首页 > 最新文献

Expert Systems with Applications最新文献

英文 中文
Anticipating impression using textual sentiment based on ensemble LRD model 基于 LRD 模型的文本情感预测印象
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-16 DOI: 10.1016/j.eswa.2024.125717
Abdul Karim , Maria Mansab , Mobeen Shahroz , Muhammad Faheem Mushtaq , In cheol Jeong
Twitter sentiment analysis is a natural language processing that analyzes the sentiments espoused in Twitter tweets, helping users understand others’ perspectives on specific issues or trends. The research aims to improve sentiment analysis applications across industries by optimizing machine learning models for accurate sentiment prediction in diverse textual data. The goal of this study is to make the development of strong ensemble learning models by utilizing a publicly available dataset, such as Twitter sentiment analysis through Kaggle. To carefully clean the data and remove any unnecessary information, preprocessing techniques are used. The data is divided into two sections to predict impressions: training data and testing data, and seven different machine learning methods are applied such as Naive Bayes Classifiers, Logistic Regression, Decision Trees, Support Vector Machines, Multilayer Perceptron, Gradient Boosting, three classifiers that were merged into one ensemble machine learning approach. To determine each words weight value within the text of a document, the TF-IDF technique is applied. The trained model is compared to testing data to determine how much variance exists between actual and expected values. The result is evaluated using evaluation parameters such as precision, recall, and F1 score. The maximum accuracy achieved by the ensemble LRD model is approximately 90.5 %. This study aims to enhance sentiment analysis in various industries and sentiment-based recommendation systems, by analyzing diverse texts and determining people’s perspectives.
推特情感分析是一种自然语言处理方法,可分析推特推文中所表达的情感,帮助用户了解他人对特定问题或趋势的看法。本研究旨在通过优化机器学习模型,在不同的文本数据中进行准确的情感预测,从而改进各行业的情感分析应用。本研究的目标是利用公开的数据集,如通过 Kaggle 进行的 Twitter 情感分析,开发强大的集合学习模型。为了仔细清理数据并去除任何不必要的信息,我们使用了预处理技术。数据被分为两个部分来预测印象:训练数据和测试数据,并应用了七种不同的机器学习方法,如 Naive Bayes 分类器、逻辑回归、决策树、支持向量机、多层感知器、梯度提升,这三种分类器被合并成一种集合机器学习方法。为了确定文档文本中每个词的权重值,采用了 TF-IDF 技术。将训练好的模型与测试数据进行比较,以确定实际值与预期值之间存在多少差异。结果使用精确度、召回率和 F1 分数等评价参数进行评估。集合 LRD 模型达到的最高准确率约为 90.5%。本研究旨在通过分析不同文本和确定人们的观点,加强各行业的情感分析和基于情感的推荐系统。
{"title":"Anticipating impression using textual sentiment based on ensemble LRD model","authors":"Abdul Karim ,&nbsp;Maria Mansab ,&nbsp;Mobeen Shahroz ,&nbsp;Muhammad Faheem Mushtaq ,&nbsp;In cheol Jeong","doi":"10.1016/j.eswa.2024.125717","DOIUrl":"10.1016/j.eswa.2024.125717","url":null,"abstract":"<div><div>Twitter sentiment analysis is a natural language processing that analyzes the sentiments espoused in Twitter tweets, helping users understand others’ perspectives on specific issues or trends. The research aims to improve sentiment analysis applications across industries by optimizing machine learning models for accurate sentiment prediction in diverse textual data. The goal of this study is to make the development of strong ensemble learning models by utilizing a publicly available dataset, such as Twitter sentiment analysis through Kaggle. To carefully clean the data and remove any unnecessary information, preprocessing techniques are used. The data is divided into two sections to predict impressions: training data and testing data, and seven different machine learning methods are applied such as Naive Bayes Classifiers, Logistic Regression, Decision Trees, Support Vector Machines, Multilayer Perceptron, Gradient Boosting, three classifiers that were merged into one ensemble machine learning approach. To determine each words weight value within the text of a document, the TF-IDF technique is applied. The trained model is compared to testing data to determine how much variance exists between actual and expected values. The result is evaluated using evaluation parameters such as precision, recall, and F1 score. The maximum accuracy achieved by the ensemble LRD model is approximately 90.5 %. This study aims to enhance sentiment analysis in various industries and sentiment-based recommendation systems, by analyzing diverse texts and determining people’s perspectives.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125717"},"PeriodicalIF":7.5,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Trusted commonsense knowledge enhanced depression detection based on three-way decision 基于三向决策的可信常识知识增强型抑郁检测
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-16 DOI: 10.1016/j.eswa.2024.125671
Jie Chen, Hui Yao, Shu Zhao, Yanping Zhang
Depression detection on social media aims to identify depressive tendencies within textual posts, providing timely intervention by the early detection of mental health issues. In predominant approaches, the Pre-trained Language Models(PLMs) are trained solely on public datasets, falling short of vertical scenarios due to insufficient domain-specific and commonsense knowledge. In addition, ambiguous commonsense knowledge could be misleading to PLMs and results in false judgments. Therefore, it poses significant challenges to select commonsense knowledge that is trusted. To address this, we propose CoKE, a model that incorporates trusted commonsense knowledge based on three-way decision theory to enhance depression detection. CoKE comprises three key modules: trusted screening, knowledge generation, and knowledge fusion. First, we utilize psychiatric clinical scales and three-way decision theory to screen out the uncertain domain from the massive user posts. Then, an adaptive framework is applied to generate and refine trusted commonsense knowledge that can explain the true semantics of posts in the uncertain domain. Finally, a dynamic integration of posts with highly trusted knowledge is achieved through a gating mechanism, resulting in embeddings enhanced by trusted commonsense knowledge that are more effective in determining depressive tendencies. We evaluate our model on two prominent datasets, eRisk2017 and eRisk2018, demonstrating its superiority over previous state-of-the-art baseline models.
