Pub Date : 2024-11-04DOI: 10.1016/j.eswa.2024.125685
Xu Zhao , Yuhan Guo , Yiyang Wang , Meirong Wang
This paper presents a novel model designed to predict the vessel speed, specifically tailored to tackle the challenges posed by incomplete information of relevant operating parameters encountered in certain scenarios. In this method, a latent trend in the operating state of marine power system is firstly identified from historical time-series data to approximate the calm water speed information. Then, the modeling of the remaining component, which corresponds to the met-ocean-induced speed loss, can be more precisely targeted. Moreover, the elements situated at diverse temporal scales of the remaining component are disentangled, aiming to resolve the intricacies of coupled factor learning, thus improving the accuracy and validity of the model. For time-series with relatively steady-state, an LSTM network with a global attention mechanism is proposed to effectively capture the temporal evolution, and a differencing operation is incorporated to mitigate potential data inconsistencies between voyages. Finally, the proposed framework has demonstrated superior predictive capabilities for speed compared to a variety of data-driven methods, using a 400,000 DWT ore carrier as an example.
{"title":"Vessel speed prediction using latent-invariant transforms in the presence of incomplete information","authors":"Xu Zhao , Yuhan Guo , Yiyang Wang , Meirong Wang","doi":"10.1016/j.eswa.2024.125685","DOIUrl":"10.1016/j.eswa.2024.125685","url":null,"abstract":"<div><div>This paper presents a novel model designed to predict the vessel speed, specifically tailored to tackle the challenges posed by incomplete information of relevant operating parameters encountered in certain scenarios. In this method, a latent trend in the operating state of marine power system is firstly identified from historical time-series data to approximate the calm water speed information. Then, the modeling of the remaining component, which corresponds to the met-ocean-induced speed loss, can be more precisely targeted. Moreover, the elements situated at diverse temporal scales of the remaining component are disentangled, aiming to resolve the intricacies of coupled factor learning, thus improving the accuracy and validity of the model. For time-series with relatively steady-state, an LSTM network with a global attention mechanism is proposed to effectively capture the temporal evolution, and a differencing operation is incorporated to mitigate potential data inconsistencies between voyages. Finally, the proposed framework has demonstrated superior predictive capabilities for speed compared to a variety of data-driven methods, using a 400,000 DWT ore carrier as an example.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125685"},"PeriodicalIF":7.5,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662847","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}
Pub Date : 2024-11-04DOI: 10.1016/j.eswa.2024.125643
Md. Rajib Hossain , Mohammed Moshiul Hoque , M. Ali Akber Dewan , Enamul Hoque , Nazmul Siddique
Authorship Attribution (AA) is crucial for identifying the author of a given text from a pool of suspects, especially with the widespread use of the internet and electronic devices. However, most AA research has primarily focused on high-resource languages like English, leaving low-resource languages such as Bengali relatively unexplored. Challenges faced in this domain include the absence of benchmark corpora, a lack of context-aware feature extractors, limited availability of tuned hyperparameters, and OOV issues. To address these challenges, this study introduces AuthorNet for authorship attribution using attention-based early fusion of transformer-based language models, i.e., concatenation of an embeddings output of two existing models that were fine-tuned. AuthorNet consists of three key modules: Feature extraction, Fine-tuning and selection of best-performing models, and Attention-based early fusion. To evaluate the performance of AuthorNet, a number of experiments using four benchmark corpora have been conducted. The results demonstrated exceptional accuracy: 98.86 ± 0.01%, 99.49 ± 0.01%, 97.91 ± 0.01%, and 99.87 ± 0.01% for four corpora. Notably, AuthorNet outperformed all foundation models, achieving accuracy improvements ranging from 0.24% to 2.92% across the four corpora.
