本文针对高温环境下传感器节点存在误报、漏报、工作状态异常等问题,提出了融合长短时记忆网络模型(long short term memory,LSTM)和改进A^(*)算法的火灾逃生路径规划研究方法。根据LSTM自适应学习火灾实时态势信息,建立异常节点数据预...本文针对高温环境下传感器节点存在误报、漏报、工作状态异常等问题,提出了融合长短时记忆网络模型(long short term memory,LSTM)和改进A^(*)算法的火灾逃生路径规划研究方法。根据LSTM自适应学习火灾实时态势信息,建立异常节点数据预测模型,实现异常节点的温度、一氧化碳浓度等威胁态势的预测;基于室内火灾实时态势信息,搭建火势威胁态势蔓延模型,利用改进的A^(*)算法动态规划逃生路径,获取异常情况下火灾最佳安全逃生路径。结果表明,该方法在不同火灾时期均能规划出最佳安全逃生路径,为人员的撤退争取宝贵的时间,具有实际应用价值。展开更多
A generalized varying-coefficient model is proposed to estimate a population size at a specific time from multiple lists of an open population.The research datasets have millions of records with a very long time span(...A generalized varying-coefficient model is proposed to estimate a population size at a specific time from multiple lists of an open population.The research datasets have millions of records with a very long time span(38 years),bringing challenges to calculations.The authors develop a regularization iterative algorithm to overcome this difficulty.The asymptotic distribution of the proposed estimators is derived.Simulation studies show that the procedure works well.The method is applied to estimate the number of drug abusers in Hong Kong,China over the period 1977–2014.展开更多
文摘本文针对高温环境下传感器节点存在误报、漏报、工作状态异常等问题,提出了融合长短时记忆网络模型(long short term memory,LSTM)和改进A^(*)算法的火灾逃生路径规划研究方法。根据LSTM自适应学习火灾实时态势信息,建立异常节点数据预测模型,实现异常节点的温度、一氧化碳浓度等威胁态势的预测;基于室内火灾实时态势信息,搭建火势威胁态势蔓延模型,利用改进的A^(*)算法动态规划逃生路径,获取异常情况下火灾最佳安全逃生路径。结果表明,该方法在不同火灾时期均能规划出最佳安全逃生路径,为人员的撤退争取宝贵的时间,具有实际应用价值。
基金supported by the National Natural Science Foundation of China under Grant Nos.11731015,11571148the Natural Science Foundation of Chongqing under Grant No.cstc2019jcyj-msxm X0709the Science and Technology Research Program of Chongqing Municipal Education Commission under Grant No.KJQN201901436。
文摘A generalized varying-coefficient model is proposed to estimate a population size at a specific time from multiple lists of an open population.The research datasets have millions of records with a very long time span(38 years),bringing challenges to calculations.The authors develop a regularization iterative algorithm to overcome this difficulty.The asymptotic distribution of the proposed estimators is derived.Simulation studies show that the procedure works well.The method is applied to estimate the number of drug abusers in Hong Kong,China over the period 1977–2014.