社交媒体上的抑郁检测旨在识别文本帖子中的抑郁倾向,通过早期发现心理健康问题提供及时干预。在主流方法中,预训练语言模型(PLMs)仅在公共数据集上进行训练,由于特定领域和常识知识不足,无法满足垂直场景的要求。此外,模棱两可的常识知识可能会误导 PLM,导致错误判断。因此,选择可信的常识性知识是一项重大挑战。为解决这一问题,我们提出了 CoKE 模型,该模型基于三向决策理论,将可信的常识知识纳入其中,以增强抑郁检测能力。CoKE 包括三个关键模块:可信筛选、知识生成和知识融合。首先,我们利用精神科临床量表和三向决策理论从海量用户帖子中筛选出不确定领域。然后,应用自适应框架生成并完善可信的常识性知识,这些知识可以解释不确定领域中帖子的真实语义。最后,通过门控机制实现帖子与高度可信知识的动态整合,从而产生由可信常识知识增强的嵌入,更有效地判断抑郁倾向。我们在两个著名的数据集(eRisk2017 和 eRisk2018)上对我们的模型进行了评估,结果表明它优于以前最先进的基线模型。
{"title":"Trusted commonsense knowledge enhanced depression detection based on three-way decision","authors":"Jie Chen,&nbsp;Hui Yao,&nbsp;Shu Zhao,&nbsp;Yanping Zhang","doi":"10.1016/j.eswa.2024.125671","DOIUrl":"10.1016/j.eswa.2024.125671","url":null,"abstract":"<div><div>Depression detection on social media aims to identify depressive tendencies within textual posts, providing timely intervention by the early detection of mental health issues. In predominant approaches, the Pre-trained Language Models(PLMs) are trained solely on public datasets, falling short of vertical scenarios due to insufficient domain-specific and commonsense knowledge. In addition, ambiguous commonsense knowledge could be misleading to PLMs and results in false judgments. Therefore, it poses significant challenges to select commonsense knowledge that is trusted. To address this, we propose CoKE, a model that incorporates trusted commonsense knowledge based on three-way decision theory to enhance depression detection. CoKE comprises three key modules: trusted screening, knowledge generation, and knowledge fusion. First, we utilize psychiatric clinical scales and three-way decision theory to screen out the uncertain domain from the massive user posts. Then, an adaptive framework is applied to generate and refine trusted commonsense knowledge that can explain the true semantics of posts in the uncertain domain. Finally, a dynamic integration of posts with highly trusted knowledge is achieved through a gating mechanism, resulting in embeddings enhanced by trusted commonsense knowledge that are more effective in determining depressive tendencies. We evaluate our model on two prominent datasets, eRisk2017 and eRisk2018, demonstrating its superiority over previous state-of-the-art baseline models.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125671"},"PeriodicalIF":7.5,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662211","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
MSU-Net: Multi-Scale self-attention semantic segmentation method for oil-tea camellia planting area extraction in hilly areas of southern China MSU-Net:用于中国南方丘陵地区油茶种植区提取的多尺度自关注语义分割方法
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-15 DOI: 10.1016/j.eswa.2024.125779
Zikun Xu , Hengkai Li , Beiping Long
Oil-tea camellia, one of the world’s four major edible woody oil trees, is acclaimed as the ’Oriental Olive Oil’ due to its exceptionally high nutritional value. The climate in southern China synchronizes with the ideal conditions for cultivating oil tea, making it the most abundant region globally in terms of its distribution. Consequently, the delineation of oil tea cultivation zones holds paramount significance for agricultural authorities in devising strategic production plans and management. However, the region is often affected by changeable weather and frequent cloud and rain, and there is a lack of continuous optical image data. Moreover, the complex topography primarily characterized by mountainous terrain, extensive coverage of farmlands, and vegetation has fragmented topographic features, posing challenges in accurately extracting semantic information from remote sensing images. To address these challenges, we propose a multi-scale self-attention semantic segmentation network aimed at meticulously identifying the semantic features of oil tea. Specifically, we introduce a self-attention mechanism to enable the model to comprehensively understand the information on feature images, followed by the integration of multi-scale feature images through the ASPP(Atrous Spatial Pyramid Pooloing) module to prevent the oversight of minor terrain features. Finally, the Dice-Loss function is applied to optimize the model’s segmentation of edge details. Experimental evaluations demonstrate that the proposed multi-scale self-attention semantic segmentation model achieved an Intersection over Union (IOU) of 0.93, Pixel Accuracy (PA) of 0.98, and Overall Accuracy (OA) of 94.83% for oil tea extraction on the dataset, showcasing a notable improvement over the original model. Additionally, we explore the method’s data requirements from the perspective of data volume and proportion. Ultimately, the experimental results demonstrate that our proposed method can accurately extract the oil tea cultivation areas in the cloudy and rainy hilly regions of southern China with high precision, thereby serving as a technological means for agricultural departments to oversee oil tea cultivation.
