【摘要】：如今,隱伏礦產(chǎn)逐漸成為勘查重點(diǎn),但由于其埋藏較深,只能通過各種地物化遙的數(shù)據(jù)間接預(yù)測找礦靶區(qū),針對(duì)這種多維數(shù)據(jù),究竟哪些屬性和隱伏礦產(chǎn)聯(lián)系密切,哪些沒有聯(lián)系,粗糙集的理論方法就在剔除冗余屬性信息方面具有很好的篩選能力。對(duì)已知的一些隱伏礦產(chǎn)各屬性特征通過機(jī)器學(xué)習(xí)建立分類模型,然后預(yù)測新的找礦靶區(qū),如今已成為一個(gè)非常熱門的研究方向�；赩C維和結(jié)構(gòu)風(fēng)險(xiǎn)最小化的統(tǒng)計(jì)學(xué)習(xí)理論的支持向量機(jī)分類模型,具有很強(qiáng)的理論基礎(chǔ)和分類能力,其能很好地解決小樣本、非線性、過學(xué)習(xí)、維數(shù)災(zāi)難和局部極小等問題。結(jié)合粗糙集對(duì)多維數(shù)據(jù)約簡降維的預(yù)處理功能,能夠達(dá)到很好的分類效果和泛化能力,使得找礦靶區(qū)的預(yù)測更加準(zhǔn)確。本文展開了如下工作:1)在云南個(gè)舊錫銅礦試驗(yàn)區(qū)內(nèi),基于ArcGIS對(duì)物探、化探數(shù)據(jù)用反距離插值的方法生成柵格數(shù)據(jù),并在試驗(yàn)區(qū)隨機(jī)提取500個(gè)隨機(jī)樣本點(diǎn)和錫銅礦礦區(qū)提取100隨機(jī)樣本點(diǎn),用柵格數(shù)據(jù)提取至點(diǎn)的方法賦予其物探、化探條件屬性值,在錫礦一定范圍內(nèi)設(shè)置一個(gè)buffer緩沖區(qū),給緩沖區(qū)內(nèi)外的樣本點(diǎn)賦予不同的決策屬性值,構(gòu)建一個(gè)完整的決策屬性系統(tǒng)。2)基于條件屬性取值的連續(xù)性,在MATLAB編程實(shí)現(xiàn)時(shí),主要采取鄰域粗糙集的方法,設(shè)置一個(gè)合適的鄰域半徑,對(duì)訓(xùn)練樣本進(jìn)行離差標(biāo)準(zhǔn)化處理,對(duì)41個(gè)物化探條件屬性進(jìn)行屬性約簡,嘗試通過構(gòu)建模糊因子的方法優(yōu)化約簡算法,用基于屬性重要性的方法對(duì)每一個(gè)約簡的屬性賦予權(quán)重,并嘗試基于挑選屬性的先后順序賦予屬性相應(yīng)的權(quán)重。編寫KNN算法排除奇異點(diǎn)時(shí),設(shè)計(jì)合適的參數(shù),并結(jié)合ArcGIS地統(tǒng)計(jì)分析的概率直方圖、半變異協(xié)方差云分析等綜合剔除噪聲數(shù)據(jù),并挑選邊界域的訓(xùn)練樣本點(diǎn)作為最終的SVM模型訓(xùn)練樣本集,完成鄰域粗糙集的預(yù)處理工作。3)在MATLAB中,選取高斯核函數(shù)對(duì)訓(xùn)練樣本構(gòu)建SVM模型,通過十折交叉驗(yàn)證的檢驗(yàn)方法優(yōu)化模型參數(shù),得到最優(yōu)分類模型,最后遍歷整個(gè)個(gè)舊錫礦試驗(yàn)區(qū),對(duì)整個(gè)區(qū)域做錫礦礦產(chǎn)資源評(píng)價(jià)分析,并通過改變鄰域半徑對(duì)比不同的屬性約簡和模型預(yù)測評(píng)價(jià)系統(tǒng)。
[Abstract]:Nowadays, hidden minerals have gradually become the focus of exploration, but because of their deep burial, they can only indirectly predict the prospecting target area through a variety of geophysical and remote data. Aiming at this kind of multidimensional data, which attributes are closely related to hidden minerals and which are not related, the theory and method of rough set has a good screening ability in eliminating redundant attribute information. It has become a very popular research direction to establish classification models for some known attributes of hidden minerals through machine learning and then to predict new prospecting targets. The support vector machine classification model based on VC and structural risk minimization theory has a strong theoretical basis and classification ability, which can solve the problems of small sample, nonlinear, over-learning, dimension disaster and local minima. Combined with the preprocessing function of rough set to reduce dimension of multidimensional data, it can achieve good classification effect and generalization ability, and make the prediction of prospecting target area more accurate. In this paper, the following work has been carried out: 1) in the Gejiu tin copper mine test area of Yunnan Province, the geophysical and geochemical data are generated by inverse distance interpolation based on ArcGIS, and 500 random sample points are randomly extracted from the experimental area and 100 random sample points are extracted from the tin copper mining area. The geophysical exploration is given by the method of extracting the grid data to the point, and a buffer is set up in a certain range of tin ore. Different decision attribute values are given to the sample points inside and outside the buffer, and a complete decision attribute system is constructed. 2) based on the continuity of conditional attribute values, the method of neighborhood rough set is mainly adopted in MATLAB programming, a suitable neighborhood radius is set, the deviation of training samples is standardized, and 41 geophysical and geophysical conditional attributes are reduced. This paper tries to optimize the reduction algorithm by constructing fuzzy factor, gives weight to the attributes of each reduction by the method based on the importance of attributes, and tries to give the corresponding weights to the attributes based on the sequence of selected attributes. When the KNN algorithm is written to eliminate singular points, the appropriate parameters are designed, combined with the probability histogram of ArcGIS statistical analysis and semi-variance covariance cloud analysis, the noise data are eliminated synthetically, and the training sample points in boundary domain are selected as the final training sample set of SVM model to complete the preprocessing of neighborhood rough set. 3) in MATLAB, Gao Si kernel function is selected to construct SVM model. The optimal classification model is obtained by optimizing the model parameters by the test method of ten fold cross verification. Finally, the whole test area of Gejiu tin mine is traversed, and the mineral resources of tin ore in the whole area are evaluated and analyzed, and the different attribute reduction and model prediction and evaluation systems are compared by changing the neighborhood radius.
【學(xué)位授予單位】：石家莊經(jīng)濟(jì)學(xué)院
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：P624

