Independent cascade(IC)models,by simulating how one node can activate another,are important tools for studying the dynamics of information spreading in complex networks.However,traditional algorithms for the IC model ...Independent cascade(IC)models,by simulating how one node can activate another,are important tools for studying the dynamics of information spreading in complex networks.However,traditional algorithms for the IC model implementation face significant efficiency bottlenecks when dealing with large-scale networks and multi-round simulations.To settle this problem,this study introduces a GPU-based parallel independent cascade(GPIC)algorithm,featuring an optimized representation of the network data structure and parallel task scheduling strategies.Specifically,for this GPIC algorithm,we propose a network data structure tailored for GPU processing,thereby enhancing the computational efficiency and the scalability of the IC model.In addition,we design a parallel framework that utilizes the full potential of GPU's parallel processing capabilities,thereby augmenting the computational efficiency.The results from our simulation experiments demonstrate that GPIC not only preserves accuracy but also significantly boosts efficiency,achieving a speedup factor of 129 when compared to the baseline IC method.Our experiments also reveal that when using GPIC for the independent cascade simulation,100-200 simulation rounds are sufficient for higher-cost studies,while high precision studies benefit from 500 rounds to ensure reliable results,providing empirical guidance for applying this new algorithm to practical research.展开更多
Knowledge Graphs(KGs)are pivotal for effectively organizing and managing structured information across various applications.Financial KGs have been successfully employed in advancing applications such as audit,anti-fr...Knowledge Graphs(KGs)are pivotal for effectively organizing and managing structured information across various applications.Financial KGs have been successfully employed in advancing applications such as audit,anti-fraud,and anti-money laundering.Despite their success,the construction of Chinese financial KGs has seen limited research due to the complex semantics.A significant challenge is the overlap triples problem,where entities feature in multiple relations within a sentence,hampering extraction accuracy-more than 39%of the triples in Chinese datasets exhibit the overlap triples.To address this,we propose the Entity-type-Enriched Cascaded Neural Network(E^(2)CNN),leveraging special tokens for entity boundaries and types.E^(2)CNN ensures consistency in entity types and excludes specific relations,mitigating overlap triple problems and enhancing relation extraction.Besides,we introduce the available Chinese financial dataset FINCORPUS.CN,annotated from annual reports of 2,000 companies,containing 48,389 entities and 23,368 triples.Experimental results on the DUIE dataset and FINCORPUS.CN underscore E^(2)CNN’s superiority over state-of-the-art models.展开更多
Compared to single-layer networks,multilayer networks exhibit a more complex node degree composition,comprising both intra-layer and inter-layer degrees.However,the distinct impacts of these degree types on cascading ...Compared to single-layer networks,multilayer networks exhibit a more complex node degree composition,comprising both intra-layer and inter-layer degrees.However,the distinct impacts of these degree types on cascading failures remain underexplored.Distinguishing their effects is crucial for a deeper understanding of network structure,information propagation,and behavior prediction.This paper proposes a capacity-load model to influence and compare the influence of different degree types on cascading failures in multilayer networks.By designing three node removal strategies based on total degree,intra-layer degree,and inter-layer degree,simulation experiments are conducted on four types of networks.Network robustness is evaluated using the maximum number of removable nodes before collapse.The relationships between network robustness and the coupling coefficient,as well as load and capacity adjustment parameters,are also analyzed.The results indicate that the node removal strategy with the least impact on cascading failures varies across different types of networks,revealing the significance of different node degrees in failure propagation.Compared to other models,the proposed model enables networks to maintain a higher maximum number of removable nodes during cascading failures,demonstrating superior robustness.展开更多