油茶是世界四大食用木本油料之一,因其营养价值极高,被誉为 "东方橄榄油"。中国南方的气候与油茶栽培的理想条件同步,是全球油茶分布最丰富的地区。因此,油茶种植区的划分对于农业部门制定战略性生产计划和管理具有重要意义。然而,该地区经常受到多变天气和频繁云雨的影响,缺乏连续的光学图像数据。此外,该地区地形复杂,以山地为主,农田覆盖面广,植被覆盖率高,地形特征破碎,为从遥感图像中准确提取语义信息带来了挑战。针对这些挑战,我们提出了一种多尺度自注意力语义分割网络,旨在细致识别油茶的语义特征。具体来说,我们引入了自注意机制,使模型能够全面理解特征图像上的信息,然后通过 ASPP(Atrous Spatial Pyramid Pooloing)模块对多尺度特征图像进行整合,以防止忽略次要地形特征。最后,应用 Dice-Loss 函数优化模型对边缘细节的分割。实验评估表明,所提出的多尺度自注意语义分割模型在数据集的油茶提取方面达到了 0.93 的交集大于联合(IOU)、0.98 的像素准确率(PA)和 94.83% 的总体准确率(OA),与原始模型相比有了显著的改进。此外,我们还从数据量和比例的角度探讨了该方法对数据的要求。最终,实验结果表明,我们提出的方法可以高精度地提取中国南方多云多雨丘陵地区的油茶种植区域,从而为农业部门监督油茶种植提供技术手段。
{"title":"MSU-Net: Multi-Scale self-attention semantic segmentation method for oil-tea camellia planting area extraction in hilly areas of southern China","authors":"Zikun Xu ,&nbsp;Hengkai Li ,&nbsp;Beiping Long","doi":"10.1016/j.eswa.2024.125779","DOIUrl":"10.1016/j.eswa.2024.125779","url":null,"abstract":"<div><div>Oil-tea camellia, one of the world’s four major edible woody oil trees, is acclaimed as the ’Oriental Olive Oil’ due to its exceptionally high nutritional value. The climate in southern China synchronizes with the ideal conditions for cultivating oil tea, making it the most abundant region globally in terms of its distribution. Consequently, the delineation of oil tea cultivation zones holds paramount significance for agricultural authorities in devising strategic production plans and management. However, the region is often affected by changeable weather and frequent cloud and rain, and there is a lack of continuous optical image data. Moreover, the complex topography primarily characterized by mountainous terrain, extensive coverage of farmlands, and vegetation has fragmented topographic features, posing challenges in accurately extracting semantic information from remote sensing images. To address these challenges, we propose a multi-scale self-attention semantic segmentation network aimed at meticulously identifying the semantic features of oil tea. Specifically, we introduce a self-attention mechanism to enable the model to comprehensively understand the information on feature images, followed by the integration of multi-scale feature images through the ASPP(Atrous Spatial Pyramid Pooloing) module to prevent the oversight of minor terrain features. Finally, the Dice-Loss function is applied to optimize the model’s segmentation of edge details. Experimental evaluations demonstrate that the proposed multi-scale self-attention semantic segmentation model achieved an Intersection over Union (IOU) of 0.93, Pixel Accuracy (PA) of 0.98, and Overall Accuracy (OA) of 94.83% for oil tea extraction on the dataset, showcasing a notable improvement over the original model. Additionally, we explore the method’s data requirements from the perspective of data volume and proportion. Ultimately, the experimental results demonstrate that our proposed method can accurately extract the oil tea cultivation areas in the cloudy and rainy hilly regions of southern China with high precision, thereby serving as a technological means for agricultural departments to oversee oil tea cultivation.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125779"},"PeriodicalIF":7.5,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662213","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
DAN: Neural network based on dual attention for anomaly detection in ICS DAN:基于双重注意力的神经网络,用于综合监控系统中的异常检测
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-14 DOI: 10.1016/j.eswa.2024.125766
Lijuan Xu , Bailing Wang , Dawei Zhao , Xiaoming Wu
In the interpretability research on anomalies of Industrial Control Systems (ICS) with Graph Convolutional Neural Networks (GCN), the causality between the equipment components is a non-negligible factor. Nonetheless, few existing interpretable anomaly detection methods keeps a good balance of detection and interpretation, because of inadequate insufficient learning of causality and improper representation of nodes in GCN. In this paper, we propose a Dual Attention Network (DAN) for a multivariate time series anomaly detection approach, in which temporal causality based on attention is used for representing the relationship of device components. With this condition, the performance of detection is hardly satisfactory. In addition, in the existing graph neural networks, hyperparameters are used to construct an adjacency matrix, so that the detection accuracy is greatly affected. To address the above problems, we introduce a graph neural network based on an attention mechanism to further learn the causal relationship between device components, and propose an adjacency matrix construction method based on the median, to break through the constraint of hyperparameters. In terms of interpretation and detection effect, the performed experiments using the SWaT and WADI datasets from highly simulated real water plants, demonstrate the validity and universality of the DAN.1
在利用图卷积神经网络(GCN)对工业控制系统(ICS)的异常情况进行可解释性研究时,设备组件之间的因果关系是一个不可忽视的因素。然而,由于对因果关系的学习不足以及 GCN 中节点的表示不当,现有的可解释异常检测方法很少能在检测和解释之间保持良好的平衡。在本文中,我们为多元时间序列异常检测方法提出了一种双注意力网络(DAN),其中基于注意力的时间因果关系被用于表示设备组件的关系。在这种情况下,检测性能很难令人满意。此外,在现有的图神经网络中,超参数用于构建邻接矩阵,因此检测精度受到很大影响。针对上述问题,我们引入了基于注意力机制的图神经网络,进一步学习设备组件之间的因果关系,并提出了基于中值的邻接矩阵构建方法,突破了超参数的限制。在解释和检测效果方面,利用高度模拟真实水厂的 SWaT 和 WADI 数据集进行的实验证明了 DAN 的有效性和普遍性。
