Information Sciences最新文献_第8页

LB-IRG: A hybrid model parameter solving algorithm based on text data LB-IRG：一种基于文本数据的混合模型参数求解算法

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-13 DOI: 10.1016/j.ins.2025.122986

Puzheng Quan, Jiaqiu Hu, Jun Tu

This paper presents a novel algorithm for parameter estimation specifically designed for non-Gaussian structured discrete data, aiming to construct accurate and generalizable representations of spatially intelligent information. Traditional approaches for such data typically rely on the maximum likelihood criterion or its equivalent Kullback–Leibler divergence criterion to form the objective function. However, these methods do not provide an explicit generalization mechanism to effectively guide parameter estimation. Furthermore, gradient-based methods commonly employ stochastic gradient descent, which requires inverse function reparameterization when handling complex functional distributions such as the Dirichlet distribution, resulting in high computational complexity. To address these challenges, the proposed algorithm introduces an iterative framework that alternates between free energy optimization and likelihood maximization, while simultaneously incorporating mutual information to enhance robustness and prevent overfitting. In the updating strategy, a differential method is employed to reparameterize the gradient directly, thereby avoiding inverse function calculations and reducing iteration time. Experimental validation is conducted on both discrete text datasets and synthetic datasets, with performance evaluated through clustering accuracy, comparative analyses with alternative algorithms, and ablation studies. Results demonstrate that the proposed method achieves superior generalization ability and more efficient parameter iteration compared with conventional techniques.

本文提出了一种针对非高斯结构离散数据的参数估计新算法，旨在构建空间智能信息的精确和可推广表示。这类数据的传统方法通常依赖于极大似然准则或其等效的Kullback-Leibler散度准则来形成目标函数。然而，这些方法并没有提供一个明确的泛化机制来有效地指导参数估计。此外，基于梯度的方法通常采用随机梯度下降，在处理Dirichlet分布等复杂函数分布时需要逆函数重新参数化，导致计算复杂度高。为了解决这些挑战，提出的算法引入了一个迭代框架，在自由能优化和似然最大化之间交替，同时结合互信息来增强鲁棒性并防止过拟合。在更新策略中，采用微分法直接对梯度进行重新参数化，避免了逆函数计算，减少了迭代时间。实验验证在离散文本数据集和合成数据集上进行，并通过聚类准确性、与替代算法的比较分析和消融研究来评估性能。结果表明，与传统方法相比，该方法具有更好的泛化能力和更高的参数迭代效率。

{"title":"LB-IRG: A hybrid model parameter solving algorithm based on text data","authors":"Puzheng Quan, Jiaqiu Hu, Jun Tu","doi":"10.1016/j.ins.2025.122986","DOIUrl":"10.1016/j.ins.2025.122986","url":null,"abstract":"<div><div>This paper presents a novel algorithm for parameter estimation specifically designed for non-Gaussian structured discrete data, aiming to construct accurate and generalizable representations of spatially intelligent information. Traditional approaches for such data typically rely on the maximum likelihood criterion or its equivalent Kullback–Leibler divergence criterion to form the objective function. However, these methods do not provide an explicit generalization mechanism to effectively guide parameter estimation. Furthermore, gradient-based methods commonly employ stochastic gradient descent, which requires inverse function reparameterization when handling complex functional distributions such as the Dirichlet distribution, resulting in high computational complexity. To address these challenges, the proposed algorithm introduces an iterative framework that alternates between free energy optimization and likelihood maximization, while simultaneously incorporating mutual information to enhance robustness and prevent overfitting. In the updating strategy, a differential method is employed to reparameterize the gradient directly, thereby avoiding inverse function calculations and reducing iteration time. Experimental validation is conducted on both discrete text datasets and synthetic datasets, with performance evaluated through clustering accuracy, comparative analyses with alternative algorithms, and ablation studies. Results demonstrate that the proposed method achieves superior generalization ability and more efficient parameter iteration compared with conventional techniques.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"734 ","pages":"Article 122986"},"PeriodicalIF":6.8,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841768","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

Learning uncertainty by constructing multi-box uncertainty sets from the datasets with complicated distributions: Validated by robust optimization 从复杂分布的数据集构造多盒不确定性集学习不确定性：鲁棒优化验证

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-13 DOI: 10.1016/j.ins.2025.122988

