遗传算法优化的BP神经网络在地震死亡人数评估中的应用

破坏性的地震灾害作为一种突发性自然灾害,往往会在短时间内造成大量的人员伤亡和财产损失。地震发生后若能有效地预测伤亡人数,可以更科学地组织人员救灾与配置救灾物资,对于减少震后的人员伤亡具有一定的指导作用。通过我国往期的地震数据信息,分析总结出对人员伤亡数目影响较大的7个因素,分别为地震等级、地震时间、震源深度、震中烈度、抗震设防烈度、震中烈度与抗震设防烈度之差(ΔL)、人口密度。鉴于这7个影响因素与地震时的死亡人数呈非线性关系,选用基于遗传算法(GA)优化的BP神经网络建立地震死亡人数预测模型。针对BP神经网络的局限性,利用遗传算法全局搜索最优值的特点,对BP神经网络的权值与阀值进行优化,防止BP神经网络陷入局部最优解,并且加快神经网络收敛速度,从而提高BP神经网络的预测精度。从我国1970年至2016年之间发生的地震灾害中,选取32组造成人员伤亡的地震数据,对初始数据进行处理后,利用遗传算法优化的BP神经网络预测模型进行训练并预测。选取27组样本作为训练样本,另外5组样本作为测试样本。预测分析结果表明,遗传算法优化的BP神经网络预测死亡人数与真实死亡人数相比平均误差为9.72%,均方误差为10.41,而BP神经网络的预测死亡人数的平均误差为17.61%,均方误差为18.02,因此GA-BP神经网络结果较为理想,相比传统的BP神经网络具有更高的逼近精度。     

汶川地震后的卫生防疫对策

2008年5月12日14点28分,四川省汶川发生里氏8．0级特大地震,造成严重的人员伤亡、房屋倒塌、道路损毁和重大的经济损失。 四川是我国人口大省,本次地震造成大量的人员伤亡和牲畜死亡,灾区基础卫生设施和生态环境受到极大的破坏和影响。灾区公路、铁路严重破坏;     

基于PCA-ELM的地震死亡人数评估

地震往往会在短时间内造成巨大的人员伤亡和财产损失,为了震后救援工作能够快速高效的展开,建立了主成分分析(Principal Components Analysis,PCA)和极限学习机(Extreme Learning Machine,ELM)相结合的地震死亡人数预测模型。综合考虑影响地震死亡人数的多种因素,选取震级、震源深度、震中烈度、抗震设防烈度、人口密度、发生时间和预报水平7项主要因素作为评价指标。首先,利用主成分分析对原始变量进行降维处理,并计算出主成分得分,作为ELM的输入;其次,对构建的ELM地震死亡人数预测模型进行训练;最后,对选取的32组地震样本进行算例仿真,并与未经PCA处理的ELM算法和BP神经网络算法进行对比。结果表明,基于主成分分析的极限学习机算法对地震死亡人数预测具有较高的预测精度,验证效果良好。     

各国地震预测研究

<正>近几个月,松原市连续发生多次地震,虽没造成重大人员伤亡,但大量房屋受损,上万人转移也对人们的生活造成了影响,也产生了不必要的恐慌。地震到底能不能预测?在各方积极抗震救灾的同时,不少人也开始议论地震到底能不能预测。事实上,地震预测也是国际上争论不休的话题,而各国地震研究也在沉浮中波折不断。     

以改变告慰逝者 以进步面对生者——写在汶川地震七周年纪念日

<正>4月25日,就在"5·12"汶川地震七周年前17天,尼泊尔发生了8.1级地震。此次尼泊尔地震,受灾人数超800万,死亡人数已过8?000。因其与记忆中的汶川地震几乎相同的震级、相近的时间而再次触发了人们内心的柔软,感同身受的同时,也让民众意识到提升防灾自救能力的必要性。细数我国近年遭遇的历次地震,虽然从汶川、玉树,及至雅安、鲁甸,每一     

地震避险自救互救常识

地震是指地球表面发生快速震动的一种现象。地震突发性强,波及范围大,极具破坏性。地震的发生常导致桥梁断落、房屋坍塌、水坝开裂,严重的更会造成人员伤亡。地震还会致使一些次生灾害的发生,如滑坡、泥石流等。地震目前还是人类尚无法避免或控制的自然灾害,但只要掌握一些技巧,能使伤害降到最低。破坏性地震从人感觉振动到建筑物被破坏平均只有12秒钟.在这短短的时间里,我们应该沉着冷静,应根据所处环境迅速作出保障安全的抉择!     