{"title":"AuthorNet: Leveraging attention-based early fusion of transformers for low-resource authorship attribution","authors":"Md. Rajib Hossain , Mohammed Moshiul Hoque , M. Ali Akber Dewan , Enamul Hoque , Nazmul Siddique","doi":"10.1016/j.eswa.2024.125643","DOIUrl":"10.1016/j.eswa.2024.125643","url":null,"abstract":"<div><div>Authorship Attribution (AA) is crucial for identifying the author of a given text from a pool of suspects, especially with the widespread use of the internet and electronic devices. However, most AA research has primarily focused on high-resource languages like English, leaving low-resource languages such as Bengali relatively unexplored. Challenges faced in this domain include the absence of benchmark corpora, a lack of context-aware feature extractors, limited availability of tuned hyperparameters, and OOV issues. To address these challenges, this study introduces AuthorNet for authorship attribution using attention-based early fusion of transformer-based language models, i.e., concatenation of an embeddings output of two existing models that were fine-tuned. AuthorNet consists of three key modules: Feature extraction, Fine-tuning and selection of best-performing models, and Attention-based early fusion. To evaluate the performance of AuthorNet, a number of experiments using four benchmark corpora have been conducted. The results demonstrated exceptional accuracy: 98.86 ± 0.01%, 99.49 ± 0.01%, 97.91 ± 0.01%, and 99.87 ± 0.01% for four corpora. Notably, AuthorNet outperformed all foundation models, achieving accuracy improvements ranging from 0.24% to 2.92% across the four corpora.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125643"},"PeriodicalIF":7.5,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662850","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}
Deep learning techniques in electronic surveillance have shown impressive performance for super-resolution (SR) of captured low-quality face images. Most of these techniques adopt facial priors to improve the feature details in the resultant super-resolved images. However, the estimation of facial priors from the captured low-quality images is often inaccurate in real-life situations because of their tiny, noisy, and blurry nature. Thus, the fusion of such priors badly affects the performance of these models. Therefore, this work presents a teacher–student-based face SR framework that efficiently preserves the personal facial structure information in the super-resolved faces. In the proposed framework, the teacher network exploits the facial heatmap-based ground-truth-prior to learn the facial structure that is utilized by the student network. The student network is trained with the identity feature loss for maintaining the identity and facial structure information in reconstructed high-resolution (HR) face images. The performance of the proposed framework is evaluated by conducting the experimental study on standard datasets namely CelebA-HQ and LFW face. The experimental results reveal that the proposed technique conquers the existing methods for the face SR task.
电子监控领域的深度学习技术在对捕捉到的低质量人脸图像进行超分辨率（SR）处理方面表现出令人印象深刻的性能。这些技术大多采用面部先验来改善超分辨率图像中的特征细节。然而，在现实生活中，由于拍摄到的低质量图像微小、嘈杂、模糊，因此从这些图像中估算出的面部先验值往往并不准确。因此，融合这些前验会严重影响这些模型的性能。因此，本研究提出了一种基于教师-学生的人脸 SR 框架，它能有效保留超分辨率人脸中的个人面部结构信息。在所提出的框架中，教师网络利用基于面部热图的地面实况先验来学习面部结构，学生网络则利用这些先验来学习面部结构。学生网络通过身份特征损失进行训练，以保持重建的高分辨率（HR）人脸图像中的身份和面部结构信息。通过在标准数据集（即 CelebA-HQ 和 LFW 人脸）上进行实验研究，对所提出框架的性能进行了评估。实验结果表明，在人脸 SR 任务中，所提出的技术战胜了现有的方法。
{"title":"Learning face super-resolution through identity features and distilling facial prior knowledge","authors":"Anurag Singh Tomar , K.V. Arya , Shyam Singh Rajput","doi":"10.1016/j.eswa.2024.125625","DOIUrl":"10.1016/j.eswa.2024.125625","url":null,"abstract":"<div><div>Deep learning techniques in electronic surveillance have shown impressive performance for super-resolution (SR) of captured low-quality face images. Most of these techniques adopt facial priors to improve the feature details in the resultant super-resolved images. However, the estimation of facial priors from the captured low-quality images is often inaccurate in real-life situations because of their tiny, noisy, and blurry nature. Thus, the fusion of such priors badly affects the performance of these models. Therefore, this work presents a teacher–student-based face SR framework that efficiently preserves the personal facial structure information in the super-resolved faces. In the proposed framework, the teacher network exploits the facial heatmap-based ground-truth-prior to learn the facial structure that is utilized by the student network. The student network is trained with the identity feature loss for maintaining the identity and facial structure information in reconstructed high-resolution (HR) face images. The performance of the proposed framework is evaluated by conducting the experimental study on standard datasets namely CelebA-HQ and LFW face. The experimental results reveal that the proposed technique conquers the existing methods for the face SR task.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125625"},"PeriodicalIF":7.5,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578464","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}