Shuyu Huang, Zhong Wan

Learning uncertainty of systems by data-driven model plays a fundamental role in information sciences, machine learning and optimal decision-making in an uncertain environment, but it is still a challenge to identify uncertainty from the data with complicated distributional features. In this research, a new computable method is presented to build a non-convex uncertainty set such that it can exactly depict the uncertainty hidden in the collected complex data, which is constructed by solving a mixed integer nonlinear programming model (MINLPM). In virtue of its non-convexity, the volume of such a set is minimized, as well as covering the sample points as many as possible when a confidence level is given. With analysis of structural and analytic properties, an alternative algorithm is proposed to solve this MINLPM. By numerical simulation, the advantages of the proposed data-driven uncertainty sets are demonstrated compared with the existing ones. Preliminary applications in robust optimization further validate their superiority. In conclusion, the proposed method of constructing the uncertainty sets in this research exhibits stronger capability of identifying non-convex distributional structure of samples than the state-of-the-art methods; the robust optimal solution based on this set is beneficial for reduction of over-conservatism in the compared robust optimization approaches, owing to its ability to cover the sample points with the smallest volume.

利用数据驱动模型学习系统的不确定性在信息科学、机器学习和不确定环境下的最优决策中发挥着重要作用，但如何从具有复杂分布特征的数据中识别不确定性仍然是一个挑战。本研究通过求解混合整数非线性规划模型（MINLPM），提出了一种新的可计算方法来构建能准确描述所采集的复杂数据中所隐藏的不确定性的非凸不确定性集。由于其非凸性，在给定置信水平的情况下，该集合的体积被最小化，并覆盖尽可能多的样本点。通过对结构和解析性质的分析，提出了一种求解该MINLPM的替代算法。通过数值仿真，对比了所提出的数据驱动不确定性集与现有不确定性集的优势。在鲁棒优化中的初步应用进一步验证了该方法的优越性。综上所述，本文提出的构造不确定性集的方法比现有方法具有更强的识别样本非凸分布结构的能力；基于该集的鲁棒最优解能够以最小的体积覆盖样本点，有利于减少鲁棒优化方法中的过保守性。

{"title":"Learning uncertainty by constructing multi-box uncertainty sets from the datasets with complicated distributions: Validated by robust optimization","authors":"Shuyu Huang, Zhong Wan","doi":"10.1016/j.ins.2025.122988","DOIUrl":"10.1016/j.ins.2025.122988","url":null,"abstract":"<div><div>Learning uncertainty of systems by data-driven model plays a fundamental role in information sciences, machine learning and optimal decision-making in an uncertain environment, but it is still a challenge to identify uncertainty from the data with complicated distributional features. In this research, a new computable method is presented to build a non-convex uncertainty set such that it can exactly depict the uncertainty hidden in the collected complex data, which is constructed by solving a mixed integer nonlinear programming model (MINLPM). In virtue of its non-convexity, the volume of such a set is minimized, as well as covering the sample points as many as possible when a confidence level is given. With analysis of structural and analytic properties, an alternative algorithm is proposed to solve this MINLPM. By numerical simulation, the advantages of the proposed data-driven uncertainty sets are demonstrated compared with the existing ones. Preliminary applications in robust optimization further validate their superiority. In conclusion, the proposed method of constructing the uncertainty sets in this research exhibits stronger capability of identifying non-convex distributional structure of samples than the state-of-the-art methods; the robust optimal solution based on this set is beneficial for reduction of over-conservatism in the compared robust optimization approaches, owing to its ability to cover the sample points with the smallest volume.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"733 ","pages":"Article 122988"},"PeriodicalIF":6.8,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791683","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

Computationally efficient adaptive fuzzy energy-based control with predefined-time convergence for longitudinal flight dynamics 纵向飞行动力学计算效率自适应模糊能量控制与预定义时间收敛

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-13 DOI: 10.1016/j.ins.2025.122975

Abdessamad El Mobaraky , Khalid Benjelloun , Ahmed Chebak , Khalid Kouiss

This paper presents a predefined-time adaptive fuzzy control framework for longitudinal flight dynamics based on a nonlinear, energy-based formulation using a multi-input multi-output (MIMO) specific-energy model. A predefined-time MIMO control scheme is developed for the total specific energy and the specific energy distribution to explicitly compensate for the coupling between airspeed and altitude dynamics. Then, a recursive backstepping design with a predefined-time command filter is proposed to derive the elevator deflection, circumventing the computational complexity inherent in conventional backstepping approaches. Moreover, to estimate unknown nonlinearities, a novel computationally efficient adaptive fuzzy system is proposed. Its implementation evaluates only the activated membership functions, fuzzy basis functions, and their associated adaptive update laws, thus reducing the computational burden, preventing parameter drift, and relaxing the persistent excitation condition. The proposed framework ensures that the airspeed and altitude tracking errors converge to a small neighborhood of zero within a predefined settling time in the presence of model uncertainties and external disturbances. Simulation results for a fixed-wing unmanned aerial vehicle are used to assess the control strategy, demonstrating accurate tracking without coupling-induced deviations.