地震后灾区生活用水中微生物抽样检测报告

四川汶川“5·12”特大地震,给灾区人民的生命安全和财产带来巨大的损失。地震发生后由于受地震影响,使灾区发生大面积、大规模的山体滑坡、房屋倒塌,城市集中式供水中断、供水设施遭受严重破坏,中小城市的分散式供水和农村生活供水都受到同程度的破坏,     

汶川地震十年国际研究的合作与主题态势

为全面认识国际汶川地震研究的合作与主题态势,利用科睿唯安Web of Science数据库采集了3 158篇汶川地震研究论文,使用科学计量学方法对国际汶川地震研究的国家/地区、机构和作者合作网络进行了分析。采用关键词词频和共词分析的方法,对国际汶川地震研究热点、主题类团和新兴主题进行了研究。研究结果表明:关于汶川地震的研究从2008—2009年开始显著增长,之后保持平稳;我国产出量第一,且在汶川地震研究合作中处于国家/地区的核心,与美国、日本和英格兰合作密切;机构层面上,中国科学院和中国地震局位于核心位置;徐锡伟和黄润秋是汶川地震研究中的代表作者;国际汶川地震热点主题涉及了滑坡、泥石流、芦山地震、创伤后应激障碍、地理信息系统、遥感等方面,并围绕高频关键词形成了“地震对人心理的影响（例如PTSD）”、“地理信息系统和遥感技术在汶川地震中应用”、“汶川地震引起的地质灾害和数值分析”以及“龙门山断裂带与汶川和芦山地震”4大主题聚类,其中“地震对人心理的影响（例如PTSD）”和“龙门山断裂带与汶川和芦山地震”是目前活跃的主题聚类。     

暴雨洪涝灾害转移安置人数的组合预测模型研究

为了更加科学精准地预测暴雨洪涝灾害下需要转移安置的人数,收集2011—2018年全国范围内严重暴雨洪涝灾害案例,通过Pearson相关性分析检验转移安置人数与表征暴雨洪涝灾害严重程度影响因素之间的关系;分别使用基于主成分分析的回归模型和支持向量机(SVM)预测暴雨洪涝灾害下需要转移安置人数,并以2种方法的结果为基础,提出1种组合预测方法对暴雨洪涝灾害转移人数进行修正。研究结果表明：组合预测法的MSE、MAE均小于回归预测和SVM模型预测。使用组合预测方法对洪涝灾害转移安置人数进行预测,可以充分结合单一预测模型的优势,提高组合预测模型的预测精度和泛化能力。研究结果可为确定暴雨洪涝灾害的避难需求并制定避难疏散计划提供参考。     

地震来了我们该怎么办

<正>地震具有突发性、破坏性和难以预测性,地震来了该怎么办？是跑还是躲？在不同场合该怎样有效避震、降低伤亡风险？地震时被埋了,如何自救和互救？三个逃生的案例惊慌失措,震小灾大1995年9月,山东省临沂市苍山县发生5.2级地震。震级不算大,震中烈度不到六度,震区房屋基本完好,本不应造成人员伤亡。但是,却有300多名小学生受伤,50多人受重伤。原因是人们在地震时惊慌失措,因跳楼、拥挤而致伤。     

基于能力谱的地震建筑破坏造成人员伤亡评估

为准确计算地震导致的人员伤亡数量,提高灾后应急保障及救援效率,根据能力谱方法计算建筑物的损坏程度,在此基础上计算相应人员伤亡数量。采用SELENA软件中能力谱方法的计算公式,利用Matlab软件编程得到建筑物破坏及人员伤亡计算程序,计算8度地震条件下建筑物不同破坏状态的概率。根据HAZUS软件中建筑物破坏和人员伤亡关系,计算地震发生在02∶00,14∶00和17∶00时不同伤亡等级的伤亡人数。计算结果表明,多数伤者为轻伤,只需基本药物及简单治疗;地震导致的钢筋混凝土建筑破坏是造成人员伤亡的主要原因;能力谱方法可为震后物质配置及震前防灾规划提供决策支持。     

