首页 > 最新文献

Information Sciences最新文献

英文 中文
A deep spatiotemporal interaction network for multimodal sentimental analysis and emotion recognition 用于多模态情感分析和情感识别的深度时空交互网络
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-26 DOI: 10.1016/j.ins.2024.121515
One of the challenges of sentiment analysis and emotion recognition is how to effectively fuse the multimodal inputs. The transformer-based models have achieved great success in applications of multimodal sentiment analysis and emotion recognition recently. However, the transformer-based model often neglects the coherence of human emotion due to its parallel structure. Additionally, a low-rank bottleneck created by multi- attention-head causes an inadequate fitting ability of models. To tackle these issues, a Deep Spatiotemporal Interaction Network (DSIN) is proposed in this study. It consists of two main components, i.e., a cross-modal transformer with a cross-talking attention module and a hierarchically temporal fusion module, where the cross-modal transformer is used to model the spatial interactions between different modalities and the hierarchically temporal fusion network is utilized to model the temporal coherence of emotion. Therefore, the DSIN can model the spatiotemporal interactions of multimodal inputs by incorporating the time-dependency into the parallel structure of transformer and decrease the redundancy of embedded features by implanting their spatiotemporal interactions into a hybrid memory network in a hierarchical manner. The experimental results on two benchmark datasets indicate that DSIN achieves superior performance compared with the state-of-the-art models, and some useful insights are derived from the results.
情感分析和情绪识别的挑战之一是如何有效地融合多模态输入。最近,基于变换器的模型在多模态情感分析和情感识别应用中取得了巨大成功。然而,由于其并行结构,基于变换器的模型往往忽略了人类情感的一致性。此外,多注意力头产生的低阶瓶颈也会导致模型拟合能力不足。为了解决这些问题,本研究提出了深度时空交互网络(DSIN)。它由两个主要部分组成,即带有交叉注意模块的跨模态转换器和分层时空融合模块,其中跨模态转换器用于模拟不同模态之间的空间交互,分层时空融合网络用于模拟情绪的时空一致性。因此,DSIN 可以通过将时间依赖性纳入变压器的并行结构来模拟多模态输入的时空交互,并通过将其时空交互分层植入混合记忆网络来减少嵌入特征的冗余。在两个基准数据集上的实验结果表明,与最先进的模型相比,DSIN 实现了更优越的性能,并从中得到了一些有用的启示。
{"title":"A deep spatiotemporal interaction network for multimodal sentimental analysis and emotion recognition","authors":"","doi":"10.1016/j.ins.2024.121515","DOIUrl":"10.1016/j.ins.2024.121515","url":null,"abstract":"<div><div>One of the challenges of sentiment analysis and emotion recognition is how to effectively fuse the multimodal inputs. The transformer-based models have achieved great success in applications of multimodal sentiment analysis and emotion recognition recently. However, the transformer-based model often neglects the coherence of human emotion due to its parallel structure. Additionally, a low-rank bottleneck created by multi- attention-head causes an inadequate fitting ability of models. To tackle these issues, a Deep Spatiotemporal Interaction Network (DSIN) is proposed in this study. It consists of two main components, i.e., a cross-modal transformer with a cross-talking attention module and a hierarchically temporal fusion module, where the cross-modal transformer is used to model the spatial interactions between different modalities and the hierarchically temporal fusion network is utilized to model the temporal coherence of emotion. Therefore, the DSIN can model the spatiotemporal interactions of multimodal inputs by incorporating the time-dependency into the parallel structure of transformer and decrease the redundancy of embedded features by implanting their spatiotemporal interactions into a hybrid memory network in a hierarchical manner. The experimental results on two benchmark datasets indicate that DSIN achieves superior performance compared with the state-of-the-art models, and some useful insights are derived from the results.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422808","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
Predefined time fuzzy adaptive control for stochastic nonlinear systems with limited time interval output constraints 具有有限时间间隔输出约束的随机非线性系统的预定义时间模糊自适应控制
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-26 DOI: 10.1016/j.ins.2024.121506
This article investigates the problem of fuzzy adaptive predefined time tracking control for stochastic nonlinear systems with limited time interval output constraints. Firstly, the considered output constraints occur within a finite time interval after the system starts running. By constructing shift functions and barrier Lyapunov functions (BLFs), the constrained system is converted into an unconstrained system, which solves the problem of function discontinuity resulting from output constraints within limited time intervals. Then, with the help of adaptive backstepping technique and predefined time control method, which reduces the parameters to be designed and removes the limitation of relatively large initial control input in existing approaches. The designed control technique ensures the boundedness of all variables of the stochastic system, the tracking error converges within a predetermined time, and the outputs do not exceed their constraint boundaries in a finite time interval. And this algorithm is applicable to both infinite time constraints and unconstrained outputs cases. Finally, the validity of this approach is demonstrated through simulation examples.