本文提出了一种基于非线性、基于能量的纵向飞行动力学模糊控制框架，该框架采用多输入多输出（MIMO）特定能量模型。提出了一种基于总比能量和比能量分布的预定义时间MIMO控制方案，以显式补偿空速和高度动力学之间的耦合。然后，提出了一种带有预定义时间命令滤波器的递归反推设计来推导电梯挠度，避免了传统反推方法固有的计算复杂性。此外，为了估计未知的非线性，提出了一种新的计算效率高的自适应模糊系统。它的实现只评估激活的隶属函数、模糊基函数及其相关的自适应更新规律，从而减少了计算量，防止了参数漂移，并放宽了持续激励条件。该框架保证了在存在模型不确定性和外部干扰的情况下，空速和高度跟踪误差在预定义的稳定时间内收敛到零的小邻域。以某固定翼无人机为例，对其控制策略进行了仿真，验证了该控制策略在无耦合偏差情况下的跟踪精度。

{"title":"Computationally efficient adaptive fuzzy energy-based control with predefined-time convergence for longitudinal flight dynamics","authors":"Abdessamad El Mobaraky , Khalid Benjelloun , Ahmed Chebak , Khalid Kouiss","doi":"10.1016/j.ins.2025.122975","DOIUrl":"10.1016/j.ins.2025.122975","url":null,"abstract":"<div><div>This paper presents a predefined-time adaptive fuzzy control framework for longitudinal flight dynamics based on a nonlinear, energy-based formulation using a multi-input multi-output (MIMO) specific-energy model. A predefined-time MIMO control scheme is developed for the total specific energy and the specific energy distribution to explicitly compensate for the coupling between airspeed and altitude dynamics. Then, a recursive backstepping design with a predefined-time command filter is proposed to derive the elevator deflection, circumventing the computational complexity inherent in conventional backstepping approaches. Moreover, to estimate unknown nonlinearities, a novel computationally efficient adaptive fuzzy system is proposed. Its implementation evaluates only the activated membership functions, fuzzy basis functions, and their associated adaptive update laws, thus reducing the computational burden, preventing parameter drift, and relaxing the persistent excitation condition. The proposed framework ensures that the airspeed and altitude tracking errors converge to a small neighborhood of zero within a predefined settling time in the presence of model uncertainties and external disturbances. Simulation results for a fixed-wing unmanned aerial vehicle are used to assess the control strategy, demonstrating accurate tracking without coupling-induced deviations.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"734 ","pages":"Article 122975"},"PeriodicalIF":6.8,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841760","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

Microblog sentiment classification via a multilayer graph with social and semantic representations using hyperbolic learning 基于双曲学习的带有社交和语义表示的多层图微博情感分类

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-13 DOI: 10.1016/j.ins.2025.122993

Zou Xiaomei , Li Taihao , Han Shoukang

The brevity and noise inherent in microblog texts make interpreting their sentiment accurately challenging. However, social context provides crucial complementary information. Existing methods extract social context features separately using graph neural networks and integrate social and content features via simple concatenation, which fails to capture the crucial interaction between social and semantic information. Moreover, these methods are primarily based on Euclidean space and suffer from structural distortion when representing the underlying hierarchical and scale-free graph. To overcome this limitation, we propose a framework that jointly leverages social and semantic components of microblogs to contextualize their interpretation in this work. Specifically, this is achieved by constructing a heterogeneous multilayer graph that incorporates both social and linguistic information, and building a model that combines large-scale pretraining with transductive learning for sentiment classification. Furthermore, we use hyperbolic graph convolutional networks to learn better microblog representations that account for the scale-free and hierarchical nature of social networks. Our experiments on two real public datasets demonstrate that our proposed method outperforms existing baselines, highlighting the advantages of our multilayer graph and hyperbolic embeddings.

