Expert Systems with Applications最新文献_第3页

GAN-based synthetic time-series data generation for improving prediction of demand for electric vehicles 基于 GAN 的合成时间序列数据生成，用于改进电动汽车需求预测

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125838

Subhajit Chatterjee , Debapriya Hazra , Yung-Cheol Byun

Demand forecasting is essential for any business to grow and manage its different business activities. With the basic needs of customers, it is hard to predict the future demand using traditional techniques. The popular approach to overcoming the difficulties faced by startup businesses is to use machine learning techniques for demand prediction. Another constraint to train machine learning algorithms for accurate prediction requires a considerable amount of data. For a new startup business, vast data acquisition is a very problematic issue. To overcome the data scarcity problem data enhancement techniques are mainly used for expanding the existing data. Synthetic data generation to balance the existing data which can lead to increased prediction model accuracy. In this study at the beginning, we found that the accuracy of the proposed clustering-based ensemble regression model was bad because of the small size of the data. To overcome this issue, we proposed a modified Conditional Wasserstein Generative Adversarial Network with a Gradient Penalty (CWGAN-GP) for generating synthetic time-series data according to the original data distribution. This generated synthetic data was further added to the original data to train the model and additionally enhanced the demand prediction accuracy for shared electric kickboards. Improved performance was noticed after the model was trained with combined data. Using a range of evaluation measures and graphical representations, we evaluated the performance of our approach against that of other ensemble models. For the production of synthetic data, our GAN model converged more quickly than other GAN models and solved the mode collapse problem. We have contrasted our suggested approach with other cutting-edge models. This study can be helpful for companies to meet the user’s demand for a better quality of service.

需求预测对任何企业的发展和管理不同业务活动都至关重要。鉴于客户的基本需求，使用传统技术很难预测未来的需求。为克服初创企业面临的困难，目前流行的方法是使用机器学习技术进行需求预测。要训练机器学习算法进行准确预测，另一个制约因素是需要大量数据。对于新创企业来说，大量数据的获取是一个非常棘手的问题。为了克服数据稀缺问题，数据增强技术主要用于扩展现有数据。合成数据的生成可以平衡现有数据，从而提高预测模型的准确性。在本研究中，一开始我们就发现，由于数据规模较小，所提出的基于聚类的集合回归模型的准确性很差。为了克服这一问题，我们提出了一种改进的带梯度惩罚的条件瓦瑟斯坦生成对抗网络（CWGAN-GP），用于根据原始数据的分布生成合成时间序列数据。生成的合成数据被进一步添加到原始数据中以训练模型，并进一步提高了共享电动脚踏板的需求预测精度。在使用综合数据对模型进行训练后，发现性能有所提高。我们使用一系列评估指标和图形表示法，对我们的方法与其他集合模型的性能进行了评估。在生成合成数据方面，我们的 GAN 模型比其他 GAN 模型收敛更快，并解决了模式崩溃问题。我们将建议的方法与其他先进模型进行了对比。这项研究有助于企业满足用户对更高质量服务的需求。

{"title":"GAN-based synthetic time-series data generation for improving prediction of demand for electric vehicles","authors":"Subhajit Chatterjee , Debapriya Hazra , Yung-Cheol Byun","doi":"10.1016/j.eswa.2024.125838","DOIUrl":"10.1016/j.eswa.2024.125838","url":null,"abstract":"<div><div>Demand forecasting is essential for any business to grow and manage its different business activities. With the basic needs of customers, it is hard to predict the future demand using traditional techniques. The popular approach to overcoming the difficulties faced by startup businesses is to use machine learning techniques for demand prediction. Another constraint to train machine learning algorithms for accurate prediction requires a considerable amount of data. For a new startup business, vast data acquisition is a very problematic issue. To overcome the data scarcity problem data enhancement techniques are mainly used for expanding the existing data. Synthetic data generation to balance the existing data which can lead to increased prediction model accuracy. In this study at the beginning, we found that the accuracy of the proposed clustering-based ensemble regression model was bad because of the small size of the data. To overcome this issue, we proposed a modified Conditional Wasserstein Generative Adversarial Network with a Gradient Penalty (CWGAN-GP) for generating synthetic time-series data according to the original data distribution. This generated synthetic data was further added to the original data to train the model and additionally enhanced the demand prediction accuracy for shared electric kickboards. Improved performance was noticed after the model was trained with combined data. Using a range of evaluation measures and graphical representations, we evaluated the performance of our approach against that of other ensemble models. For the production of synthetic data, our GAN model converged more quickly than other GAN models and solved the mode collapse problem. We have contrasted our suggested approach with other cutting-edge models. This study can be helpful for companies to meet the user’s demand for a better quality of service.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125838"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723356","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

Towards bias-aware visual question answering: Rectifying and mitigating comprehension biases 实现具有偏见感知能力的视觉问题解答：纠正和减轻理解偏差

