首页 > 最新文献
paperpass

Applied Soft Computing最新文献

英文 中文
An enhanced multi-criteria decision making framework for evaluating LLM-integrated smart product-service systems using spherical fuzzy rough numbers 利用球面模糊粗糙数评价llm集成智能产品服务系统的增强多准则决策框架
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-05-01 Epub Date: 2026-02-11 DOI: 10.1016/j.asoc.2026.114797
Zhongkui Liu , Danhui Zhang , Qinghua Liu
Integrating Large Language Model (LLM) into Smart Product-Service Systems (SPSS) introduces challenges in design evaluation due to inherent uncertainties and complex decision criteria. To address these challenges, we propose SFRN-LOPCOW-RAFSI, a novel multi-criteria decision making (MCDM) framework that combines spherical fuzzy rough numbers (SFRN), logarithmic percentage change-driven objective weighting (LOPCOW), and ranking of alternatives through functional mapping of criterion sub-intervals into a single interval (RAFSI). This study applies the proposed framework to a conceptual design evaluation case for a refrigerator service system, where four LLM-integrated service solutions are assessed based on 15 evaluation criteria. The methodology consists of three stages: (1) defining the problem structure, (2) computing the weight coefficients of the criteria using the SFRN-based LOPCOW method, and (3) ranking the design alternatives through the SFRN-based RAFSI approach. SFRN can represent a more extensive range of uncertainty and effectively handle uncertainty within the decision-making group, enhancing the reliability of the evaluation process. Sensitivity analysis and comparative analysis were conducted to validate the proposed method, confirming its robustness and effectiveness. This study's findings provide valuable insights for DMs in optimizing the integration of LLMs into SPSS design processes.
将大型语言模型(LLM)集成到智能产品服务系统(SPSS)中,由于固有的不确定性和复杂的决策标准,在设计评估中引入了挑战。为了解决这些挑战,我们提出了SFRN-LOPCOW-RAFSI,这是一个新的多准则决策(MCDM)框架,它结合了球面模糊粗糙数(SFRN)、对数百分比变化驱动的目标加权(LOPCOW)和通过将准则子区间函数映射到单个区间(RAFSI)来对备选方案进行排序。本研究将提出的框架应用于冰箱服务系统的概念设计评估案例,其中基于15个评估标准评估了四个llm集成服务解决方案。该方法包括三个阶段:(1)定义问题结构;(2)使用基于sfrn的LOPCOW方法计算准则的权重系数;(3)通过基于sfrn的RAFSI方法对设计方案进行排序。SFRN可以代表更广泛的不确定性范围,有效地处理决策群体内部的不确定性,提高了评估过程的可靠性。通过灵敏度分析和对比分析对方法进行了验证,验证了方法的鲁棒性和有效性。本研究的发现提供了有价值的见解,在优化整合法学硕士到SPSS设计过程的dm。
{"title":"An enhanced multi-criteria decision making framework for evaluating LLM-integrated smart product-service systems using spherical fuzzy rough numbers","authors":"Zhongkui Liu ,&nbsp;Danhui Zhang ,&nbsp;Qinghua Liu","doi":"10.1016/j.asoc.2026.114797","DOIUrl":"10.1016/j.asoc.2026.114797","url":null,"abstract":"<div><div>Integrating Large Language Model (LLM) into Smart Product-Service Systems (SPSS) introduces challenges in design evaluation due to inherent uncertainties and complex decision criteria. To address these challenges, we propose SFRN-LOPCOW-RAFSI, a novel multi-criteria decision making (MCDM) framework that combines spherical fuzzy rough numbers (SFRN), logarithmic percentage change-driven objective weighting (LOPCOW), and ranking of alternatives through functional mapping of criterion sub-intervals into a single interval (RAFSI). This study applies the proposed framework to a conceptual design evaluation case for a refrigerator service system, where four LLM-integrated service solutions are assessed based on 15 evaluation criteria. The methodology consists of three stages: (1) defining the problem structure, (2) computing the weight coefficients of the criteria using the SFRN-based LOPCOW method, and (3) ranking the design alternatives through the SFRN-based RAFSI approach. SFRN can represent a more extensive range of uncertainty and effectively handle uncertainty within the decision-making group, enhancing the reliability of the evaluation process. Sensitivity analysis and comparative analysis were conducted to validate the proposed method, confirming its robustness and effectiveness. This study's findings provide valuable insights for DMs in optimizing the integration of LLMs into SPSS design processes.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"193 ","pages":"Article 114797"},"PeriodicalIF":6.6,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146196903","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 decision-making control of cutter suction dredger based on multi-scale graph representation with Bayesian optimization 基于贝叶斯优化多尺度图表示的绞吸式挖泥船多目标决策控制
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-05-01 Epub Date: 2026-02-11 DOI: 10.1016/j.asoc.2026.114811
Yong Chen , Qiubing Ren , Mingchao Li , Bolong Gao , Yonghuang Xiang , Zhongzhi Fu
The operational parameters of cutter suction dredger (CSD) are frequently set based on empirical experience, leading to low productivity and high energy consumption. To address this issue, the present study proposes a Bayesian multi-objective optimization (MOO) framework integrating a multi-scale adaptive graph convolutional network (MAGCN) model and a multi-objective tree-structured Parzen estimator (MOTPE) algorithm. This framework aims to predict and optimize construction productivity and energy consumption performance while providing well-informed support for intelligent decision-making control. First, a hybrid feature selection method combining maximum information coefficient and Pearson correlation coefficient is applied to identify 6 key control parameters from 256 operational parameters. Second, an MAGCN model with multi-scale graph representation is proposed to establish the nonlinear mapping among geological conditions, operational parameters, construction productivity, and energy consumption. Third, the MOO framework with its mathematical formulation is constructed, and the Pareto optimal front for productivity and energy consumption is derived using the MOTPE-based Bayesian optimization algorithm. The optimal trade-off solution and corresponding operational parameters are determined by a weighted sum method. The proposed MOO framework is validated using operational data from the Tian Jing Hao CSD in the Pinglu Canal dredging project in China. The results show that the MAGCN model achieves high prediction accuracy for real-time productivity and energy consumption, with R2 values of 0.942 and 0.979, respectively. The MOTPE-driven optimization reduces standard deviations of operational parameters by 21.24 % - 97.90 %, enhancing operational stability. The framework improves productivity by 3.79 % and reduces energy consumption by 3.53 %. This work provides real-time decision-making support for optimizing CSD operations.
