Aiming at the problem of poor tracking robustness caused by severe occlusion,deformation,and object rotation of deep learning object tracking algorithm in complex scenes,an improved deep reinforcement learning object ...Aiming at the problem of poor tracking robustness caused by severe occlusion,deformation,and object rotation of deep learning object tracking algorithm in complex scenes,an improved deep reinforcement learning object tracking algorithm based on actor-double critic network is proposed.In offline training phase,the actor network moves the rectangular box representing the object location according to the input sequence image to obtain the action value,that is,the horizontal,vertical,and scale transformation of the object.Then,the designed double critic network is used to evaluate the action value,and the output double Q value is averaged to guide the actor network to optimize the tracking strategy.The design of double critic network effectively improves the stability and convergence,especially in challenging scenes such as object occlusion,and the tracking performance is significantly improved.In online tracking phase,the well-trained actor network is used to infer the changing action of the bounding box,directly causing the tracker to move the box to the object position in the current frame.Several comparative tracking experiments were conducted on the OTB100 visual tracker benchmark and the experimental results show that more intensive reward settings significantly increase the actor network’s output probability of positive actions.This makes the tracking algorithm proposed in this paper outperforms the mainstream deep reinforcement learning tracking algorithms and deep learning tracking algorithms under the challenging attributes such as occlusion,deformation,and rotation.展开更多
Air transport network, or airport network, is a complex network involving numerous airports. Effective management of the air transport system requires an in-depth understanding of the roles of airports in the network....Air transport network, or airport network, is a complex network involving numerous airports. Effective management of the air transport system requires an in-depth understanding of the roles of airports in the network. Whereas knowledge on air transport network properties has been improved greatly, methods to find critical airports in the network are still lacking. In this paper, we present methods to investigate network properties and to identify critical airports in the network. A novel network model is proposed with airports as nodes and the correlations between traffic flow of airports as edges. Spectral clustering algorithm is developed to classify air- ports. Spatial distribution characteristics and intraclass correlation of different categories of air- ports are carefully analyzed. The analyses based on the fluctuation trend of distance-correlation and power spectrum of time series are performed to examine the self-organized criticality of the net- work. The results indicate that there is one category of airports which dominates the self-organized critical state of the network. Six airports in this category are found to be the most important ones in the Chinese air transport network. The flights delay occurred in these six airports can propagate to the other airports, having huge impact on the operation characteristics of the entire network. The methods proposed here taking traffic dynamics into account are capable of identifying critical air- ports in the whole air transport network.展开更多
We study the criticality in excitatory-inhibitory networks consisting of excitable elements. We investigate the effects of the inhibitory strength using both numerical simulations and theoretical analysis. We show tha...We study the criticality in excitatory-inhibitory networks consisting of excitable elements. We investigate the effects of the inhibitory strength using both numerical simulations and theoretical analysis. We show that the inhibitory strength cannot affect the critical point. The dynamic range is decreased as the inhibitory strength increases.To simulate of decreasing the efficacy of excitation and inhibition which was studied in experiments, we remove excitatory or inhibitory nodes, delete excitatory or inhibitory links, and weaken excitatory or inhibitory coupling strength in critical excitatory-inhibitory network. Decreasing the excitation, the change of the dynamic range is most dramatic as the same as previous experimental results. However, decreasing inhibition has no effect on the criticality in excitatory-inhibitory network.展开更多
