Fault diagnosis on large-scale and complex networks is a challenging task, as it requires efficient and accurate inference from huge data volumes. Active probing is a cost-efficient tool for fault diagnosis. However a...Fault diagnosis on large-scale and complex networks is a challenging task, as it requires efficient and accurate inference from huge data volumes. Active probing is a cost-efficient tool for fault diagnosis. However almost all existing probing-based techniques face the following problems: 1) performing inaccurately in noisy networks; 2) generating additional traffic to the network; 3) high cost computation. To address these problems, we propose an efficient probe selection algorithm for fault diagnosis based on Bayesian network. Moreover, two approaches which could significantly reduce the computational complexity of the probe selection process are provided. Finally, we implement the new proposed algorithm and a former representative probing-based algorithm (BPEA algorithm) on different settings of networks. The results show that, the new algorithm performs much faster than BPEA does without sacrificing the diagnostic quality, especially in large, noisy and multiple-fault networks.展开更多
It will show the feasibility of a Wireless Sensor Network (WSN) devoted to monitoring water basin, river, lake, and sea both on the surface and in depth. The swarm of floating probes can be programmed to periodically ...It will show the feasibility of a Wireless Sensor Network (WSN) devoted to monitoring water basin, river, lake, and sea both on the surface and in depth. The swarm of floating probes can be programmed to periodically sink some tens of meters below the surface, collecting data, characterizing water properties and then coming to the surface again. The life span of the probes may be assured by an on-board power supply or through batteries recharged by solar cells. The basic idea of the WSN is reported together with a detailed analysis of the operational constraints, the energy requirements, and the electronic and mechanical discussion.展开更多
在天然气净化过程中,强腐蚀性气体会导致反应容器出现不同程度的损耗。尽管传统腐蚀探针可以提供腐蚀预警,但其存在一定的滞后性。为解决这一问题,提出了基于小波变换-长短期记忆(Wavelet Transform-Long Short Term Memory, WT-LSTM)...在天然气净化过程中,强腐蚀性气体会导致反应容器出现不同程度的损耗。尽管传统腐蚀探针可以提供腐蚀预警,但其存在一定的滞后性。为解决这一问题,提出了基于小波变换-长短期记忆(Wavelet Transform-Long Short Term Memory, WT-LSTM)网络的腐蚀数据趋势预测方法。对原始数据采用db10小波进行分解,获取各细节分量后,利用LSTM网络对各分量进行预测并重构信号。实验结果显示,WT-LSTM模型的均方根误差(Root Mean Square Error, RMSE)为0.002 562,低于仅使用LSTM模型的RMSE值0.003 178,表明WT-LSTM网络在趋势预测上更加精准。基于WT-LSTM网络的预测方案能够有效跟踪腐蚀数据的变化,尤其在数据突变时效果显著,从而增强了腐蚀探针的在线监测能力,实现了对腐蚀情况的预测和预警,确保了天然气净化过程的安稳运行。展开更多
基于应用层探测来识别传输层安全性协议(transport layer security,TLS)的上层服务是了解互联网服务配置和安全性的重要手段。当前的应用层扫描器在工作时依赖于默认的网络协议栈,其传输控制协议(transmission control protocol,TCP)协...基于应用层探测来识别传输层安全性协议(transport layer security,TLS)的上层服务是了解互联网服务配置和安全性的重要手段。当前的应用层扫描器在工作时依赖于默认的网络协议栈,其传输控制协议(transmission control protocol,TCP)协议专为通用场景设计,只能以受限的速率获取TLS上层服务信息;而TLS协议部分,由于现代化安全配置的软件库,与部分目标服务器不兼容。针对当前应用层扫描器识别TLS上层服务效率不高且不够全面的问题,本文从协议栈优化的角度,首先提出了一种应用于TCP协议栈的混合状态模型,通过引入无状态工作模式和优化有状态工作模式,以减少协议栈中不必要的状态维护和转换,从而提高应用层探测效率;然后,提出了一种面向TLS协议栈的宽松配置策略,通过最大限度的版本和配置兼容来与更加广泛的服务器建立TLS会话;最后,以用户态协议栈的方式将该模型和配置策略实现为异步应用层扫描器TLSnap,并通过可扩展模块的形式提供自定义接口,以支持多种TLS上层服务的识别任务。实验结果表明,在普通硬件配置下,TLSnap扫描器针对大规模端口的TLS上层服务的识别效率比当前先进方法提高3.5倍以上,且平均识别数量增加9%,有效提高了TLS上层服务识别的效率和全面性。展开更多
