本文選題：洪災(zāi)損失評(píng)估 + Hadoop��； 參考：《江西理工大學(xué)》2017年碩士論文

【摘要】：在我國(guó)洪災(zāi)屬于最為嚴(yán)重的自然災(zāi)害之一,其頻率高、影響范圍廣及經(jīng)濟(jì)損失大等特征已經(jīng)嚴(yán)重制約了我國(guó)國(guó)民經(jīng)濟(jì)的發(fā)展,因此對(duì)洪災(zāi)經(jīng)濟(jì)損失進(jìn)行科學(xué)有效的估算是必要的。但是近年來(lái),由于人類的活動(dòng)增多、洪災(zāi)損失評(píng)估的數(shù)據(jù)種類和數(shù)劇量不斷增加,導(dǎo)致傳統(tǒng)BP神經(jīng)網(wǎng)絡(luò)技術(shù)在洪災(zāi)損失評(píng)估應(yīng)用中可能出現(xiàn)耗時(shí)過(guò)長(zhǎng)、訓(xùn)練困難等問(wèn)題�？紤]云計(jì)算平臺(tái)在處理大量數(shù)據(jù)方面問(wèn)題的優(yōu)越性與實(shí)用性,而現(xiàn)有洪災(zāi)損失評(píng)估相關(guān)研究還未在云計(jì)算平臺(tái)下進(jìn)行應(yīng)用。因此,開(kāi)展云計(jì)算平臺(tái)支持下的BP神經(jīng)網(wǎng)絡(luò)在洪災(zāi)損失評(píng)估中的應(yīng)用研究具有現(xiàn)實(shí)意義。本文選取江西省鄱陽(yáng)湖區(qū)范圍內(nèi)的某縣作為研究區(qū)域,主要研究?jī)?nèi)容如下:首先,闡述了洪災(zāi)損失評(píng)估及相關(guān)技術(shù)的國(guó)內(nèi)外的研究現(xiàn)狀,論述本文所運(yùn)用的關(guān)鍵技術(shù):Hadoop分布式計(jì)算框架及BP神經(jīng)網(wǎng)絡(luò)技術(shù),可為本文洪災(zāi)損失評(píng)估應(yīng)用研究提供理論基礎(chǔ)。其次,運(yùn)用數(shù)理統(tǒng)計(jì)的方法對(duì)原始數(shù)據(jù)進(jìn)行收集與整理,結(jié)合洪災(zāi)損失理論選擇能夠反映洪災(zāi)損失情況的洪災(zāi)影響因子,并根據(jù)洪災(zāi)影響因子劃分得到進(jìn)行計(jì)算的樣本數(shù)據(jù)與測(cè)試數(shù)據(jù);然后,在BP神經(jīng)網(wǎng)絡(luò)算法基本結(jié)構(gòu)的基礎(chǔ)上,將其拆分成兩大部分:首先是網(wǎng)絡(luò)學(xué)習(xí)部分,其次是權(quán)值調(diào)整部分。根據(jù)算法的拆分,將其分別在Map函數(shù)與Reduce函數(shù)中實(shí)現(xiàn),得到云計(jì)算平臺(tái)支持下的Mapreduce-bp算法;最后,根據(jù)Mapreduce-bp算法,建立云計(jì)算平臺(tái)支持下的Mapreduce-bp神經(jīng)網(wǎng)絡(luò)洪災(zāi)損失評(píng)估模型,利用該模型對(duì)本文研究區(qū)域2013年的洪災(zāi)經(jīng)濟(jì)損失進(jìn)行應(yīng)用,并得出最終估算結(jié)果。本文的研究結(jié)果表明,云計(jì)算平臺(tái)支持下的Mapreduce-bp洪災(zāi)損失評(píng)估模型能準(zhǔn)確、快速的對(duì)洪災(zāi)經(jīng)濟(jì)損失值進(jìn)行估算,因此該模型在大數(shù)據(jù)量的情況下能為高效的進(jìn)行洪災(zāi)損失評(píng)估工作提供新的解決思路。
[Abstract]:Flood disaster is one of the most serious natural disasters in China. Its high frequency, wide range of influence and large economic losses have seriously restricted the development of our national economy. Therefore, it is necessary to estimate flood economic losses scientifically and effectively. However, in recent years, due to the increase of human activities, the variety and amount of flood damage assessment data is increasing, which may lead to the problems of time-consuming and difficult training in the application of traditional BP neural network technology in flood damage assessment. Considering the advantages and practicability of cloud computing platform in dealing with a large number of data problems, the existing flood loss assessment research has not been applied in cloud computing platform. Therefore, it is of practical significance to research the application of BP neural network supported by cloud computing platform in flood damage assessment. In this paper, a county in Poyang Lake region of Jiangxi Province is selected as the research area. The main research contents are as follows: firstly, the current research situation of flood disaster loss assessment and related technologies at home and abroad is expounded. This paper discusses the key technology used in this paper: the distributed computing framework of: Hadoop and BP neural network, which can provide a theoretical basis for the application of flood damage assessment in this paper. Secondly, using the method of mathematical statistics to collect and collate the original data, combined with the theory of flood loss to select the flood impact factors which can reflect the situation of flood losses. Then, based on the basic structure of BP neural network algorithm, it is divided into two parts: first, the network learning part. Second is the weight adjustment part. According to the split algorithm, it is implemented in Map function and Reduce function respectively, and the Mapreduce-bp algorithm supported by cloud computing platform is obtained. Finally, according to the Mapreduce-bp algorithm, the Mapreduce-bp neural network flood damage assessment model supported by cloud computing platform is established. The model is used to study the regional flood economic losses in 2013, and the final estimated results are obtained. The results of this paper show that the Mapreduce-bp flood loss assessment model supported by cloud computing platform can estimate the economic loss of flood accurately and quickly. Therefore, this model can provide a new solution for flood damage assessment in the case of large amount of data.
【學(xué)位授予單位】：江西理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP393.09;X43;TV87