Pub Date : 2024-11-04DOI: 10.1016/j.eswa.2024.125640
Svenja Bergmann , Stefan Feuerriegel
Millions of used cars are sold every year, and, hence, accurate estimates of resale values are needed. One reason is that under- and overestimating the value of used cars at the end of their leasing period is directly related to the financial return of car retailers. However, in previous literature, granular vehicle equipment information (e.g., alloy rims, park assistance systems) as a predictor has been largely overlooked. In order to address this research gap, we assess the predictive power of granular information about vehicle equipment when forecasting the resale value of used cars. To achieve this, we first preprocess 50,000 equipment options through a tailored, end-to-end automated procedure. Subsequently, we employ machine learning using a comprehensive real-world dataset comprising 92,239 sales where each vehicle is characterized by a unique equipment configuration. We find that including equipment information improves the prediction performance (i.e., mean absolute error) by 3.27% and at a statistically significant level. Altogether, car retailers can use information about the specific vehicle configuration to more accurately predict prices of used vehicles, and, as an implication for businesses, this may eventually increase returns.
{"title":"Machine learning for predicting used car resale prices using granular vehicle equipment information","authors":"Svenja Bergmann , Stefan Feuerriegel","doi":"10.1016/j.eswa.2024.125640","DOIUrl":"10.1016/j.eswa.2024.125640","url":null,"abstract":"<div><div>Millions of used cars are sold every year, and, hence, accurate estimates of resale values are needed. One reason is that under- and overestimating the value of used cars at the end of their leasing period is directly related to the financial return of car retailers. However, in previous literature, granular vehicle equipment information (e.g., alloy rims, park assistance systems) as a predictor has been largely overlooked. In order to address this research gap, we assess the predictive power of granular information about vehicle equipment when forecasting the resale value of used cars. To achieve this, we first preprocess 50,000 equipment options through a tailored, end-to-end automated procedure. Subsequently, we employ machine learning using a comprehensive real-world dataset comprising 92,239 sales where each vehicle is characterized by a unique equipment configuration. We find that including equipment information improves the prediction performance (i.e., mean absolute error) by 3.27% and at a statistically significant level. Altogether, car retailers can use information about the specific vehicle configuration to more accurately predict prices of used vehicles, and, as an implication for businesses, this may eventually increase returns.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"263 ","pages":"Article 125640"},"PeriodicalIF":7.5,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662113","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}
Pub Date : 2024-11-04DOI: 10.1016/j.eswa.2024.125696
Rubén Muñoz Pavón , Marcos García Alberti , Antonio Alfonso Arcos Álvarez , Jorge Jerez Cepa
Innovation and digitalization are outstanding topics acquiring each day more importance for local governments, especially in Facility Management sector. Moreover, during the COVID-19 situation, new management needs emerged, especially in large public buildings. Building Information Modeling (BIM) is considered as one of the emerging technologies used to reach a total digitalization of the infrastructure. Nevertheless, BIM implementation carries important barriers with itself like, high software and hardware investments, initial BIM skills training or low data interoperability. The objective of this project is to overpass those implementation barriers. For this purpose, the paper shows the creation of a BIM-based intelligent platform for infrastructure management that leads to the development of a Digital Twin (DT). To show the potential of the software developed, a real implementation in the Civil Engineering School at Universidad Politécnica de Madrid was carried out, obtaining significant results thanks to the actual feedback of infrastructure users and managers. The novelty of this project relies on the final results achieved, obtaining a complete DT for management functionalities like space reservation, live sensors data or assets management. All of it, linking BIM models with own software and hardware development using Internet of Things and cloud computing. A multidisciplinary work is compiled in this paper, providing the reader with the most relevant challenges detected in a real digitalization process.
