Knowledge-Based Systems最新文献_第3页

Dynamic multi-scale spatial-temporal graph convolutional network for traffic flow prediction 用于交通流量预测的动态多尺度时空图卷积网络

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-24 DOI: 10.1016/j.knosys.2024.112586

Ming Gao , Zhuoran Du , Hongmao Qin , Wei Wang , Guangyin Jin , Guotao Xie

This paper proposes a dynamic multi-scale spatial-temporal graph convolutional network (DS-STGCN) for traffic flow prediction. The network aims to comprehensively extract global and local dependencies in dynamic spatial-temporal data by inputting traffic network flow data to construct node feature graphs, topology graphs, and time slot feature graphs, capturing the complexity and dynamics of traffic flow. DS-STGCN interprets feature information of the traffic network from both spatial and temporal dimensions through dynamic multi-scale graph convolutional blocks. In the spatial dimension, these blocks use constraints at different levels to balance fine-grained local features and extensive global features, revealing the intrinsic structure of traffic flow data. In the temporal dimension, these blocks jointly learn with temporal convolutional blocks to capture multi-frequency time patterns and handle long sequence data, effectively extracting potential dependencies of time series. Furthermore, DS-STGCN effectively models the changing spatial-temporal relationships in road network flow by constructing dynamically adaptive updated adjacency tensors, generating dynamic graph structures to address the challenge of changing spatial-temporal relationships in the transportation system. Experimental results show that our method significantly outperforms other competing methods on five real traffic datasets (PEMS03, PEMS04, PEMS07, PEMS08 and METR-LA).

本文提出了一种用于交通流预测的动态多尺度时空图卷积网络（DS-STGCN）。该网络旨在通过输入交通网络流量数据，构建节点特征图、拓扑图和时隙特征图，全面提取动态时空数据中的全局和局部依赖关系，捕捉交通流的复杂性和动态性。DS-STGCN 通过动态多尺度图卷积块从空间和时间两个维度解释交通网络的特征信息。在空间维度上，这些区块利用不同层次的约束来平衡细粒度的局部特征和广泛的全局特征，从而揭示交通流数据的内在结构。在时间维度上，这些块与时间卷积块联合学习，捕捉多频率时间模式并处理长序列数据，有效提取时间序列的潜在依赖关系。此外，DS-STGCN 通过构建动态自适应更新的邻接张量，有效地模拟了路网流量中不断变化的时空关系，生成动态图结构，以应对交通系统中不断变化的时空关系所带来的挑战。实验结果表明，在五个真实交通数据集（PEMS03、PEMS04、PEMS07、PEMS08 和 METR-LA）上，我们的方法明显优于其他竞争方法。

{"title":"Dynamic multi-scale spatial-temporal graph convolutional network for traffic flow prediction","authors":"Ming Gao , Zhuoran Du , Hongmao Qin , Wei Wang , Guangyin Jin , Guotao Xie","doi":"10.1016/j.knosys.2024.112586","DOIUrl":"10.1016/j.knosys.2024.112586","url":null,"abstract":"<div><div>This paper proposes a dynamic multi-scale spatial-temporal graph convolutional network (DS-STGCN) for traffic flow prediction. The network aims to comprehensively extract global and local dependencies in dynamic spatial-temporal data by inputting traffic network flow data to construct node feature graphs, topology graphs, and time slot feature graphs, capturing the complexity and dynamics of traffic flow. DS-STGCN interprets feature information of the traffic network from both spatial and temporal dimensions through dynamic multi-scale graph convolutional blocks. In the spatial dimension, these blocks use constraints at different levels to balance fine-grained local features and extensive global features, revealing the intrinsic structure of traffic flow data. In the temporal dimension, these blocks jointly learn with temporal convolutional blocks to capture multi-frequency time patterns and handle long sequence data, effectively extracting potential dependencies of time series. Furthermore, DS-STGCN effectively models the changing spatial-temporal relationships in road network flow by constructing dynamically adaptive updated adjacency tensors, generating dynamic graph structures to address the challenge of changing spatial-temporal relationships in the transportation system. Experimental results show that our method significantly outperforms other competing methods on five real traffic datasets (PEMS03, PEMS04, PEMS07, PEMS08 and METR-LA).</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112586"},"PeriodicalIF":7.2,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573330","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

Denoising for balanced representation: A diffusion-informed approach to causal effect estimation 均衡表示的去噪：以扩散为基础的因果效应估算方法

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-24 DOI: 10.1016/j.knosys.2024.112647

Hai Yang , Jing Yao , Zhe Wang , Yijing Yang

Estimating individual treatment effects with observational data is crucial in causal inference. While it faces two major challenges: the absence of counterfactual outcomes and selection bias due to non-random assignment and intervention of confounding variables. This paper specifically addresses these by quantifying the distribution shift between the treated and control groups from a generative view to achieve balanced representation and then predict causal effects. We propose a novel method called Denoising for a Balanced Representation in Treatment Effect Estimation (DBRT). Motivated by the aim to generate analogous distributions in the Diffusion model, which aligns with our goal of achieving similar distributions in the latent space, our approach considers the divergence between the treated and control groups as’noise’ that needs to be removed incrementally. We then construct a network to fit and then denoise it step by step, ensuring a consistent reduction of discrepancies between the two groups. Additionally, to enhance the representation of input features, we incorporate memory vectors into the attention mechanism to capture prior information and combined correlations between covariates. Furthermore, we utilize the Hilbert–Schmidt Independence Criterion (HSIC) within the loss function to constrain the learned representation, ensuring its relevance to the original data. DBRT has demonstrated superior performance on different datasets compared to previous classic works, highlighting its effectiveness in treatment effect estimation.