绞吸式挖泥船(CSD)的作业参数通常是根据经验设定的,导致生产率低、能耗高。为了解决这一问题,本研究提出了一个贝叶斯多目标优化(MOO)框架,该框架集成了多尺度自适应图卷积网络(MAGCN)模型和多目标树结构Parzen估计(MOTPE)算法。该框架旨在预测和优化建筑生产力和能耗性能,同时为智能决策控制提供充分的信息支持。首先,采用最大信息系数和Pearson相关系数相结合的混合特征选择方法,从256个操作参数中识别出6个关键控制参数;其次,提出了多尺度图表示的MAGCN模型,建立了地质条件、运行参数、施工生产率和能耗之间的非线性映射;第三,构建了MOO框架及其数学表达式,利用基于mope的贝叶斯优化算法推导了生产率和能耗的Pareto最优前沿;采用加权和法确定最优权衡解和相应的运行参数。利用中国平陆运河疏浚项目天井号CSD的运行数据,对拟议的MOO框架进行了验证。结果表明,MAGCN模型对实时生产率和能耗具有较高的预测精度,R2分别为0.942和0.979。mope驱动优化后,运行参数标准差降低21.24% % ~ 97.90 %,提高了运行稳定性。该框架提高了3.79 %的生产率,降低了3.53 %的能耗。这项工作为优化CSD作业提供了实时决策支持。
{"title":"Multi-objective decision-making control of cutter suction dredger based on multi-scale graph representation with Bayesian optimization","authors":"Yong Chen ,&nbsp;Qiubing Ren ,&nbsp;Mingchao Li ,&nbsp;Bolong Gao ,&nbsp;Yonghuang Xiang ,&nbsp;Zhongzhi Fu","doi":"10.1016/j.asoc.2026.114811","DOIUrl":"10.1016/j.asoc.2026.114811","url":null,"abstract":"<div><div>The operational parameters of cutter suction dredger (CSD) are frequently set based on empirical experience, leading to low productivity and high energy consumption. To address this issue, the present study proposes a Bayesian multi-objective optimization (MOO) framework integrating a multi-scale adaptive graph convolutional network (MAGCN) model and a multi-objective tree-structured Parzen estimator (MOTPE) algorithm. This framework aims to predict and optimize construction productivity and energy consumption performance while providing well-informed support for intelligent decision-making control. First, a hybrid feature selection method combining maximum information coefficient and Pearson correlation coefficient is applied to identify 6 key control parameters from 256 operational parameters. Second, an MAGCN model with multi-scale graph representation is proposed to establish the nonlinear mapping among geological conditions, operational parameters, construction productivity, and energy consumption. Third, the MOO framework with its mathematical formulation is constructed, and the Pareto optimal front for productivity and energy consumption is derived using the MOTPE-based Bayesian optimization algorithm. The optimal trade-off solution and corresponding operational parameters are determined by a weighted sum method. The proposed MOO framework is validated using operational data from the Tian Jing Hao CSD in the Pinglu Canal dredging project in China. The results show that the MAGCN model achieves high prediction accuracy for real-time productivity and energy consumption, with R<sup>2</sup> values of 0.942 and 0.979, respectively. The MOTPE-driven optimization reduces standard deviations of operational parameters by 21.24 % - 97.90 %, enhancing operational stability. The framework improves productivity by 3.79 % and reduces energy consumption by 3.53 %. This work provides real-time decision-making support for optimizing CSD operations.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"193 ","pages":"Article 114811"},"PeriodicalIF":6.6,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146196907","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
MFU-Depth: Modeling and fusing uncertainty for self-supervised multi-frame monocular depth estimation MFU-Depth:自监督多帧单目深度估计的建模和融合不确定性
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-04-01 Epub Date: 2026-01-23 DOI: 10.1016/j.asoc.2026.114705
Fuji Fu , Jinfu Yang , Jiaqi Ma
Self-supervised monocular depth estimation, valued for its simplified configuration and excellent geometric perception, is gaining attention in autonomous driving and robotics. Mainstream self-supervised multi-frame methods, due to the lack of a unified multi-cue uncertainty representation mechanism, often struggle to effectively reflect depth prediction errors. To address this issue, we propose a self-supervised multi-frame monocular depth estimation method by Modeling and Fusing Uncertainty, termed MFU-Depth. (1) At the probability distribution level, we design an Uncertainty Estimation-based Single-frame Probability Prediction (UE-SPP) module and a Depth-Aware Multi-frame Probability Transformation (DA-MPT) module, achieving unified uncertainty modeling of single-frame and multi-frame cues in the form of probability distributions. Building on these, we establish a Relation Modeling-guided Probability Fusion (RM-PF) mechanism, which adaptively adjusts fusion weights through pixel-wise difference relation modeling, enabling the complementary integration of these two distributions. (2) At the probabilistic self-supervision level, an Information Entropy Uncertainty Loss (IEUL) is devised to further model the uncertainty of both single-frame and fused depth probability distributions, thereby mitigating supervision distortion caused by high-uncertainty pixels. Experimental results show that MFU-Depth achieves exceptional performance on multiple public datasets. Compared to baseline methods, MFU-Depth reduces the depth error by 15.3% and the uncertainty metric by 29.0%.