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125817

Chongqing Chen , Dezhi Han , Zihan Guo , Chin-Chen Chang

Transformers have become essential for capturing intra- and inter-dependencies in visual question answering (VQA). Yet, challenges remain in overcoming inherent comprehension biases and improving the relational dependency modeling and reasoning capabilities crucial for VQA tasks. This paper presents RMCB, a novel VQA model designed to mitigate these biases by integrating contextual information from both visual and linguistic sources and addressing potential comprehension limitations at each end. RMCB introduces enhanced relational modeling for language tokens by leveraging textual context, addressing comprehension biases arising from the isolated pairwise modeling of token relationships. For the visual component, RMCB systematically incorporates both absolute and relative spatial relational information as contextual cues for image tokens, refining dependency modeling and strengthening inferential reasoning to alleviate biases caused by limited contextual understanding. The model’s effectiveness was evaluated on benchmark datasets VQA-v2 and CLEVR, achieving state-of-the-art results with accuracies of 71.78% and 99.27%, respectively. These results underscore RMCB’s capability to effectively address comprehension biases while advancing the relational reasoning needed for VQA.

变换器对于捕捉视觉问题解答（VQA）中的内部和相互依赖关系至关重要。然而，在克服固有的理解偏差和提高对 VQA 任务至关重要的关系依赖建模和推理能力方面仍然存在挑战。本文介绍的 RMCB 是一种新颖的 VQA 模型，旨在通过整合来自视觉和语言来源的上下文信息以及解决两端潜在的理解限制来减轻这些偏差。RMCB 利用文本上下文为语言标记引入了增强的关系建模，解决了孤立的标记关系配对建模所产生的理解偏差。在视觉部分，RMCB 系统地将绝对和相对空间关系信息作为图像标记的上下文线索，完善了依赖关系建模，加强了推理能力，从而减轻了因上下文理解有限而产生的偏差。该模型的有效性在基准数据集 VQA-v2 和 CLEVR 上进行了评估，结果达到了最先进的水平，准确率分别为 71.78% 和 99.27%。这些结果凸显了 RMCB 在推进 VQA 所需的关系推理的同时有效解决理解偏差的能力。

{"title":"Towards bias-aware visual question answering: Rectifying and mitigating comprehension biases","authors":"Chongqing Chen , Dezhi Han , Zihan Guo , Chin-Chen Chang","doi":"10.1016/j.eswa.2024.125817","DOIUrl":"10.1016/j.eswa.2024.125817","url":null,"abstract":"<div><div>Transformers have become essential for capturing intra- and inter-dependencies in visual question answering (VQA). Yet, challenges remain in overcoming inherent comprehension biases and improving the relational dependency modeling and reasoning capabilities crucial for VQA tasks. This paper presents RMCB, a novel VQA model designed to mitigate these biases by integrating contextual information from both visual and linguistic sources and addressing potential comprehension limitations at each end. RMCB introduces enhanced relational modeling for language tokens by leveraging textual context, addressing comprehension biases arising from the isolated pairwise modeling of token relationships. For the visual component, RMCB systematically incorporates both absolute and relative spatial relational information as contextual cues for image tokens, refining dependency modeling and strengthening inferential reasoning to alleviate biases caused by limited contextual understanding. The model’s effectiveness was evaluated on benchmark datasets VQA-v2 and CLEVR, achieving state-of-the-art results with accuracies of 71.78% and 99.27%, respectively. These results underscore RMCB’s capability to effectively address comprehension biases while advancing the relational reasoning needed for VQA.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125817"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723454","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

FOMOsim: An open-source simulator for rigorous analysis of micromobility planning problems FOMOsim：用于严格分析微型交通规划问题的开源模拟器

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125842

Steffen J.S. Bakker , Mohamed Ben Ahmed , Asbjørn Djupdal , Lasse Natvig , Henrik Andersson , Magnus Jahre , Kjetil Fagerholt

Existing simulation models for micromobility systems often face significant limitations: they are typically custom-built for specific contexts, lack generalizability, are not open-source, and undergo limited testing, which again question their reliability and applicability in broader settings. To address these challenges, this paper presents FOMOsim, an open-source simulator developed to analyze micromobility systems. The simulator’s modular design allows for better scalability and usability, facilitating detailed and realistic simulations of shared transport operations. New benchmark instances, utilizing data from bike-sharing systems (BSSs) in major American and Norwegian cities, are created and embedded within the simulator. Additionally, we introduce a new greedy heuristic for the dynamic bike rebalancing problem, integrated within FOMOsim. Rigorous testing demonstrates that the proposed heuristic, when combined with FOMOsim, outperforms state-of-the-art methods, significantly improving BSS performance by reducing bike shortages and surpluses. Furthermore, a comprehensive experimental study is designed to assess the impact of key strategic and operational decisions on BSS performance. The findings underscore the simulator’s adaptability in addressing various planning challenges and its potential to improve BSS management through informed decision-making. Consequently, FOMOsim provides the research community with a robust platform for replicating experiments, generating new instances, and exploring innovative solutions in BSS management, thereby substantially enriching the field’s body of knowledge.