利用观察数据估计个体治疗效果对于因果推断至关重要。但它面临着两大挑战：反事实结果的缺失以及非随机分配和混杂变量干预导致的选择偏差。本文通过从生成视角量化治疗组和对照组之间的分布偏移来具体解决这些问题，从而实现均衡表征，进而预测因果效应。我们提出了一种名为 "治疗效果估算中的去噪平衡表征"（Denoising for a Balanced Representation in Treatment Effect Estimation，DBRT）的新方法。我们的方法将治疗组和对照组之间的差异视为 "噪音"，需要逐步去除。然后，我们构建一个网络进行拟合，然后逐步去噪，确保持续减少两组之间的差异。此外，为了增强输入特征的代表性，我们在注意力机制中加入了记忆向量，以捕捉先验信息和协变因素之间的综合相关性。此外，我们还在损失函数中使用了希尔伯特-施密特独立准则（HSIC）来约束学习到的表征，确保其与原始数据的相关性。与之前的经典作品相比，DBRT 在不同的数据集上都表现出了卓越的性能，突出了其在治疗效果估计中的有效性。

{"title":"Denoising for balanced representation: A diffusion-informed approach to causal effect estimation","authors":"Hai Yang , Jing Yao , Zhe Wang , Yijing Yang","doi":"10.1016/j.knosys.2024.112647","DOIUrl":"10.1016/j.knosys.2024.112647","url":null,"abstract":"<div><div>Estimating individual treatment effects with observational data is crucial in causal inference. While it faces two major challenges: the absence of counterfactual outcomes and selection bias due to non-random assignment and intervention of confounding variables. This paper specifically addresses these by quantifying the distribution shift between the treated and control groups from a generative view to achieve balanced representation and then predict causal effects. We propose a novel method called <strong>D</strong>enoising for a <strong>B</strong>alanced <strong>R</strong>epresentation in <strong>T</strong>reatment Effect Estimation (<strong>DBRT</strong>). Motivated by the aim to generate analogous distributions in the Diffusion model, which aligns with our goal of achieving similar distributions in the latent space, our approach considers the divergence between the treated and control groups as’noise’ that needs to be removed incrementally. We then construct a network to fit and then denoise it step by step, ensuring a consistent reduction of discrepancies between the two groups. Additionally, to enhance the representation of input features, we incorporate memory vectors into the attention mechanism to capture prior information and combined correlations between covariates. Furthermore, we utilize the Hilbert–Schmidt Independence Criterion (HSIC) within the loss function to constrain the learned representation, ensuring its relevance to the original data. DBRT has demonstrated superior performance on different datasets compared to previous classic works, highlighting its effectiveness in treatment effect estimation.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112647"},"PeriodicalIF":7.2,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573331","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

Anti-forgetting source-free domain adaptation method for machine fault diagnosis 用于机器故障诊断的防遗忘无源域适应方法

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-24 DOI: 10.1016/j.knosys.2024.112672

Hao Li , Zongyang Liu , Jing Lin , Jinyang Jiao , Tian Zhang , Wenhao Li

Unsupervised domain adaptation methods have made significant progress in the field of machine fault diagnosis. However, these methods generally assume the accessibility of source domain data during the cross-domain transfer phase. In practice, this assumption is often impractical due to data privacy requirements and the burden of data transmission and storage. Additionally, a key challenge lies in preventing the forgetting of source domain knowledge while performing cross-domain diagnosis in a source-free scenario. To address these issues, this paper proposes an anti-forgetting source-free domain adaptation method for machine fault diagnosis. Specifically, a prototype-based pseudo-label generation strategy, combined with a nearest-neighbor constraint, is employed to deeply explore diagnosis information in the unlabeled target domain data. Then, a fast nuclear-norm maximization constraint is introduced to reduce the density of target domain samples near the classification boundary, thereby decreasing the probability of misdiagnosis. Furthermore, a weighted Fisher regularization is designed to retain the diagnosis information of healthy states inherent in the source domain, thus mitigating information forgetting. Finally, comprehensive experiments are conducted to validate the superiority of our method in source-free cross-domain diagnosis from multiple perspectives, while also demonstrating its anti-forgetting properties.