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 李寶龍;毛景文;莫國培;陳興壽;朱德全;;云南個(gè)舊錫多金屬礦區(qū)礦田構(gòu)造實(shí)測與分析[J];中國地質(zhì);2012年06期

2 邢修三;物理熵、信息熵及其演化方程[J];中國科學(xué)(A輯);2001年01期

3 王國勝,鐘義信;支持向量機(jī)的理論基礎(chǔ)——統(tǒng)計(jì)學(xué)習(xí)理論[J];計(jì)算機(jī)工程與應(yīng)用;2001年19期

4 談樹成,秦德先,陳愛兵,范柱國,薛傳東,李俊,夏既勝,普傳杰;個(gè)舊錫礦區(qū)域地殼演化與成礦探討[J];礦物學(xué)報(bào);2004年02期

5 王學(xué)恩;韓崇昭;韓德強(qiáng);范卿;;粗糙集研究綜述[J];控制工程;2013年01期

6 胡可云,陸玉昌,石純一;粗糙集理論及其應(yīng)用進(jìn)展[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2001年01期

7 劉太安;楊柏翠;楊曉東;;Lagrange支持向量回歸機(jī)算法研究[J];計(jì)算機(jī)工程與設(shè)計(jì);2007年14期

8 劉玉梅;路穎超;王井利;;方差-協(xié)方差分量的驗(yàn)后估計(jì)與分析[J];沈陽建筑大學(xué)學(xué)報(bào)(自然科學(xué)版);2007年05期

9 范玉剛,李平,宋執(zhí)環(huán);基于樣本取樣的SMO算法[J];信息與控制;2004年06期

相關(guān)博士學(xué)位論文 前3條

1 崔廣才;基于粗糙集的數(shù)據(jù)挖掘方法研究[D];吉林大學(xué);2004年

2 安金龍;支持向量機(jī)若干問題的研究[D];天津大學(xué);2004年

3 王禾軍;基于支持向量機(jī)與模糊推理的智能信息融合方法研究[D];華南理工大學(xué);2012年

相關(guān)碩士學(xué)位論文 前1條

1 吳輝;數(shù)據(jù)挖掘技術(shù)的研究與應(yīng)用[D];武漢理工大學(xué);2009年

，

本文編號(hào)：2501010