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張敬偉;尚宏佳;錢俊彥;周萍;楊青;;非均勻數(shù)據(jù)分布下的MapReduce連接查詢算法優(yōu)化[J];計(jì)算機(jī)科學(xué)與探索;2017年05期

2 喻寅昀;田云;王昶;許可;;洪水災(zāi)害經(jīng)濟(jì)損失的預(yù)測(cè)研究[J];沈陽(yáng)理工大學(xué)學(xué)報(bào);2016年02期

3 李謝輝;韓薈芬;;河南省黃河中下游地區(qū)洪災(zāi)損失評(píng)估與預(yù)測(cè)[J];災(zāi)害學(xué);2014年01期

4 王志華;龐海波;李占波;;一種適用于Hadoop云平臺(tái)的訪問(wèn)控制方案[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年01期

5 崔文斌;牟少敏;王云誠(chéng);浩慶波;昌騰騰;;Hadoop大數(shù)據(jù)平臺(tái)的搭建與測(cè)試[J];山東農(nóng)業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年04期

6 董新華;李瑞軒;周灣灣;王聰;薛正元;廖東杰;;Hadoop系統(tǒng)性能優(yōu)化與功能增強(qiáng)綜述[J];計(jì)算機(jī)研究與發(fā)展;2013年S2期

7 林闖;蘇文博;孟坤;劉渠;劉衛(wèi)東;;云計(jì)算安全:架構(gòu)、機(jī)制與模型評(píng)價(jià)[J];計(jì)算機(jī)學(xué)報(bào);2013年09期

8 林曉婧;吳俊平;;關(guān)于Hadoop集群作業(yè)調(diào)度算法的探討[J];價(jià)值工程;2013年07期

9 許丞;劉洪;譚良;;Hadoop云平臺(tái)的一種新的任務(wù)調(diào)度和監(jiān)控機(jī)制[J];計(jì)算機(jī)科學(xué);2013年01期

10 蒲道北;白鵬;;對(duì)云計(jì)算理論及其應(yīng)用的探討[J];計(jì)算機(jī)光盤軟件與應(yīng)用;2012年20期

相關(guān)博士學(xué)位論文 前1條

1 劉森;云計(jì)算技術(shù)的價(jià)值創(chuàng)造及作用機(jī)理研究[D];浙江大學(xué);2014年

相關(guān)碩士學(xué)位論文 前10條

1 何沖;Hadoop集群調(diào)度優(yōu)化的研究[D];上海師范大學(xué);2015年

2 袁國(guó)偉;HDFS高可用性方案的研究與設(shè)計(jì)[D];杭州電子科技大學(xué);2015年

3 朱啟敏;基于云計(jì)算平臺(tái)的神經(jīng)網(wǎng)絡(luò)計(jì)算方法及其應(yīng)用研究[D];華南理工大學(xué);2014年

4 肖圓秀;云計(jì)算環(huán)境下海量GML空間數(shù)據(jù)存儲(chǔ)索引機(jī)制研究[D];江西理工大學(xué);2013年

5 黃懋;基于集群的HDFS高可用性研究和實(shí)現(xiàn)[D];復(fù)旦大學(xué);2012年

6 胡嘯;神經(jīng)網(wǎng)絡(luò)集成在洪災(zāi)損失評(píng)估中的應(yīng)用研究[D];江西理工大學(xué);2012年

7 胡飛輝;改進(jìn)的BP神經(jīng)網(wǎng)絡(luò)算法在洪災(zāi)損失評(píng)估中的應(yīng)用研究[D];江西理工大學(xué);2012年

8 劉猛;云計(jì)算平臺(tái)下神經(jīng)網(wǎng)絡(luò)方法研究[D];電子科技大學(xué);2011年

9 楊柳;基于云計(jì)算的GIS應(yīng)用模式研究[D];河南大學(xué);2011年

10 黃娟;基于GIS的洪災(zāi)預(yù)警與淹沒(méi)評(píng)估系統(tǒng)研究[D];南京信息工程大學(xué);2008年

，

本文編號(hào)：1946147