无监督域适应方法在机器故障诊断领域取得了重大进展。然而，这些方法通常假定在跨域传输阶段可以访问源域数据。在实践中，由于数据隐私要求以及数据传输和存储的负担，这种假设往往是不切实际的。此外，在无源场景下进行跨域诊断时，如何防止遗忘源域知识也是一个关键挑战。为解决这些问题，本文提出了一种用于机器故障诊断的防遗忘无源域适应方法。具体来说，该方法采用基于原型的伪标签生成策略，结合最近邻约束，深入挖掘无标签目标域数据中的诊断信息。然后，引入快速核规范最大化约束，降低分类边界附近目标域样本的密度，从而降低误诊概率。此外，还设计了加权 Fisher 正则化，以保留源域中固有的健康状态诊断信息，从而减轻信息遗忘。最后，我们进行了全面的实验，从多个角度验证了我们的方法在无源跨域诊断中的优越性，同时也证明了它的抗遗忘特性。

{"title":"Anti-forgetting source-free domain adaptation method for machine fault diagnosis","authors":"Hao Li , Zongyang Liu , Jing Lin , Jinyang Jiao , Tian Zhang , Wenhao Li","doi":"10.1016/j.knosys.2024.112672","DOIUrl":"10.1016/j.knosys.2024.112672","url":null,"abstract":"<div><div>Unsupervised domain adaptation methods have made significant progress in the field of machine fault diagnosis. However, these methods generally assume the accessibility of source domain data during the cross-domain transfer phase. In practice, this assumption is often impractical due to data privacy requirements and the burden of data transmission and storage. Additionally, a key challenge lies in preventing the forgetting of source domain knowledge while performing cross-domain diagnosis in a source-free scenario. To address these issues, this paper proposes an anti-forgetting source-free domain adaptation method for machine fault diagnosis. Specifically, a prototype-based pseudo-label generation strategy, combined with a nearest-neighbor constraint, is employed to deeply explore diagnosis information in the unlabeled target domain data. Then, a fast nuclear-norm maximization constraint is introduced to reduce the density of target domain samples near the classification boundary, thereby decreasing the probability of misdiagnosis. Furthermore, a weighted Fisher regularization is designed to retain the diagnosis information of healthy states inherent in the source domain, thus mitigating information forgetting. Finally, comprehensive experiments are conducted to validate the superiority of our method in source-free cross-domain diagnosis from multiple perspectives, while also demonstrating its anti-forgetting properties.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112672"},"PeriodicalIF":7.2,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553809","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

Underwater image restoration via spatially adaptive polarization imaging and color correction 通过空间自适应偏振成像和色彩校正修复水下图像

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-24 DOI: 10.1016/j.knosys.2024.112651

Yafeng Li, Jiqing Zhang, Yuehan Chen, Yudong Li, Haoming Tang, Xianping Fu

Polarization imaging is extensively employed in underwater image restoration owing to its effectiveness in eliminating backscattered light. However, the existing polarization-based imaging methods rely on the strong assumption that the degrees of polarization (DoPs) of the target and backscattered light remain constant. Additionally, these methods ignore wavelength-specific absorption phenomena. To address these challenges, we propose an underwater image restoration method via spatially adaptive polarization imaging and color correction. First, based on optimal polarization difference images, we propose a method for calculating the spatial DoP of the target. In this method, the polarization characteristics of the target and background are fully exploited, and a scoring function is designed to achieve an optimal differential image. Second, we propose an adaptive local optimization method to estimate the spatial DoP of backscattering, which involves dividing the image into multiple local regions, and then employing improved particle swarm optimization (IPSO) algorithms to obtain the optimal value of DoP for each region. Finally, we introduce an adaptive compensation method based on the channel with minimal color absorption to correct color shifts during underwater polarization imaging. Extensive experiments demonstrate that our method exhibits superior generalization capability and outstanding restoration performance compared to existing methods.

由于偏振成像能有效消除后向散射光，因此被广泛用于水下图像修复。然而，现有的基于偏振的成像方法依赖于目标光和背向散射光的偏振度（DoPs）保持不变这一强有力的假设。此外，这些方法还忽略了特定波长的吸收现象。为了应对这些挑战，我们提出了一种通过空间自适应偏振成像和色彩校正进行水下图像修复的方法。首先，基于最佳偏振差图像，我们提出了一种计算目标空间 DoP 的方法。在该方法中，我们充分利用了目标和背景的偏振特性，并设计了一个评分函数来获得最佳差分图像。其次，我们提出了一种估算反向散射空间 DoP 的自适应局部优化方法，该方法将图像划分为多个局部区域，然后采用改进的粒子群优化（IPSO）算法来获取每个区域的 DoP 最佳值。最后，我们引入了一种基于颜色吸收最小通道的自适应补偿方法，以纠正水下偏振成像过程中的颜色偏移。广泛的实验证明，与现有方法相比，我们的方法具有卓越的泛化能力和出色的恢复性能。

{"title":"Underwater image restoration via spatially adaptive polarization imaging and color correction","authors":"Yafeng Li, Jiqing Zhang, Yuehan Chen, Yudong Li, Haoming Tang, Xianping Fu","doi":"10.1016/j.knosys.2024.112651","DOIUrl":"10.1016/j.knosys.2024.112651","url":null,"abstract":"<div><div>Polarization imaging is extensively employed in underwater image restoration owing to its effectiveness in eliminating backscattered light. However, the existing polarization-based imaging methods rely on the strong assumption that the degrees of polarization (DoPs) of the target and backscattered light remain constant. Additionally, these methods ignore wavelength-specific absorption phenomena. To address these challenges, we propose an underwater image restoration method via spatially adaptive polarization imaging and color correction. First, based on optimal polarization difference images, we propose a method for calculating the spatial DoP of the target. In this method, the polarization characteristics of the target and background are fully exploited, and a scoring function is designed to achieve an optimal differential image. Second, we propose an adaptive local optimization method to estimate the spatial DoP of backscattering, which involves dividing the image into multiple local regions, and then employing improved particle swarm optimization (IPSO) algorithms to obtain the optimal value of DoP for each region. Finally, we introduce an adaptive compensation method based on the channel with minimal color absorption to correct color shifts during underwater polarization imaging. Extensive experiments demonstrate that our method exhibits superior generalization capability and outstanding restoration performance compared to existing methods.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112651"},"PeriodicalIF":7.2,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553805","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