现有的微移动系统仿真模型通常面临着很大的局限性：它们通常是为特定环境定制的，缺乏通用性，不是开源的，并且只经过有限的测试，这再次质疑了它们在更广泛环境中的可靠性和适用性。为了应对这些挑战，本文介绍了 FOMOsim，这是一个为分析微移动系统而开发的开源模拟器。该模拟器采用模块化设计，具有更好的可扩展性和可用性，便于对共享交通运营进行详细而逼真的模拟。我们利用美国和挪威主要城市共享单车系统（BSS）的数据创建了新的基准实例，并将其嵌入到模拟器中。此外，我们还针对动态自行车再平衡问题引入了一种新的贪婪启发式，并将其集成到 FOMOsim 中。严格的测试表明，所提出的启发式与 FOMOsim 结合使用时，性能优于最先进的方法，通过减少自行车短缺和过剩，显著提高了 BSS 性能。此外，还设计了一项综合实验研究，以评估关键战略和运营决策对 BSS 性能的影响。研究结果凸显了模拟器在应对各种规划挑战方面的适应性，以及通过明智决策改善 BSS 管理的潜力。因此，FOMOsim 为研究界提供了一个强大的平台，用于复制实验、生成新实例和探索 BSS 管理的创新解决方案，从而极大地丰富了该领域的知识体系。

{"title":"FOMOsim: An open-source simulator for rigorous analysis of micromobility planning problems","authors":"Steffen J.S. Bakker , Mohamed Ben Ahmed , Asbjørn Djupdal , Lasse Natvig , Henrik Andersson , Magnus Jahre , Kjetil Fagerholt","doi":"10.1016/j.eswa.2024.125842","DOIUrl":"10.1016/j.eswa.2024.125842","url":null,"abstract":"<div><div>Existing simulation models for micromobility systems often face significant limitations: they are typically custom-built for specific contexts, lack generalizability, are not open-source, and undergo limited testing, which again question their reliability and applicability in broader settings. To address these challenges, this paper presents FOMOsim, an open-source simulator developed to analyze micromobility systems. The simulator’s modular design allows for better scalability and usability, facilitating detailed and realistic simulations of shared transport operations. New benchmark instances, utilizing data from bike-sharing systems (BSSs) in major American and Norwegian cities, are created and embedded within the simulator. Additionally, we introduce a new greedy heuristic for the dynamic bike rebalancing problem, integrated within FOMOsim. Rigorous testing demonstrates that the proposed heuristic, when combined with FOMOsim, outperforms state-of-the-art methods, significantly improving BSS performance by reducing bike shortages and surpluses. Furthermore, a comprehensive experimental study is designed to assess the impact of key strategic and operational decisions on BSS performance. The findings underscore the simulator’s adaptability in addressing various planning challenges and its potential to improve BSS management through informed decision-making. Consequently, FOMOsim provides the research community with a robust platform for replicating experiments, generating new instances, and exploring innovative solutions in BSS management, thereby substantially enriching the field’s body of knowledge.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125842"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723464","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

Population-based evolutionary search for joint hyperparameter and architecture optimization in brain-computer interface 基于群体进化搜索的脑机接口超参数和架构联合优化技术

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125832

Dong-Hee Shin , Deok-Joong Lee , Ji-Wung Han, Young-Han Son, Tae-Eui Kam

In recent years, deep learning (DL)-based models have become the de facto standard for motor imagery brain-computer interface (MI-BCI) systems due to their notable performance. However, these models often require extensive hyperparameter optimization process to achieve optimal results. To tackle this challenge, recent studies have proposed various methods to automate this process. Despite promising results, these methods overlook the architecture elements, which are crucial factors for MI-BCI system performance and are highly intertwined with hyperparameter settings. To overcome this limitation, we propose a joint optimization framework that uses a population-based evolutionary search to optimize both hyperparameters and architectures. Our framework adopts a two-stage optimization approach that alternates between hyperparameter and architecture optimization to effectively manage the complexity of the joint search process. Furthermore, we introduce a novel ensemble method that leverages diverse promising configurations to enhance generalization and robustness. Evaluations on two public MI-BCI datasets show that our framework consistently outperforms competing methods across a range of backbone models, demonstrating its effectiveness and versatility.