本文研究了具有有限时间间隔输出约束的随机非线性系统的模糊自适应预定义时间跟踪控制问题。首先,所考虑的输出约束发生在系统开始运行后的有限时间间隔内。通过构建移位函数和障碍李亚普诺夫函数(BLF),有约束系统被转换为无约束系统,从而解决了有限时间间隔内输出约束导致的函数不连续性问题。然后,借助自适应反步进技术和预定义时间控制方法,减少了需要设计的参数,并消除了现有方法中相对较大的初始控制输入的限制。所设计的控制技术确保了随机系统所有变量的有界性,跟踪误差在预定时间内收敛,输出在有限时间间隔内不超过其约束边界。该算法同时适用于无限时间约束和无约束输出两种情况。最后,通过仿真实例证明了这种方法的有效性。
{"title":"Predefined time fuzzy adaptive control for stochastic nonlinear systems with limited time interval output constraints","authors":"","doi":"10.1016/j.ins.2024.121506","DOIUrl":"10.1016/j.ins.2024.121506","url":null,"abstract":"<div><div>This article investigates the problem of fuzzy adaptive predefined time tracking control for stochastic nonlinear systems with limited time interval output constraints. Firstly, the considered output constraints occur within a finite time interval after the system starts running. By constructing shift functions and barrier Lyapunov functions (BLFs), the constrained system is converted into an unconstrained system, which solves the problem of function discontinuity resulting from output constraints within limited time intervals. Then, with the help of adaptive backstepping technique and predefined time control method, which reduces the parameters to be designed and removes the limitation of relatively large initial control input in existing approaches. The designed control technique ensures the boundedness of all variables of the stochastic system, the tracking error converges within a predetermined time, and the outputs do not exceed their constraint boundaries in a finite time interval. And this algorithm is applicable to both infinite time constraints and unconstrained outputs cases. Finally, the validity of this approach is demonstrated through simulation examples.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142423888","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
Hyperspectral image classification using feature fusion fuzzy graph broad network 利用特征融合模糊图广网络进行高光谱图像分类
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-26 DOI: 10.1016/j.ins.2024.121504
In recent years, graph convolutional networks (GCNs) have shown strong performance in hyperspectral image (HSI) classification. However, traditional GCN methods often use superpixel-based nodes to reduce computational complexity, which fails to capture pixel-level spectral-spatial features. Additionally, these methods typically focus on matching predicted labels with ground truth, neglecting the relationships between inter-class and intra-class distances, leading to less discriminative features. To address these issues, we propose a feature fusion fuzzy graph broad network (F3GBN) for HSI classification. Our method extracts pixel-level attribute contour features using attribute filters and fuses them with superpixel features through canonical correlation analysis. We employ a broad learning system (BLS) as the classifier, which fully utilizes spectral-spatial information via nonlinear transformations. Furthermore, we construct intra-class and inter-class graphs based on fuzzy set and manifold learning theories to ensure better clustering of samples within the same class and separation between different classes. A novel loss function is introduced in BLS to minimize intra-class distances and maximize inter-class distances, enhancing feature discriminability. The proposed F3GBN model achieved impressive overall accuracy on public datasets: 96.73% on Indian Pines, 98.29% on Pavia University, 98.69% on Salinas, and 99.43% on Kennedy Space Center, outperforming several classical and state-of-the-art methods, thereby demonstrating its effectiveness and feasibility.