Transfer graph feature alignment guided multi-source domain adaptation network for machinery fault diagnosis 用于机械故障诊断的转移图特征对齐引导的多源域适应网络

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-24 DOI: 10.1016/j.knosys.2024.112606

Zhengwu Liu , Xiang Zhong , Haidong Shao , Shen Yan , Bin Liu

In recent years, the application of unsupervised multi-source domain adaptation (MSDA) techniques for fault diagnosis has gained significant traction. Current research typically overlooks or fails to effectively capture critical data structure information during feature extraction. Another challenge is optimising the integration of information from multiple source domains to diagnose the target domain while avoiding negative transfer. To address these challenges, this study proposes a transfer graph feature alignment guided multi-source domain adaptation network (MDTGAL). In the proposed method, a transfer graph sample generator module (GSG) is constructed to model the data structure between source and target domains, and multiple graph feature extractors are employed to learn the data structure information from different domain combinations. A regularisation technique is introduced to extract the domain-invariant features by aligning the parameters across multiple independent graph feature extractors. In addition, a weighted soft-voting mechanism based on the polynomial kernel-induced maximum mean difference metric (PK-MMD) is designed to fuse the outputs from multiple classifiers, to comprehensively account for the influence of each source domain. The proposed method was tested on multi-source domain transfer tasks involving various operating conditions of rotating machinery. The experimental results demonstrate that the MDTGAL exhibits superior cross-domain diagnostic performance, outperforming existing mainstream methods. In addition, this study explored the impact of varying numbers of source domains on the diagnostic accuracy of the target domain, providing insights into selecting the correct number of source domains for specific MSDA tasks.

近年来，无监督多源域适应（MSDA）技术在故障诊断中的应用得到了广泛关注。目前的研究通常会忽略或无法在特征提取过程中有效捕捉关键的数据结构信息。另一个挑战是如何优化整合来自多个源域的信息，以诊断目标域，同时避免负迁移。为应对这些挑战，本研究提出了一种转移图特征配准引导的多源域适应网络（MDTGAL）。在所提出的方法中，构建了一个转移图样本生成器模块（GSG）来模拟源域和目标域之间的数据结构，并采用多个图特征提取器来学习不同域组合的数据结构信息。通过调整多个独立图特征提取器的参数，引入正则化技术来提取域不变特征。此外，还设计了一种基于多项式核诱导最大均值差度量（PK-MMD）的加权软投票机制，用于融合多个分类器的输出，以全面考虑每个源域的影响。所提出的方法在涉及旋转机械各种运行条件的多源域转移任务中进行了测试。实验结果表明，MDTGAL 具有卓越的跨域诊断性能，优于现有的主流方法。此外，本研究还探讨了不同数量的源域对目标域诊断准确性的影响，为特定 MSDA 任务选择正确数量的源域提供了启示。

{"title":"Transfer graph feature alignment guided multi-source domain adaptation network for machinery fault diagnosis","authors":"Zhengwu Liu , Xiang Zhong , Haidong Shao , Shen Yan , Bin Liu","doi":"10.1016/j.knosys.2024.112606","DOIUrl":"10.1016/j.knosys.2024.112606","url":null,"abstract":"<div><div>In recent years, the application of unsupervised multi-source domain adaptation (MSDA) techniques for fault diagnosis has gained significant traction. Current research typically overlooks or fails to effectively capture critical data structure information during feature extraction. Another challenge is optimising the integration of information from multiple source domains to diagnose the target domain while avoiding negative transfer. To address these challenges, this study proposes a transfer graph feature alignment guided multi-source domain adaptation network (MDTGAL). In the proposed method, a transfer graph sample generator module (GSG) is constructed to model the data structure between source and target domains, and multiple graph feature extractors are employed to learn the data structure information from different domain combinations. A regularisation technique is introduced to extract the domain-invariant features by aligning the parameters across multiple independent graph feature extractors. In addition, a weighted soft-voting mechanism based on the polynomial kernel-induced maximum mean difference metric (PK-MMD) is designed to fuse the outputs from multiple classifiers, to comprehensively account for the influence of each source domain. The proposed method was tested on multi-source domain transfer tasks involving various operating conditions of rotating machinery. The experimental results demonstrate that the MDTGAL exhibits superior cross-domain diagnostic performance, outperforming existing mainstream methods. In addition, this study explored the impact of varying numbers of source domains on the diagnostic accuracy of the target domain, providing insights into selecting the correct number of source domains for specific MSDA tasks.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112606"},"PeriodicalIF":7.2,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594092","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

IDSV-GCN: Integrating Dual Syntactic Views Graph Convolutional Network for aspect-based sentiment analysis IDSV-GCN：整合双句法视图图卷积网络，用于基于方面的情感分析