自监督单目深度估计以其简化的结构和优异的几何感知能力在自动驾驶和机器人领域受到越来越多的关注。主流的自监督多帧方法由于缺乏统一的多线索不确定性表示机制,往往难以有效反映深度预测误差。为了解决这个问题,我们提出了一种基于建模和融合不确定性的自监督多帧单目深度估计方法,称为MFU-Depth。(1)在概率分布层面,设计了基于不确定性估计的单帧概率预测(UE-SPP)模块和深度感知的多帧概率变换(DA-MPT)模块,实现了单帧和多帧线索以概率分布形式的统一不确定性建模。在此基础上,我们建立了一种关系建模引导的概率融合(RM-PF)机制,该机制通过逐像素的差异关系建模自适应调整融合权重,实现了这两种分布的互补集成。(2)在概率自监督层面,设计了一种信息熵不确定性损失(Information Entropy Uncertainty Loss, IEUL),进一步对单帧和融合深度概率分布的不确定性进行建模,从而减轻高不确定性像素造成的监督失真。实验结果表明,MFU-Depth在多个公共数据集上取得了优异的性能。与基线方法相比,MFU-Depth将深度误差降低了15.3%,不确定度度量降低了29.0%。
{"title":"MFU-Depth: Modeling and fusing uncertainty for self-supervised multi-frame monocular depth estimation","authors":"Fuji Fu ,&nbsp;Jinfu Yang ,&nbsp;Jiaqi Ma","doi":"10.1016/j.asoc.2026.114705","DOIUrl":"10.1016/j.asoc.2026.114705","url":null,"abstract":"<div><div>Self-supervised monocular depth estimation, valued for its simplified configuration and excellent geometric perception, is gaining attention in autonomous driving and robotics. Mainstream self-supervised multi-frame methods, due to the lack of a unified multi-cue uncertainty representation mechanism, often struggle to effectively reflect depth prediction errors. To address this issue, we propose a self-supervised multi-frame monocular depth estimation method by Modeling and Fusing Uncertainty, termed MFU-Depth. (1) At the probability distribution level, we design an Uncertainty Estimation-based Single-frame Probability Prediction (UE-SPP) module and a Depth-Aware Multi-frame Probability Transformation (DA-MPT) module, achieving unified uncertainty modeling of single-frame and multi-frame cues in the form of probability distributions. Building on these, we establish a Relation Modeling-guided Probability Fusion (RM-PF) mechanism, which adaptively adjusts fusion weights through pixel-wise difference relation modeling, enabling the complementary integration of these two distributions. (2) At the probabilistic self-supervision level, an Information Entropy Uncertainty Loss (IEUL) is devised to further model the uncertainty of both single-frame and fused depth probability distributions, thereby mitigating supervision distortion caused by high-uncertainty pixels. Experimental results show that MFU-Depth achieves exceptional performance on multiple public datasets. Compared to baseline methods, MFU-Depth reduces the depth error by 15.3% and the uncertainty metric by 29.0%.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"191 ","pages":"Article 114705"},"PeriodicalIF":6.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080105","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
MACSENet: A novel lightweight CNN with multi-scale atrous convolutions and attention mechanism for accurate lung cancer detection 基于多尺度亚特卷积和关注机制的新型轻量级CNN精确肺癌检测
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-04-01 Epub Date: 2026-01-23 DOI: 10.1016/j.asoc.2026.114698
Fazal Hadi , Omair Bilal , Sohaib Asif
Lung cancer represents a critical global health challenge, characterized by high mortality rates and complex diagnostic processes. Identifying tumors in CT images manually is a time-intensive and complex task. While deep learning models can aid in the process, their complexity often leads to overfitting, and their single-branch, linear structures struggle to capture multi-scale features, ultimately reducing detection accuracy. This paper presents MACSENet, an innovative lightweight CNN developed to improve early detection and diagnostic accuracy using advanced deep learning techniques. The proposed model combines three key components: a standard CNN for basic feature extraction, a multiscale atrous convolutional module for capturing spatial features at different resolutions, and a squeeze-and-excitation (SE) block to refine channel-wise features through adaptive attention mechanisms. We designed the Multiscale Atrous Feature Extraction Block (MAFEB), which incorporates a multiscale atrous convolution module with varying dilation rates. This approach expands the receptive field without adding extra parameters, capturing intricate tumor details and providing a comprehensive contextual understanding to address the complex morphological variations in lung cancer. The SE block is applied after extracting features from the multiscale atrous convolution module, dynamically refining the feature maps by amplifying key diagnostic information and suppressing irrelevant details. To assess the broader applicability and generalizability of MACSENet, we evaluated it on the publicly available IQ-OTH/NCCD lung cancer dataset, which consists of 1097 CT images from 110 patients, encompassing benign, malignant, and normal cases. Additional experiments were carried out to evaluate the robustness of MACSENet using two other datasets: the Chest CT-Scan dataset, which consists of 1000 images across four classes, and the Lung histopathological images dataset, containing 15,000 images across three classes. The experimental results demonstrate that MACSENet outperforms both traditional deep CNNs and state-of-the-art methods in terms of accuracy and efficiency. Our approach achieved an outstanding accuracy of 99.55 % on the IQ-OTH/NCCD dataset, and 92 % and 99.97 % on the additional datasets while maintaining the smallest parameter size of 0.27 million among all competitors. Additionally, the model exhibited the smallest model size and FLOPS compared to other deep CNNs. Our proposed model is also compared with well-established baseline models including ResNet, DenseNet, and MobileNet series to demonstrate its superior performance in lung cancer detection. The proposed approach provides critical insights to support clinical decision-making for advancing patient care and treatment precision in lung cancer diagnostics.