近年来，基于深度学习（DL）的模型因其显著的性能已成为运动图像脑机接口（MI-BCI）系统的事实标准。然而，这些模型通常需要大量的超参数优化过程才能达到最佳效果。为了应对这一挑战，最近的研究提出了各种方法来实现这一过程的自动化。尽管这些方法取得了可喜的成果，但它们忽略了结构元素，而结构元素是 MI-BCI 系统性能的关键因素，与超参数设置密切相关。为了克服这一局限，我们提出了一个联合优化框架，利用基于种群的进化搜索来优化超参数和架构。我们的框架采用两阶段优化方法，在超参数和架构优化之间交替进行，以有效管理联合搜索过程的复杂性。此外，我们还引入了一种新颖的集合方法，利用各种有前景的配置来增强通用性和鲁棒性。在两个公开的 MI-BCI 数据集上进行的评估表明，我们的框架在一系列骨干模型中始终优于其他竞争方法，这证明了它的有效性和多功能性。

{"title":"Population-based evolutionary search for joint hyperparameter and architecture optimization in brain-computer interface","authors":"Dong-Hee Shin , Deok-Joong Lee , Ji-Wung Han, Young-Han Son, Tae-Eui Kam","doi":"10.1016/j.eswa.2024.125832","DOIUrl":"10.1016/j.eswa.2024.125832","url":null,"abstract":"<div><div>In recent years, deep learning (DL)-based models have become the de facto standard for motor imagery brain-computer interface (MI-BCI) systems due to their notable performance. However, these models often require extensive hyperparameter optimization process to achieve optimal results. To tackle this challenge, recent studies have proposed various methods to automate this process. Despite promising results, these methods overlook the architecture elements, which are crucial factors for MI-BCI system performance and are highly intertwined with hyperparameter settings. To overcome this limitation, we propose a joint optimization framework that uses a population-based evolutionary search to optimize both hyperparameters and architectures. Our framework adopts a two-stage optimization approach that alternates between hyperparameter and architecture optimization to effectively manage the complexity of the joint search process. Furthermore, we introduce a novel ensemble method that leverages diverse promising configurations to enhance generalization and robustness. Evaluations on two public MI-BCI datasets show that our framework consistently outperforms competing methods across a range of backbone models, demonstrating its effectiveness and versatility.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125832"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723357","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

TBAuth: A continuous authentication framework based on tap behavior for smartphones TBAuth：基于智能手机点击行为的连续认证框架

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125811

Yijing Chen , Gang Liu , Lin Yu , Hongzhaoning Kang , Lei Meng , Tao Wang

With the widespread adoption of smartphones, the security risks associated by the single authentication scheme have become increasingly serious. This promptes researchers to shift focus towards continuous authentication(CA) techniques. tap is a kind of behavior that can reflect the user’s identity. In this paper, a CA framework based on tap behavior (TBAuth) is proposed, which utilizes a vibration model to model tap behavior. In order to fully explore the potential of tap behavior, we analyze the user identity information embedded in it and its correlation with vibration. The data from motion sensors and touchscreen sensors are combined to fully extract tap behavioral features, and a feature selection method is proposed. In addition, a single classifier local outlier factor (LOF) is used to train authentication model. We validate TBAuth using a dataset of tap behavior collected from 40 volunteers. Extensive experiments are conducted, including method evaluation, authentication performance evaluation, and simulation experiments. The experimental results demonstrate that excellent user identity verification performance is achieved by TBAuth, as it can achieve an authentication performance as low as a 2.95% equal error rate (EER).

随着智能手机的普及，单一身份验证方案带来的安全风险日益严重。点击是一种能反映用户身份的行为。本文提出了一种基于拍击行为的 CA 框架（TBAuth），它利用振动模型对拍击行为进行建模。为了充分挖掘点击行为的潜力，我们分析了其中蕴含的用户身份信息及其与振动的相关性。我们将运动传感器和触摸屏传感器的数据结合起来，以充分提取轻拍行为特征，并提出了一种特征选择方法。此外，还使用了单分类器局部离群因子（LOF）来训练认证模型。我们使用从 40 名志愿者那里收集的点击行为数据集对 TBAuth 进行了验证。我们进行了广泛的实验，包括方法评估、认证性能评估和模拟实验。实验结果表明，TBAuth 实现了出色的用户身份验证性能，其验证性能可低至 2.95% 的等效错误率 (EER)。

{"title":"TBAuth: A continuous authentication framework based on tap behavior for smartphones","authors":"Yijing Chen , Gang Liu , Lin Yu , Hongzhaoning Kang , Lei Meng , Tao Wang","doi":"10.1016/j.eswa.2024.125811","DOIUrl":"10.1016/j.eswa.2024.125811","url":null,"abstract":"<div><div>With the widespread adoption of smartphones, the security risks associated by the single authentication scheme have become increasingly serious. This promptes researchers to shift focus towards continuous authentication(CA) techniques. tap is a kind of behavior that can reflect the user’s identity. In this paper, a CA framework based on tap behavior (TBAuth) is proposed, which utilizes a vibration model to model tap behavior. In order to fully explore the potential of tap behavior, we analyze the user identity information embedded in it and its correlation with vibration. The data from motion sensors and touchscreen sensors are combined to fully extract tap behavioral features, and a feature selection method is proposed. In addition, a single classifier local outlier factor (LOF) is used to train authentication model. We validate TBAuth using a dataset of tap behavior collected from 40 volunteers. Extensive experiments are conducted, including method evaluation, authentication performance evaluation, and simulation experiments. The experimental results demonstrate that excellent user identity verification performance is achieved by TBAuth, as it can achieve an authentication performance as low as a 2.95% equal error rate (EER).</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125811"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723312","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