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-24 DOI: 10.1016/j.knosys.2024.112656

Mei Yu , Feng Peng , Yue Zhao , Wenbin Zhang , Jian Yu , Mankun Zhao

Aspect-based sentiment analysis (ABSA) aims to predict the sentiment polarity towards given aspects in a sentence. Recent research has highlighted that graph neural networks based on syntactic dependency trees effectively convey rich syntactic information and are suitable for ABSA tasks. Most existing work typically adopt either dependency type or minimum distance between nodes in the original syntactic tree to construct different views. However, existing work overlooks the high-dimensional local feature information in dependency relations, resulting in inadequate exploration of this view. Meanwhile, most work ignores that the minimum distance view and the dependency view can be complementary and integrated in syntactic analysis. Unfortunately, directly adding the two views introduces noise issues, leading to unsatisfactory results after their integration. To address these issues, this paper introduces an integrating dual syntactic views graph convolutional network (IDSV-GCN) model that seamlessly integrates dependency type view and minimum distance view, enabling comprehensive utilization of syntactic structure and information. To better address the computation of weights in the dependency type view, we innovatively propose a fusion attention mechanism. This approach effectively captures both global and local feature information. To more effectively integrate the two views and reduce the impact of noise, we employ a syntactic mask layer to filter out noise in the dependency type view and highlighting important dependency feature information. Then, we construct a minimum distance weight matrix based on the matrix obtained from the dependency type view. Finally, we merge the two matrices and feed them into the GCN to facilitate the model’s learning of syntactic information. Experimental results on three widely-used benchmark datasets demonstrate that our proposed IDSV-GCN model outperforms state-of-the-art methods.

基于方面的情感分析（ABSA）旨在预测句子中给定方面的情感极性。最近的研究表明，基于句法依存树的图神经网络能有效传递丰富的句法信息，适用于 ABSA 任务。大多数现有研究通常采用依赖类型或原始句法树中节点间的最小距离来构建不同的视图。然而，现有工作忽略了依赖关系中的高维局部特征信息，导致对该视图的探索不够充分。同时，大多数工作忽视了最小距离视图和依赖关系视图在句法分析中可以互补和整合。遗憾的是，直接添加这两种视图会带来噪音问题，导致整合后的结果不尽如人意。为了解决这些问题，本文介绍了一种整合双句法视图图卷积网络（IDSV-GCN）模型，它能无缝整合依赖类型视图和最小距离视图，从而实现对句法结构和信息的综合利用。为了更好地解决依赖类型视图中权重的计算问题，我们创新性地提出了一种融合关注机制。这种方法能有效捕捉全局和局部特征信息。为了更有效地整合两种视图并减少噪声的影响，我们采用了语法掩码层来过滤依赖类型视图中的噪声，并突出重要的依赖特征信息。然后，我们根据从依赖类型视图中获得的矩阵构建最小距离权重矩阵。最后，我们将两个矩阵合并并输入 GCN，以促进模型对句法信息的学习。在三个广泛使用的基准数据集上的实验结果表明，我们提出的 IDSV-GCN 模型优于最先进的方法。

{"title":"IDSV-GCN: Integrating Dual Syntactic Views Graph Convolutional Network for aspect-based sentiment analysis","authors":"Mei Yu , Feng Peng , Yue Zhao , Wenbin Zhang , Jian Yu , Mankun Zhao","doi":"10.1016/j.knosys.2024.112656","DOIUrl":"10.1016/j.knosys.2024.112656","url":null,"abstract":"<div><div>Aspect-based sentiment analysis (ABSA) aims to predict the sentiment polarity towards given aspects in a sentence. Recent research has highlighted that graph neural networks based on syntactic dependency trees effectively convey rich syntactic information and are suitable for ABSA tasks. Most existing work typically adopt either dependency type or minimum distance between nodes in the original syntactic tree to construct different views. However, existing work overlooks the high-dimensional local feature information in dependency relations, resulting in inadequate exploration of this view. Meanwhile, most work ignores that the minimum distance view and the dependency view can be complementary and integrated in syntactic analysis. Unfortunately, directly adding the two views introduces noise issues, leading to unsatisfactory results after their integration. To address these issues, this paper introduces an integrating dual syntactic views graph convolutional network (IDSV-GCN) model that seamlessly integrates dependency type view and minimum distance view, enabling comprehensive utilization of syntactic structure and information. To better address the computation of weights in the dependency type view, we innovatively propose a fusion attention mechanism. This approach effectively captures both global and local feature information. To more effectively integrate the two views and reduce the impact of noise, we employ a syntactic mask layer to filter out noise in the dependency type view and highlighting important dependency feature information. Then, we construct a minimum distance weight matrix based on the matrix obtained from the dependency type view. Finally, we merge the two matrices and feed them into the GCN to facilitate the model’s learning of syntactic information. Experimental results on three widely-used benchmark datasets demonstrate that our proposed IDSV-GCN model outperforms state-of-the-art methods.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112656"},"PeriodicalIF":7.2,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573325","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

Considering representation diversity and prediction consistency for domain generalization semantic segmentation 考虑领域泛化语义分割的表征多样性和预测一致性

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-23 DOI: 10.1016/j.knosys.2024.112649