{"title":"Bim-based Digital Twin development for university Campus management. Case study ETSICCP","authors":"Rubén Muñoz Pavón , Marcos García Alberti , Antonio Alfonso Arcos Álvarez , Jorge Jerez Cepa","doi":"10.1016/j.eswa.2024.125696","DOIUrl":"10.1016/j.eswa.2024.125696","url":null,"abstract":"<div><div>Innovation and digitalization are outstanding topics acquiring each day more importance for local governments, especially in Facility Management sector. Moreover, during the COVID-19 situation, new management needs emerged, especially in large public buildings. Building Information Modeling (BIM) is considered as one of the emerging technologies used to reach a total digitalization of the infrastructure. Nevertheless, BIM implementation carries important barriers with itself like, high software and hardware investments, initial BIM skills training or low data interoperability. The objective of this project is to overpass those implementation barriers. For this purpose, the paper shows the creation of a BIM-based intelligent platform for infrastructure management that leads to the development of a Digital Twin (DT). To show the potential of the software developed, a real implementation in the Civil Engineering School at Universidad Politécnica de Madrid was carried out, obtaining significant results thanks to the actual feedback of infrastructure users and managers. The novelty of this project relies on the final results achieved, obtaining a complete DT for management functionalities like space reservation, live sensors data or assets management. All of it, linking BIM models with own software and hardware development using Internet of Things and cloud computing. A multidisciplinary work is compiled in this paper, providing the reader with the most relevant challenges detected in a real digitalization process.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125696"},"PeriodicalIF":7.5,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662778","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}
Pub Date : 2024-11-03DOI: 10.1016/j.eswa.2024.125661
Behnam Yousefimehr, Mehdi Ghatee
Fraud detection is a challenging task that can be difficult to carry out. To address these challenges, a comprehensive framework has been developed which includes a new resampling method combined with a data-dependent classifier that can detect fraud effectively. The proposed framework uses two hybrid approaches that leverage the strengths of a One-Class Support Vector Machine (OCSVM) with the Synthetic Minority Oversampling Technique (SMOTE) and random undersampling. The distribution of fraud instances is effectively preserved by this innovative framework. The comparison of the probability functions of fraud data before and after resampling is demonstrated, indeed. Afterward, The outputs of our hybrid approaches are analyzed using two distinct models, the Light Gradient-Boosting Machine (LightGBM) and the Long Short-Term Memory (LSTM) model. Our case study on European credit cards has consistently demonstrated the effectiveness of our techniques over existing methods, achieving a high F1 score of 87% with a corresponding AUC score of 96% in non-sequential fraud detection and The F1 score of 85% with an AUC score of 87% in sequential fraud detection. Additionally, we have developed an innovative algorithm for determining optimal window sizes for sequence-wise fraud analysis, which recommends window sizes of 3 for the European dataset, highlighting the efficacy of sequence-wise analysis. Overall, the proposed framework, not only offers a promising solution to enhance fraud detection accuracy, but it also reduces false positives.