近年来,图卷积网络(GCN)在高光谱图像(HSI)分类中表现出强劲的性能。然而,传统的 GCN 方法通常使用基于超像素的节点来降低计算复杂度,从而无法捕捉像素级的光谱空间特征。此外,这些方法通常只关注预测标签与地面实况的匹配,而忽略了类间距离和类内距离之间的关系,导致特征的区分度较低。为了解决这些问题,我们提出了一种用于 HSI 分类的特征融合模糊图广网络(F3GBN)。我们的方法使用属性过滤器提取像素级属性轮廓特征,并通过典型相关分析将其与超像素特征融合。我们采用广义学习系统(BLS)作为分类器,通过非线性变换充分利用光谱空间信息。此外,我们还基于模糊集和流形学习理论构建了类内和类间图,以确保更好地聚类同一类别内的样本和分离不同类别之间的样本。在 BLS 中引入了一个新的损失函数,使类内距离最小化,类间距离最大化,从而增强了特征的可区分性。所提出的 F3GBN 模型在公共数据集上取得了令人印象深刻的总体准确率:Indian Pines 96.73%、Pavia University 98.29%、Salinas 98.69%、Kennedy Space Center 99.43%,超过了几种经典和最先进的方法,从而证明了其有效性和可行性。
{"title":"Hyperspectral image classification using feature fusion fuzzy graph broad network","authors":"","doi":"10.1016/j.ins.2024.121504","DOIUrl":"10.1016/j.ins.2024.121504","url":null,"abstract":"<div><div>In recent years, graph convolutional networks (GCNs) have shown strong performance in hyperspectral image (HSI) classification. However, traditional GCN methods often use superpixel-based nodes to reduce computational complexity, which fails to capture pixel-level spectral-spatial features. Additionally, these methods typically focus on matching predicted labels with ground truth, neglecting the relationships between inter-class and intra-class distances, leading to less discriminative features. To address these issues, we propose a feature fusion fuzzy graph broad network (F<sup>3</sup>GBN) for HSI classification. Our method extracts pixel-level attribute contour features using attribute filters and fuses them with superpixel features through canonical correlation analysis. We employ a broad learning system (BLS) as the classifier, which fully utilizes spectral-spatial information via nonlinear transformations. Furthermore, we construct intra-class and inter-class graphs based on fuzzy set and manifold learning theories to ensure better clustering of samples within the same class and separation between different classes. A novel loss function is introduced in BLS to minimize intra-class distances and maximize inter-class distances, enhancing feature discriminability. The proposed F<sup>3</sup>GBN model achieved impressive overall accuracy on public datasets: 96.73% on Indian Pines, 98.29% on Pavia University, 98.69% on Salinas, and 99.43% on Kennedy Space Center, outperforming several classical and state-of-the-art methods, thereby demonstrating its effectiveness and feasibility.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323407","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
MRRFGNN: Multi-relation reconstruction and fusion graph neural network for stock crash prediction MRRFGNN:用于股灾预测的多相关重构与融合图神经网络
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-24 DOI: 10.1016/j.ins.2024.121507
Stock crash risk often propagates through various interconnected relationships between firms, amplifying its impact across financial markets. Few studies predicted the crash risk of one firm in terms of its relevant firms. A common strategy is to adopt graph neural networks (GNNs) with some predefined firm relations. However, many relations remain undetected or evolve over time. Restricting to several predefined relations inevitably makes noise and thus misleads stock crash predictions. In addition, these relationships are not independent during the process of propagating information and interacting with each other. This study proposes the multi-relation reconstruction and fusion graph neural network (MRRFGNN) to predict stock crash risk by capturing complex relations among listed companies. First, the model employs self-supervised learning and contrastive learning to reconstruct and infer implicit relationships between companies. Second, the model incorporates a relation self-attention mechanism to integrate various types of relationships, enabling a more nuanced understanding of the multiple spillover effects. Empirical evidence from a series of experiments demonstrates the superiority of the proposed method, which achieves the best performance with improvements of at least 2.14% in area under the curve (AUC) and 2.64% in Matthews correlation coefficient (MCC), highlighting its potential for practical application in financial markets.