微博文本固有的简洁和噪音给准确解读其情感带来了挑战。然而，社会背景提供了至关重要的补充信息。现有方法利用图神经网络分别提取社会语境特征，并通过简单的拼接将社会特征与内容特征整合，未能捕捉到社会信息与语义信息之间的关键交互作用。此外，这些方法主要基于欧几里得空间，在表示底层分层和无标度图时存在结构失真。为了克服这一限制，我们提出了一个框架，共同利用微博的社交和语义组件，在本工作中对其进行语境化解释。具体来说，这是通过构建一个包含社会和语言信息的异构多层图，以及构建一个将大规模预训练与情感分类的转换学习相结合的模型来实现的。此外，我们使用双曲图卷积网络来学习更好的微博表示，以解释社交网络的无标度和分层性质。我们在两个真实的公共数据集上的实验表明，我们提出的方法优于现有的基线，突出了我们的多层图和双曲嵌入的优势。

{"title":"Microblog sentiment classification via a multilayer graph with social and semantic representations using hyperbolic learning","authors":"Zou Xiaomei , Li Taihao , Han Shoukang","doi":"10.1016/j.ins.2025.122993","DOIUrl":"10.1016/j.ins.2025.122993","url":null,"abstract":"<div><div>The brevity and noise inherent in microblog texts make interpreting their sentiment accurately challenging. However, social context provides crucial complementary information. Existing methods extract social context features separately using graph neural networks and integrate social and content features via simple concatenation, which fails to capture the crucial interaction between social and semantic information. Moreover, these methods are primarily based on Euclidean space and suffer from structural distortion when representing the underlying hierarchical and scale-free graph. To overcome this limitation, we propose a framework that jointly leverages social and semantic components of microblogs to contextualize their interpretation in this work. Specifically, this is achieved by constructing a heterogeneous multilayer graph that incorporates both social and linguistic information, and building a model that combines large-scale pretraining with transductive learning for sentiment classification. Furthermore, we use hyperbolic graph convolutional networks to learn better microblog representations that account for the scale-free and hierarchical nature of social networks. Our experiments on two real public datasets demonstrate that our proposed method outperforms existing baselines, highlighting the advantages of our multilayer graph and hyperbolic embeddings.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"734 ","pages":"Article 122993"},"PeriodicalIF":6.8,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841767","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

Dual-stream interactive diagnosis of spatio-temporal heterogeneous features: Joint modeling with multi-scale variable temporal convolutions and transfer learning 时空异质性特征的双流交互诊断：多尺度可变时间卷积和迁移学习联合建模

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-12 DOI: 10.1016/j.ins.2025.122995

Liangliang Jia , Lingxia Mu , Shihai Wu , Ding Liu

Accurate fault diagnosis of rotating machinery under complex operating conditions is hindered by strongly coupled spatio-temporal dynamics and the limited expressiveness of single-modality representations. To address this challenge, we propose a dual-stream interactive diagnosis framework for heterogeneous spatio-temporal features. In the temporal stream, a multi-scale variable temporal convolutional network is designed to jointly employ multi-scale dilated convolutions and a novel variable ReLU dynamic activation, enabling concurrent capture of short-term transient shocks and long-range periodic attenuation in vibration signals. In the spatial stream, raw one-dimensional signals are first transformed into Gramian angular difference field images; then, a transfer-learning strategy migrates selected layers of a pretrained AlexNet with a hierarchical scheme combining early-layer freezing and layer-wise fine-tuning to extract high-quality spatial descriptors efficiently. A gated fusion module establishes deep correlations between the two modalities and adaptively integrates the branch outputs for precise multi-class fault identification. Experimental results on the Paderborn University bearing dataset, the University of Connecticut gear dataset, and a self-built crystal lifting and rotation mechanism dataset show that the proposed method attains accuracies of 99.58%, 99.54%, and 98.33%, respectively. Comparative and ablation studies further demonstrate that its generalization ability and robustness are significantly superior to those of mainstream diagnostic approaches.

强耦合时空动力学和单模态表征的有限性阻碍了旋转机械在复杂工况下的准确故障诊断。为了解决这一挑战，我们提出了一个针对异构时空特征的双流交互式诊断框架。在时间流中，设计了一个多尺度可变时间卷积网络，联合使用多尺度扩展卷积和一种新的可变ReLU动态激活，可以同时捕获振动信号中的短期瞬态冲击和长期周期性衰减。在空间流中，首先将原始一维信号转换为格拉姆角差场图像；然后，迁移学习策略通过结合早期层冻结和分层微调的分层方案迁移预训练AlexNet的选定层，以有效地提取高质量的空间描述符。门控融合模块在两个模态之间建立深度关联，并自适应集成分支输出，实现精确的多类故障识别。在帕德伯恩大学轴承数据集、康涅狄格大学齿轮数据集和自建晶体提升和旋转机构数据集上的实验结果表明，该方法的精度分别为99.58%、99.54%和98.33%。对比和消融研究进一步证明其泛化能力和稳健性明显优于主流诊断方法。