欺诈检测是一项具有挑战性的任务，执行起来有一定难度。为了应对这些挑战，我们开发了一个综合框架，其中包括一种新的重采样方法，结合一种能有效检测欺诈行为的数据依赖分类器。所提出的框架采用了两种混合方法，充分利用了单类支持向量机（OCSVM）与合成少数群体过采样技术（SMOTE）和随机欠采样的优势。这一创新框架有效地保留了欺诈实例的分布。重采样前后欺诈数据概率函数的比较得到了证实。随后，我们使用两种不同的模型--光梯度提升机（LightGBM）和长短期记忆（LSTM）模型--分析了混合方法的输出结果。我们对欧洲信用卡的案例研究持续证明了我们的技术优于现有方法的有效性，在非序列欺诈检测中取得了 87% 的高 F1 分数和 96% 的相应 AUC 分数，在序列欺诈检测中取得了 85% 的 F1 分数和 87% 的 AUC 分数。此外，我们还开发了一种创新算法，用于确定序列欺诈分析的最佳窗口大小，该算法建议欧洲数据集的窗口大小为 3，突出了序列分析的功效。总之，所提出的框架不仅为提高欺诈检测的准确性提供了一个有前途的解决方案，而且还能减少误报。
{"title":"A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions","authors":"Behnam Yousefimehr, Mehdi Ghatee","doi":"10.1016/j.eswa.2024.125661","DOIUrl":"10.1016/j.eswa.2024.125661","url":null,"abstract":"<div><div>Fraud detection is a challenging task that can be difficult to carry out. To address these challenges, a comprehensive framework has been developed which includes a new resampling method combined with a data-dependent classifier that can detect fraud effectively. The proposed framework uses two hybrid approaches that leverage the strengths of a One-Class Support Vector Machine (OCSVM) with the Synthetic Minority Oversampling Technique (SMOTE) and random undersampling. The distribution of fraud instances is effectively preserved by this innovative framework. The comparison of the probability functions of fraud data before and after resampling is demonstrated, indeed. Afterward, The outputs of our hybrid approaches are analyzed using two distinct models, the Light Gradient-Boosting Machine (LightGBM) and the Long Short-Term Memory (LSTM) model. Our case study on European credit cards has consistently demonstrated the effectiveness of our techniques over existing methods, achieving a high F1 score of 87% with a corresponding AUC score of 96% in non-sequential fraud detection and The F1 score of 85% with an AUC score of 87% in sequential fraud detection. Additionally, we have developed an innovative algorithm for determining optimal window sizes for sequence-wise fraud analysis, which recommends window sizes of 3 for the European dataset, highlighting the efficacy of sequence-wise analysis. Overall, the proposed framework, not only offers a promising solution to enhance fraud detection accuracy, but it also reduces false positives.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125661"},"PeriodicalIF":7.5,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662815","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}
Pub Date : 2024-11-03DOI: 10.1016/j.eswa.2024.125674
Marcelo Vasconcelos , Luís Cavique
Imbalanced datasets present a challenge in machine learning, especially in binary classification scenarios where one class significantly outweighs the other. This imbalance often leads to models favoring the majority class, resulting in inadequate predictions for the minority class, specifically in false negatives. In response to this issue, this work introduces the MinFNR ensemble algorithm, designed to minimize False Negative Rates (FNR) in imbalanced datasets. The new approach strategically combines data-level, algorithmic-level, and hybrid-level approaches to enhance overall predictive capabilities while minimizing computational resources using the Set Covering Problem (SCP) formulation. Through a comprehensive evaluation of diverse datasets, MinFNR consistently outperforms individual algorithms, showing its potential for applications where the cost of false negatives is substantial, such as fraud detection and medical diagnosis. This work also contributes to ongoing efforts to improve the reliability and effectiveness of machine learning algorithms in real imbalanced scenarios.