Muxin Liao , Shishun Tian , Yuhang Zhang , Guoguang Hua , Wenbin Zou , Xia Li

Existing domain generalization semantic segmentation (DGSS) methods aim to learn domain-invariant representation from single or multiple domains by using the consistency constraint or normalization strategy. Although these methods can improve the generalization capability of the models, the representation capability may be inevitably weakened since some effective information is eliminated, which may lead to the low discrimination capability of models. To simultaneously preserve the generalization and discrimination capability of models, we provide a novel perspective that encourages to learn the distinct representation while keeping the consistent prediction. Based on this, we propose a novel approach for domain generalization semantic segmentation by simultaneously considering the representation diversity and prediction consistency. The proposed approach consists of an adaptive style randomization (ASR) module, a representation diversity (RD) constraint, and a prediction consistency (PC) constraint. Specifically, first, since diverse stylized images are beneficial for the RD constraint to learn the distinct representation, the ASR module is proposed to leverage global and local style randomization to generate diverse stylized images which have the same content as the source domain images. Then, the distinct representation is learned from the source domain images and the stylized images by using the RD constraint to improve the discrimination capability of the model. Finally, the distinct representation is expected to generate consistent prediction by using the PC constraint for preserving the generalization capability of the model. Extensive experiments demonstrate that our approach achieves superior performance over current approaches on several benchmarks.

现有的领域泛化语义分割（DGSS）方法旨在通过使用一致性约束或归一化策略，从单个或多个领域中学习与领域无关的表征。虽然这些方法可以提高模型的泛化能力，但由于消除了一些有效信息，表征能力可能会不可避免地被削弱，从而导致模型的辨别能力低下。为了同时保持模型的泛化能力和判别能力，我们提供了一种新的视角，鼓励在保持预测一致性的同时学习不同的表征。在此基础上，我们提出了一种同时考虑表征多样性和预测一致性的领域泛化语义分割新方法。所提出的方法由自适应风格随机化（ASR）模块、表征多样性（RD）约束和预测一致性（PC）约束组成。具体来说，首先，由于多样化的风格化图像有利于 RD 约束学习独特表示法，因此建议 ASR 模块利用全局和局部风格随机化生成与源领域图像内容相同的多样化风格化图像。然后，利用 RD 约束从源域图像和风格化图像中学习独特表征，以提高模型的分辨能力。最后，通过使用 PC 约束来保持模型的泛化能力，从而使不同的表征产生一致的预测。广泛的实验证明，我们的方法在多个基准测试中取得了优于现有方法的性能。

{"title":"Considering representation diversity and prediction consistency for domain generalization semantic segmentation","authors":"Muxin Liao , Shishun Tian , Yuhang Zhang , Guoguang Hua , Wenbin Zou , Xia Li","doi":"10.1016/j.knosys.2024.112649","DOIUrl":"10.1016/j.knosys.2024.112649","url":null,"abstract":"<div><div>Existing domain generalization semantic segmentation (DGSS) methods aim to learn domain-invariant representation from single or multiple domains by using the consistency constraint or normalization strategy. Although these methods can improve the generalization capability of the models, the representation capability may be inevitably weakened since some effective information is eliminated, which may lead to the low discrimination capability of models. To simultaneously preserve the generalization and discrimination capability of models, we provide a novel perspective that encourages to learn the distinct representation while keeping the consistent prediction. Based on this, we propose a novel approach for domain generalization semantic segmentation by simultaneously considering the representation diversity and prediction consistency. The proposed approach consists of an adaptive style randomization (ASR) module, a representation diversity (RD) constraint, and a prediction consistency (PC) constraint. Specifically, first, since diverse stylized images are beneficial for the RD constraint to learn the distinct representation, the ASR module is proposed to leverage global and local style randomization to generate diverse stylized images which have the same content as the source domain images. Then, the distinct representation is learned from the source domain images and the stylized images by using the RD constraint to improve the discrimination capability of the model. Finally, the distinct representation is expected to generate consistent prediction by using the PC constraint for preserving the generalization capability of the model. Extensive experiments demonstrate that our approach achieves superior performance over current approaches on several benchmarks.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112649"},"PeriodicalIF":7.2,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594093","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

Contrastive learning for fair graph representations via counterfactual graph augmentation 通过反事实图增强对公平图表示进行对比学习

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-23 DOI: 10.1016/j.knosys.2024.112635

Chengyu Li , Debo Cheng , Guixian Zhang , Shichao Zhang

Graph neural networks (GNNs) have exhibited excellent performance in graph representation learning. However, GNNs might inherit biases from the data, leading to discriminatory predictions. Existing study mainly concentrates on attaining fairness through counterfactuals related to node attributes, overlooking the causal impact of bias in the graph structure. Herein, we introduce a novel framework called fair contrastive learning based on counterfactual graph augmentation (FCLCA), aimed at learning counterfactual fairness by mitigating graph structure bias. FCLCA first generates two counterfactual graphs through structural augmentation. Next, we maximize the consistency between representations produced by nodes in these two counterfactual graphs using contrastive learning. In addition, FCLCA uses adversarial debiasing learning to further reduce the influence of sensitive attributes on the learned node representations. Finally, an optimized training strategy is used for contrastive learning to enhance the learning of counterfactual fairness. Comprehensive experiments conducted on four real-world datasets proved the effectiveness of FCLCA in balancing classification performance and fairness.