肺癌是一项重大的全球健康挑战,其特点是死亡率高,诊断过程复杂。人工识别CT图像中的肿瘤是一项耗时且复杂的任务。虽然深度学习模型可以在这一过程中提供帮助,但它们的复杂性往往会导致过拟合,而且它们的单分支线性结构难以捕捉多尺度特征,最终降低了检测精度。本文介绍了MACSENet,一种创新的轻量级CNN,用于使用先进的深度学习技术提高早期检测和诊断的准确性。该模型结合了三个关键组件:用于基本特征提取的标准CNN,用于捕获不同分辨率空间特征的多尺度亚历克斯卷积模块,以及通过自适应注意机制来细化通道特征的挤压和激励(SE)块。我们设计了多尺度亚光束特征提取块(mateb),它包含了一个具有不同膨胀率的多尺度亚光束卷积模块。这种方法在不增加额外参数的情况下扩展了感受野,捕获了复杂的肿瘤细节,并提供了全面的背景理解,以解决肺癌中复杂的形态变化。从多尺度亚属性卷积模块中提取特征,通过放大关键诊断信息和抑制无关细节来动态细化特征映射,然后应用SE块。为了评估MACSENet更广泛的适用性和泛化性,我们在公开的IQ-OTH/NCCD肺癌数据集上对其进行了评估,该数据集由110名患者的1097张CT图像组成,包括良性、恶性和正常病例。使用另外两个数据集进行了额外的实验来评估MACSENet的鲁棒性:胸部ct扫描数据集,包含四个类别的1000张图像,以及肺组织病理学图像数据集,包含三个类别的15,000张图像。实验结果表明,MACSENet在精度和效率方面优于传统的深度cnn和最先进的方法。我们的方法在IQ-OTH/NCCD数据集上取得了99.55 %的出色准确率,在其他数据集上达到了92 %和99.97 %,同时在所有竞争对手中保持了最小的参数大小0.27万。此外,与其他深度cnn相比,该模型具有最小的模型尺寸和FLOPS。我们提出的模型还与已建立的基线模型(包括ResNet, DenseNet和MobileNet系列)进行了比较,以证明其在肺癌检测方面的优越性能。所提出的方法为支持临床决策提供了关键的见解,以提高肺癌诊断的患者护理和治疗精度。
{"title":"MACSENet: A novel lightweight CNN with multi-scale atrous convolutions and attention mechanism for accurate lung cancer detection","authors":"Fazal Hadi ,&nbsp;Omair Bilal ,&nbsp;Sohaib Asif","doi":"10.1016/j.asoc.2026.114698","DOIUrl":"10.1016/j.asoc.2026.114698","url":null,"abstract":"<div><div>Lung cancer represents a critical global health challenge, characterized by high mortality rates and complex diagnostic processes. Identifying tumors in CT images manually is a time-intensive and complex task. While deep learning models can aid in the process, their complexity often leads to overfitting, and their single-branch, linear structures struggle to capture multi-scale features, ultimately reducing detection accuracy. This paper presents MACSENet, an innovative lightweight CNN developed to improve early detection and diagnostic accuracy using advanced deep learning techniques. The proposed model combines three key components: a standard CNN for basic feature extraction, a multiscale atrous convolutional module for capturing spatial features at different resolutions, and a squeeze-and-excitation (SE) block to refine channel-wise features through adaptive attention mechanisms. We designed the Multiscale Atrous Feature Extraction Block (MAFEB), which incorporates a multiscale atrous convolution module with varying dilation rates. This approach expands the receptive field without adding extra parameters, capturing intricate tumor details and providing a comprehensive contextual understanding to address the complex morphological variations in lung cancer. The SE block is applied after extracting features from the multiscale atrous convolution module, dynamically refining the feature maps by amplifying key diagnostic information and suppressing irrelevant details. To assess the broader applicability and generalizability of MACSENet, we evaluated it on the publicly available IQ-OTH/NCCD lung cancer dataset, which consists of 1097 CT images from 110 patients, encompassing benign, malignant, and normal cases. Additional experiments were carried out to evaluate the robustness of MACSENet using two other datasets: the Chest CT-Scan dataset, which consists of 1000 images across four classes, and the Lung histopathological images dataset, containing 15,000 images across three classes. The experimental results demonstrate that MACSENet outperforms both traditional deep CNNs and state-of-the-art methods in terms of accuracy and efficiency. Our approach achieved an outstanding accuracy of 99.55 % on the IQ-OTH/NCCD dataset, and 92 % and 99.97 % on the additional datasets while maintaining the smallest parameter size of 0.27 million among all competitors. Additionally, the model exhibited the smallest model size and FLOPS compared to other deep CNNs. Our proposed model is also compared with well-established baseline models including ResNet, DenseNet, and MobileNet series to demonstrate its superior performance in lung cancer detection. The proposed approach provides critical insights to support clinical decision-making for advancing patient care and treatment precision in lung cancer diagnostics.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"191 ","pages":"Article 114698"},"PeriodicalIF":6.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080113","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 two-stage solution incorporating large neighborhood search for the priority-aware 2D bin packing problem in furniture manufacturing 基于大邻域搜索的家具制造中优先级感知二维装箱问题的两阶段解决方案
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-04-01 Epub Date: 2026-01-20 DOI: 10.1016/j.asoc.2026.114659
Jianming Wang , Yang Xu , Zhouwang Yang
This paper explores the two-dimensional bin packing problem involving both rectangular and irregular shapes, with a focus on part priority, a critical factor in the furniture manufacturing and woodworking industries. Part priority is essential due to specific processing requirements and customer urgency. We propose a two-stage methodology aimed at minimizing both the number of bins containing priority parts and the total number of bins utilized. In the first stage, multiple parts are iteratively paired and approximated as rectangles to maximize the overall benefit of all pairings, diverging from traditional methods that focus on pairing two specific parts. The second stage introduces a rectangular packing module that incorporates two large-neighborhood search (LNS) algorithms. This module employs efficient operators that respect the priority objective, addressing the difficulty of large-scale priority problems. We evaluate the strengths and limitations of the rectangularization approach through experiments on irregular bin packing benchmarks and assess its applicability. Experiments on rectangular benchmark instances demonstrate the superiority of our approach in large-scale scenarios. Furthermore, tests on industrial data reveal that our method increases material utilization by 0.86% and reduces the number of priority bins by 1.71%, surpassing leading commercial software in both objectives. These results suggest that the proposed approach can be integrated into cutting software to provide practical and efficient solutions, thereby advancing intelligent manufacturing.