{"title":"Mitigating false negatives in imbalanced datasets: An ensemble approach","authors":"Marcelo Vasconcelos , Luís Cavique","doi":"10.1016/j.eswa.2024.125674","DOIUrl":"10.1016/j.eswa.2024.125674","url":null,"abstract":"<div><div>Imbalanced datasets present a challenge in machine learning, especially in binary classification scenarios where one class significantly outweighs the other. This imbalance often leads to models favoring the majority class, resulting in inadequate predictions for the minority class, specifically in false negatives. In response to this issue, this work introduces the MinFNR ensemble algorithm, designed to minimize False Negative Rates (FNR) in imbalanced datasets. The new approach strategically combines data-level, algorithmic-level, and hybrid-level approaches to enhance overall predictive capabilities while minimizing computational resources using the Set Covering Problem (SCP) formulation. Through a comprehensive evaluation of diverse datasets, MinFNR consistently outperforms individual algorithms, showing its potential for applications where the cost of false negatives is substantial, such as fraud detection and medical diagnosis. This work also contributes to ongoing efforts to improve the reliability and effectiveness of machine learning algorithms in real imbalanced scenarios.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125674"},"PeriodicalIF":7.5,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662818","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}
Pub Date : 2024-11-03DOI: 10.1016/j.eswa.2024.125662
Bowen Gong , Binwen Zhao , Yue Wang , Ciyun Lin , Hongchao Liu
High-precision and consistent vehicle trajectories encompass microscopic traffic parameters, mesoscopic traffic flow characteristics, and macroscopic traffic flow features, which is the cornerstone of innovation in data-driven traffic management and control applications. However, occlusion and trajectory interruption remain challenging in multivehicle tracking under complex traffic environments using low-channel roadside LiDAR. To address the challenge, a novel framework for vehicle trajectory extraction using low-channel roadside LiDAR was proposed. First, the geometric features of the cluster and its L-shape bounding box were used to address the over-segmentation in vehicle detection arising from occlusion and point cloud sparse. Then, objects within adjacent point cloud frames were associated by developing an improved Hungarian algorithm integrated with an adaptive distance threshold to solve the mismatching problem caused by objects entrancing and exiting in a new point cloud frame. Finally, an improved interacting multiple model by considering vehicle driving patterns was deployed to predict the location of missing vehicles and connect the interrupted trajectories. Experimental results showed that the proposed methods achieve 98.76 % of vehicle detection accuracy and 97.40 % of data association precision. The mean absolute error (MAE) and mean square error (MSE) of the vehicle position estimation are 0.2252 m and 0.0729 m2, respectively. The trajectory extraction precision outperforms most of the state-of-the-art algorithms.
高精度和一致的车辆轨迹包含微观交通参数、中观交通流特征和宏观交通流特征，是数据驱动交通管理和控制应用创新的基石。然而，在复杂交通环境下使用低通道路边激光雷达进行多车跟踪时，遮挡和轨迹中断仍然是一个挑战。为了应对这一挑战，我们提出了一种利用低信道路边激光雷达进行车辆轨迹提取的新型框架。首先，利用集群的几何特征及其 L 形边界框来解决车辆检测中因遮挡和点云稀疏而产生的过度分割问题。然后，通过改进的匈牙利算法与自适应距离阈值相结合，将相邻点云帧内的物体关联起来，以解决新点云帧中物体进出造成的不匹配问题。最后，考虑到车辆驾驶模式，采用改进的交互式多重模型来预测丢失车辆的位置，并将中断的轨迹连接起来。实验结果表明，所提出的方法实现了 98.76% 的车辆检测准确率和 97.40% 的数据关联精度。车辆位置估计的平均绝对误差（MAE）和平均平方误差（MSE）分别为 0.2252 m 和 0.0729 m2。轨迹提取精度优于大多数最先进的算法。
{"title":"Vehicle trajectory extraction with interacting multiple model for low-channel roadside LiDAR","authors":"Bowen Gong , Binwen Zhao , Yue Wang , Ciyun Lin , Hongchao Liu","doi":"10.1016/j.eswa.2024.125662","DOIUrl":"10.1016/j.eswa.2024.125662","url":null,"abstract":"<div><div>High-precision and consistent vehicle trajectories encompass microscopic traffic parameters, mesoscopic traffic flow characteristics, and macroscopic traffic flow features, which is the cornerstone of innovation in data-driven traffic management and control applications. However, occlusion and trajectory interruption remain challenging in multivehicle tracking under complex traffic environments using low-channel roadside LiDAR. To address the challenge, a novel framework for vehicle trajectory extraction using low-channel roadside LiDAR was proposed. First, the geometric features of the cluster and its L-shape bounding box were used to address the over-segmentation in vehicle detection