Intelligent multi-rebar layouts in precast concrete components using multi-agent coordination and particle swarm optimization 利用多代理协调和粒子群优化技术实现预制混凝土构件中的智能多钢筋布局

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125896

Chengran Xu , Xiaolei Zheng , Jiepeng Liu , Weibing Peng , Kai Jiang , Chao Zhang , Zhou Wu

For precast concrete (PC) components, product-oriented design plays a vital role to achieve the industrial production and lean construction. Rebar collisions occur more frequently in PC components due to the irregular concrete profile and the numerous embedded parts. This paper presents an automated detailed design framework for PC components to generate the multi-rebar collision-free layout. Inspired by the formation moving capability of multi-agent flock, a multi-rebar layout module is developed to avoid rebar collision and uneven spacing. An integrated multi-agent coordination strategy is proposed for the multi-layout module, which includes three subtasks: virtual leader path planning, obstacle avoidance for collided agents, and formation optimization of agent flock. An optimization model is formulated to adjust multi-agent formation and particle swarm optimization (PSO) algorithm is employed to find the optimal solution. The developed framework is applied to the detailed design of a PC stair to demonstrate its practicability and efficiency.

对于预制混凝土（PC）构件而言，以产品为导向的设计对于实现工业化生产和精益施工起着至关重要的作用。由于不规则的混凝土轮廓和众多的预埋件，钢筋碰撞在 PC 组件中发生得更为频繁。本文提出了一种用于 PC 构件的自动详细设计框架，以生成无碰撞的多钢筋布局。受多代理群的编队移动能力启发，开发了多钢筋布局模块，以避免钢筋碰撞和间距不均。该模块包括三个子任务：虚拟领导者路径规划、碰撞代理避障和代理群编队优化。建立了调整多代理编队的优化模型，并采用粒子群优化（PSO）算法找到最优解。开发的框架被应用于 PC 楼梯的详细设计，以证明其实用性和效率。

{"title":"Intelligent multi-rebar layouts in precast concrete components using multi-agent coordination and particle swarm optimization","authors":"Chengran Xu , Xiaolei Zheng , Jiepeng Liu , Weibing Peng , Kai Jiang , Chao Zhang , Zhou Wu","doi":"10.1016/j.eswa.2024.125896","DOIUrl":"10.1016/j.eswa.2024.125896","url":null,"abstract":"<div><div>For precast concrete (PC) components, product-oriented design plays a vital role to achieve the industrial production and lean construction. Rebar collisions occur more frequently in PC components due to the irregular concrete profile and the numerous embedded parts. This paper presents an automated detailed design framework for PC components to generate the multi-rebar collision-free layout. Inspired by the formation moving capability of multi-agent flock, a multi-rebar layout module is developed to avoid rebar collision and uneven spacing. An integrated multi-agent coordination strategy is proposed for the multi-layout module, which includes three subtasks: virtual leader path planning, obstacle avoidance for collided agents, and formation optimization of agent flock. An optimization model is formulated to adjust multi-agent formation and particle swarm optimization (PSO) algorithm is employed to find the optimal solution. The developed framework is applied to the detailed design of a PC stair to demonstrate its practicability and efficiency.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125896"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723363","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

Evolutionary game and LGPSO for attack-defense confrontation analysis in WSN from macro perspective 从宏观角度分析 WSN 中攻防对抗的进化博弈和 LGPSO

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125815

Ning Liu, Shangkun Liu, Wei-Min Zheng

Wireless sensor network node security requires effective security mechanisms to protect the security and reliability, so as to ensure that sensor nodes can operate normally and provide reliable data in various environments. The security state change of wireless sensor network nodes is an important research content in the field of wireless sensor security. In this paper, an evolutionary game model is proposed to analyze the security state changes of sensor network nodes from a macro perspective. The existing methods define the parameters subjectively, which leads to the lack of rationality. In this paper, a Levy Flight Global Learning Particle Swarm Optimization (LGPSO) is proposed to calculate the Nash equilibrium of the game and quantify the parameters of the evolutionary game. The method proposed in this paper determines the parameters of the evolutionary game by solving the Nash equilibrium, which makes the model more realistic. The LGPSO has better optimization performance than other algorithms in solving Nash equilibrium problems. The CEC2013 dataset is used to test the performance of LGPSO. The experimental results show that LGPSO is superior to all other algorithms on 68% of the problems. This paper also discusses the influence of the game difficulty coefficient on the evolution process, and experiments show that a larger coefficient is more beneficial to the defender. The macro analysis in this paper provides the method of active defense for the attack-defense confrontation in wireless sensor networks.