{"title":"DAN: Neural network based on dual attention for anomaly detection in ICS","authors":"Lijuan Xu ,&nbsp;Bailing Wang ,&nbsp;Dawei Zhao ,&nbsp;Xiaoming Wu","doi":"10.1016/j.eswa.2024.125766","DOIUrl":"10.1016/j.eswa.2024.125766","url":null,"abstract":"<div><div>In the interpretability research on anomalies of Industrial Control Systems (ICS) with Graph Convolutional Neural Networks (GCN), the causality between the equipment components is a non-negligible factor. Nonetheless, few existing interpretable anomaly detection methods keeps a good balance of detection and interpretation, because of inadequate insufficient learning of causality and improper representation of nodes in GCN. In this paper, we propose a Dual Attention Network (DAN) for a multivariate time series anomaly detection approach, in which temporal causality based on attention is used for representing the relationship of device components. With this condition, the performance of detection is hardly satisfactory. In addition, in the existing graph neural networks, hyperparameters are used to construct an adjacency matrix, so that the detection accuracy is greatly affected. To address the above problems, we introduce a graph neural network based on an attention mechanism to further learn the causal relationship between device components, and propose an adjacency matrix construction method based on the median, to break through the constraint of hyperparameters. In terms of interpretation and detection effect, the performed experiments using the SWaT and WADI datasets from highly simulated real water plants, demonstrate the validity and universality of the DAN.<span><span><sup>1</sup></span></span></div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125766"},"PeriodicalIF":7.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662204","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 reinforcement learning-enhanced multi-objective iterated greedy algorithm for weeding-robot operation scheduling problems 针对除草机器人作业调度问题的强化学习增强型多目标迭代贪婪算法
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-14 DOI: 10.1016/j.eswa.2024.125760
Zhonghua Miao, Hengwei Guo, Quan-ke Pan, Chen Peng, Ziyu Xu
With technological advancements, robots have been widely used in various fields and play a vital role in the production execution system of a smart farm. However, the operation scheduling problem of robots within production execution systems has not received much attention so far. To enable efficient management, this paper develops a multi-objective mathematical model concerning both the efficiency and economic indicators. We propose a population-based iterated greedy algorithm enhanced with Q-learning (Q_DPIG) for a multi-weeding-robots operation scheduling problem. An index-based heuristic (IBH) is designed to generate a diverse set of initial solutions, while an adaptive destruction phase, guided by the Q-learning framework, ensures effective neighborhood search and solution optimization. Additionally, a local search method focusing on the high-load and the critical robots is employed to further optimize the two objectives. Finally, Q_DPIG is demonstrated to be effective and significantly outperform the state-of-the-art algorithms through comprehensive test datasets and a real case study from a farmland management center.
随着技术的进步,机器人已广泛应用于各个领域,并在智能农场的生产执行系统中发挥着重要作用。然而,机器人在生产执行系统中的操作调度问题至今尚未得到广泛关注。为了实现高效管理,本文建立了一个涉及效率和经济指标的多目标数学模型。我们提出了一种基于种群的迭代贪婪算法,并用 Q-learning (Q_DPIG) 对多机器人操作调度问题进行了增强。基于索引的启发式(IBH)旨在生成一组多样化的初始解,而在 Q-learning 框架指导下的自适应破坏阶段确保了有效的邻域搜索和解优化。此外,还采用了一种局部搜索方法,重点关注高负载机器人和关键机器人,以进一步优化这两个目标。最后,通过综合测试数据集和一个农田管理中心的实际案例研究,证明了 Q_DPIG 的有效性,其性能明显优于最先进的算法。
{"title":"A reinforcement learning-enhanced multi-objective iterated greedy algorithm for weeding-robot operation scheduling problems","authors":"Zhonghua Miao,&nbsp;Hengwei Guo,&nbsp;Quan-ke Pan,&nbsp;Chen Peng,&nbsp;Ziyu Xu","doi":"10.1016/j.eswa.2024.125760","DOIUrl":"10.1016/j.eswa.2024.125760","url":null,"abstract":"<div><div>With technological advancements, robots have been widely used in various fields and play a vital role in the production execution system of a smart farm. However, the operation scheduling problem of robots within production execution systems has not received much attention so far. To enable efficient management, this paper develops a multi-objective mathematical model concerning both the efficiency and economic indicators. We propose a population-based iterated greedy algorithm enhanced with Q-learning (Q_DPIG) for a multi-weeding-robots operation scheduling problem. An index-based heuristic (IBH) is designed to generate a diverse set of initial solutions, while an adaptive destruction phase, guided by the Q-learning framework, ensures effective neighborhood search and solution optimization. Additionally, a local search method focusing on the high-load and the critical robots is employed to further optimize the two objectives. Finally, Q_DPIG is demonstrated to be effective and significantly outperform the state-of-the-art algorithms through comprehensive test datasets and a real case study from a farmland management center.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125760"},"PeriodicalIF":7.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662210","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
Scheduling identical parallel machines involving flexible maintenance activities 对涉及灵活维护活动的相同并联机器进行调度
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-14 DOI: 10.1016/j.eswa.2024.125722
Chunhao Li , Feng Wang , Jatinder N.D. Gupta , Tsui-Ping Chung
Motivated by a practical situation in chip manufacturing process, for the first time in the literature, this paper considers an identical parallel-machine scheduling problem with new flexible maintenance activities to minimize makespan where a maintenance activity is needed if and only if the machine capability has deteriorated by a critical value. To address the proposed problem, a mixed integer linear programming model and a lower bound are established. Since this problem is NP-hard, a combined constructive heuristic algorithm with six priority rules is developed. In order to improve the solution obtained by the proposed combined heuristic algorithm, an embedded learning mechanism is combined with the existing artificial immune system (AIS) algorithm to help self-adjust and modify the search direction. The effectiveness of the proposed combined constructive heuristic and the AIS algorithms is empirically tested on the randomly generated problem instances. These computational results show that the proposed AIS algorithm can generate better near-optimal solutions than several adaptations of the existing algorithms.