股票暴跌风险往往会通过公司之间各种相互关联的关系传播,扩大其对整个金融市场的影响。很少有研究从相关公司的角度预测一家公司的崩盘风险。一种常见的策略是采用具有某些预定义公司关系的图神经网络(GNN)。然而,许多关系仍未被发现或随时间演变。局限于几种预定义的关系不可避免地会产生噪音,从而误导股灾预测。此外,这些关系在信息传播和相互影响的过程中并不是独立的。本研究提出了多关系重构与融合图神经网络(MRRFGNN),通过捕捉上市公司之间的复杂关系来预测股灾风险。首先,该模型采用自监督学习和对比学习来重构和推断公司之间的隐含关系。其次,该模型纳入了一种关系自我关注机制,以整合各种类型的关系,从而更细致地理解多重溢出效应。来自一系列实验的经验证据证明了所提出方法的优越性,该方法达到了最佳性能,曲线下面积(AUC)至少提高了 2.14%,马修斯相关系数(MCC)至少提高了 2.64%,突出了其在金融市场中的实际应用潜力。
{"title":"MRRFGNN: Multi-relation reconstruction and fusion graph neural network for stock crash prediction","authors":"","doi":"10.1016/j.ins.2024.121507","DOIUrl":"10.1016/j.ins.2024.121507","url":null,"abstract":"<div><div>Stock crash risk often propagates through various interconnected relationships between firms, amplifying its impact across financial markets. Few studies predicted the crash risk of one firm in terms of its relevant firms. A common strategy is to adopt graph neural networks (GNNs) with some predefined firm relations. However, many relations remain undetected or evolve over time. Restricting to several predefined relations inevitably makes noise and thus misleads stock crash predictions. In addition, these relationships are not independent during the process of propagating information and interacting with each other. This study proposes the multi-relation reconstruction and fusion graph neural network (MRRFGNN) to predict stock crash risk by capturing complex relations among listed companies. First, the model employs self-supervised learning and contrastive learning to reconstruct and infer implicit relationships between companies. Second, the model incorporates a relation self-attention mechanism to integrate various types of relationships, enabling a more nuanced understanding of the multiple spillover effects. Empirical evidence from a series of experiments demonstrates the superiority of the proposed method, which achieves the best performance with improvements of at least 2.14% in area under the curve (AUC) and 2.64% in Matthews correlation coefficient (MCC), highlighting its potential for practical application in financial markets.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358206","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
Herd behavior identification based on coevolution in human–machine collaborative multi-stage large group decision-making 人机协作多阶段大型群体决策中基于协同进化的群体行为识别
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-24 DOI: 10.1016/j.ins.2024.121511
As the scale of multi-stage large group decision-making (LGDM) continues to expand, the possibility of low-contribution individuals exhibiting herd behavior also increases, potentially leading to the phenomenon of “fishing in troubled waters.” This may obstruct the speed of consensus reaching while generating no valuable opinions, which is a topic worthy of exploration. Considering that humans are easily influenced by interests, the employment of machine intelligence to objectively identify herd behavior is more appropriate. In this context, a herd behavior identification method based on behavioral characteristics clustering from the perspective of human–machine collaboration is herein proposed. First, from the human side, an opinion–social network coevolution model is constructed to simulate the consensus reaching process (CRP) of the expert group. Then, the group is clustered into three subgroups in consideration of behavior that encompasses both opinion changes and trust relationship changes. Based on this, the low-contribution cluster with a herd behavior pattern can be optimized from the machine side. Through simulation experiments, it is verified that herd behavior management significantly accelerates the consensus-reaching speed under the premise of having minimal impact on the decision-making results. In general terms, this study is the first to propose the concept of herd behavior and provides a solution to manage it from a new perspective, which is suitable for application in multi-stage LGDM scenarios.
随着多阶段大型群体决策(LGDM)规模的不断扩大,低贡献个体表现出从众行为的可能性也随之增加,从而可能导致 "浑水摸鱼 "的现象。这可能会阻碍达成共识的速度,同时又不会产生有价值的意见,这是一个值得探讨的话题。考虑到人类容易受到利益的影响,利用机器智能来客观识别群体行为更为合适。为此,本文从人机协作的角度出发,提出了一种基于行为特征聚类的羊群行为识别方法。首先,从人的角度出发,构建一个意见-社会网络协同演化模型,模拟专家组的共识达成过程(CRP)。然后,考虑到包括意见变化和信任关系变化在内的行为,将专家组分为三个子组。在此基础上,可以从机器端优化具有羊群行为模式的低贡献群组。通过模拟实验,验证了群行为管理在对决策结果影响最小的前提下,显著加快了达成共识的速度。总的来说,本研究首次提出了羊群行为的概念,并从一个新的角度提供了管理羊群行为的解决方案,适合应用于多阶段 LGDM 场景。
{"title":"Herd behavior identification based on coevolution in human–machine collaborative multi-stage large group decision-making","authors":"","doi":"10.1016/j.ins.2024.121511","DOIUrl":"10.1016/j.ins.2024.121511","url":null,"abstract":"<div><div>As the scale of multi-stage large group decision-making (LGDM) continues to expand, the possibility of low-contribution individuals exhibiting herd behavior also increases, potentially leading to the phenomenon of “fishing in troubled waters.” This may obstruct the speed of consensus reaching while generating no valuable opinions, which is a topic worthy of exploration. Considering that humans are easily influenced by interests, the employment of machine intelligence to objectively identify herd behavior is more appropriate. In this context, a herd behavior identification method based on behavioral characteristics clustering from the perspective of human–machine collaboration is herein proposed. First, from the human side, an opinion–social network coevolution model is constructed to simulate the consensus reaching process (CRP) of the expert group. Then, the group is clustered into three subgroups in consideration of behavior that encompasses both opinion changes and trust relationship changes. Based on this, the low-contribution cluster with a herd behavior pattern can be optimized from the machine side. Through simulation experiments, it is verified that herd behavior management significantly accelerates the consensus-reaching speed under the premise of having minimal impact on the decision-making results. In general terms, this study is the first to propose the concept of herd behavior and provides a solution to manage it from a new perspective, which is suitable for application in multi-stage LGDM scenarios.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358207","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
k-plex-based community detection with graph neural networks 基于图神经网络的 k-plex 群落检测
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-24 DOI: 10.1016/j.ins.2024.121509
Community detection is an effective way to determine the structure and characteristics of a complex network. With the expansion of the network scale, traditional community detection approaches such as modularity-based optimization models face new challenges related to representing and learning the topological structure and node attributes from a large scale complex network. Moreover, in many practical applications, there is little knowledge about label information or the number of communities, which greatly limits the performance of existing supervised or semi-supervised community detection approaches. To solve these problems, in this paper, we propose a graph neural network-based unsupervised community detection approach, which first applies the k-plex to generate the community seeds, then uses a node sampling algorithm to reduce the network complexity, and finally constructs a graph neural network model to learn the relationships of the network nodes and assign the nodes to different communities. Extensive empirical studies on various scale networks demonstrate both the effectiveness and efficiency of the proposed approach. Our codes are available at https://github.com/lol12854/KPGN.