无线传感器网络节点安全需要有效的安全机制来保障其安全性和可靠性，从而保证传感器节点在各种环境下都能正常运行并提供可靠的数据。无线传感器网络节点的安全状态变化是无线传感器安全领域的重要研究内容。本文提出了一种进化博弈模型，从宏观角度分析传感器网络节点的安全状态变化。现有方法主观定义参数，缺乏合理性。本文提出了一种利维飞行全局学习粒子群优化（LGPSO）方法，用于计算博弈的纳什均衡并量化进化博弈的参数。本文提出的方法通过求解纳什均衡来确定演化博弈的参数，这使得模型更加逼真。与其他算法相比，LGPSO 在求解纳什均衡问题时具有更好的优化性能。本文使用 CEC2013 数据集测试 LGPSO 的性能。实验结果表明，在 68% 的问题上，LGPSO 优于所有其他算法。本文还讨论了博弈难度系数对演化过程的影响，实验结果表明，系数越大对防守方越有利。本文的宏观分析为无线传感器网络中的攻防对抗提供了主动防御的方法。

{"title":"Evolutionary game and LGPSO for attack-defense confrontation analysis in WSN from macro perspective","authors":"Ning Liu, Shangkun Liu, Wei-Min Zheng","doi":"10.1016/j.eswa.2024.125815","DOIUrl":"10.1016/j.eswa.2024.125815","url":null,"abstract":"<div><div>Wireless sensor network node security requires effective security mechanisms to protect the security and reliability, so as to ensure that sensor nodes can operate normally and provide reliable data in various environments. The security state change of wireless sensor network nodes is an important research content in the field of wireless sensor security. In this paper, an evolutionary game model is proposed to analyze the security state changes of sensor network nodes from a macro perspective. The existing methods define the parameters subjectively, which leads to the lack of rationality. In this paper, a Levy Flight Global Learning Particle Swarm Optimization (LGPSO) is proposed to calculate the Nash equilibrium of the game and quantify the parameters of the evolutionary game. The method proposed in this paper determines the parameters of the evolutionary game by solving the Nash equilibrium, which makes the model more realistic. The LGPSO has better optimization performance than other algorithms in solving Nash equilibrium problems. The CEC2013 dataset is used to test the performance of LGPSO. The experimental results show that LGPSO is superior to all other algorithms on 68% of the problems. This paper also discusses the influence of the game difficulty coefficient on the evolution process, and experiments show that a larger coefficient is more beneficial to the defender. The macro analysis in this paper provides the method of active defense for the attack-defense confrontation in wireless sensor networks.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125815"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723452","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

Enhanced multi-label feature selection considering label-specific relevant information 考虑特定标签相关信息的增强型多标签特征选择

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125819

Qingqi Han , Zhanpeng Zhao , Liang Hu, Wanfu Gao

In fields such as text classification and image recognition, multi-label data is frequently encountered. However, extracting information-rich and reliable features from high-dimensional multi-label datasets presents significant challenges in pattern recognition tasks. Traditional information-theoretic feature selection methods utilize a greedy algorithm strategy, selecting the feature that best meets the evaluation criteria in each iteration. However, the optimal result of each iteration does not necessarily yield a globally optimal solution. These methods primarily focus on the overall relevance of each feature with respect to all labels from a macro perspective, often overlooking the distribution of relevant information among features. This oversight can lead to the selection of features that are weakly correlated with the labels. Additionally, they neglect the impact of redundancy measures on feature scoring, resulting in the selection of some irrelevant features. To address these issues, we propose a novel multi-label feature selection method that evaluates the relevance between feature sets and label sets from both macro and micro perspectives. This method maximizes the relevance between features and the label set while ensuring the selection of features that are strongly correlated with each individual label. Classification experiments conducted on eight multi-label datasets demonstrate that the proposed method consistently outperforms seven comparative methods.

在文本分类和图像识别等领域，经常会遇到多标签数据。然而，在模式识别任务中，从高维多标签数据集中提取信息丰富且可靠的特征是一项重大挑战。传统的信息论特征选择方法采用贪婪算法策略，在每次迭代中选择最符合评价标准的特征。然而，每次迭代的最优结果并不一定产生全局最优解。这些方法主要从宏观角度关注每个特征与所有标签的整体相关性，往往忽略了特征间相关信息的分布。这种忽略可能会导致选择与标签相关性较弱的特征。此外，它们还忽视了冗余度测量对特征评分的影响，从而导致选择了一些不相关的特征。为了解决这些问题，我们提出了一种新颖的多标签特征选择方法，从宏观和微观两个角度评估特征集和标签集之间的相关性。这种方法既能最大限度地提高特征与标签集之间的相关性，又能确保选择与每个标签密切相关的特征。在八个多标签数据集上进行的分类实验表明，所提出的方法始终优于七种比较方法。