{"title":"Dual-stream interactive diagnosis of spatio-temporal heterogeneous features: Joint modeling with multi-scale variable temporal convolutions and transfer learning","authors":"Liangliang Jia , Lingxia Mu , Shihai Wu , Ding Liu","doi":"10.1016/j.ins.2025.122995","DOIUrl":"10.1016/j.ins.2025.122995","url":null,"abstract":"<div><div>Accurate fault diagnosis of rotating machinery under complex operating conditions is hindered by strongly coupled spatio-temporal dynamics and the limited expressiveness of single-modality representations. To address this challenge, we propose a dual-stream interactive diagnosis framework for heterogeneous spatio-temporal features. In the temporal stream, a multi-scale variable temporal convolutional network is designed to jointly employ multi-scale dilated convolutions and a novel variable ReLU dynamic activation, enabling concurrent capture of short-term transient shocks and long-range periodic attenuation in vibration signals. In the spatial stream, raw one-dimensional signals are first transformed into Gramian angular difference field images; then, a transfer-learning strategy migrates selected layers of a pretrained AlexNet with a hierarchical scheme combining early-layer freezing and layer-wise fine-tuning to extract high-quality spatial descriptors efficiently. A gated fusion module establishes deep correlations between the two modalities and adaptively integrates the branch outputs for precise multi-class fault identification. Experimental results on the Paderborn University bearing dataset, the University of Connecticut gear dataset, and a self-built crystal lifting and rotation mechanism dataset show that the proposed method attains accuracies of 99.58%, 99.54%, and 98.33%, respectively. Comparative and ablation studies further demonstrate that its generalization ability and robustness are significantly superior to those of mainstream diagnostic approaches.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"733 ","pages":"Article 122995"},"PeriodicalIF":6.8,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791950","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

Path planning and task allocation based on community detection in Voronoi diagrams 基于Voronoi图社区检测的路径规划和任务分配

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-11 DOI: 10.1016/j.ins.2025.122991

Fan Zhang, Jintao Chen, Hongru Ren

A balanced path planning method for multi-robot systems (MRS) in indoor firefighting scenarios is presented by integrating community detection with Voronoi diagrams. The environment is partitioned into communities via the Louvain algorithm, with centroids serving as proxy nodes. Using these nodes together with the obstacles, the system generates Voronoi-based initial paths, which are then decomposed into robot tasks through spectral clustering. A path duplication and allocation mechanism ensures that the multi-robot system performs a cyclic, cooperative search. Designed for time-sensitive fire rescue operations, the method achieves planning within 1.5–2.5 s across residential, maze-like, and complex interiors, and it demonstrates efficient obstacle avoidance and coverage even in densely obstructed layouts. Experiments confirm notable improvements in search accuracy and robustness, enabling the multi-robot system to be rapidly deployed in large-scale missions. The combination of proxy nodes and Voronoi diagrams effectively addresses vertical complexity and spatial fragmentation in high-rise buildings, enabling coordinated navigation through narrow spaces while minimizing mission time. Comparative results verify that the proposed approach offers a significant advantage in time efficiency.

将社区检测与Voronoi图相结合，提出了一种室内消防场景下多机器人系统的平衡路径规划方法。通过Louvain算法将环境划分为社区，以质心作为代理节点。利用这些节点和障碍物，系统生成基于voronoi的初始路径，然后通过谱聚类将其分解为机器人任务。路径复制和分配机制确保多机器人系统执行循环、协作搜索。该方法专为时间敏感型火灾救援行动而设计，可在1.5-2.5秒内完成住宅、迷宫和复杂室内的规划，即使在密集障碍物布局中也能有效地避障和覆盖。实验证实，该方法在搜索精度和鲁棒性方面有显著提高，使多机器人系统能够快速部署到大规模任务中。代理节点和Voronoi图的结合有效地解决了高层建筑中的垂直复杂性和空间碎片化问题，实现了在狭窄空间内的协调导航，同时最大限度地减少了任务时间。对比结果表明，该方法在时间效率上具有显著优势。