群落检测是确定复杂网络结构和特征的有效方法。随着网络规模的扩大,传统的社群检测方法(如基于模块化的优化模型)在表示和学习大规模复杂网络的拓扑结构和节点属性方面面临着新的挑战。此外,在许多实际应用中,对标签信息或社群数量知之甚少,这大大限制了现有监督或半监督社群检测方法的性能。为了解决这些问题,本文提出了一种基于图神经网络的无监督社群检测方法,该方法首先应用 k-plex 生成社群种子,然后使用节点抽样算法降低网络复杂度,最后构建图神经网络模型来学习网络节点的关系,并将节点分配到不同的社群中。在各种规模的网络上进行的大量实证研究证明了所提方法的有效性和效率。我们的代码见 https://github.com/lol12854/KPGN。
{"title":"k-plex-based community detection with graph neural networks","authors":"","doi":"10.1016/j.ins.2024.121509","DOIUrl":"10.1016/j.ins.2024.121509","url":null,"abstract":"<div><div>Community detection is an effective way to determine the structure and characteristics of a complex network. With the expansion of the network scale, traditional community detection approaches such as modularity-based optimization models face new challenges related to representing and learning the topological structure and node attributes from a large scale complex network. Moreover, in many practical applications, there is little knowledge about label information or the number of communities, which greatly limits the performance of existing supervised or semi-supervised community detection approaches. To solve these problems, in this paper, we propose a graph neural network-based unsupervised community detection approach, which first applies the <em>k</em>-plex to generate the community seeds, then uses a node sampling algorithm to reduce the network complexity, and finally constructs a graph neural network model to learn the relationships of the network nodes and assign the nodes to different communities. Extensive empirical studies on various scale networks demonstrate both the effectiveness and efficiency of the proposed approach. Our codes are available at <span><span>https://github.com/lol12854/KPGN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142326809","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
Image based information hiding via minimization of entropy and randomization 通过熵最小化和随机化实现基于图像的信息隐藏
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-24 DOI: 10.1016/j.ins.2024.121514
In this paper, a new approach that can effectively and securely hide information into color images with significantly improved security and hiding capacity is proposed. The proposed approach performs information hiding in three major steps. As the first step, two binary sequences are constructed from the least significant bits in the pixels of a cover image and the information that needs to be embedded, the information entropies of both sequences are minimized with a dynamic programming method. In the second step, the resulting sequences are randomly reshuffled into randomized sequences with mappings based on a set of one-dimensional chaotic systems, a single binary sequence can be obtained by a matching operation performed between the two randomized sequences. Finally, an inverse mapping is applied to the sequence obtained in the second step, and the transformed sequence is embedded into the least significant bits in the pixels of the cover image. Both analysis and experiments show that the proposed approach can achieve guaranteed performance in both security and capacity for long binary sequences. In addition, a comparison with other state-of-the-art methods for image-based information hiding suggests that the proposed approach can achieve significantly improved performance and is promising for practical applications.