{"title":"Enhanced multi-label feature selection considering label-specific relevant information","authors":"Qingqi Han , Zhanpeng Zhao , Liang Hu, Wanfu Gao","doi":"10.1016/j.eswa.2024.125819","DOIUrl":"10.1016/j.eswa.2024.125819","url":null,"abstract":"<div><div>In fields such as text classification and image recognition, multi-label data is frequently encountered. However, extracting information-rich and reliable features from high-dimensional multi-label datasets presents significant challenges in pattern recognition tasks. Traditional information-theoretic feature selection methods utilize a greedy algorithm strategy, selecting the feature that best meets the evaluation criteria in each iteration. However, the optimal result of each iteration does not necessarily yield a globally optimal solution. These methods primarily focus on the overall relevance of each feature with respect to all labels from a macro perspective, often overlooking the distribution of relevant information among features. This oversight can lead to the selection of features that are weakly correlated with the labels. Additionally, they neglect the impact of redundancy measures on feature scoring, resulting in the selection of some irrelevant features. To address these issues, we propose a novel multi-label feature selection method that evaluates the relevance between feature sets and label sets from both macro and micro perspectives. This method maximizes the relevance between features and the label set while ensuring the selection of features that are strongly correlated with each individual label. Classification experiments conducted on eight multi-label datasets demonstrate that the proposed method consistently outperforms seven comparative methods.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125819"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723359","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

Secure medical image encryption scheme for Healthcare IoT using novel hyperchaotic map and DNA cubes 使用新型超混沌图和 DNA 立方体的医疗物联网安全医疗图像加密方案

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125854

Qiang Lai, Hanqiang Hua

To enhance the security and transmission efficiency of medical data within the Healthcare Internet of Things (IoT), this study proposes a novel encryption scheme for medical images that integrates integer wavelet transform (IWT) with DNA encoding. The scheme aims to ensure the confidentiality of medical images while optimizing cloud storage and transmission speed. It employs pseudo-random sequences generated by a novel 3D hyperchaotic map. Initially, IWT is applied to extract the approximation components of the images, followed by a novel diffusion algorithm that masks critical information. A bit-level permutation mechanism further enhances encryption complexity by rearranging pixel positions. To augment security, the scheme introduces a random DNA operation, encoding the permuted images with a unique DNA technique and shuffling DNA bases using specialized DNA cubes. Performance analysis reveals that the decrypted medical images exhibit high visual fidelity, consistently achieving a

P S N R

above 35 dB. Moreover, in terms of encryption efficiency, the proposed algorithm demonstrates faster processing speed, while its security performance is comparable to that of the current state-of-the-art algorithms.

为了提高医疗物联网（IoT）中医疗数据的安全性和传输效率，本研究提出了一种新型医疗图像加密方案，该方案将整数小波变换（IWT）与 DNA 编码相结合。该方案旨在确保医疗图像的保密性，同时优化云存储和传输速度。它采用了由新型三维超混沌图生成的伪随机序列。首先，应用 IWT 提取图像的近似分量，然后采用新颖的扩散算法掩盖关键信息。位级排列机制通过重新排列像素位置，进一步提高了加密的复杂性。为了增强安全性，该方案引入了随机 DNA 操作，使用独特的 DNA 技术对排列后的图像进行编码，并使用专门的 DNA 立方体对 DNA 碱基进行洗牌。性能分析表明，解密后的医学图像具有很高的视觉保真度，PSNR 一直保持在 35 dB 以上。此外，就加密效率而言，拟议算法的处理速度更快，而其安全性能与当前最先进的算法相当。

{"title":"Secure medical image encryption scheme for Healthcare IoT using novel hyperchaotic map and DNA cubes","authors":"Qiang Lai, Hanqiang Hua","doi":"10.1016/j.eswa.2024.125854","DOIUrl":"10.1016/j.eswa.2024.125854","url":null,"abstract":"<div><div>To enhance the security and transmission efficiency of medical data within the Healthcare Internet of Things (IoT), this study proposes a novel encryption scheme for medical images that integrates integer wavelet transform (IWT) with DNA encoding. The scheme aims to ensure the confidentiality of medical images while optimizing cloud storage and transmission speed. It employs pseudo-random sequences generated by a novel 3D hyperchaotic map. Initially, IWT is applied to extract the approximation components of the images, followed by a novel diffusion algorithm that masks critical information. A bit-level permutation mechanism further enhances encryption complexity by rearranging pixel positions. To augment security, the scheme introduces a random DNA operation, encoding the permuted images with a unique DNA technique and shuffling DNA bases using specialized DNA cubes. Performance analysis reveals that the decrypted medical images exhibit high visual fidelity, consistently achieving a <span><math><mrow><mi>P</mi><mi>S</mi><mi>N</mi><mi>R</mi></mrow></math></span> above 35 dB. Moreover, in terms of encryption efficiency, the proposed algorithm demonstrates faster processing speed, while its security performance is comparable to that of the current state-of-the-art algorithms.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125854"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-objective optimization approach for permanent magnet machine via improved soft actor–critic based on deep reinforcement learning 通过基于深度强化学习的改进型软演员评判器实现永磁机械的多目标优化方法