本文探讨了涉及矩形和不规则形状的二维装箱问题,重点是零件优先级,这是家具制造和木工行业的一个关键因素。由于特殊的加工要求和客户的紧急情况,零件优先级是必不可少的。我们提出了一种两阶段的方法,旨在最小化包含优先级部分的箱子的数量和使用的箱子的总数。在第一阶段,将多个部分迭代配对并近似为矩形,以最大限度地提高所有配对的总体效益,这与传统方法专注于配对两个特定部分的方法不同。第二阶段介绍了一个矩形封装模块,该模块包含两个大邻域搜索(LNS)算法。该模块采用尊重优先目标的高效算子,解决了大规模优先问题的难点。我们通过不规则箱子包装基准的实验来评估矩形化方法的优势和局限性,并评估其适用性。矩形基准实例的实验证明了我们的方法在大规模场景中的优越性。此外,对工业数据的测试表明,我们的方法提高了0.86%的材料利用率,减少了1.71%的优先箱数,在这两个目标上都超过了领先的商业软件。这些结果表明,该方法可以集成到切割软件中,提供实用高效的解决方案,从而推进智能制造。
{"title":"A two-stage solution incorporating large neighborhood search for the priority-aware 2D bin packing problem in furniture manufacturing","authors":"Jianming Wang ,&nbsp;Yang Xu ,&nbsp;Zhouwang Yang","doi":"10.1016/j.asoc.2026.114659","DOIUrl":"10.1016/j.asoc.2026.114659","url":null,"abstract":"<div><div>This paper explores the two-dimensional bin packing problem involving both rectangular and irregular shapes, with a focus on part priority, a critical factor in the furniture manufacturing and woodworking industries. Part priority is essential due to specific processing requirements and customer urgency. We propose a two-stage methodology aimed at minimizing both the number of bins containing priority parts and the total number of bins utilized. In the first stage, multiple parts are iteratively paired and approximated as rectangles to maximize the overall benefit of all pairings, diverging from traditional methods that focus on pairing two specific parts. The second stage introduces a rectangular packing module that incorporates two large-neighborhood search (LNS) algorithms. This module employs efficient operators that respect the priority objective, addressing the difficulty of large-scale priority problems. We evaluate the strengths and limitations of the rectangularization approach through experiments on irregular bin packing benchmarks and assess its applicability. Experiments on rectangular benchmark instances demonstrate the superiority of our approach in large-scale scenarios. Furthermore, tests on industrial data reveal that our method increases material utilization by 0.86% and reduces the number of priority bins by 1.71%, surpassing leading commercial software in both objectives. These results suggest that the proposed approach can be integrated into cutting software to provide practical and efficient solutions, thereby advancing intelligent manufacturing.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"191 ","pages":"Article 114659"},"PeriodicalIF":6.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080197","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 differential evolutionary algorithm improvement framework based on artificial potential fields 基于人工势场的差分进化算法改进框架
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-04-01 Epub Date: 2026-01-24 DOI: 10.1016/j.asoc.2026.114714
Zhe Yang , Libao Deng , Xianxin Mao , Lili Zhang
The Artificial Potential Field (APF) method, widely utilized in path planning, uses virtual environmental forces derived from potential field gradients for guidance. While Differential Evolution (DE) algorithms are recognized for their simplicity and robust global optimization capabilities, they often suffer from premature convergence and reduced search efficiency in complex scenarios. Motivated by the similarity between APF pathfinding and DE optimization, this study proposes an APF-inspired framework that utilizes virtual forces to guide the population. Attractive forces guide individuals toward potential optima, while repulsive forces generated by treating inferior solutions as virtual obstacles mitigate the risk of stagnation. This mechanism effectively steers the population toward promising areas, thereby enhancing search efficiency. Furthermore, an integrated adaptive strategy enhances performance by dynamically adjusting key parameters based on problem characteristics. Comprehensive experiments on the CEC2020 benchmark suite and 36 real-world engineering problems validate the effectiveness of the framework. The results indicate performance improvements over baseline algorithms and competitiveness in comparative studies.
人工势场法(Artificial Potential Field, APF)是一种利用势场梯度产生的虚拟环境力进行路径引导的方法,在路径规划中得到广泛应用。差分进化(DE)算法以其简单性和鲁棒的全局优化能力而闻名,但在复杂场景中,它们往往存在过早收敛和搜索效率降低的问题。基于APF寻路与DE优化之间的相似性,本研究提出了一种基于APF的框架,该框架利用虚拟力来引导种群。吸引力引导个体走向潜在的最佳状态,而将次等解决方案视为虚拟障碍所产生的排斥力则减轻了停滞的风险。这一机制有效地引导人们转向有希望的领域,从而提高搜索效率。此外,集成自适应策略通过根据问题特征动态调整关键参数来提高性能。在CEC2020基准测试套件和36个实际工程问题上的综合实验验证了该框架的有效性。结果表明性能优于基线算法和竞争力的比较研究。
{"title":"A differential evolutionary algorithm improvement framework based on artificial potential fields","authors":"Zhe Yang ,&nbsp;Libao Deng ,&nbsp;Xianxin Mao ,&nbsp;Lili Zhang","doi":"10.1016/j.asoc.2026.114714","DOIUrl":"10.1016/j.asoc.2026.114714","url":null,"abstract":"<div><div>The Artificial Potential Field (APF) method, widely utilized in path planning, uses virtual environmental forces derived from potential field gradients for guidance. While Differential Evolution (DE) algorithms are recognized for their simplicity and robust global optimization capabilities, they often suffer from premature convergence and reduced search efficiency in complex scenarios. Motivated by the similarity between APF pathfinding and DE optimization, this study proposes an APF-inspired framework that utilizes virtual forces to guide the population. Attractive forces guide individuals toward potential optima, while repulsive forces generated by treating inferior solutions as virtual obstacles mitigate the risk of stagnation. This mechanism effectively steers the population toward promising areas, thereby enhancing search efficiency. Furthermore, an integrated adaptive strategy enhances performance by dynamically adjusting key parameters based on problem characteristics. Comprehensive experiments on the CEC2020 benchmark suite and 36 real-world engineering problems validate the effectiveness of the framework. The results indicate performance improvements over baseline algorithms and competitiveness in comparative studies.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"192 ","pages":"Article 114714"},"PeriodicalIF":6.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146096146","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
Development of federated learning neural networks with combined horizontal and vertical data partitioning 结合水平和垂直数据划分的联邦学习神经网络的发展
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-04-01 Epub Date: 2026-02-02 DOI: 10.1016/j.asoc.2026.114734
Amir Anees , Matthew Field , Lois Holloway
Federated learning trains a global machine learning model without moving data that is distributed geographically, thereby preserving privacy. Most of the existing works focus on either horizontal- or vertical-federated learning. This paper proposes two new federated learning frameworks, addressing different dataset setups, for combined horizontal and vertical data-partitioned scenarios based on neural networks. The data is horizontally partitioned for a subset of clients, referred to as horizontal clients, and it is further vertically partitioned with another client, labelled as a vertical client. In the first proposed framework, referred to as ‘Horizontal-OutputFed’, the output feature is stored at clients with horizontal partitioning, while in the second proposed framework, referred to as ‘Vertical-OutputFed’, the output feature is stored at the vertical client. The accuracy, loss and convergence rate of the Horizontal-OutputFed are the same as those achieved with a horizontally partitioned federated learning framework. Furthermore, the impact of non-identically and independently distributed data is the same in both the Horizontal-OutputFed and purely horizontal federated learning setups for combined features. Compared to a centrally trained model, the globally trained model in the Vertical-OutputFed has the same performance metrics such as accuracy and convergence rate. Moreover, there is no effect of imbalanced data on the performance of the Vertical-OutputFed, contrary to some of the previous works on individual horizontal- or vertical-federated learning. Privacy attack analysis were conducted for active, passive, white-box, and black-box attacks demonstrating no risk of input and output feature leakage, nor any data inference from the resulting models or while sharing hidden layers’ outputs for either of the combined federated approaches.