{"title":"Path planning and task allocation based on community detection in Voronoi diagrams","authors":"Fan Zhang, Jintao Chen, Hongru Ren","doi":"10.1016/j.ins.2025.122991","DOIUrl":"10.1016/j.ins.2025.122991","url":null,"abstract":"<div><div>A balanced path planning method for multi-robot systems (MRS) in indoor firefighting scenarios is presented by integrating community detection with Voronoi diagrams. The environment is partitioned into communities via the Louvain algorithm, with centroids serving as proxy nodes. Using these nodes together with the obstacles, the system generates Voronoi-based initial paths, which are then decomposed into robot tasks through spectral clustering. A path duplication and allocation mechanism ensures that the multi-robot system performs a cyclic, cooperative search. Designed for time-sensitive fire rescue operations, the method achieves planning within 1.5–2.5 s across residential, maze-like, and complex interiors, and it demonstrates efficient obstacle avoidance and coverage even in densely obstructed layouts. Experiments confirm notable improvements in search accuracy and robustness, enabling the multi-robot system to be rapidly deployed in large-scale missions. The combination of proxy nodes and Voronoi diagrams effectively addresses vertical complexity and spatial fragmentation in high-rise buildings, enabling coordinated navigation through narrow spaces while minimizing mission time. Comparative results verify that the proposed approach offers a significant advantage in time efficiency.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"733 ","pages":"Article 122991"},"PeriodicalIF":6.8,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791681","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

MSTAN: A multi-scale temporal attention network for stock prediction MSTAN：股票预测的多尺度时间关注网络

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-11 DOI: 10.1016/j.ins.2025.122992

Yunzhu Chen , Neng Ye , Wenyu Zhang , Shenghui Song , Xiangming Li

Stock price prediction remains a challenging task due to the inherent non-stationarity, multi-scale temporal dependencies, and complex cross-asset correlations in financial markets. In this paper, we propose MSTAN, a novel Multi-Scale Temporal Attention Network designed to model these spatiotemporal dependencies explicitly. MSTAN constructs multi-scale representations through a two-dimensional periodic reconstruction strategy and employs a Temporal Hybrid Attention mechanism to jointly learn local fluctuations and global trends jointly. Furthermore, MSTAN employs an adaptive module with channel-wise attention to dynamically capture inter-stock dependencies and integrates multi-scale features through a progressive coarse-to-fine fusion strategy. Extensive experiments across diverse datasets, including Chinese A-shares and the US market, demonstrate that MSTAN consistently outperforms state-of-the-art baselines, achieving MAE reductions of up to 28.6 %. Portfolio backtesting further validates its practical utility, showing superior risk-adjusted returns.

由于金融市场固有的非平稳性、多尺度时间依赖性和复杂的跨资产相关性，股票价格预测仍然是一项具有挑战性的任务。在本文中，我们提出了一种新的多尺度时间注意网络MSTAN，旨在明确地模拟这些时空依赖性。MSTAN通过二维周期重构策略构建多尺度表示，采用时间混合注意机制共同学习局部波动和全局趋势。此外，MSTAN采用具有通道智能关注的自适应模块来动态捕获库存之间的依赖关系，并通过渐进的粗到精融合策略集成多尺度特征。在包括中国a股和美国市场在内的不同数据集上进行的广泛实验表明，MSTAN始终优于最先进的基线，MAE降低幅度高达28.6%。投资组合回溯测试进一步验证了其实际效用，显示出更高的风险调整收益。

引用次数: 0

Multi-granularity kernelized fuzzy neighborhood-based outlier detection 基于多粒度核模糊邻域的离群点检测

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-10 DOI: 10.1016/j.ins.2025.122983

Qilin Li , Rui Wang , Sihan Wang , Luoshu Yang , Dezhong Peng , Zhong Yuan , Xinyu Su

Unsupervised outlier detection aims to identify samples that significantly deviate from normal patterns by leveraging the inherent information within the data, without relying on labeled guidance. Density-based outlier detection methods employ various density metrics to evaluate and determine how anomalous a sample is by leveraging the neighborhood density information of samples. Despite their effectiveness, most rely on deterministic density estimation, neglecting data uncertainty, which can lead to misclassification of normal and abnormal samples. Additionally, they often overlook multi-granularity information, limiting their ability to capture complex data structures. In this study, we propose the Multi-granularity Fuzzy Neighborhood Outlier Detection (MFNOD), which measures the degree to which samples are outliers using the density of their multi-granularity fuzzy neighborhoods. Within MFNOD, we first employ a kernelized fuzzy relation to characterize complex relationships between samples. To better capture the multi-granularity characteristics present in the data, we introduce varying bandwidths for the kernelized fuzzy relation, thereby defining novel multi-granularity kernelized fuzzy relations. Based on the new fuzzy relations, we construct multi-granularity kernelized fuzzy neighborhood granules for each sample. Utilizing these information granules, we compute the multi-granularity kernelized fuzzy neighborhood density for each sample and compare its density with the densities of its neighbors to compute the final outlier scores. Experiments conducted with 13 methods across 24 datasets demonstrate that MFNOD achieves superior outlier detection performance, validating its effectiveness. The source code is available at https://github.com/Mxeron/MFNOD.