受芯片制造过程中实际情况的启发,本文在文献中首次考虑了一个相同的并行机器调度问题,该问题具有新的灵活维护活动,以最大限度地缩短生产周期,其中只有当机器能力下降到临界值时才需要进行维护活动。为了解决所提出的问题,本文建立了一个混合整数线性规划模型和一个下限。由于该问题具有 NP 难度,因此开发了一种包含六条优先规则的组合式构造启发式算法。为了改进所提出的组合启发式算法所得到的解,将嵌入式学习机制与现有的人工免疫系统(AIS)算法相结合,以帮助自我调整和修改搜索方向。在随机生成的问题实例上,对所提出的组合式构造启发式算法和 AIS 算法的有效性进行了实证测试。计算结果表明,所提出的 AIS 算法能比现有算法的几种适应性算法生成更好的近优解决方案。
{"title":"Scheduling identical parallel machines involving flexible maintenance activities","authors":"Chunhao Li ,&nbsp;Feng Wang ,&nbsp;Jatinder N.D. Gupta ,&nbsp;Tsui-Ping Chung","doi":"10.1016/j.eswa.2024.125722","DOIUrl":"10.1016/j.eswa.2024.125722","url":null,"abstract":"<div><div>Motivated by a practical situation in chip manufacturing process, for the first time in the literature, this paper considers an identical parallel-machine scheduling problem with new flexible maintenance activities to minimize makespan where a maintenance activity is needed if and only if the machine capability has deteriorated by a critical value. To address the proposed problem, a mixed integer linear programming model and a lower bound are established. Since this problem is NP-hard, a combined constructive heuristic algorithm with six priority rules is developed. In order to improve the solution obtained by the proposed combined heuristic algorithm, an embedded learning mechanism is combined with the existing artificial immune system (AIS) algorithm to help self-adjust and modify the search direction. The effectiveness of the proposed combined constructive heuristic and the AIS algorithms is empirically tested on the randomly generated problem instances. These computational results show that the proposed AIS algorithm can generate better near-optimal solutions than several adaptations of the existing algorithms.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125722"},"PeriodicalIF":7.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662214","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
Prediction and reliability analysis of ultimate axial strength for outer circular CFRP-strengthened CFST columns with CTGAN and hybrid MFO-ET model 利用 CTGAN 和混合 MFO-ET 模型对 CFRP 加固 CFST 外圆柱的极限轴向强度进行预测和可靠性分析
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-13 DOI: 10.1016/j.eswa.2024.125704
Viet-Linh Tran , Jaehong Lee , Jin-Kook Kim
This study develops a novel hybrid machine learning model to estimate the ultimate axial strength and conduct a reliability analysis for outer circular carbon fiber-reinforced polymer (CFRP)-strengthened concrete-filled steel tube (CFST) columns. The experimental datasets are collected and enriched using the conditional tabular generative adversarial network (CTGAN). The column length, the steel properties (cross-section diameter, thickness, and yield strength), the CFRP properties (thickness, tensile strength, and elastic modulus), and concrete strength are selected as input variables to develop the Extra Trees (ET) model hybridized with Moth-Flame Optimization (MFO) algorithm for the ultimate axial strength estimation. The results reveal that the CTGAN can efficiently capture the actual data distribution of CFRP-strengthened CFST columns and the developed hybrid MFO-ET model can accurately predict the ultimate axial strength with a high accuracy (R2 of 0.985, A10 of 0.867, RMSE of 182.810 kN, and MAE of 124.534 kN) based on the synthetic database. In addition, compared with the best empirical model, the MFO-ET model increases the R2 by (6.78% and 13.48%) and A10 by (108.19% and 122.88%) and reduces the RMSE by (68.19% and 66.24%) and MAE by (71.33% and 68.48%) based on real and synthetic databases, respectively. Notably, a reliability analysis is performed to evaluate the safety of the developed MFO-ET model using Monte Carlo Simulation (MCS). Finally, a web application tool is created to make the developed MFO-ET model easier for users to design practical applications.
本研究开发了一种新型混合机器学习模型,用于估算碳纤维增强聚合物(CFRP)加固混凝土填充钢管(CFST)外圆柱的极限轴向强度并进行可靠性分析。实验数据集由条件表格生成式对抗网络(CTGAN)收集和丰富。选择支柱长度、钢材属性(横截面直径、厚度和屈服强度)、CFRP 属性(厚度、抗拉强度和弹性模量)和混凝土强度作为输入变量,开发了与飞蛾-火焰优化算法(MFO)混合的额外树(ET)模型,用于极限轴向强度估算。结果表明,基于合成数据库,CTGAN 可以有效捕捉 CFRP 加固 CFST 柱的实际数据分布,所开发的 MFO-ET 混合模型可以准确预测极限轴向强度,且精度较高(R2 为 0.985,A10 为 0.867,RMSE 为 182.810 kN,MAE 为 124.534 kN)。此外,与最佳经验模型相比,基于真实数据库和合成数据库的 MFO-ET 模型分别提高了 R2(6.78% 和 13.48%)和 A10(108.19% 和 122.88%),降低了 RMSE(68.19% 和 66.24%)和 MAE(71.33% 和 68.48%)。值得注意的是,还利用蒙特卡罗模拟(MCS)进行了可靠性分析,以评估所开发的 MFO-ET 模型的安全性。最后,创建了一个网络应用工具,使开发的 MFO-ET 模型更易于用户设计实际应用。
{"title":"Prediction and reliability analysis of ultimate axial strength for outer circular CFRP-strengthened CFST columns with CTGAN and hybrid MFO-ET model","authors":"Viet-Linh Tran ,&nbsp;Jaehong Lee ,&nbsp;Jin-Kook Kim","doi":"10.1016/j.eswa.2024.125704","DOIUrl":"10.1016/j.eswa.2024.125704","url":null,"abstract":"<div><div>This study develops a novel hybrid machine learning model to estimate the ultimate axial strength and conduct a reliability analysis for outer circular carbon fiber-reinforced polymer (CFRP)-strengthened concrete-filled steel tube (CFST) columns. The experimental datasets are collected and enriched using the conditional tabular generative adversarial network (CTGAN). The column length, the steel properties (cross-section diameter, thickness, and yield strength), the CFRP properties (thickness, tensile strength, and elastic modulus), and concrete strength are selected as input variables to develop the Extra Trees (ET) model