联邦学习训练一个全局机器学习模型,而不移动地理上分布的数据,从而保护隐私。现有的大部分工作都集中在水平或垂直联合学习上。本文提出了两个新的联邦学习框架,针对不同的数据集设置,基于神经网络的组合水平和垂直数据分区场景。数据为一个客户机子集(称为水平客户机)进行水平分区,并与另一个客户机(标记为垂直客户机)进一步进行垂直分区。在第一个被提议的框架(称为“horizontal - outputfed”)中,输出特性存储在具有水平分区的客户机上,而在第二个被提议的框架(称为“vertical - outputfed”)中,输出特性存储在垂直客户机上。Horizontal-OutputFed的准确率、损失和收敛率与水平分割的联邦学习框架相同。此外,在针对组合特征的水平- outputfed和纯水平联邦学习设置中,非相同和独立分布数据的影响是相同的。与集中训练的模型相比,Vertical-OutputFed中的全局训练模型具有相同的性能指标,如准确性和收敛率。此外,与之前关于个人水平或垂直联邦学习的一些研究相反,数据不平衡对Vertical-OutputFed的性能没有影响。对主动、被动、白盒和黑盒攻击进行了隐私攻击分析,表明没有输入和输出特征泄漏的风险,也没有来自结果模型的任何数据推断,也没有共享两种联合方法的隐藏层输出的风险。
{"title":"Development of federated learning neural networks with combined horizontal and vertical data partitioning","authors":"Amir Anees ,&nbsp;Matthew Field ,&nbsp;Lois Holloway","doi":"10.1016/j.asoc.2026.114734","DOIUrl":"10.1016/j.asoc.2026.114734","url":null,"abstract":"<div><div>Federated learning trains a global machine learning model without moving data that is distributed geographically, thereby preserving privacy. Most of the existing works focus on either horizontal- or vertical-federated learning. This paper proposes two new federated learning frameworks, addressing different dataset setups, for combined horizontal and vertical data-partitioned scenarios based on neural networks. The data is horizontally partitioned for a subset of clients, referred to as horizontal clients, and it is further vertically partitioned with another client, labelled as a vertical client. In the first proposed framework, referred to as ‘Horizontal-OutputFed’, the output feature is stored at clients with horizontal partitioning, while in the second proposed framework, referred to as ‘Vertical-OutputFed’, the output feature is stored at the vertical client. The accuracy, loss and convergence rate of the Horizontal-OutputFed are the same as those achieved with a horizontally partitioned federated learning framework. Furthermore, the impact of non-identically and independently distributed data is the same in both the Horizontal-OutputFed and purely horizontal federated learning setups for combined features. Compared to a centrally trained model, the globally trained model in the Vertical-OutputFed has the same performance metrics such as accuracy and convergence rate. Moreover, there is no effect of imbalanced data on the performance of the Vertical-OutputFed, contrary to some of the previous works on individual horizontal- or vertical-federated learning. Privacy attack analysis were conducted for active, passive, white-box, and black-box attacks demonstrating no risk of input and output feature leakage, nor any data inference from the resulting models or while sharing hidden layers’ outputs for either of the combined federated approaches.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"192 ","pages":"Article 114734"},"PeriodicalIF":6.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191516","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
Optimal scheduling of integrated energy systems with power-to-hydrogen for flexible supply-demand balance via Q-learning-enhanced grey wolf optimizer 基于q -学习增强灰狼优化器的电转氢综合能源系统灵活供需平衡优化调度
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-04-01 Epub Date: 2026-02-07 DOI: 10.1016/j.asoc.2026.114795
Kuiyuan Pan , Tianhe Sun , Xinfu Pang , Zedong Zheng , Haibo Li
The integrated energy system (IES) has garnered increasing attention as an effective means of optimizing the utilization of multiple energy sources. With the growing share of renewable energy, enhancing the flexibility of system operation has become a critical issue. This paper proposes an optimal scheduling model for IES that incorporates flexible supply-demand balance constraints. Firstly, a quantitative model for flexible resources is introduced, followed by the formulation of a flexible supply-demand balance constraint model. Secondly, focusing on minimizing operating costs, an optimal scheduling model for IES is developed, incorporating power-to-hydrogen (P2H) technology and considering the flexibility of supply-demand balance constraints. Finally, a grey wolf optimizer (GWO) based on Q-learning (Q-GWO) is designed to solve the optimal scheduling model. The Q-learning algorithm is used to dynamically adjust the search factor of the Q-GWO, thereby enhancing the algorithm's search capability. Simulation results under various scenarios demonstrate that the proposed optimization model significantly improves the flexibility and economy of system operation while reducing the wind curtailment rate. The superiority of the Q-GWO algorithm in solving this problem is confirmed by comparing its convergence performance with that of other algorithms.