基金supported by National Key Basic Research Program of China (973 program) under Grant No.2007CB310703Funds for Creative Research Groups of China under Grant No.60821001+1 种基金National Natural Science Foundation of China under Grant No. 60973108National S&T Major Project under Grant No.2011ZX03005-004-02
文摘Fault diagnosis on large-scale and complex networks is a challenging task, as it requires efficient and accurate inference from huge data volumes. Active probing is a cost-efficient tool for fault diagnosis. However almost all existing probing-based techniques face the following problems: 1) performing inaccurately in noisy networks; 2) generating additional traffic to the network; 3) high cost computation. To address these problems, we propose an efficient probe selection algorithm for fault diagnosis based on Bayesian network. Moreover, two approaches which could significantly reduce the computational complexity of the probe selection process are provided. Finally, we implement the new proposed algorithm and a former representative probing-based algorithm (BPEA algorithm) on different settings of networks. The results show that, the new algorithm performs much faster than BPEA does without sacrificing the diagnostic quality, especially in large, noisy and multiple-fault networks.
文摘It will show the feasibility of a Wireless Sensor Network (WSN) devoted to monitoring water basin, river, lake, and sea both on the surface and in depth. The swarm of floating probes can be programmed to periodically sink some tens of meters below the surface, collecting data, characterizing water properties and then coming to the surface again. The life span of the probes may be assured by an on-board power supply or through batteries recharged by solar cells. The basic idea of the WSN is reported together with a detailed analysis of the operational constraints, the energy requirements, and the electronic and mechanical discussion.
文摘在天然气净化过程中,强腐蚀性气体会导致反应容器出现不同程度的损耗。尽管传统腐蚀探针可以提供腐蚀预警,但其存在一定的滞后性。为解决这一问题,提出了基于小波变换-长短期记忆(Wavelet Transform-Long Short Term Memory, WT-LSTM)网络的腐蚀数据趋势预测方法。对原始数据采用db10小波进行分解,获取各细节分量后,利用LSTM网络对各分量进行预测并重构信号。实验结果显示,WT-LSTM模型的均方根误差(Root Mean Square Error, RMSE)为0.002 562,低于仅使用LSTM模型的RMSE值0.003 178,表明WT-LSTM网络在趋势预测上更加精准。基于WT-LSTM网络的预测方案能够有效跟踪腐蚀数据的变化,尤其在数据突变时效果显著,从而增强了腐蚀探针的在线监测能力,实现了对腐蚀情况的预测和预警,确保了天然气净化过程的安稳运行。
文摘基于应用层探测来识别传输层安全性协议(transport layer security,TLS)的上层服务是了解互联网服务配置和安全性的重要手段。当前的应用层扫描器在工作时依赖于默认的网络协议栈,其传输控制协议(transmission control protocol,TCP)协议专为通用场景设计,只能以受限的速率获取TLS上层服务信息;而TLS协议部分,由于现代化安全配置的软件库,与部分目标服务器不兼容。针对当前应用层扫描器识别TLS上层服务效率不高且不够全面的问题,本文从协议栈优化的角度,首先提出了一种应用于TCP协议栈的混合状态模型,通过引入无状态工作模式和优化有状态工作模式,以减少协议栈中不必要的状态维护和转换,从而提高应用层探测效率;然后,提出了一种面向TLS协议栈的宽松配置策略,通过最大限度的版本和配置兼容来与更加广泛的服务器建立TLS会话;最后,以用户态协议栈的方式将该模型和配置策略实现为异步应用层扫描器TLSnap,并通过可扩展模块的形式提供自定义接口,以支持多种TLS上层服务的识别任务。实验结果表明,在普通硬件配置下,TLSnap扫描器针对大规模端口的TLS上层服务的识别效率比当前先进方法提高3.5倍以上,且平均识别数量增加9%,有效提高了TLS上层服务识别的效率和全面性。