图神经网络（GNN）在图表示学习中表现出卓越的性能。然而，图神经网络可能会从数据中继承偏差，从而导致歧视性预测。现有研究主要集中在通过与节点属性相关的反事实来实现公平性，而忽略了图结构中偏差的因果影响。在这里，我们引入了一种新的框架，称为基于反事实图增强的公平对比学习（FCLCA），旨在通过减轻图结构偏差来学习反事实公平性。FCLCA 首先通过结构增强生成两个反事实图。接下来，我们利用对比学习最大化这两个反事实图中节点产生的表征之间的一致性。此外，FCLCA 还使用对抗性去杂学习来进一步降低敏感属性对所学节点表征的影响。最后，对比学习采用了优化的训练策略，以增强对反事实公平性的学习。在四个真实世界数据集上进行的综合实验证明了 FCLCA 在平衡分类性能和公平性方面的有效性。

{"title":"Contrastive learning for fair graph representations via counterfactual graph augmentation","authors":"Chengyu Li , Debo Cheng , Guixian Zhang , Shichao Zhang","doi":"10.1016/j.knosys.2024.112635","DOIUrl":"10.1016/j.knosys.2024.112635","url":null,"abstract":"<div><div>Graph neural networks (GNNs) have exhibited excellent performance in graph representation learning. However, GNNs might inherit biases from the data, leading to discriminatory predictions. Existing study mainly concentrates on attaining fairness through counterfactuals related to node attributes, overlooking the causal impact of bias in the graph structure. Herein, we introduce a novel framework called fair contrastive learning based on counterfactual graph augmentation (FCLCA), aimed at learning counterfactual fairness by mitigating graph structure bias. FCLCA first generates two counterfactual graphs through structural augmentation. Next, we maximize the consistency between representations produced by nodes in these two counterfactual graphs using contrastive learning. In addition, FCLCA uses adversarial debiasing learning to further reduce the influence of sensitive attributes on the learned node representations. Finally, an optimized training strategy is used for contrastive learning to enhance the learning of counterfactual fairness. Comprehensive experiments conducted on four real-world datasets proved the effectiveness of FCLCA in balancing classification performance and fairness.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112635"},"PeriodicalIF":7.2,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529407","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

Payoff-driven migration promotes the evolution of trust in networked populations 回报驱动的迁移促进了网络群体中信任的进化

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-23 DOI: 10.1016/j.knosys.2024.112645

Yuying Zhu , Wenbo Li , Chengyi Xia , Manuel Chica

Establishing and maintaining trustworthy behaviors in large populations of self-interested individuals is a significant problem which received extensive attentions from research fields such as evolutionary biology, economics, sociology and engineering. As a well-known model that captures social trust dilemmas, the

N

-player trust game is adopted to investigate the evolution of trust in groups consisting of investors and trustees. In addition, to model real scenarios in dynamic environments, we introduce a novel migration mechanism, called adaptive environment-benefit-driven migration, which considers the influence of individuals’ payoffs on migration. Through theoretical analysis and Monte Carlo simulations, we demonstrate the effectiveness of the migration mechanism on facilitating trust behaviors in the framework of evolutionary game theory. We find that the population density plays a crucial role in establishing trust. Simulation results reveal that trust can be fostered in a dynamic environment influenced by individual migration with the medium vacancy rate. This work significantly contributes to the understanding of mutual trust behaviors in networked social systems from a more realistic perspective.

在大量自利个体中建立和维持信任行为是一个重要问题，受到进化生物学、经济学、社会学和工程学等研究领域的广泛关注。作为一个能捕捉社会信任困境的著名模型，本文采用 N 人信任博弈来研究由投资者和受托人组成的群体中的信任演化。此外，为了模拟动态环境中的真实场景，我们引入了一种新的迁移机制，即自适应环境-收益驱动迁移，该机制考虑了个体收益对迁移的影响。通过理论分析和蒙特卡罗模拟，我们在进化博弈论的框架内证明了迁移机制在促进信任行为方面的有效性。我们发现，种群密度在建立信任方面起着至关重要的作用。模拟结果表明，在一个受中等空缺率的个体迁移影响的动态环境中，信任是可以促进的。这项工作极大地促进了人们从更现实的角度理解网络社会系统中的相互信任行为。

{"title":"Payoff-driven migration promotes the evolution of trust in networked populations","authors":"Yuying Zhu , Wenbo Li , Chengyi Xia , Manuel Chica","doi":"10.1016/j.knosys.2024.112645","DOIUrl":"10.1016/j.knosys.2024.112645","url":null,"abstract":"<div><div>Establishing and maintaining trustworthy behaviors in large populations of self-interested individuals is a significant problem which received extensive attentions from research fields such as evolutionary biology, economics, sociology and engineering. As a well-known model that captures social trust dilemmas, the <span><math><mi>N</mi></math></span>-player trust game is adopted to investigate the evolution of trust in groups consisting of investors and trustees. In addition, to model real scenarios in dynamic environments, we introduce a novel migration mechanism, called adaptive environment-benefit-driven migration, which considers the influence of individuals’ payoffs on migration. Through theoretical analysis and Monte Carlo simulations, we demonstrate the effectiveness of the migration mechanism on facilitating trust behaviors in the framework of evolutionary game theory. We find that the population density plays a crucial role in establishing trust. Simulation results reveal that trust can be fostered in a dynamic environment influenced by individual migration with the medium vacancy rate. This work significantly contributes to the understanding of mutual trust behaviors in networked social systems from a more realistic perspective.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112645"},"PeriodicalIF":7.2,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573333","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

