This paper examines the noise and rotation resistance capacity of Hopfield Neural Network （HNN） given four corrupted traffic sign images. In the study, Signal-to-Noise Ratio （SNR）, recall rate and pattern complexi...This paper examines the noise and rotation resistance capacity of Hopfield Neural Network （HNN） given four corrupted traffic sign images. In the study, Signal-to-Noise Ratio （SNR）, recall rate and pattern complexity are defined and employed to evaluate the recall performance. The experimental results indicate that the HNN possesses significant recall capacity against the strong noise corruption, and certain restoring competence to the rotation. It is also found that combining noise with rotation does not further challenge the HNN corruption resistance capability as the noise or rotation alone does.展开更多
Abstract Recently, much attention has been paid to the reliability and vulnerability of critical infrastructure. In air traffic systems, the vulnerability analysis for airport networks can be used to guide air traffic...Abstract Recently, much attention has been paid to the reliability and vulnerability of critical infrastructure. In air traffic systems, the vulnerability analysis for airport networks can be used to guide air traffic administrations in their prioritization of the maintenance and repair of airports, as well as to avoid unnecessary disturbances in the planning of flight schedules. In this paper, the evaluation methods of airport importance and network efficiency arc established. Firstly, the evaluation indices of airport importance are proposed from both the topological and functional perspectives. The topological characteristics come from the structure of airport network and the functional features stem from the traffic flow distribution taking place inside the network. Secondly, an integrated evaluation method based on fuzzy soft set theory is proposed to identify the key airports, which can fuse together importance indices over different time intervals. Thirdly, an airport network efficiency method is established for the purpose of assessing the accuracy of the evaluation method. Finally, empirical studies using real traffic data of US and China＇s airport networks show that the evaluation method proposed in this papcr is the most accuratc. Thc vulucrability of US and China＇s airport networks is compared. The similarities and differences between airport geography distribution and airport importance distribution are discussed here and the dynamics of airport importance is studied as well.展开更多
针对最短路径或最小花费的路径导航策略由于交通流量、交通拥堵度、出行花费等原因,其所选择的路径往往不是出行的最优路径。通过分析路网中道路的介数中心性与道路的出行花费,建立了一种基于介数中心性的最小花费导航模型(McBc-Minimum...针对最短路径或最小花费的路径导航策略由于交通流量、交通拥堵度、出行花费等原因,其所选择的路径往往不是出行的最优路径。通过分析路网中道路的介数中心性与道路的出行花费,建立了一种基于介数中心性的最小花费导航模型(McBc-Minimum cost model based on betweenness centrality)来降低出行交通阻塞的发生和减少出行的花费,同时提出了一种新的网络通行质量指标来度量当前路网的通行质量。实验选取芝加哥的部分路网,分析该路网的空间结构特征后,比较了不同模型所得到路径的路径长度、路径花费、路径拥堵度、单位长度车流量以及当前路径的通行质量后,文中模型所得路径在选择介数中心性较低且花费较小的路径后,并没有造成出行长度和出行花费偏大的结果,反而较最短路径和最小花费模型,文中模型规划路径的平均拥堵度降低了63%和78%,使得路径具有较高的路径通行质量。展开更多
基金Supported by the Natural Science Foundation of Zhejiang Province(No.2010A610105)
文摘This paper examines the noise and rotation resistance capacity of Hopfield Neural Network （HNN） given four corrupted traffic sign images. In the study, Signal-to-Noise Ratio （SNR）, recall rate and pattern complexity are defined and employed to evaluate the recall performance. The experimental results indicate that the HNN possesses significant recall capacity against the strong noise corruption, and certain restoring competence to the rotation. It is also found that combining noise with rotation does not further challenge the HNN corruption resistance capability as the noise or rotation alone does.
基金co-supported by the National Natural Science Foundation of China(No.61039001)the Scientific Research Foundation of Civil Aviation University of China(No.2014QD01S)
文摘Abstract Recently, much attention has been paid to the reliability and vulnerability of critical infrastructure. In air traffic systems, the vulnerability analysis for airport networks can be used to guide air traffic administrations in their prioritization of the maintenance and repair of airports, as well as to avoid unnecessary disturbances in the planning of flight schedules. In this paper, the evaluation methods of airport importance and network efficiency arc established. Firstly, the evaluation indices of airport importance are proposed from both the topological and functional perspectives. The topological characteristics come from the structure of airport network and the functional features stem from the traffic flow distribution taking place inside the network. Secondly, an integrated evaluation method based on fuzzy soft set theory is proposed to identify the key airports, which can fuse together importance indices over different time intervals. Thirdly, an airport network efficiency method is established for the purpose of assessing the accuracy of the evaluation method. Finally, empirical studies using real traffic data of US and China＇s airport networks show that the evaluation method proposed in this papcr is the most accuratc. Thc vulucrability of US and China＇s airport networks is compared. The similarities and differences between airport geography distribution and airport importance distribution are discussed here and the dynamics of airport importance is studied as well.
文摘针对最短路径或最小花费的路径导航策略由于交通流量、交通拥堵度、出行花费等原因,其所选择的路径往往不是出行的最优路径。通过分析路网中道路的介数中心性与道路的出行花费,建立了一种基于介数中心性的最小花费导航模型(McBc-Minimum cost model based on betweenness centrality)来降低出行交通阻塞的发生和减少出行的花费,同时提出了一种新的网络通行质量指标来度量当前路网的通行质量。实验选取芝加哥的部分路网,分析该路网的空间结构特征后,比较了不同模型所得到路径的路径长度、路径花费、路径拥堵度、单位长度车流量以及当前路径的通行质量后,文中模型所得路径在选择介数中心性较低且花费较小的路径后,并没有造成出行长度和出行花费偏大的结果,反而较最短路径和最小花费模型,文中模型规划路径的平均拥堵度降低了63%和78%,使得路径具有较高的路径通行质量。