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2024-11-23 DOI: 10.1016/j.eswa.2024.125834

Chen Wang , Tianyu Dong , Lei Chen , Guixiang Zhu , Yihan Chen

As awareness of environmental protection grows, the development of electric vehicles has emerged as a prominent area of research. Naturally, optimizing Permanent Magnet (PM) machines is critical for enhancing the power performance of electric vehicles, as they are essential components of these vehicles. Benefitting from the advantage of Deep Neural Network (DNN), optimizing the PM machine by leveraging DNN has drawn great attention from industry and academia. To increase the torque of the PM machine and reduce torque ripple from a structural design perspective, this paper proposes a Multi-objective Optimization approach for PM machine via improved Soft Actor Critic (called MOPM-SAC) based on Deep Reinforcement Learning (DRL). MOPM-SAC consists of two core components: a surrogate model based on DNN and a SAC algorithm. Specifically, the SAC algorithm based on DNN is used to optimize the PM machine. The surrogate model is established by training the DNN to use Finite Element (FE) simulation samples, which possesses higher accuracy than other methods, such as Support Vector Machine (SVM), Random Forest (RF), and so on. Moreover, the SAC algorithm integrates a trained DNN as the state transition function within the DRL environment, which enhances the optimization algorithm’s generalization ability in the context of PM machines. In addition, the reward function is designed based on optimization requirements to guide the agent in the SAC algorithm toward learning the optimal strategy. Finally, a 75 kW prototype is manufactured and tested. The effectiveness of the proposed method is validated through FE simulations and prototype experiments.

随着环保意识的增强，电动汽车的发展已成为一个突出的研究领域。永磁（PM）机器是电动汽车的重要组成部分，因此优化永磁机器对于提高电动汽车的动力性能自然至关重要。得益于深度神经网络（DNN）的优势，利用 DNN 优化永磁机引起了业界和学术界的极大关注。为了从结构设计的角度提高永磁机械的扭矩并减少扭矩波纹，本文提出了一种基于深度强化学习（DRL）、通过改进的软行为批判（称为 MOPM-SAC）对永磁机械进行多目标优化的方法。MOPM-SAC 由两个核心部分组成：基于 DNN 的代理模型和 SAC 算法。具体来说，基于 DNN 的 SAC 算法用于优化 PM 机器。代用模型是通过使用有限元（FE）仿真样本训练 DNN 而建立的，它比支持向量机（SVM）、随机森林（RF）等其他方法具有更高的精度。此外，SAC 算法在 DRL 环境中集成了训练有素的 DNN 作为状态转换函数，从而增强了优化算法在 PM 机器背景下的泛化能力。此外，还根据优化要求设计了奖励函数，以引导 SAC 算法中的代理学习最优策略。最后，制造并测试了一台 75 千瓦的原型机。通过 FE 仿真和原型实验，验证了所提方法的有效性。

{"title":"Multi-objective optimization approach for permanent magnet machine via improved soft actor–critic based on deep reinforcement learning","authors":"Chen Wang , Tianyu Dong , Lei Chen , Guixiang Zhu , Yihan Chen","doi":"10.1016/j.eswa.2024.125834","DOIUrl":"10.1016/j.eswa.2024.125834","url":null,"abstract":"<div><div>As awareness of environmental protection grows, the development of electric vehicles has emerged as a prominent area of research. Naturally, optimizing Permanent Magnet (PM) machines is critical for enhancing the power performance of electric vehicles, as they are essential components of these vehicles. Benefitting from the advantage of Deep Neural Network (DNN), optimizing the PM machine by leveraging DNN has drawn great attention from industry and academia. To increase the torque of the PM machine and reduce torque ripple from a structural design perspective, this paper proposes a <strong>M</strong>ulti-objective <strong>O</strong>ptimization approach for <strong>PM</strong> machine via improved <strong>S</strong>oft <strong>A</strong>ctor <strong>C</strong>ritic (called MOPM-SAC) based on Deep Reinforcement Learning (DRL). MOPM-SAC consists of two core components: a surrogate model based on DNN and a SAC algorithm. Specifically, the SAC algorithm based on DNN is used to optimize the PM machine. The surrogate model is established by training the DNN to use Finite Element (FE) simulation samples, which possesses higher accuracy than other methods, such as Support Vector Machine (SVM), Random Forest (RF), and so on. Moreover, the SAC algorithm integrates a trained DNN as the state transition function within the DRL environment, which enhances the optimization algorithm’s generalization ability in the context of PM machines. In addition, the reward function is designed based on optimization requirements to guide the agent in the SAC algorithm toward learning the optimal strategy. Finally, a 75 kW prototype is manufactured and tested. The effectiveness of the proposed method is validated through FE simulations and prototype experiments.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125834"},"PeriodicalIF":7.5,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723378","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