The paper describes modern technologies of Computer Network Reliability. Software tool is developed to estimate of the CCN critical failure probability (construction of a criticality matrix) by results of the FME(C)A-...The paper describes modern technologies of Computer Network Reliability. Software tool is developed to estimate of the CCN critical failure probability (construction of a criticality matrix) by results of the FME(C)A-technique. The internal information factors, such as collisions and congestion of switchboards, routers and servers, influence on a network reliability and safety (besides of hardware and software reliability and external extreme factors). The means and features of Failures Modes and Effects (Critical) Analysis (FME(C)A) for reliability and criticality analysis of corporate computer networks (CCN) are considered. The examples of FME(C)A-Technique for structured cable system (SCS) is given. We also discuss measures that can be used for criticality analysis and possible means of criticality reduction. Finally, we describe a technique and basic principles of dependable development and deployment of computer networks that are based on results of FMECA analysis and procedures of optimization choice of means for fault-tolerance ensuring.展开更多
Natural hazards impact interdependent infrastructure networks that keep modern society functional.While a va-riety of modelling approaches are available to represent critical infrastructure networks(CINs)on different ...Natural hazards impact interdependent infrastructure networks that keep modern society functional.While a va-riety of modelling approaches are available to represent critical infrastructure networks(CINs)on different scales and analyse the impacts of natural hazards,a recurring challenge for all modelling approaches is the availability and accessibility of sufficiently high-quality input and validation data.The resulting data gaps often require mod-ellers to assume specific technical parameters,functional relationships,and system behaviours.In other cases,expert knowledge from one sector is extrapolated to other sectoral structures or even cross-sectorally applied to fill data gaps.The uncertainties introduced by these assumptions and extrapolations and their influence on the quality of modelling outcomes are often poorly understood and difficult to capture,thereby eroding the reliability of these models to guide resilience enhancements.Additionally,ways of overcoming the data avail-ability challenges in CIN modelling,with respect to each modelling purpose,remain an open question.To address these challenges,a generic modelling workflow is derived from existing modelling approaches to examine model definition and validations,as well as the six CIN modelling stages,including mapping of infrastructure assets,quantification of dependencies,assessment of natural hazard impacts,response&recovery,quantification of CI services,and adaptation measures.The data requirements of each stage were systematically defined,and the literature on potential sources was reviewed to enhance data collection and raise awareness of potential pitfalls.The application of the derived workflow funnels into a framework to assess data availability challenges.This is shown through three case studies,taking into account their different modelling purposes:hazard hotspot assess-ments,hazard risk management,and sectoral adaptation.Based on the three model purpose types provided,a framework is suggested to explore the implications of data scarcity for certain data types,as well as their reasons and consequences for CIN model reliability.Finally,a discussion on overcoming the challenges of data scarcity is presented.展开更多
The research is focused on the development of automatic detection method of abnormal features, that occur in recorded time series of ionosphere critical frequency fOF2 during periods of high solar or seismic activity....The research is focused on the development of automatic detection method of abnormal features, that occur in recorded time series of ionosphere critical frequency fOF2 during periods of high solar or seismic activity. The method is based on joint application of wavelet-transformation and neural networks. On the basis of wavelet transformation algorithms for the detection of features and estimation of their parameters were developed. Detection and analysis of characteristic components of time series are performed on the basis of joint application of wavelet transformation and neural networks. Method's approbation is performed on fOF2 data obtained at the observatory “Paratunka” (Paratunka settlement, Kamchatskiy Kray).展开更多
抽水蓄能作为电力系统中最为成熟的新能源储能技术,凭借其能调节电网负荷、平衡电力波动及提升系统稳定性的独特优势,已成为实现中国“双碳”目标的重要路径之一。因此,对抽水蓄能电站综合效益进行科学评估,是项目决策及政策制定中至关...抽水蓄能作为电力系统中最为成熟的新能源储能技术,凭借其能调节电网负荷、平衡电力波动及提升系统稳定性的独特优势,已成为实现中国“双碳”目标的重要路径之一。因此,对抽水蓄能电站综合效益进行科学评估,是项目决策及政策制定中至关重要的一环。为此,本文提出一种基于博弈论组合赋权‒云模型的综合效益评价模型。首先,运用社会网络分析法(SNA)筛选关键评价指标,构建包含财务评价、国民经济评价、技术效益、动态效益、静态效益、电网效益、综合可持续性效益和社会效益8个1级指标及其下属30个2级指标的评价指标体系。其次,采用序关系分析(G1)法和CRITIC(criteria importance through intercriteria correlation)法相结合的方式,对各评价指标进行主观与客观权重赋值。通过引入博弈论组合赋权方法,进一步优化各指标的权重分配。最终,基于云模型构建综合效益评价模型。利用博弈论组合赋权‒云模型对紫云山抽水蓄能电站进行实例分析,结果表明,该电站的综合效益评估等级为“好”,与实际情况相符,充分验证了所构建模型的有效性与准确性。该研究不仅为抽水蓄能电站的综合效益评估提供了科学的评估框架,并为类似项目的决策和实施提供了理论支持和实践依据。展开更多
基金supported in part by the National Key R&D Program of China(No.2022YFB2602203)in part by the National Natural Science Foundation of China(Nos.U20A20225 and 61873200)Shaanxi Provincial Key Research and Development Program(No.2022-GY111).