Cutting off or controlling the enemy’s power supply at critical moments or strategic locations may result in a cascade failure,thus gaining an advantage in a war.However,the exist-ing cascading failure modeling analy...Cutting off or controlling the enemy’s power supply at critical moments or strategic locations may result in a cascade failure,thus gaining an advantage in a war.However,the exist-ing cascading failure modeling analysis of interdependent net-works is insufficient for describing the load characteristics and dependencies of subnetworks,and it is difficult to use for model-ing and failure analysis of power-combat(P-C)coupling net-works.This paper considers the physical characteristics of the two subnetworks and studies the mechanism of fault propaga-tion between subnetworks and across systems.Then the surviv-ability of the coupled network is evaluated.Firstly,an integrated modeling approach for the combat system and power system is predicted based on interdependent network theory.A heteroge-neous one-way interdependent network model based on proba-bility dependence is constructed.Secondly,using the operation loop theory,a load-capacity model based on combat-loop betweenness is proposed,and the cascade failure model of the P-C coupling system is investigated from three perspectives:ini-tial capacity,allocation strategy,and failure mechanism.Thirdly,survivability indexes based on load loss rate and network sur-vival rate are proposed.Finally,the P-C coupling system is con-structed based on the IEEE 118-bus system to demonstrate the proposed method.展开更多
In neuropathological diseases such as Alzheimer's Disease(AD),neuroimaging and Magnetic Resonance Imaging(MRI)play crucial roles in the realm of Artificial Intelligence of Medical Things(AIoMT)by leveraging edge i...In neuropathological diseases such as Alzheimer's Disease(AD),neuroimaging and Magnetic Resonance Imaging(MRI)play crucial roles in the realm of Artificial Intelligence of Medical Things(AIoMT)by leveraging edge intelligence resources.However,accurately classifying MRI scans based on neurodegenerative diseases faces challenges due to significant variability across classes and limited intra-class differences.To address this challenge,we propose a novel approach aimed at improving the early detection of AD through MRI imaging.This method integrates a Convolutional Neural Network(CNN)with a Cascade Attention Model(CAM-CNN).The CAM-CNN model outperforms traditional CNNs in AD classification accuracy and processing complexity.In this architecture,the attention mechanism is effectively implemented by utilizing two constraint cost functions and a cross-network with diverse pre-trained parameters for a two-stream architecture.Additionally,two new cost functions,Satisfied Rank Loss(SRL)and Cross-Network Similarity Loss(CNSL),are introduced to enhance collaboration and overall network performance.Finally,a unique entropy addition method is employed in the attention module for network integration,converting intermediate outcomes into the final prediction.These components are designed to work collaboratively and can be sequentially trained for optimal performance,thereby enhancing the effectiveness of AD stage classification and robustness to interference from MR images.Validation using the Kaggle dataset demonstrates the model's accuracy of 99.07%in multiclass classification,ensuring precise classification and early detection of all AD subtypes.Further validation across three feature categories with varying numbers confirms the robustness of the proposed approach,with deviations from the standard criteria of less than 1%.Applied in Alzheimer's patient care,this capability holds promise for enhancing value-based therapy and clinical decision-making.It aids in differentiating Alzheimer's patients from healthy individuals,thereby improving patient care and enabling more targeted therapies.展开更多
针对光照不均、噪声大、拍摄质量不高的夜晚水下环境,为实现夜晚水下图像中鱼类目标的快速检测,利用计算机视觉技术,提出了一种基于改进Cascade R-CNN算法和具有色彩保护的MSRCP(Multi-scale Retinex with color restoration)图像增强...针对光照不均、噪声大、拍摄质量不高的夜晚水下环境,为实现夜晚水下图像中鱼类目标的快速检测,利用计算机视觉技术,提出了一种基于改进Cascade R-CNN算法和具有色彩保护的MSRCP(Multi-scale Retinex with color restoration)图像增强算法的夜晚水下鱼类目标检测方法。首先针对夜晚水下环境的视频数据,根据时间间隔,截取出相应的夜晚水下鱼类图像,对截取的原始图像进行MSRCP图像增强。然后采用DetNASNet主干网络进行网络训练和水下鱼类特征信息的提取,将提取出的特征信息输入到Cascade R-CNN模型中,并使用Soft-NMS候选框优化算法对其中的RPN网络进行优化,最后对夜晚水下鱼类目标进行检测。实验结果表明,该方法解决了夜晚水下环境中的图像降质、鱼类目标重叠检测问题,实现了对夜晚水下鱼类目标的快速检测,对夜晚水下鱼类图像目标检测的查准率达到95.81%,比Cascade R-CNN方法提高了11.57个百分点。展开更多
混凝土内部损伤破坏形态具有明显的离散性和随机性,内部损伤特征检测是混凝土细观研究的重要内容.针对已有混凝土结构内部损伤特征检测模型精度低的问题,提出一种特征共享双头Cascade R-CNN模型对混凝土CT图像的损伤特征进行检测.首先,...混凝土内部损伤破坏形态具有明显的离散性和随机性,内部损伤特征检测是混凝土细观研究的重要内容.针对已有混凝土结构内部损伤特征检测模型精度低的问题,提出一种特征共享双头Cascade R-CNN模型对混凝土CT图像的损伤特征进行检测.首先,为了有效识别损伤特征的空间信息,构建具有空间敏感性的fc-head(fully connected head)与空间相关性的conv-head(convolution head)相结合的Cascade R-CNN网络模型;其次,通过特征共享的方法将检测网络各层级分类信息进行融合,提升低IOU(intersection over union)阈值(0.5~0.7) ROI (regions of interest)检测任务的精度.实验结果表明,所提方法在检测混凝土CT图像的损伤特征中平均精度达到91.31%,比原始的Cascade R-CNN提高3.04%,低IOU阈值(0.5~0.7) ROI平均精度提高1.49%,该模型可以较好地从混凝土CT图像中检测出细观损伤部分,具有精度高、运算简单、易于工程实现等特点.展开更多