本文提出了一种新方法,可以有效、安全地将信息隐藏到彩色图像中,并显著提高安全性和隐藏能力。所提出的方法分三大步骤进行信息隐藏。第一步,利用封面图像像素中的最小有效位和需要嵌入的信息构建两个二进制序列,并利用动态编程方法使两个序列的信息熵最小化。第二步,根据一组一维混沌系统的映射,将得到的序列随机地重新洗牌为随机序列,通过在两个随机序列之间进行匹配操作,可以得到一个单独的二进制序列。最后,对第二步得到的序列进行反映射,并将变换后的序列嵌入到覆盖图像像素的最小有效位中。分析和实验都表明,对于长二进制序列,所提出的方法在安全性和容量方面都能达到保证的性能。此外,与其他最先进的基于图像的信息隐藏方法的比较表明,所提出的方法可以显著提高性能,在实际应用中大有可为。
{"title":"Image based information hiding via minimization of entropy and randomization","authors":"","doi":"10.1016/j.ins.2024.121514","DOIUrl":"10.1016/j.ins.2024.121514","url":null,"abstract":"<div><div>In this paper, a new approach that can effectively and securely hide information into color images with significantly improved security and hiding capacity is proposed. The proposed approach performs information hiding in three major steps. As the first step, two binary sequences are constructed from the least significant bits in the pixels of a cover image and the information that needs to be embedded, the information entropies of both sequences are minimized with a dynamic programming method. In the second step, the resulting sequences are randomly reshuffled into randomized sequences with mappings based on a set of one-dimensional chaotic systems, a single binary sequence can be obtained by a matching operation performed between the two randomized sequences. Finally, an inverse mapping is applied to the sequence obtained in the second step, and the transformed sequence is embedded into the least significant bits in the pixels of the cover image. Both analysis and experiments show that the proposed approach can achieve guaranteed performance in both security and capacity for long binary sequences. In addition, a comparison with other state-of-the-art methods for image-based information hiding suggests that the proposed approach can achieve significantly improved performance and is promising for practical applications.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142326735","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-level optimizing of parameters in stochastic configuration networks based on cloud model and nutcracker optimization algorithm 基于云模型和胡桃夹子优化算法的随机配置网络参数多级优化
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-24 DOI: 10.1016/j.ins.2024.121495
As a state-of-the-art neural network model, stochastic configuration networks (SCNs) are widely employed in diverse fields due to their exceptional approximation capabilities. Similar to other neural network models, an excessive number of parameters can potentially compromise the generalization ability of SCNs, including hyper-parameters such as the stochastic scale factors (λ) and the maximum number of nodes (Lmax), as well as model parameters like input weight (w) and input bias (b). To tackle this issue, this study proposes a multi-level parameter optimization approach, termed stochastic configuration network with cloud models (CMSCNs). Firstly, the optimal parameter range is determined based on the concept of “cloud droplet” from the cloud model. Herein, mathematical expectation (Ex) is substituted by a polynomial function constructed with λ as the dependent variable and other parameters as independent variables. Secondly, we employ the nutcracker optimization algorithm (NOA) to optimize w and b, using residuals as evaluation indices to identify their optimal combination. Thirdly, singular value decomposition (SVD) is integrated to compress the network structure of CMSCNs for enhanced computational efficiency. Finally, 18 public real datasets and submergence depth data from an oil well are utilized to assess the performance of CMSCNs. The experimental results demonstrate that our proposed method offers improved generalizability and stability while also exhibiting significant potential in practical applications.
作为最先进的神经网络模型,随机配置网络(SCN)因其卓越的逼近能力而被广泛应用于各个领域。与其他神经网络模型类似,过多的参数可能会影响随机配置网络的泛化能力,其中包括随机比例因子(λ)和最大节点数(Lmax)等超参数,以及输入权重(w)和输入偏置(b)等模型参数。针对这一问题,本研究提出了一种多层次参数优化方法,即云模型随机配置网络(CMSCN)。首先,根据云模型中 "云滴 "的概念确定最佳参数范围。在这里,数学期望(Ex)被一个以λ为因变量、其他参数为自变量的多项式函数所取代。其次,我们采用胡桃钳优化算法(NOA)来优化 w 和 b,以残差作为评价指标来确定它们的最优组合。第三,我们采用奇异值分解(SVD)来压缩 CMSCN 的网络结构,以提高计算效率。最后,利用 18 个公共真实数据集和油井的浸没深度数据来评估 CMSCN 的性能。实验结果表明,我们提出的方法具有更好的普适性和稳定性,同时在实际应用中也展现出巨大的潜力。
