yin ,&nbsp;Yuankai Wu","doi":"10.1016/j.eswa.2025.127579","DOIUrl":"10.1016/j.eswa.2025.127579","url":null,"abstract":"<div><div>Recent advances in Deep Reinforcement Learning (DRL)-based CR have shown promise; however, the end-to-end nature of DRL systems, which rely on reward-driven mechanisms, poses challenges in adhering to ATC’s stringent regulations. Traditional geometric methods, such as the Modified Voltage Potential (MVP) technique, theoretically meet ATC requirements by minimizing deviations from planned paths during conflicts but struggle to ensure optimal performance in complex, uncertain environments. In this study, we amalgamate DRL with the geometric MVP technique, leveraging DRL’s capacity for intelligent decision-making in complex environments and MVP’s ability to theoretically minimize deviations from planned paths. Within this framework, we utilize a look-ahead DRL agent, in conjunction with MVP conflict detection methods, to foresee potential conflicts. Should a conflict be imminent, a Maneuver DRL agent takes immediate control of the aircraft to adeptly navigate the situation, ensuring conflict avoidance. Once the aircraft is clear of the conflict, a rule-based method is employed to swiftly return it to the planned path. Extensive simulations demonstrate that our proposed framework significantly reduces conflict rates, maintains efficient trajectory adherence with minimal deviations, lowers unnecessary computational overhead, and effectively adapts to dynamic environmental conditions.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"281 ","pages":"Article 127579"},"PeriodicalIF":7.5,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838778","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
High-Frequency Enhanced Hybrid Neural Representation for video compression 视频压缩的高频增强混合神经表示
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-13 DOI: 10.1016/j.eswa.2025.127552
Li Yu , Zhihui Li , Jimin Xiao , Moncef Gabbouj
{"title":"High-Frequency Enhanced Hybrid Neural Representation for video compression","authors":"Li Yu ,&nbsp;Zhihui Li ,&nbsp;Jimin Xiao ,&nbsp;Moncef Gabbouj","doi":"10.1016/j.eswa.2025.127552","DOIUrl":"10.1016/j.eswa.2025.127552","url":null,"abstract":"<div><div>Neural Representations for Videos (NeRV) have simplified the video codec process and achieved swift decoding speeds by encoding video content into a neural network, presenting a promising solution for video compression. However, existing work overlooks the crucial issue that videos reconstructed by these methods lack high-frequency details. To address this problem, this paper introduces a High-Frequency Enhanced Hybrid Neural Representation Network. Our method focuses on leveraging high-frequency information to improve the synthesis of fine details by the network. Specifically, we design a wavelet high-frequency encoder that incorporates Wavelet Frequency Decomposer (WFD) blocks to generate high-frequency feature embeddings. Next, we design the High-Frequency Feature Modulation (HFM) block, which leverages the extracted high-frequency embeddings to enhance the fitting process of the decoder. Finally, with the refined Harmonic decoder block and a Dynamic Weighted Frequency Loss, we further reduce the potential loss of high-frequency information. Experiments on the Bunny and UVG datasets demonstrate that our method outperforms other methods, showing notable improvements in detail preservation and compression performance.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"281 ","pages":"Article 127552"},"PeriodicalIF":7.5,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842729","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 topic coherence and diversity in document embeddings using LLMs: A focus on BERTopic 利用法学硕士增强文档嵌入中的主题一致性和多样性:以BERTopic为重点
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-12 DOI: 10.1016/j.eswa.2025.127517
Chibok Yang, Yangsok Kim
{"title":"Enhancing topic coherence and diversity in document embeddings using LLMs: A focus on BERTopic","authors":"Chibok Yang,&nbsp;Yangsok Kim","doi":"10.1016/j.eswa.2025.127517","DOIUrl":"10.1016/j.eswa.2025.127517","url":null,"abstract":"<div><div>With the rapid growth of digital textual data, the need for systematic organization of large datasets has become critical. Topic modeling stands out as an effective approach for analyzing large volumes of text datasets. Neural Topic Models (NTMs) have been developed to overcome the limitations of traditional methods by using contextual embeddings, such as Bidirectional Encoder Representations from Transformers (BERT), to improve topic coherence. Recent advancements in Natural Language Processing (NLP) have further enhanced document processing capabilities through large language models (LLMs) such as LLaMA and the Generative Pre-trained Transformer (GPT). This research explores whether LLM embeddings within NTMs offer better performance compared to conventional models like Sentence-BERT (S-BERT) and DistilBERT. In particular, we examine the impact of text preprocessing on topic modeling. A comparative analysis is conducted using datasets from three domains, evaluating six topic models, including LLMs such as Falcon and LLaMA3, using three evaluation metrics. Results show that while no single model consistently excelled across all metrics, LLaMA3 demonstrated the best performance in coherence among the LLMs. In addition, overall topic modeling performance improved with the application of all six preprocessing techniques. LLaMA3 showed progressively better performance with additional preprocessing, confirming its stability and effectiveness in topic modeling. These findings suggest that LLMs can be reliable tools for topic identification across diverse datasets.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"281 ","pages":"Article 127517"},"PeriodicalIF":7.5,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842936","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