文摘Aiming at the problem of poor tracking robustness caused by severe occlusion,deformation,and object rotation of deep learning object tracking algorithm in complex scenes,an improved deep reinforcement learning object tracking algorithm based on actor-double critic network is proposed.In offline training phase,the actor network moves the rectangular box representing the object location according to the input sequence image to obtain the action value,that is,the horizontal,vertical,and scale transformation of the object.Then,the designed double critic network is used to evaluate the action value,and the output double Q value is averaged to guide the actor network to optimize the tracking strategy.The design of double critic network effectively improves the stability and convergence,especially in challenging scenes such as object occlusion,and the tracking performance is significantly improved.In online tracking phase,the well-trained actor network is used to infer the changing action of the bounding box,directly causing the tracker to move the box to the object position in the current frame.Several comparative tracking experiments were conducted on the OTB100 visual tracker benchmark and the experimental results show that more intensive reward settings significantly increase the actor network’s output probability of positive actions.This makes the tracking algorithm proposed in this paper outperforms the mainstream deep reinforcement learning tracking algorithms and deep learning tracking algorithms under the challenging attributes such as occlusion,deformation,and rotation.
基金co-supported by the National Natural Science Foundation of China(No.61304190)the Fundamental Research Funds for the Central Universities of China(No.NJ20150030)the Natural Science Foundation of Jiangsu Province of China(No.BK20130818)
文摘Air transport network, or airport network, is a complex network involving numerous airports. Effective management of the air transport system requires an in-depth understanding of the roles of airports in the network. Whereas knowledge on air transport network properties has been improved greatly, methods to find critical airports in the network are still lacking. In this paper, we present methods to investigate network properties and to identify critical airports in the network. A novel network model is proposed with airports as nodes and the correlations between traffic flow of airports as edges. Spectral clustering algorithm is developed to classify air- ports. Spatial distribution characteristics and intraclass correlation of different categories of air- ports are carefully analyzed. The analyses based on the fluctuation trend of distance-correlation and power spectrum of time series are performed to examine the self-organized criticality of the net- work. The results indicate that there is one category of airports which dominates the self-organized critical state of the network. Six airports in this category are found to be the most important ones in the Chinese air transport network. The flights delay occurred in these six airports can propagate to the other airports, having huge impact on the operation characteristics of the entire network. The methods proposed here taking traffic dynamics into account are capable of identifying critical air- ports in the whole air transport network.
基金Supported by National Natural Science Foundation of China under Grants No.11675096Fundamental Research Funds for the Central Universities under Grant No.GK201702001FPALAB-SNNU under Grant No.16QNGG007
文摘We study the criticality in excitatory-inhibitory networks consisting of excitable elements. We investigate the effects of the inhibitory strength using both numerical simulations and theoretical analysis. We show that the inhibitory strength cannot affect the critical point. The dynamic range is decreased as the inhibitory strength increases.To simulate of decreasing the efficacy of excitation and inhibition which was studied in experiments, we remove excitatory or inhibitory nodes, delete excitatory or inhibitory links, and weaken excitatory or inhibitory coupling strength in critical excitatory-inhibitory network. Decreasing the excitation, the change of the dynamic range is most dramatic as the same as previous experimental results. However, decreasing inhibition has no effect on the criticality in excitatory-inhibitory network.
文摘The paper describes modern technologies of Computer Network Reliability. Software tool is developed to estimate of the CCN critical failure probability (construction of a criticality matrix) by results of the FME(C)A-technique. The internal information factors, such as collisions and congestion of switchboards, routers and servers, influence on a network reliability and safety (besides of hardware and software reliability and external extreme factors). The means and features of Failures Modes and Effects (Critical) Analysis (FME(C)A) for reliability and criticality analysis of corporate computer networks (CCN) are considered. The examples of FME(C)A-Technique for structured cable system (SCS) is given. We also discuss measures that can be used for criticality analysis and possible means of criticality reduction. Finally, we describe a technique and basic principles of dependable development and deployment of computer networks that are based on results of FMECA analysis and procedures of optimization choice of means for fault-tolerance ensuring.