综合能源系统(IES)作为一种优化多种能源利用的有效手段,越来越受到人们的关注。随着可再生能源比重的不断增加,提高系统运行的灵活性已成为一个关键问题。本文提出了一种考虑柔性供需平衡约束的IES最优调度模型。首先介绍了柔性资源的定量模型,然后建立了柔性供需平衡约束模型。其次,以运营成本最小化为目标,结合P2H技术,考虑供需平衡约束的灵活性,建立了IES最优调度模型。最后,设计了一个基于q -学习的灰狼优化器(GWO)来求解最优调度模型。采用Q-learning算法动态调整Q-GWO的搜索因子,增强算法的搜索能力。各种场景下的仿真结果表明,所提出的优化模型在降低弃风率的同时,显著提高了系统运行的灵活性和经济性。通过与其他算法的收敛性能比较,证实了Q-GWO算法在解决这一问题方面的优越性。
{"title":"Optimal scheduling of integrated energy systems with power-to-hydrogen for flexible supply-demand balance via Q-learning-enhanced grey wolf optimizer","authors":"Kuiyuan Pan ,&nbsp;Tianhe Sun ,&nbsp;Xinfu Pang ,&nbsp;Zedong Zheng ,&nbsp;Haibo Li","doi":"10.1016/j.asoc.2026.114795","DOIUrl":"10.1016/j.asoc.2026.114795","url":null,"abstract":"<div><div>The integrated energy system (IES) has garnered increasing attention as an effective means of optimizing the utilization of multiple energy sources. With the growing share of renewable energy, enhancing the flexibility of system operation has become a critical issue. This paper proposes an optimal scheduling model for IES that incorporates flexible supply-demand balance constraints. Firstly, a quantitative model for flexible resources is introduced, followed by the formulation of a flexible supply-demand balance constraint model. Secondly, focusing on minimizing operating costs, an optimal scheduling model for IES is developed, incorporating power-to-hydrogen (P2H) technology and considering the flexibility of supply-demand balance constraints. Finally, a grey wolf optimizer (GWO) based on Q-learning (Q-GWO) is designed to solve the optimal scheduling model. The Q-learning algorithm is used to dynamically adjust the search factor of the Q-GWO, thereby enhancing the algorithm's search capability. Simulation results under various scenarios demonstrate that the proposed optimization model significantly improves the flexibility and economy of system operation while reducing the wind curtailment rate. The superiority of the Q-GWO algorithm in solving this problem is confirmed by comparing its convergence performance with that of other algorithms.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"192 ","pages":"Article 114795"},"PeriodicalIF":6.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191850","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
Soft-label guided multi-granularity prompts learning for human-object interaction detection 软标签引导的多粒度提示学习用于人-物交互检测
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-04-01 Epub Date: 2026-02-05 DOI: 10.1016/j.asoc.2026.114765
Xiaoqian Han , Xiaowei Zhang , Guanglin Niu , Mingliang Zhou , Zhenkuan Pan
Vision-language models (VLMs) have driven substantial progress in human-object interaction (HOI) detection. However, existing VLM-based HOI detectors typically rely on coarse multimodal prompts for knowledge transfer, which makes it difficult to comprehensively capture interaction-relevant contextual cues and consequently weakens generalization to HOI detection. Meanwhile, hard-label supervised learning fundamentally ignores semantic correlations among interaction categories, which tends to suppress knowledge transfer due to misalignment with the continuous semantic similarity structure encoded by VLM representations in the embedding space. To address these challenges, we propose SMPL, a Soft-label guided Multi-granularity Prompt Learning model for HOI detection, which facilitates prompt learning by jointly capturing multi-level interaction cues and providing semantically calibrated supervision aligned with VLM embeddings. Specifically, we design multi-granularity visual and textual prompts to capture interaction cues at different levels of detail, thereby improving generalization to interaction categories. Moreover, we introduce soft-label learning to jointly optimize interaction classification with the hard-labels and soft-label supervision, which naturally reflects interaction-level semantic similarity, enabling the model to learn implicit interaction relations without additional annotations. Extensive experiments demonstrate that SMPL achieves 38.97 mAP on the HICO-DET dataset and improves performance by 2.64 mAP over the current state of the art on the challenging Rare split. SMPL also performs strongly under multiple zero-shot HOI settings, demonstrating excellent generalization to unseen interactions. The code and models are available at https://github.com/hxqstree/SMPL.
视觉语言模型(VLMs)推动了人-物交互(HOI)检测的实质性进展。然而,现有的基于vlm的HOI检测器通常依赖于粗糙的多模态提示进行知识转移,这使得难以全面捕获与交互相关的上下文线索,从而削弱了对HOI检测的泛化。同时,硬标签监督学习从根本上忽略了交互类别之间的语义相关性,由于与嵌入空间中VLM表示编码的连续语义相似结构不一致,容易抑制知识迁移。为了解决这些挑战,我们提出了一种用于HOI检测的软标签引导多粒度提示学习模型SMPL,该模型通过联合捕获多层次交互线索并提供与VLM嵌入一致的语义校准监督来促进提示学习。具体来说,我们设计了多粒度的视觉和文本提示来捕获不同细节级别的交互线索,从而提高了对交互类别的泛化。此外,我们引入软标签学习,与硬标签和软标签监督共同优化交互分类,这自然地反映了交互级的语义相似度,使模型无需额外的注释即可学习隐含的交互关系。大量的实验表明,SMPL在HICO-DET数据集上实现了38.97 mAP,并在具有挑战性的Rare分割上提高了2.64 mAP的性能。SMPL在多个零射击HOI设置下也表现出色,展示了对看不见的相互作用的出色泛化。代码和模型可在https://github.com/hxqstree/SMPL上获得。
{"title":"Soft-label guided multi-granularity prompts learning for human-object interaction detection","authors":"Xiaoqian Han ,&nbsp;Xiaowei Zhang ,&nbsp;Guanglin Niu ,&nbsp;Mingliang Zhou ,&nbsp;Zhenkuan Pan","doi":"10.1016/j.asoc.2026.114765","DOIUrl":"10.1016/j.asoc.2026.114765","url":null,"abstract":"<div><div>Vision-language models (VLMs) have driven substantial progress in human-object interaction (HOI) detection. However, existing VLM-based HOI detectors typically rely on coarse multimodal prompts for knowledge transfer, which makes it difficult to comprehensively capture interaction-relevant contextual cues and consequently weakens generalization to HOI detection. Meanwhile, hard-label supervised learning fundamentally ignores semantic correlations among interaction categories, which tends to suppress knowledge transfer due to misalignment with the continuous semantic similarity structure encoded by VLM representations in the embedding space. To address these challenges, we propose SMPL, a <strong>S</strong>oft-label guided <strong>M</strong>ulti-granularity <strong>P</strong>rompt <strong>L</strong>earning model for HOI detection, which facilitates prompt learning by jointly capturing multi-level interaction cues and providing semantically calibrated supervision aligned with VLM embeddings. Specifically, we design multi-granularity visual and textual prompts to capture interaction cues at different levels of detail, thereby improving generalization to interaction categories. Moreover, we introduce soft-label learning to jointly optimize interaction classification with the hard-labels and soft-label supervision, which naturally reflects interaction-level semantic similarity, enabling the model to learn implicit interaction relations without additional annotations. Extensive experiments demonstrate that SMPL achieves 38.97 mAP on the HICO-DET dataset and improves performance by 2.64 mAP over the current state of the art on the challenging Rare split. SMPL also performs strongly under multiple zero-shot HOI settings, demonstrating excellent generalization to unseen interactions. The code and models are available at <span><span>https://github.com/hxqstree/SMPL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"192 ","pages":"Article 114765"},"PeriodicalIF":6.