无监督异常值检测旨在通过利用数据中的固有信息来识别明显偏离正常模式的样本，而不依赖于标记指导。基于密度的离群点检测方法采用各种密度度量，通过利用样本的邻域密度信息来评估和确定样本的异常程度。尽管它们很有效，但大多数依赖于确定性密度估计，忽略了数据的不确定性，这可能导致正常和异常样本的错误分类。此外，它们经常忽略多粒度信息，从而限制了它们捕获复杂数据结构的能力。在这项研究中，我们提出了多粒度模糊邻域离群检测（MFNOD），它使用样本的多粒度模糊邻域密度来测量样本的离群程度。在MFNOD中，我们首先采用核模糊关系来表征样本之间的复杂关系。为了更好地捕捉数据中存在的多粒度特征，我们为核模糊关系引入了不同的带宽，从而定义了新的多粒度核模糊关系。基于新的模糊关系，我们为每个样本构造了多粒度的核模糊邻域颗粒。利用这些信息颗粒，计算每个样本的多粒度核化模糊邻域密度，并将其密度与邻域密度进行比较，计算最终的离群值得分。在24个数据集上使用13种方法进行的实验表明，MFNOD具有优越的离群点检测性能，验证了其有效性。源代码可从https://github.com/Mxeron/MFNOD获得。

{"title":"Multi-granularity kernelized fuzzy neighborhood-based outlier detection","authors":"Qilin Li , Rui Wang , Sihan Wang , Luoshu Yang , Dezhong Peng , Zhong Yuan , Xinyu Su","doi":"10.1016/j.ins.2025.122983","DOIUrl":"10.1016/j.ins.2025.122983","url":null,"abstract":"<div><div>Unsupervised outlier detection aims to identify samples that significantly deviate from normal patterns by leveraging the inherent information within the data, without relying on labeled guidance. Density-based outlier detection methods employ various density metrics to evaluate and determine how anomalous a sample is by leveraging the neighborhood density information of samples. Despite their effectiveness, most rely on deterministic density estimation, neglecting data uncertainty, which can lead to misclassification of normal and abnormal samples. Additionally, they often overlook multi-granularity information, limiting their ability to capture complex data structures. In this study, we propose the Multi-granularity Fuzzy Neighborhood Outlier Detection (MFNOD), which measures the degree to which samples are outliers using the density of their multi-granularity fuzzy neighborhoods. Within MFNOD, we first employ a kernelized fuzzy relation to characterize complex relationships between samples. To better capture the multi-granularity characteristics present in the data, we introduce varying bandwidths for the kernelized fuzzy relation, thereby defining novel multi-granularity kernelized fuzzy relations. Based on the new fuzzy relations, we construct multi-granularity kernelized fuzzy neighborhood granules for each sample. Utilizing these information granules, we compute the multi-granularity kernelized fuzzy neighborhood density for each sample and compare its density with the densities of its neighbors to compute the final outlier scores. Experiments conducted with 13 methods across 24 datasets demonstrate that MFNOD achieves superior outlier detection performance, validating its effectiveness. The source code is available at <span><span>https://github.com/Mxeron/MFNOD</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"733 ","pages":"Article 122983"},"PeriodicalIF":6.8,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791870","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

Conflict management in sequential evidence combination 顺序证据组合中的冲突管理

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-09 DOI: 10.1016/j.ins.2025.122958

Zixuan Zhou , Fuyuan Xiao

Efficient conflict management in evidence combination remains an open issue in sensor data fusion. Although many methods, such as averaging strategy and distance-based weighting averaging strategy have been proposed to avoid the counter-intuitive results of traditional Dempster rule in highly conflicting situations, the computation time remains very high. Therefore, it is necessary to present a more efficient method for real-time applications. In this paper, an odds-based probability transformation is proposed. A novel sequential evidence combination is presented based on the odds-based probability transformation. To evaluate the proposed method’s performance, both numerical examples and a real-world application are illustrated to show the efficiency of the proposed method. The results show that the sequential combination can deal with the highly conflicting evidence in real-time systems.