{"title":"Multi-level optimizing of parameters in stochastic configuration networks based on cloud model and nutcracker optimization algorithm","authors":"","doi":"10.1016/j.ins.2024.121495","DOIUrl":"10.1016/j.ins.2024.121495","url":null,"abstract":"<div><div>As a state-of-the-art neural network model, stochastic configuration networks (SCNs) are widely employed in diverse fields due to their exceptional approximation capabilities. Similar to other neural network models, an excessive number of parameters can potentially compromise the generalization ability of SCNs, including hyper-parameters such as the stochastic scale factors (<em>λ</em>) and the maximum number of nodes (<span><math><msub><mrow><mi>L</mi></mrow><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msub></math></span>), as well as model parameters like input weight (<em>w</em>) and input bias (<em>b</em>). To tackle this issue, this study proposes a multi-level parameter optimization approach, termed stochastic configuration network with cloud models (CMSCNs). Firstly, the optimal parameter range is determined based on the concept of “cloud droplet” from the cloud model. Herein, mathematical expectation (<span><math><msub><mrow><mi>E</mi></mrow><mrow><mi>x</mi></mrow></msub></math></span>) is substituted by a polynomial function constructed with <em>λ</em> as the dependent variable and other parameters as independent variables. Secondly, we employ the nutcracker optimization algorithm (NOA) to optimize <em>w</em> and <em>b</em>, using residuals as evaluation indices to identify their optimal combination. Thirdly, singular value decomposition (SVD) is integrated to compress the network structure of CMSCNs for enhanced computational efficiency. Finally, 18 public real datasets and submergence depth data from an oil well are utilized to assess the performance of CMSCNs. The experimental results demonstrate that our proposed method offers improved generalizability and stability while also exhibiting significant potential in practical applications.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323405","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
Reliability-based ordinal consensus adjustment model for large scale group decision making 基于可靠性的大规模群体决策序数共识调整模型
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-24 DOI: 10.1016/j.ins.2024.121496
In large scale group decision-making (LSGDM), there are the substantial number of decision makers (DMs) with diverse knowledge, backgrounds, and interests related to the decision-making problem, and it is not possible to assure that all DMs are completely reliable. Thus, in order to enhance the quality of decision-making, it is necessary to analyze the reliabilities of DMs in LSGDM. This paper proposes the method to evaluate the reliabilities of DMs, sorts these DMs according to their degree of reliability, and investigates the consensus reaching process based on categories and an ordinal consensus measure. Considering the DMs' trust network, the uncertainty of a DM's evaluation information represented by a fuzzy preference relation (FPR), the deviation between a DM's FPR and those of the other DMs, and additive consistency of FPRs, the reliability of a DM is assessed using four criteria: PageRank centrality, professional competence, collaborative competence, and additive consistency. Following these reliability assessment criteria, ELECTRE-TRI is employed to sort DMs into three ordered categories according to DMs' different levels of reliability under the four assessment criteria. Furthermore, an improved ordinal consensus measure is designed to consider both the importance weights of positions and the deviation of Borda counts of the same alternative in two rankings. As for the consensus reaching process, due to the varied reliabilities of DMs in different categories, we propose a multiple strategies feedback mechanism for DMs in different categories. Finally, a numerical example is provided to illustrate the rationality and validity of the proposed model.
在大规模群体决策(LSGDM)中,有大量的决策者(DMs),他们的知识、背景和兴趣与决策问题相关,不可能保证所有的 DMs 都是完全可靠的。因此,为了提高决策质量,有必要对 LSGDM 中 DM 的可靠性进行分析。本文提出了评估 DM 可靠性的方法,根据 DM 的可靠程度对其进行分类,并研究了基于分类和顺序共识度量的共识达成过程。考虑到DM的信任网络、由模糊偏好关系(FPR)表示的DM评价信息的不确定性、DM的FPR与其他DM的FPR之间的偏差以及FPR的加法一致性,使用四个标准来评估DM的可靠性:通过 PageRank 中心性、专业能力、协作能力和加法一致性这四个标准来评估 DM 的可靠性。根据这些可靠性评估标准,ELECTRE-TRI 将根据 DM 在四个评估标准下的不同可靠性水平将其分为三个有序类别。此外,还设计了一种改进的顺序共识度量方法,既考虑了两个排序中同一备选方案的位置重要性权重,也考虑了 Borda 计数的偏差。在达成共识的过程中,由于不同类别的 DM 可靠性不同,我们提出了针对不同类别 DM 的多策略反馈机制。最后,我们提供了一个数字示例来说明所提模型的合理性和有效性。
{"title":"Reliability-based ordinal consensus adjustment model for large scale group decision making","authors":"","doi":"10.1016/j.ins.2024.121496","DOIUrl":"10.1016/j.ins.2024.121496","url":null,"abstract":"<div><div>In large scale group decision-making (LSGDM), there are the substantial number of decision makers (DMs) with diverse knowledge, backgrounds, and interests related to the decision-making problem, and it is not possible to assure that all DMs are completely reliable. Thus, in order to enhance the quality of decision-making, it is necessary to analyze the reliabilities of DMs in LSGDM. This paper proposes the method to evaluate the reliabilities of DMs, sorts these DMs according to their degree of reliability, and investigates the consensus reaching process based on categories and an ordinal consensus