基金partially funded by Germany’s Federal Ministry of Education and Research within the framework of IKARIM and the PARADeS project,grant number 13N15273,the ARSINOE project(GA 101037424)the MIRACA(GA 101093854)under European Union’s H2020 innovation action programme.
文摘Natural hazards impact interdependent infrastructure networks that keep modern society functional.While a va-riety of modelling approaches are available to represent critical infrastructure networks(CINs)on different scales and analyse the impacts of natural hazards,a recurring challenge for all modelling approaches is the availability and accessibility of sufficiently high-quality input and validation data.The resulting data gaps often require mod-ellers to assume specific technical parameters,functional relationships,and system behaviours.In other cases,expert knowledge from one sector is extrapolated to other sectoral structures or even cross-sectorally applied to fill data gaps.The uncertainties introduced by these assumptions and extrapolations and their influence on the quality of modelling outcomes are often poorly understood and difficult to capture,thereby eroding the reliability of these models to guide resilience enhancements.Additionally,ways of overcoming the data avail-ability challenges in CIN modelling,with respect to each modelling purpose,remain an open question.To address these challenges,a generic modelling workflow is derived from existing modelling approaches to examine model definition and validations,as well as the six CIN modelling stages,including mapping of infrastructure assets,quantification of dependencies,assessment of natural hazard impacts,response&recovery,quantification of CI services,and adaptation measures.The data requirements of each stage were systematically defined,and the literature on potential sources was reviewed to enhance data collection and raise awareness of potential pitfalls.The application of the derived workflow funnels into a framework to assess data availability challenges.This is shown through three case studies,taking into account their different modelling purposes:hazard hotspot assess-ments,hazard risk management,and sectoral adaptation.Based on the three model purpose types provided,a framework is suggested to explore the implications of data scarcity for certain data types,as well as their reasons and consequences for CIN model reliability.Finally,a discussion on overcoming the challenges of data scarcity is presented.
文摘The research is focused on the development of automatic detection method of abnormal features, that occur in recorded time series of ionosphere critical frequency fOF2 during periods of high solar or seismic activity. The method is based on joint application of wavelet-transformation and neural networks. On the basis of wavelet transformation algorithms for the detection of features and estimation of their parameters were developed. Detection and analysis of characteristic components of time series are performed on the basis of joint application of wavelet transformation and neural networks. Method's approbation is performed on fOF2 data obtained at the observatory “Paratunka” (Paratunka settlement, Kamchatskiy Kray).
文摘抽水蓄能作为电力系统中最为成熟的新能源储能技术,凭借其能调节电网负荷、平衡电力波动及提升系统稳定性的独特优势,已成为实现中国“双碳”目标的重要路径之一。因此,对抽水蓄能电站综合效益进行科学评估,是项目决策及政策制定中至关重要的一环。为此,本文提出一种基于博弈论组合赋权‒云模型的综合效益评价模型。首先,运用社会网络分析法(SNA)筛选关键评价指标,构建包含财务评价、国民经济评价、技术效益、动态效益、静态效益、电网效益、综合可持续性效益和社会效益8个1级指标及其下属30个2级指标的评价指标体系。其次,采用序关系分析(G1)法和CRITIC(criteria importance through intercriteria correlation)法相结合的方式,对各评价指标进行主观与客观权重赋值。通过引入博弈论组合赋权方法,进一步优化各指标的权重分配。最终,基于云模型构建综合效益评价模型。利用博弈论组合赋权‒云模型对紫云山抽水蓄能电站进行实例分析,结果表明,该电站的综合效益评估等级为“好”,与实际情况相符,充分验证了所构建模型的有效性与准确性。该研究不仅为抽水蓄能电站的综合效益评估提供了科学的评估框架,并为类似项目的决策和实施提供了理论支持和实践依据。
文摘提出一种基于模糊RBF网络的自适应模糊A ctor-C ritic学习.采用一个模糊RBF神经网络同时逼近A ctor的动作函数和C ritic的值函数,解决状态空间泛化中易出现的“维数灾”问题.模糊RBF网络能够根据环境状态和被控对象特性的变化进行网络结构和参数的自适应学习,使得网络结构更加紧凑,整个模糊A ctor-C ritic学习具有泛化性能好、控制结构简单和学习效率高的特点.M oun ta in C ar的仿真结果验证了所提方法的有效性.