Advanced drone-based weed detection using feature-enriched deep learning approach 利用丰富特征的深度学习方法进行先进的无人机杂草检测

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-23 DOI: 10.1016/j.knosys.2024.112655

Mobeen Ur Rehman , Hassan Eesaar , Zeeshan Abbas , Lakmal Seneviratne , Irfan Hussain , Kil To Chong

This research addresses the pressing challenge of weed identification in agriculture, crucial for ensuring food security in anticipation of a global population exceeding 9.7 billion by 2050. Utilizing drone imagery, we collected a dataset and proposed a customized model to achieve optimal performance. Our proposed model uses strategically modified backbone, neck, and head components, leveraging elements such as Ghost Convolution, BottleNeckCSP, and ECA (Efficient Channel Attention) layers. These modifications enhance the model’s capability to discern intricate patterns in drone imagery, ultimately leading to improved precision in weed detection. We introduce a purposefully crafted dataset to complement the model’s training, and our experiments demonstrate superior performance compared to the baseline models. Our model achieves a precision of 72.5%, recall of 68.0%, and [email protected] of 73.9, showcasing the effectiveness of our approach in enhancing detection accuracy. Leveraging a unique blend of feature extraction mechanisms, our model achieves remarkable accuracy in real-time soybean detection, outperforming established models like RT-DETR (Real-Time DEtection TransfoRmer) and YOLOv10. A detailed ablation study and comparative analysis with different YOLO versions and the transformer-based RT-DETR showcase the effectiveness of the proposed enhancements. Our work signifies a significant step towards advancing the field of precision agriculture, offering a model that is not only adaptive but also robust in identifying and localizing weeds in soybean fields.

这项研究解决了农业中杂草识别这一紧迫挑战，因为预计到 2050 年全球人口将超过 97 亿，而杂草识别对于确保粮食安全至关重要。利用无人机图像，我们收集了一个数据集，并提出了一个定制模型，以实现最佳性能。我们提出的模型采用了经过战略性修改的骨干、颈部和头部组件，利用了幽灵卷积、BottleNeckCSP 和 ECA（高效通道注意）层等元素。这些修改增强了模型辨别无人机图像中复杂模式的能力，最终提高了杂草检测的精度。我们引入了一个特意制作的数据集来补充模型的训练，实验证明，与基线模型相比，我们的模型性能更优。我们的模型精确度达到 72.5%，召回率达到 68.0%，[email protected] 达到 73.9%，展示了我们的方法在提高检测精度方面的有效性。利用独特的混合特征提取机制，我们的模型在实时大豆检测方面取得了显著的准确性，优于 RT-DETR（Real-Time DEtection TransfoRmer）和 YOLOv10 等成熟模型。详细的消融研究以及与不同 YOLO 版本和基于变压器的 RT-DETR 的比较分析表明了所提出的增强功能的有效性。我们的工作标志着向推进精准农业领域迈出了重要一步，提供了一个不仅具有自适应能力，而且在识别和定位大豆田杂草方面具有鲁棒性的模型。

{"title":"Advanced drone-based weed detection using feature-enriched deep learning approach","authors":"Mobeen Ur Rehman , Hassan Eesaar , Zeeshan Abbas , Lakmal Seneviratne , Irfan Hussain , Kil To Chong","doi":"10.1016/j.knosys.2024.112655","DOIUrl":"10.1016/j.knosys.2024.112655","url":null,"abstract":"<div><div>This research addresses the pressing challenge of weed identification in agriculture, crucial for ensuring food security in anticipation of a global population exceeding 9.7 billion by 2050. Utilizing drone imagery, we collected a dataset and proposed a customized model to achieve optimal performance. Our proposed model uses strategically modified backbone, neck, and head components, leveraging elements such as Ghost Convolution, BottleNeckCSP, and ECA (Efficient Channel Attention) layers. These modifications enhance the model’s capability to discern intricate patterns in drone imagery, ultimately leading to improved precision in weed detection. We introduce a purposefully crafted dataset to complement the model’s training, and our experiments demonstrate superior performance compared to the baseline models. Our model achieves a precision of 72.5%, recall of 68.0%, and [email protected] of 73.9, showcasing the effectiveness of our approach in enhancing detection accuracy. Leveraging a unique blend of feature extraction mechanisms, our model achieves remarkable accuracy in real-time soybean detection, outperforming established models like RT-DETR (Real-Time DEtection TransfoRmer) and YOLOv10. A detailed ablation study and comparative analysis with different YOLO versions and the transformer-based RT-DETR showcase the effectiveness of the proposed enhancements. Our work signifies a significant step towards advancing the field of precision agriculture, offering a model that is not only adaptive but also robust in identifying and localizing weeds in soybean fields.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112655"},"PeriodicalIF":7.2,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0