在传感器数据融合中，证据组合中的有效冲突管理一直是一个有待解决的问题。虽然已经提出了许多方法，如平均策略和基于距离的加权平均策略，以避免传统Dempster规则在高度冲突情况下的反直觉结果，但计算时间仍然很高。因此，有必要提出一种更有效的实时应用方法。本文提出了一种基于奇数的概率变换。提出了一种基于概率变换的序列证据组合方法。为了评价所提方法的性能，通过数值算例和实际应用说明了所提方法的有效性。结果表明，序列组合可以有效地处理实时系统中高度冲突的证据。

引用次数: 0

Generalization of deep learning image restoration method for compressed sensing in electron tomography with a limited number of projections 有限投影电子断层扫描压缩感知中深度学习图像恢复方法的推广

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2025-12-09 DOI: 10.1016/j.ins.2025.122989

Alberto Japón , Miguel López-Haro , José Marqueses-Rodríguez , Juan M. Muñoz-Ocaña , Justo Puerto , Antonio M. Rodríguez-Chía

Electron tomography (ET) is a technique for 3D nanoscale characterization whose practical application is often hampered by severe artifacts arising from an experimentally limited number of projections and a restricted tilt range. While methods like Compressed Sensing (CS) have been developed to address this data scarcity, their performance degrades significantly under highly constrained conditions. This paper introduces a novel deep learning methodology for image restoration that overcomes these limitations. We propose a supervised Convolutional Neural Network (CNN) architecture based on conditional GAN and RIDNet to eliminate artifacts from initial reconstructions. The central innovation lies in our training strategy: the network is trained exclusively on simple geometric primitives, such as circles and squares, thereby circumventing the need for large, complex, and sample-specific training datasets. We demonstrate that a network trained on this simple basis can remarkably generalize to restore complex, irregular nanomaterials that it has never seen. Quantitative and qualitative comparisons demonstrate that our method significantly outperforms traditional CS, producing high-fidelity 3D reconstructions free of common artifacts. This work establishes a broadly applicable and data-efficient restoration framework that presents a robust and accessible tool for improving the reliability of electron tomography in materials science.

电子断层扫描（ET）是一种用于三维纳米级表征的技术，其实际应用经常受到实验中有限数量的投影和有限倾斜范围引起的严重伪影的阻碍。虽然已经开发了压缩感知（CS）等方法来解决这种数据稀缺问题，但在高度受限的条件下，它们的性能会显著下降。本文介绍了一种新的用于图像恢复的深度学习方法，克服了这些限制。我们提出了一种基于条件GAN和RIDNet的监督卷积神经网络（CNN）架构，以消除初始重建中的伪影。核心创新在于我们的训练策略：网络只训练简单的几何原语，如圆形和正方形，从而避免了对大型、复杂和特定样本的训练数据集的需求。我们证明，在这种简单的基础上训练的网络可以显著地泛化，以恢复它从未见过的复杂、不规则的纳米材料。定量和定性比较表明，我们的方法明显优于传统的CS，产生高保真的3D重建，没有常见的伪影。这项工作建立了一个广泛适用和数据高效的恢复框架，为提高材料科学中电子断层扫描的可靠性提供了一个强大的和可访问的工具。

{"title":"Generalization of deep learning image restoration method for compressed sensing in electron tomography with a limited number of projections","authors":"Alberto Japón , Miguel López-Haro , José Marqueses-Rodríguez , Juan M. Muñoz-Ocaña , Justo Puerto , Antonio M. Rodríguez-Chía","doi":"10.1016/j.ins.2025.122989","DOIUrl":"10.1016/j.ins.2025.122989","url":null,"abstract":"<div><div>Electron tomography (ET) is a technique for 3D nanoscale characterization whose practical application is often hampered by severe artifacts arising from an experimentally limited number of projections and a restricted tilt range. While methods like Compressed Sensing (CS) have been developed to address this data scarcity, their performance degrades significantly under highly constrained conditions. This paper introduces a novel deep learning methodology for image restoration that overcomes these limitations. We propose a supervised Convolutional Neural Network (CNN) architecture based on conditional GAN and RIDNet to eliminate artifacts from initial reconstructions. The central innovation lies in our training strategy: the network is trained exclusively on simple geometric primitives, such as circles and squares, thereby circumventing the need for large, complex, and sample-specific training datasets. We demonstrate that a network trained on this simple basis can remarkably generalize to restore complex, irregular nanomaterials that it has never seen. Quantitative and qualitative comparisons demonstrate that our method significantly outperforms traditional CS, producing high-fidelity 3D reconstructions free of common artifacts. This work establishes a broadly applicable and data-efficient restoration framework that presents a robust and accessible tool for improving the reliability of electron tomography in materials science.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"733 ","pages":"Article 122989"},"PeriodicalIF":6.8,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791949","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