arising from occlusion and point cloud sparse. Then, objects within adjacent point cloud frames were associated by developing an improved Hungarian algorithm integrated with an adaptive distance threshold to solve the mismatching problem caused by objects entrancing and exiting in a new point cloud frame. Finally, an improved interacting multiple model by considering vehicle driving patterns was deployed to predict the location of missing vehicles and connect the interrupted trajectories. Experimental results showed that the proposed methods achieve 98.76 % of vehicle detection accuracy and 97.40 % of data association precision. The mean absolute error (MAE) and mean square error (MSE) of the vehicle position estimation are 0.2252 m and 0.0729 m<sup>2</sup>, respectively. The trajectory extraction precision outperforms most of the state-of-the-art algorithms.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125662"},"PeriodicalIF":7.5,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586044","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}
Pub Date : 2024-11-02DOI: 10.1016/j.eswa.2024.125615
Hua Li , Zhenghong Jin
Semiconductor wafer fabrication systems (SWFS) are among the most intricate discrete processing environments globally. Since the costs associated with automated material handling systems (AMHS) within fabs account for 20%–50% of manufacturing expenses, it is crucial to enhance the efficiency of material handling in semiconductor production lines. However, optimizing AMHS is difficult due to the complexities inherent in large-scale, nonlinear, dynamic, and stochastic production settings, as well as differing objectives and goals. To overcome these challenges, this paper presents a novel fuzzy-based learning algorithm to enhance the multi-objective dispatching model, which incorporates both transportation and production aspects for interbay AMHS in wafer fabrication manufacturing, aligning it more closely with real-world conditions. Furthermore, we formulate a new constrained nonlinear dispatching problem. To tackle the inherent nonlinearity, a Takagi-Sugeno (T–S) fuzzy modeling approach is developed, which transforms nonlinear terms into a fuzzy linear dispatching model and optimizes the weight in multi-objective problems to obtain the optimal solution. The effectiveness and superiority of the proposed approach are demonstrated through extensive simulations and comparative analysis with existing methods. As a result, the proposed method significantly improves transport efficiency, increases wafer throughput, and reduces processing cycle times.
{"title":"A new look of dispatching for multi-objective interbay AMHS in semiconductor wafer manufacturing: A T–S fuzzy-based learning approach","authors":"Hua Li , Zhenghong Jin","doi":"10.1016/j.eswa.2024.125615","DOIUrl":"10.1016/j.eswa.2024.125615","url":null,"abstract":"<div><div>Semiconductor wafer fabrication systems (SWFS) are among the most intricate discrete processing environments globally. Since the costs associated with automated material handling systems (AMHS) within fabs account for 20%–50% of manufacturing expenses, it is crucial to enhance the efficiency of material handling in semiconductor production lines. However, optimizing AMHS is difficult due to the complexities inherent in large-scale, nonlinear, dynamic, and stochastic production settings, as well as differing objectives and goals. To overcome these challenges, this paper presents a novel fuzzy-based learning algorithm to enhance the multi-objective dispatching model, which incorporates both transportation and production aspects for interbay AMHS in wafer fabrication manufacturing, aligning it more closely with real-world conditions. Furthermore, we formulate a new constrained nonlinear dispatching problem. To tackle the inherent nonlinearity, a Takagi-Sugeno (T–S) fuzzy modeling approach is developed, which transforms nonlinear terms into a fuzzy linear dispatching model and optimizes the weight in multi-objective problems to obtain the optimal solution. The effectiveness and superiority of the proposed approach are demonstrated through extensive simulations and comparative analysis with existing methods. As a result, the proposed method significantly improves transport efficiency, increases wafer throughput, and reduces processing cycle times.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125615"},"PeriodicalIF":7.5,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572124","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}
Pub Date : 2024-11-02DOI: 10.1016/j.eswa.2024.125663