hybridized with Moth-Flame Optimization (MFO) algorithm for the ultimate axial strength estimation. The results reveal that the CTGAN can efficiently capture the actual data distribution of CFRP-strengthened CFST columns and the developed hybrid MFO-ET model can accurately predict the ultimate axial strength with a high accuracy (R<sup>2</sup> of 0.985, A10 of 0.867, RMSE of 182.810 kN, and MAE of 124.534 kN) based on the synthetic database. In addition, compared with the best empirical model, the MFO-ET model increases the R<sup>2</sup> by (6.78% and 13.48%) and A10 by (108.19% and 122.88%) and reduces the RMSE by (68.19% and 66.24%) and MAE by (71.33% and 68.48%) based on real and synthetic databases, respectively. Notably, a reliability analysis is performed to evaluate the safety of the developed MFO-ET model using Monte Carlo Simulation (MCS). Finally, a web application tool is created to make the developed MFO-ET model easier for users to design practical applications.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125704"},"PeriodicalIF":7.5,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662275","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
Segment Anything Model for fetal head-pubic symphysis segmentation in intrapartum ultrasound image analysis 用于产前超声图像分析中胎儿头-耻骨联合分割的 "任何分割 "模型
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-12 DOI: 10.1016/j.eswa.2024.125699
Zihao Zhou , Yaosheng Lu , Jieyun Bai , Víctor M. Campello , Fan Feng , Karim Lekadir
The Angle of Progression (AoP), determined by the contour delineations of the pubic symphysis and fetal head (PSFH) in intrapartum ultrasound (US) images, is crucial for predicting delivery mode and significantly influences labor outcomes. However, automating AoP measurement based on PSFH segmentation remains challenging due to poor foreground-background contrast, blurred boundaries, and anatomical variability in shapes, sizes, and positions during labor. We propose a novel Segment Anything Model (SAM) framework, AoP-SAM, designed to enhance the PSFH segmentation, AoP measurement and outcome prediction, tackling the challenges of small target segmentation and accurate boundary segmentation. It synergistically combines CNNs and Transformers within a cooperative encoder to process complex spatial relationships and contextual information to segment the PSFH. In this encoder, we devise a multi-scale CNN branch to capture intrinsic local details, which compensates for the defects of the Transformer branch in extracting local features. Further, a cross-branch attention module is applied to improve prediction by fostering the effective information exchange and integration between two branches. Evaluations on the benchmark dataset demonstrate that our method achieves state-of-the-art (SOTA) performance. Specifically, in the PSFH segmentation task, the AoP measurement task, and the AoP classification task, we achieved a DSC of 0.8745 on the PS structure, a ΔAoP of 7.6743°, and an F1-score of 0.7719, respectively. Compared to the second-ranking method, these results represent improvements of 2.5%, 6.3%, and 1.1%. Our study presents a framework for intrapartum biometry, offering significant advancements in labor monitoring and delivery mode prediction in clinical settings. Future efforts will focus on optimizing AoP-SAM for resource-constrained environments, highlighting its potential for lightweight adaptation. https://github.com/maskoffs/AoP-SAM.
耻骨联合和胎头(PSFH)在产前超声(US)图像中的轮廓划分决定了产程进展角(AoP),它对预测分娩方式至关重要,并对分娩结果有重大影响。然而,由于前景-背景对比度差、边界模糊以及分娩过程中形状、大小和位置的解剖变异,基于 PSFH 分割的 AoP 自动测量仍具有挑战性。我们提出了一种新颖的 "任意分割模型"(Segment Anything Model,SAM)框架,即 AoP-SAM,旨在增强 PSFH 分割、AoP 测量和结果预测,解决小目标分割和精确边界分割的难题。它将 CNN 和变换器协同结合到一个合作编码器中,以处理复杂的空间关系和上下文信息,从而分割 PSFH。在该编码器中,我们设计了一个多尺度 CNN 分支来捕捉固有的局部细节,从而弥补了 Transformer 分支在提取局部特征方面的缺陷。此外,我们还应用了跨分支关注模块,通过促进两个分支之间的有效信息交换和整合来改进预测。在基准数据集上进行的评估表明,我们的方法达到了最先进(SOTA)的性能。具体来说,在 PSFH 分割任务、AoP 测量任务和 AoP 分类任务中,我们在 PS 结构上分别取得了 0.8745 的 DSC 值、7.6743° 的 ΔAoP 值和 0.7719 的 F1 分数。与二级排序法相比,这些结果分别提高了 2.5%、6.3% 和 1.1%。我们的研究提出了产中生物测量的框架,为临床环境中的产程监测和分娩方式预测提供了重大进展。未来的工作重点是针对资源有限的环境优化 AoP-SAM,突出其轻量级适应的潜力。https://github.com/maskoffs/AoP-SAM。
{"title":"Segment Anything Model for fetal head-pubic symphysis segmentation in intrapartum ultrasound image analysis","authors":"Zihao Zhou ,&nbsp;Yaosheng Lu ,&nbsp;Jieyun Bai ,&nbsp;Víctor M. Campello ,&nbsp;Fan Feng ,&nbsp;Karim Lekadir","doi":"10.1016/j.eswa.2024.125699","DOIUrl":"10.1016/j.eswa.2024.125699","url":null,"abstract":"<div><div>The Angle of Progression (AoP), determined by the contour delineations of the pubic symphysis and fetal head (PSFH) in intrapartum ultrasound (US) images, is crucial for predicting delivery mode and significantly influences labor outcomes. However, automating AoP measurement based on PSFH segmentation remains challenging due to poor foreground-background contrast, blurred boundaries, and anatomical variability in shapes, sizes, and positions during labor. We propose a novel Segment Anything Model (SAM) framework, AoP-SAM, designed to enhance the PSFH segmentation, AoP measurement and outcome prediction, tackling the challenges of small target segmentation and accurate boundary segmentation. It synergistically combines CNNs and Transformers within a cooperative encoder to process complex spatial relationships and contextual information to segment the PSFH. In this encoder, we devise