我国公路交通伤亡现状分析

本文对统计、上报、公布交通伤亡数据业务的不足作了简要分析,分别对城市交通伤亡、收费道路交通伤亡、乡村和山区非收费道路交通伤亡提出了相应的数学描述模型,并提出了收费路伤亡高发期和稳定期的观点和数学模型。提出了交通伤亡责任追究制的思想,行政管理的效果非常有限,应该根据不同情况进行技术型专业管理。     

Estimation of the real number of road casualties in Europe

Within this research, the police under-reporting of non-fatal road accident casualties in eight European countries was examined by means of a common methodology applied in each country. Eight national studies were carried out using the common methodology, and this allowed to prepare valid estimates of the level of under-reporting of non-fatal road casualties in Europe in a disaggregate form (namely by country, road user type and injury severity). This provided an insight into the variation of road casualty under-reporting in Europe. Moreover, a new common definition for road casualty severity was proposed that makes use of internationally recognised medical standards. This was established by examining two different injury severity standards, the casualty’s length of stay in hospital and the casualty’s maximum AIS score. The under-reporting coefficients developed within this research were applied to estimate the real number of non-fatal serious road accident casualties, according to the new proposed common definition. For almost all countries, the actual number of serious casualties according to the new proposed definition was found lower than the number of police-recorded serious casualties. With the newly estimated number of serious casualties, the values of the ratio of serious casualties to fatalities are much less widespread across countries. These remaining differences can thus be attributed to real differences in road safety between the countries, after having controlled for the different under-reporting levels and injury severity definitions.     

The expected number of road traffic casualties using stratified data

Road safety policy plans often require robust calculation of the expected number of road casualties in a certain target year. The relevance of such estimations should be measured by their power to influence and support safety policy makers. Thus, techniques to evaluate the safety developments and the estimating methods must be sound, robust, and preferably accepted by both policy makers and the scientific community. In this paper, we concentrate on choosing an appropriate model used for the calculation, rather than on statistical techniques. We calculate a casualty rate from casualty data and mobility (distance travelled) data, which is extrapolated and subsequently multiplied by an expected future distance travelled. After correction for separately assessed effects of additional safety measures, the number of casualties is estimated. We investigate a method where this is done after both mobility data and casualty data are stratified into properly chosen subsets. Projecting these different trends generally leads to a result that differs from the projection of the aggregated data. Also, stratification enables incorporation in the estimation of explaining factors or additional measures related to a specific subset of the casualties. The principles of stratified projections are illustrated by three Dutch projections which were carried out between 2006 and 2008. Also, some preliminary results of further research on stratification are given. The results imply that the rates of change in casualty rate for different traffic modes or driver age, are not necessarily equal. We propose that these specific decreasing trends are a consequence of external influencing factors.     

Providing the numerical context for British casualty reduction targets

The first national target for reducing road accident casualties in Great Britain was set in 1987, the target year being 2000. As the year 2000 approached, preparations were made for setting a subsequent target, the target year being 2010. A major part of the preparation consisted of forecasting the number of casualties that might be expected in 2010, conditional upon predictions about how the volume of road travel by the various transport modes might change and the type of new road safety measures that the Government might introduce. The forecasts provided the numerical context for the casualty reduction target that the Government announced in March 2000.This paper summarises the statistical analyses of accident data from 1983 to 1998 upon which the forecasts were based, and compares the approach with alternatives that have been adopted elsewhere. It also describes how progress towards the target has been monitored annually, allowing the Government to judge whether additional efforts might be needed to achieve the target. This examination of the actual data from 1999 to 2007 shows how far the original forecasts have proved to be successful.The improvement of car secondary safety over the past 15 years has probably been the development that has had the most significant effect on the national casualty total. A statistical model is used to quantify this effect by analysis of accident data, and the results of the most recent analyses are included.     