基金support from the National Natural Science Foundation of China(Grant No.T2293771)the STI 2030-Major Projects(Grant No.2022ZD0211400)the Sichuan Province Outstanding Young Scientists Foundation(Grant No.2023NSFSC1919)。
文摘Independent cascade(IC)models,by simulating how one node can activate another,are important tools for studying the dynamics of information spreading in complex networks.However,traditional algorithms for the IC model implementation face significant efficiency bottlenecks when dealing with large-scale networks and multi-round simulations.To settle this problem,this study introduces a GPU-based parallel independent cascade(GPIC)algorithm,featuring an optimized representation of the network data structure and parallel task scheduling strategies.Specifically,for this GPIC algorithm,we propose a network data structure tailored for GPU processing,thereby enhancing the computational efficiency and the scalability of the IC model.In addition,we design a parallel framework that utilizes the full potential of GPU's parallel processing capabilities,thereby augmenting the computational efficiency.The results from our simulation experiments demonstrate that GPIC not only preserves accuracy but also significantly boosts efficiency,achieving a speedup factor of 129 when compared to the baseline IC method.Our experiments also reveal that when using GPIC for the independent cascade simulation,100-200 simulation rounds are sufficient for higher-cost studies,while high precision studies benefit from 500 rounds to ensure reliable results,providing empirical guidance for applying this new algorithm to practical research.
基金supported in part by the National Key R&D Program of China(Grant No.2020AAA0108501).
文摘Knowledge Graphs(KGs)are pivotal for effectively organizing and managing structured information across various applications.Financial KGs have been successfully employed in advancing applications such as audit,anti-fraud,and anti-money laundering.Despite their success,the construction of Chinese financial KGs has seen limited research due to the complex semantics.A significant challenge is the overlap triples problem,where entities feature in multiple relations within a sentence,hampering extraction accuracy-more than 39%of the triples in Chinese datasets exhibit the overlap triples.To address this,we propose the Entity-type-Enriched Cascaded Neural Network(E^(2)CNN),leveraging special tokens for entity boundaries and types.E^(2)CNN ensures consistency in entity types and excludes specific relations,mitigating overlap triple problems and enhancing relation extraction.Besides,we introduce the available Chinese financial dataset FINCORPUS.CN,annotated from annual reports of 2,000 companies,containing 48,389 entities and 23,368 triples.Experimental results on the DUIE dataset and FINCORPUS.CN underscore E^(2)CNN’s superiority over state-of-the-art models.
基金supported by the National Social Science Fund Project(No.23&ZD115)the Graduate Student Research Innovation Project of the School of Mathematics and Statistics,Hubei Minzu University(No.STK2023011)。
文摘Compared to single-layer networks,multilayer networks exhibit a more complex node degree composition,comprising both intra-layer and inter-layer degrees.However,the distinct impacts of these degree types on cascading failures remain underexplored.Distinguishing their effects is crucial for a deeper understanding of network structure,information propagation,and behavior prediction.This paper proposes a capacity-load model to influence and compare the influence of different degree types on cascading failures in multilayer networks.By designing three node removal strategies based on total degree,intra-layer degree,and inter-layer degree,simulation experiments are conducted on four types of networks.Network robustness is evaluated using the maximum number of removable nodes before collapse.The relationships between network robustness and the coupling coefficient,as well as load and capacity adjustment parameters,are also analyzed.The results indicate that the node removal strategy with the least impact on cascading failures varies across different types of networks,revealing the significance of different node degrees in failure propagation.Compared to other models,the proposed model enables networks to maintain a higher maximum number of removable nodes during cascading failures,demonstrating superior robustness.
基金supported by the National Natural Science Foundation of China(72271242)Hunan Provincial Natural Science Foundation of China for Excellent Young Scholars(2022JJ20046).