a multi-scale CNN branch to capture intrinsic local details, which compensates for the defects of the Transformer branch in extracting local features. Further, a cross-branch attention module is applied to improve prediction by fostering the effective information exchange and integration between two branches. Evaluations on the benchmark dataset demonstrate that our method achieves state-of-the-art (SOTA) performance. Specifically, in the PSFH segmentation task, the AoP measurement task, and the AoP classification task, we achieved a DSC of 0.8745 on the PS structure, a <span><math><mi>Δ</mi></math></span>AoP of 7.6743°, and an F1-score of 0.7719, respectively. Compared to the second-ranking method, these results represent improvements of 2.5%, 6.3%, and 1.1%. Our study presents a framework for intrapartum biometry, offering significant advancements in labor monitoring and delivery mode prediction in clinical settings. Future efforts will focus on optimizing AoP-SAM for resource-constrained environments, highlighting its potential for lightweight adaptation. <span><span>https://github.com/maskoffs/AoP-SAM</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125699"},"PeriodicalIF":7.5,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662273","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 multi teacher knowledge distillation for semantic parsing in KBQA 在 KBQA 中进行语义解析的动态多教师知识提炼
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-12 DOI: 10.1016/j.eswa.2024.125599
Ao Zou , Jun Zou , Shulin Cao , Jiajie Zhang , Jinxin Liu , Jing Wan , Lei Hou
Knowledge base question answering (KBQA) is an important task of extracting answers from a knowledge base by analyzing natural language questions. Semantic parsing methods convert natural language questions into executable logical forms to obtain answers on the knowledge base. Conventional approaches often prioritize singular logical forms, overlooking the distinct strengths inherent in various logical frameworks for problem solving. Recognizing that different logical forms may excel in addressing specific types of questions, our aim is to harness these strengths. By integrating the strengths of different logical forms, we expect to achieve more comprehensive and effective semantic parsing solutions. In our paper, we propose a Dynamic Multi Teacher Knowledge Distillation for Semantic Parsing (DMTKD-SP). DMTKD-SP leverages a collection of teacher models, each mastering a unique logical form, to collaboratively guide a student model so that knowledge from different logical forms can be transferred into the student model. To achieve this, we employ a confidence-based weight assignment module to dynamically assign weights for each teacher model. Furthermore, we introduce a self-distillation mechanism to mitigate the confusion caused by simultaneous learning from multiple teachers. We evaluate DMTKD-SP across variants of the KQA Pro dataset, demonstrating an accuracy improvement of 0.35% on five types of questions, with a notable 0.75% improvement for Count questions.
知识库问题解答(KBQA)是通过分析自然语言问题从知识库中提取答案的一项重要任务。语义解析方法将自然语言问题转换为可执行的逻辑形式,从而获得知识库中的答案。传统方法往往优先考虑单一的逻辑形式,而忽视了解决问题的各种逻辑框架所固有的独特优势。我们认识到不同的逻辑形式在解决特定类型的问题时可能会表现出色,因此我们的目标是利用这些优势。通过整合不同逻辑形式的优势,我们有望实现更全面、更有效的语义解析解决方案。在本文中,我们提出了用于语义解析的动态多教师知识蒸馏(DMTKD-SP)。DMTKD-SP 利用教师模型集合(每个模型都掌握一种独特的逻辑形式)协同指导学生模型,从而将不同逻辑形式的知识转移到学生模型中。为此,我们采用了基于置信度的权重分配模块,为每个教师模型动态分配权重。此外,我们还引入了一种自我蒸馏机制,以减轻同时向多个教师学习所造成的混乱。我们在 KQA Pro 数据集的各种变体中对 DMTKD-SP 进行了评估,结果表明它在五种类型的问题上提高了 0.35% 的准确率,其中计数问题的准确率显著提高了 0.75%。
{"title":"Dynamic multi teacher knowledge distillation for semantic parsing in KBQA","authors":"Ao Zou ,&nbsp;Jun Zou ,&nbsp;Shulin Cao ,&nbsp;Jiajie Zhang ,&nbsp;Jinxin Liu ,&nbsp;Jing Wan ,&nbsp;Lei Hou","doi":"10.1016/j.eswa.2024.125599","DOIUrl":"10.1016/j.eswa.2024.125599","url":null,"abstract":"<div><div>Knowledge base question answering (KBQA) is an important task of extracting answers from a knowledge base by analyzing natural language questions. Semantic parsing methods convert natural language questions into executable logical forms to obtain answers on the knowledge base. Conventional approaches often prioritize singular logical forms, overlooking the distinct strengths inherent in various logical frameworks for problem solving. Recognizing that different logical forms may excel in addressing specific types of questions, our aim is to harness these strengths. By integrating the strengths of different logical forms, we expect to achieve more comprehensive and effective semantic parsing solutions. In our paper, we propose a Dynamic Multi Teacher Knowledge Distillation for Semantic Parsing (DMTKD-SP). DMTKD-SP leverages a collection of teacher models, each mastering a unique logical form, to collaboratively guide a student model so that knowledge from different logical forms can be transferred into the student model. To achieve this, we employ a confidence-based weight assignment module to dynamically assign weights for each teacher model. Furthermore, we introduce a self-distillation mechanism to mitigate the confusion caused by simultaneous learning from multiple teachers. We evaluate DMTKD-SP across variants of the KQA Pro dataset, demonstrating an accuracy improvement of 0.35% on five types of questions, with a notable 0.75% improvement for Count questions.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125599"},"PeriodicalIF":7.5,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662186","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 cross-domain recommendations: Leveraging personality-based transfer learning with probabilistic matrix factorization 加强跨领域推荐:利用概率矩阵因式分解进行基于个性的迁移学习
IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-11-12 DOI: 10.1016/j.eswa.2024.125667
Somdeep Acharyya, Nargis Pervin
The conventional method of computing personality scores through extensive questionnaire-based surveys poses practical challenges in real-world scenarios. An alternate route is to predict personality scores from user reviews by analysing various linguistic features such as writing style, word choices, and specific phrases. However, the reviews are domain-dependent and classification models trained on one domain cannot be readily applied to other domains. To mitigate this challenge, we propose a cross-domain recommendation framework called PEMF-CD which leverages a novel mixing strategy to integrate user reviews from multiple domains with common joint embedding space and predict user personality scores using a transformer model. By capturing the underlying semantics and latent representations within the textual data, the transformer architecture can effectively model the linguistic cues to infer users’ personality traits, and the learning is transferred across domains. To further enhance the recommendation process, our model integrates personality-wise and rating pattern-based similarities of users into a probabilistic matrix factorization method that fosters user neighbourhoods based on similarity scores among users. Comprehensive experiments were conducted using five real-world datasets from TripAdvisor and Amazon with varied numbers of users, items, and reviews of up to 44,187, 26,386, and 426,791, respectively. The performance has been benchmarked against thirteen baseline algorithms and the experimental results demonstrate a significant improvements of up to 24.72%, 64.28%, 48.79%, and 61% in RMSE, and 55.9%, 76.7%, 67.6%, and 71.5% in MAE for a 90:10 train–test split with Digital Music, Fashion, Magazine Subscriptions and Video Games datasets from Amazon, respectively. Similar results have been observed for the 80:20 train–test split.
在现实世界中,通过大量问卷调查计算个性分数的传统方法面临着实际挑战。另一种方法是通过分析各种语言特征(如写作风格、用词选择和特定短语),从用户评论中预测个性分数。然而,评论是与领域相关的,在一个领域训练的分类模型不能轻易应用到其他领域。为了缓解这一难题,我们提出了一个名为 PEMF-CD 的跨领域推荐框架,该框架利用新颖的混合策略,将来自多个领域的用户评论与共同的联合嵌入空间整合在一起,并使用转换器模型预测用户个性得分。通过捕捉文本数据中的底层语义和潜在表征,转换器架构可以有效地对语言线索进行建模,从而推断出用户的个性特征,并且这种学习可以跨领域转移。为了进一步加强推荐过程,我们的模型将用户的个性特征和基于评分模式的相似性整合到概率矩阵因式分解方法中,根据用户之间的相似性得分建立用户邻域。我们使用 TripAdvisor 和亚马逊的五个真实数据集进行了综合实验,这些数据集的用户数、项目数和评论数分别高达 44,187 条、26,386 条和 426,791 条。实验结果表明,在亚马逊的数字音乐、时尚、杂志订阅和视频游戏数据集上,训练-测试比例为 90:10,RMSE 分别提高了 24.72%、64.28%、48.79% 和 61%,MAE 分别提高了 55.9%、76.7%、67.6% 和 71.5%。在训练-测试比例为 80:20 的情况下,也观察到了类似的结果。
{"title":"Enhancing cross-domain recommendations: Leveraging personality-based transfer learning with probabilistic matrix factorization","authors":"Somdeep Acharyya,&nbsp;Nargis Pervin","doi":"10.1016/j.eswa.2024.125667","DOIUrl":"10.1016/j.eswa.2024.125667","url":null,"abstract":"<div><div>The conventional method of computing personality scores through extensive questionnaire-based surveys poses practical challenges in real-world scenarios. An alternate route is to predict personality scores from user reviews by analysing various linguistic features such as writing style, word choices, and specific phrases. However, the reviews are domain-dependent and classification models trained on one domain cannot be readily applied to other domains. To mitigate this challenge, we propose a cross-domain recommendation framework called PEMF-CD which leverages a novel mixing strategy to integrate user reviews from multiple domains with common joint embedding space and predict user personality scores using a transformer model. By capturing the underlying semantics and latent representations within the textual data, the transformer architecture can effectively model the linguistic cues to infer users’ personality traits, and the learning is transferred across domains. To further enhance the recommendation process, our model integrates personality-wise and rating pattern-based similarities of users into a probabilistic matrix factorization method that fosters user neighbourhoods based on similarity scores among users. Comprehensive experiments were conducted using five real-world datasets from TripAdvisor and Amazon with varied numbers of users, items, and reviews of up to 44,187, 26,386, and 426,791, respectively. The performance has been benchmarked against thirteen baseline algorithms and the experimental results demonstrate a significant improvements of up to 24.72%, 64.28%, 48.79%, and 61% in RMSE, and 55.9%, 76.7%, 67.6%, and 71.5% in MAE for a 90:10 train–test split with Digital Music, Fashion, Magazine Subscriptions and Video Games datasets from Amazon, respectively. Similar results have been observed for the 80:20 train–test split.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125667"},"PeriodicalIF":7.5,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662278","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
期刊
Expert Systems with Applications
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
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
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1