基于零膨胀负二项回归模型的内河水上交通人命安全分析

运用零膨胀负二项回归模型,分析水上交通事故中人员死亡失踪数量的各影响因素的影响程度。通过Pearson相关分析得到与水上交通事故中人员死亡失踪人数密切相关的因素,建立ZINB回归模型得到各因素的参数估计值。运用弹性分析方法对不同影响因素的影响程度进行评估,根据影响程度对各影响因素进行排序。将该方法应用于长江海事局辖区范围内的水上交通事故人员死亡失踪分析,取得了理想效果。     

2002-2014年我国煤矿重特大事故特征及发生规律研究

为了研究我国煤矿重特大事故的一般规律,分析了2002-2014年我国煤矿发生的421起重特大事故,得到我国煤矿重特大事故的基本特征.利用统计分析法从地域、类型、所有制3个维度综合分析了421起煤矿重特大事故.结果表明:山西、贵州、河南、黑龙江和湖南5个省份的重特大事故起数和死亡人数分别占全国总数的56.1％和56.8％,是我国需重点监管和治理的省份,并对山西、河南和黑龙江3省重特大事故频发的原因进行了分析;瓦斯事故和水害事故的发生起数及死亡人数占比分别为83.3％和86.3％,是需要重点防治的事故类型;国有重点煤矿重特大事故平均每起死亡人数为29.87,且近两年重特大事故起数和死亡人数均大幅度上升,是需要重点防范的对象;乡镇煤矿重特大事故起数及死亡人数下降速度均较快,但事故起数和死亡人数仍较多,是国家重点监控、治理的对象.     

Cycle helmets and road casualties in the UK

OBJECTIVES: Bicycle helmets have been advocated as a means of reducing injury among cyclists. This assertion, derived from a number of case controlled studies carried out in hospitals, conflicts with results from population level studies. In the Western countries where these case control studies have been performed, it appears that cycling morbidity is dominated by sports and leisure users. The generalizability of studies on helmet effectiveness in relation to utilitarian transport cycling is not clear. This study therefore considers population level data for reported road traffic injuries of cyclists and pedestrians. METHODS: Generalized linear and generalized additive models were used to investigate patterns of pedestrian and cyclist injury in the UK based on the police reported "Stats 19" data. Comparisons have been made with survey data on helmet wearing rates to examine evidence for the effectiveness of cycle helmets on overall reported road casualties. While it must be acknowledged that police casualty reports are prone to under-reporting, particularly of incidents involving lower severity casualties the attractive feature of these data are that by definition they only concern road casualties. RESULTS: There is little evidence in UK from the subset of road collisions recorded by the police corresponding to the overall benefits that have been predicted by the results of a number of published case controlled studies. In particular, no association could be found between differing patterns of helmet wearing rates and casualty rates for adults and children. CONCLUSIONS: There is no evidence that cycle helmets reduce the overall cyclist injury burden at the population level in the UK when data on road casualties is examined. This finding, supported by research elsewhere could simply be due to cycle helmets having little potential to reduce the overall transport-related cycle injury burden. Equally, it could be a manifestation of the "ecological fallacy" where it could be conceived that the existence of various sub-groups of cyclists, with different risk profiles, may need to be accounted for in understanding the difference between predicted and realised casualty patterns.     

基于Vague集的城市地震灾害综合脆弱性度量及其应用

为度量城市地震灾害综合脆弱性及灾害中生命及财产的可挽救性,将社会脆弱性、应急系统脆弱性引入城市综合脆弱性研究。利用Vague集的相似度量理论,构建基于Vague集的城市地震灾害综合脆弱性度量模型;扩展可挽救性的概念,建立基于综合脆弱性度量的城市地震灾害可挽救性度量模型。以2003年日本北海道地震损失为标准,通过上述2个模型,得到某城市地震灾害综合脆弱度为2.76×10-4,可挽救度分别为:死亡人数减少18人、重伤人数减少72人、直接经济损失减少0.2亿元人民币。     

消防部队灭火救援安全现状分析及对策

通过对"十五"期间我国消防队员伤亡数据及近年来部分消防队员在灭火救援过程中伤亡案例的剖析,造成消防队员伤亡既有救援对象复杂、救援工作固有危险性增大等客观原因,更重要的是由于部分消防队员安全观念滞后、安全防护措施落实不到位、安全训练不够而导致伤亡的发生。建立健全消防员伤亡事故调查制度、风险管理制度和专职安全员制度,提升灭火救援活动标准化管理水平,提高消防员综合素质,加强灭火救援现场的安全管理是减少消防员伤亡的有效措施。