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An intelligent over-sampling framework with physics-driven guidance for noise robust imbalanced rolling bearing fault diagnosis 基于物理驱动的智能过采样框架噪声鲁棒不平衡滚动轴承故障诊断
IF 6.6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2026-04-01 Epub Date: 2026-02-06 DOI: 10.1016/j.asoc.2026.114791
Weidong Jiao , Daxuan Lin , Zhilin Dong , Jianfeng Sun , Wanxiu Xu , Xiaohao Chen , Siyu Liu , Yonghua Jiang
Driven by advances in deep learning, intelligent fault diagnosis is widely deployed in predictive maintenance and reliability assurance for rotating machinery. However, these methodologies hinge on noiseless, balanced data—an ideal that rarely aligns with real-world engineering scenarios. To address this issue, a Physics-driven Feature Space Synthetic Minority Over-Sampling Technique (PFS-SMOTE) is introduced that augments minority-class samples in the feature space by incorporating physical prior knowledge, thereby improving the performance of intelligent fault-diagnosis models. Initially, a Neural Blind Deconvolution Mechanism (NBDM) is proposed, which utilizes adaptive fuzzy kernels optimized via complex frequency domain vectors to effectively extract fault impulse features. Next, we construct the Multi-Resolution Time-Frequency Convolution (MRTFConv) layer, utilizing Short-Time Fourier Transform-inspired kernels with adaptive Gaussian temporal envelopes and learnable oscillatory components for physically interpretable time-frequency representations. Building upon these innovations, a deep Siamese Network, integrating NBDM and MRTFConv, maps original data into a physically separable feature space, guided by a physics-informed loss function encompassing contrastive loss, time-frequency consistency loss, and fuzzy kernel consistency loss. Ultimately, PFS-SMOTE generates synthetic fault samples in this well-separated space, ensuring a balanced dataset. Experimental validation across two bearing datasets demonstrates that PFS-SMOTE achieves 100 % accuracy under an imbalance ratio (IR) of 1:10 and maintains 93 % accuracy at SNR= 0 dB. Even under extreme conditions with IR= 1:40 and SNR= 4 dB, the method still achieves an accuracy rate of 89.5 %.
在深度学习技术的推动下,智能故障诊断在旋转机械的预测性维护和可靠性保障中得到了广泛应用。然而,这些方法依赖于无噪声、平衡的数据——这种理想很少与现实世界的工程场景保持一致。为了解决这一问题,提出了一种物理驱动的特征空间合成少数派过采样技术(PFS-SMOTE),该技术通过结合物理先验知识来增加特征空间中的少数派样本,从而提高智能故障诊断模型的性能。首先,提出了一种神经盲反卷积机制(NBDM),利用复频域向量优化的自适应模糊核有效提取故障脉冲特征。接下来,我们构建了多分辨率时频卷积(MRTFConv)层,利用短时傅立叶变换启发的核,具有自适应高斯时间包络和可学习的振荡分量,用于物理可解释的时频表示。在这些创新的基础上,一个深度Siamese网络,集成了NBDM和MRTFConv,将原始数据映射到物理上可分离的特征空间,由包含对比损失、时频一致性损失和模糊核一致性损失的物理通知损失函数指导。最终,PFS-SMOTE在这个分离良好的空间中生成合成故障样本,确保数据集的平衡。在两个轴承数据集上的实验验证表明,PFS-SMOTE在不平衡比(IR)为1:10时达到100 %的精度,在信噪比= 0 dB时保持93 %的精度。即使在IR= 1:40,信噪比= 4 dB的极端条件下,该方法仍能达到89.5 %的准确率。
{"title":"An intelligent over-sampling framework with physics-driven guidance for noise robust imbalanced rolling bearing fault diagnosis","authors":"Weidong Jiao ,&nbsp;Daxuan Lin ,&nbsp;Zhilin Dong ,&nbsp;Jianfeng Sun ,&nbsp;Wanxiu Xu ,&nbsp;Xiaohao Chen ,&nbsp;Siyu Liu ,&nbsp;Yonghua Jiang","doi":"10.1016/j.asoc.2026.114791","DOIUrl":"10.1016/j.asoc.2026.114791","url":null,"abstract":"<div><div>Driven by advances in deep learning, intelligent fault diagnosis is widely deployed in predictive maintenance and reliability assurance for rotating machinery. However, these methodologies hinge on noiseless, balanced data—an ideal that rarely aligns with real-world engineering scenarios. To address this issue, a Physics-driven Feature Space Synthetic Minority Over-Sampling Technique (PFS-SMOTE) is introduced that augments minority-class samples in the feature space by incorporating physical prior knowledge, thereby improving the performance of intelligent fault-diagnosis models. Initially, a Neural Blind Deconvolution Mechanism (NBDM) is proposed, which utilizes adaptive fuzzy kernels optimized via complex frequency domain vectors to effectively extract fault impulse features. Next, we construct the Multi-Resolution Time-Frequency Convolution (MRTFConv) layer, utilizing Short-Time Fourier Transform-inspired kernels with adaptive Gaussian temporal envelopes and learnable oscillatory components for physically interpretable time-frequency representations. Building upon these innovations, a deep Siamese Network, integrating NBDM and MRTFConv, maps original data into a physically separable feature space, guided by a physics-informed loss function encompassing contrastive loss, time-frequency consistency loss, and fuzzy kernel consistency loss. Ultimately, PFS-SMOTE generates synthetic fault samples in this well-separated space, ensuring a balanced dataset. Experimental validation across two bearing datasets demonstrates that PFS-SMOTE achieves 100 % accuracy under an imbalance ratio (IR) of 1:10 and maintains 93 % accuracy at SNR= 0 dB. Even under extreme conditions with IR= 1:40 and SNR= 4 dB, the method still achieves an accuracy rate of 89.5 %.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"192 ","pages":"Article 114791"},"PeriodicalIF":6.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191781","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
Applied Soft Computing
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.
﹀
mjeditor
×
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学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
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