measure. Considering the DMs' trust network, the uncertainty of a DM's evaluation information represented by a fuzzy preference relation (FPR), the deviation between a DM's FPR and those of the other DMs, and additive consistency of FPRs, the reliability of a DM is assessed using four criteria: PageRank centrality, professional competence, collaborative competence, and additive consistency. Following these reliability assessment criteria, ELECTRE-TRI is employed to sort DMs into three ordered categories according to DMs' different levels of reliability under the four assessment criteria. Furthermore, an improved ordinal consensus measure is designed to consider both the importance weights of positions and the deviation of Borda counts of the same alternative in two rankings. As for the consensus reaching process, due to the varied reliabilities of DMs in different categories, we propose a multiple strategies feedback mechanism for DMs in different categories. Finally, a numerical example is provided to illustrate the rationality and validity of the proposed model.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422813","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
Positivity and semi-global polynomial stability of high-order Cohen–Grossberg BAM neural networks with multiple proportional delays 具有多比例延迟的高阶科恩-格罗斯伯格 BAM 神经网络的正向性和半全局多项式稳定性
IF 8.1 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-24 DOI: 10.1016/j.ins.2024.121512
In this paper, we study positivity and semi-global polynomial stability (PS) of higher-order Cohen-Grossberg BAM neural networks with multiple proportional time delays. The proportional delays considered here are unbounded and time-varying, differing from constant, bounded, and distributional time delays. The system model cannot be represented using vector and matrices, making certain approaches within the vector-matrix framework unsuitable for applying. To address this limitation, a direct method based on the solution of the system is proposed to provide sufficient conditions guaranteeing the positivity and semi-global polynomial stability (PS) of the model under consideration. Furthermore, the direct method is applied to establish global PS conditions for BAM neural networks with multiple proportional delays. The obtained conditions contain only a few simple linear scalar inequalities that are easily solved. The applicability of the obtained PS conditions is verified by two numerical examples, and the solution of a linear programming problem is also obtained based on these theoretical results. Notably, this method can be applied to many system models with proportional delays after minor modifications.
本文研究了具有多比例时间延迟的高阶 Cohen-Grossberg BAM 神经网络的正相关性和半全局多项式稳定性(PS)。本文考虑的比例延迟是无界和时变的,不同于恒定、有界和分布式时间延迟。系统模型无法用向量和矩阵表示,因此向量矩阵框架内的某些方法不适合应用。为了解决这一局限性,我们提出了一种基于系统解的直接方法,以提供充分条件,保证所考虑模型的正向性和半全局多项式稳定性(PS)。此外,该直接方法还被用于建立具有多比例延迟的 BAM 神经网络的全局 PS 条件。所获得的条件只包含几个简单的线性标量不等式,易于求解。通过两个数值实例验证了所获 PS 条件的适用性,并基于这些理论结果获得了线性规划问题的解。值得注意的是,在稍作修改后,这种方法可应用于许多具有比例延迟的系统模型。
{"title":"Positivity and semi-global polynomial stability of high-order Cohen–Grossberg BAM neural networks with multiple proportional delays","authors":"","doi":"10.1016/j.ins.2024.121512","DOIUrl":"10.1016/j.ins.2024.121512","url":null,"abstract":"<div><div>In this paper, we study positivity and semi-global polynomial stability (PS) of higher-order Cohen-Grossberg BAM neural networks with multiple proportional time delays. The proportional delays considered here are unbounded and time-varying, differing from constant, bounded, and distributional time delays. The system model cannot be represented using vector and matrices, making certain approaches within the vector-matrix framework unsuitable for applying. To address this limitation, a direct method based on the solution of the system is proposed to provide sufficient conditions guaranteeing the positivity and semi-global polynomial stability (PS) of the model under consideration. Furthermore, the direct method is applied to establish global PS conditions for BAM neural networks with multiple proportional delays. The obtained conditions contain only a few simple linear scalar inequalities that are easily solved. The applicability of the obtained PS conditions is verified by two numerical examples, and the solution of a linear programming problem is also obtained based on these theoretical results. Notably, this method can be applied to many system models with proportional delays after minor modifications.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":null,"pages":null},"PeriodicalIF":8.1,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323307","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
Information Sciences
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1