文摘Cutting off or controlling the enemy’s power supply at critical moments or strategic locations may result in a cascade failure,thus gaining an advantage in a war.However,the exist-ing cascading failure modeling analysis of interdependent net-works is insufficient for describing the load characteristics and dependencies of subnetworks,and it is difficult to use for model-ing and failure analysis of power-combat(P-C)coupling net-works.This paper considers the physical characteristics of the two subnetworks and studies the mechanism of fault propaga-tion between subnetworks and across systems.Then the surviv-ability of the coupled network is evaluated.Firstly,an integrated modeling approach for the combat system and power system is predicted based on interdependent network theory.A heteroge-neous one-way interdependent network model based on proba-bility dependence is constructed.Secondly,using the operation loop theory,a load-capacity model based on combat-loop betweenness is proposed,and the cascade failure model of the P-C coupling system is investigated from three perspectives:ini-tial capacity,allocation strategy,and failure mechanism.Thirdly,survivability indexes based on load loss rate and network sur-vival rate are proposed.Finally,the P-C coupling system is con-structed based on the IEEE 118-bus system to demonstrate the proposed method.
基金funded by the National Elites Foundation(No.711.5095).
文摘In neuropathological diseases such as Alzheimer's Disease(AD),neuroimaging and Magnetic Resonance Imaging(MRI)play crucial roles in the realm of Artificial Intelligence of Medical Things(AIoMT)by leveraging edge intelligence resources.However,accurately classifying MRI scans based on neurodegenerative diseases faces challenges due to significant variability across classes and limited intra-class differences.To address this challenge,we propose a novel approach aimed at improving the early detection of AD through MRI imaging.This method integrates a Convolutional Neural Network(CNN)with a Cascade Attention Model(CAM-CNN).The CAM-CNN model outperforms traditional CNNs in AD classification accuracy and processing complexity.In this architecture,the attention mechanism is effectively implemented by utilizing two constraint cost functions and a cross-network with diverse pre-trained parameters for a two-stream architecture.Additionally,two new cost functions,Satisfied Rank Loss(SRL)and Cross-Network Similarity Loss(CNSL),are introduced to enhance collaboration and overall network performance.Finally,a unique entropy addition method is employed in the attention module for network integration,converting intermediate outcomes into the final prediction.These components are designed to work collaboratively and can be sequentially trained for optimal performance,thereby enhancing the effectiveness of AD stage classification and robustness to interference from MR images.Validation using the Kaggle dataset demonstrates the model's accuracy of 99.07%in multiclass classification,ensuring precise classification and early detection of all AD subtypes.Further validation across three feature categories with varying numbers confirms the robustness of the proposed approach,with deviations from the standard criteria of less than 1%.Applied in Alzheimer's patient care,this capability holds promise for enhancing value-based therapy and clinical decision-making.It aids in differentiating Alzheimer's patients from healthy individuals,thereby improving patient care and enabling more targeted therapies.
文摘针对光照不均、噪声大、拍摄质量不高的夜晚水下环境,为实现夜晚水下图像中鱼类目标的快速检测,利用计算机视觉技术,提出了一种基于改进Cascade R-CNN算法和具有色彩保护的MSRCP(Multi-scale Retinex with color restoration)图像增强算法的夜晚水下鱼类目标检测方法。首先针对夜晚水下环境的视频数据,根据时间间隔,截取出相应的夜晚水下鱼类图像,对截取的原始图像进行MSRCP图像增强。然后采用DetNASNet主干网络进行网络训练和水下鱼类特征信息的提取,将提取出的特征信息输入到Cascade R-CNN模型中,并使用Soft-NMS候选框优化算法对其中的RPN网络进行优化,最后对夜晚水下鱼类目标进行检测。实验结果表明,该方法解决了夜晚水下环境中的图像降质、鱼类目标重叠检测问题,实现了对夜晚水下鱼类目标的快速检测,对夜晚水下鱼类图像目标检测的查准率达到95.81%,比Cascade R-CNN方法提高了11.57个百分点。
文摘混凝土内部损伤破坏形态具有明显的离散性和随机性,内部损伤特征检测是混凝土细观研究的重要内容.针对已有混凝土结构内部损伤特征检测模型精度低的问题,提出一种特征共享双头Cascade R-CNN模型对混凝土CT图像的损伤特征进行检测.首先,为了有效识别损伤特征的空间信息,构建具有空间敏感性的fc-head(fully connected head)与空间相关性的conv-head(convolution head)相结合的Cascade R-CNN网络模型;其次,通过特征共享的方法将检测网络各层级分类信息进行融合,提升低IOU(intersection over union)阈值(0.5~0.7) ROI (regions of interest)检测任务的精度.实验结果表明,所提方法在检测混凝土CT图像的损伤特征中平均精度达到91.31%,比原始的Cascade R-CNN提高3.04%,低IOU阈值(0.5~0.7) ROI平均精度提高1.49%,该模型可以较好地从混凝土CT图像中检测出细观损伤部分,具有精度高、运算简单、易于工程实现等特点.