Xiaoman Duan , Xiao Fan Ding , Samira Khoz , Xiongbiao Chen , Ning Zhu
High-pitch X-ray helical computed tomography (HCT) imaging has been recently drawing considerable attention in biomedical fields due to its ability to reduce the scanning time and thus lower the radiation dose that objects (being imagined) may receive. However, the issue of compromised reconstruction quality caused by incomplete data in these high-pitch CT scans remains, thus limiting its applications. By addressing the aforementioned issue, this paper presents our study on the development of a novel deep leaning (DL)-based algorithm, ViT-U, for high-pitch X-ray propagation-based imaging HCT (PBI-HCT) reconstruction. ViT-U consists of two key process modules of a vision transformer (ViT) and a convolutional neural network (i.e., U-Net), where ViT addresses the missing information in the data domain and U-Net enhances the post data-processing in the reconstruction domain. For verification, we designed and conducted simulations and experiments with both low-density-biomaterial samples and biological-tissue samples to exemplify the biomedical applications, and then examined the ViT-U performance with varying pitches of 3, 3.5, 4, and 4.5, respectively, for comparison in term of radiation does and reconstruction quality. Our results showed that the high-pitch PBI-HCT allowed for the dose reduction from 72% to 93%. Importantly, our results demonstrated that the ViT-U exhibited outstanding performance by effectively removing the missing wedge artifacts thus enhancing the reconstruction quality of high-pitch PBI-HCT imaging. Also, our results showed the superior capability of ViT-U to achieve high quality of reconstruction from the high-pitch images with the helical pitch value up to 4 (which allowed for the substantial reduction of radiation doses). Taken together, our DL-based ViT-U algorithm not only enables high-speed imaging with low radiation dose, but also maintains the high quality of imaging reconstruction, thereby offering significant potentials for biomedical imaging applications.
{"title":"Development of A deep Learning-based algorithm for High-Pitch helical computed tomography imaging","authors":"Xiaoman Duan , Xiao Fan Ding , Samira Khoz , Xiongbiao Chen , Ning Zhu","doi":"10.1016/j.eswa.2024.125663","DOIUrl":"10.1016/j.eswa.2024.125663","url":null,"abstract":"<div><div>High-pitch X-ray helical computed tomography (HCT) imaging has been recently drawing considerable attention in biomedical fields due to its ability to reduce the scanning time and thus lower the radiation dose that objects (being imagined) may receive. However, the issue of compromised reconstruction quality caused by incomplete data in these high-pitch CT scans remains, thus limiting its applications. By addressing the aforementioned issue, this paper presents our study on the development of a novel deep leaning (DL)-based algorithm, ViT-U, for high-pitch X-ray propagation-based imaging HCT (PBI-HCT) reconstruction. ViT-U consists of two key process modules of a vision transformer (ViT) and a convolutional neural network (i.e., U-Net), where ViT addresses the missing information in the data domain and U-Net enhances the post data-processing in the reconstruction domain. For verification, we designed and conducted simulations and experiments with both low-density-biomaterial samples and biological-tissue samples to exemplify the biomedical applications, and then examined the ViT-U performance with varying pitches of 3, 3.5, 4, and 4.5, respectively, for comparison in term of radiation does and reconstruction quality. Our results showed that the high-pitch PBI-HCT allowed for the dose reduction from 72% to 93%. Importantly, our results demonstrated that the ViT-U exhibited outstanding performance by effectively removing the missing wedge artifacts thus enhancing the reconstruction quality of high-pitch PBI-HCT imaging. Also, our results showed the superior capability of ViT-U to achieve high quality of reconstruction from the high-pitch images with the helical pitch value up to 4 (which allowed for the substantial reduction of radiation doses). Taken together, our DL-based ViT-U algorithm not only enables high-speed imaging with low radiation dose, but also maintains the high quality of imaging reconstruction, thereby offering significant potentials for biomedical imaging applications.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125663"},"PeriodicalIF":7.5,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578467","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号