Varieties of approaches and algorithms have been presented to identify the distribution of elements. Previous researches based on the type of problem, categorized their data in proper clusters or classes. This means t...Varieties of approaches and algorithms have been presented to identify the distribution of elements. Previous researches based on the type of problem, categorized their data in proper clusters or classes. This means that the process of solution could be supervised or unsupervised. In cases, where there is no idea about dependency of samples to specific groups, clustering methods (unsupervised) are applied. About geochemistry data, since various elements are involved, in addition to the complex nature of geochemical data, clustering algorithms would be useful for recognition of elements distribution. In this paper, Self-Organizing Map (SOM) algorithm, as an unsupervised method, is applied for clustering samples based on REEs contents. For this reason the Choghart Fe-REE deposit (Bafq district, central Iran), was selected as study area and dataset was a collection of 112 lithology samples that were assayed with laboratory tests such as ICP-MS and XRF analysis. In this study, input vectors include 19 features which are coordinates x, y, z and concentrations of REEs as well as the concentration of Phosphate (P<sub>2</sub>O<sub>5</sub>) since the apatite is the main source of REEs in this particular research. Four clusters were determined as an optimal number of clusters using silhouette criterion as well as k-means clustering method and SOM. Therefore, using self-organizing map, study area was subdivided in four zones. These four zones can be described as phosphate type, albitofyre type, metasomatic and phosphorus iron ore, and Iron Ore type. Phosphate type is the most prone to rare earth elements. Eventually, results were validated with laboratory analysis.展开更多
The convergence analysis of MaxMin-SOMO algorithm is presented. The SOM-based optimization (SOMO) is an optimization algorithm based on the self-organizing map (SOM) in order to find a winner in the network. Generally...The convergence analysis of MaxMin-SOMO algorithm is presented. The SOM-based optimization (SOMO) is an optimization algorithm based on the self-organizing map (SOM) in order to find a winner in the network. Generally, through a competitive learning process, the SOMO algorithm searches for the minimum of an objective function. The MaxMin-SOMO algorithm is the generalization of SOMO with two winners for simultaneously finding two winning neurons i.e., first winner stands for minimum and second one for maximum of the objective function. In this paper, the convergence analysis of the MaxMin-SOMO is presented. More specifically, we prove that the distance between neurons decreases at each iteration and finally converge to zero. The work is verified with the experimental results.展开更多
An improved clustering method based on artificial immune is proposed. To obtain the better initial solution, the initial antibody network is introduced by self organizing map （SOM） method. In the process of the clus...An improved clustering method based on artificial immune is proposed. To obtain the better initial solution, the initial antibody network is introduced by self organizing map （SOM） method. In the process of the clustering iteration, a series of optimization and evolution strategies are designed, such as clustering satisfaction, the threshold design of scale compression, the learning rate, the clustering monitoring points and the clustering evaluations indexes. These strategies can make the clustering thresholds be quantified and reduce the operator’s subjective factors. Thus, the local optimal and the global optimal clustering simultaneously are proposed by the synthesized function of these strategies. Finally, the experiment and the comparisons demonstrate the proposed method effectiveness.展开更多
针对基因表达数据样本少,维数高的特点,尤其是在样本分型缺乏先验知识的情况下,结合自组织特征映射的优点提出了基于代表熵的双向聚类算法。该算法首先通过自组织特征映射网络(SOM)对基因聚类,根据波动系数挑选特征基因。然后根据代表...针对基因表达数据样本少,维数高的特点,尤其是在样本分型缺乏先验知识的情况下,结合自组织特征映射的优点提出了基于代表熵的双向聚类算法。该算法首先通过自组织特征映射网络(SOM)对基因聚类,根据波动系数挑选特征基因。然后根据代表熵的大小判断基因聚类的好坏,并确定网络的神经元个数。最后采用FCM(Fuzzy C Means)聚类算法对挑选出的特征基因集进行样本分型。将该算法用于两组公开的基因表达数据集,实验结果表明该算法在降低特征维数的同时,得出了较高的聚类准确率。展开更多
文摘Varieties of approaches and algorithms have been presented to identify the distribution of elements. Previous researches based on the type of problem, categorized their data in proper clusters or classes. This means that the process of solution could be supervised or unsupervised. In cases, where there is no idea about dependency of samples to specific groups, clustering methods (unsupervised) are applied. About geochemistry data, since various elements are involved, in addition to the complex nature of geochemical data, clustering algorithms would be useful for recognition of elements distribution. In this paper, Self-Organizing Map (SOM) algorithm, as an unsupervised method, is applied for clustering samples based on REEs contents. For this reason the Choghart Fe-REE deposit (Bafq district, central Iran), was selected as study area and dataset was a collection of 112 lithology samples that were assayed with laboratory tests such as ICP-MS and XRF analysis. In this study, input vectors include 19 features which are coordinates x, y, z and concentrations of REEs as well as the concentration of Phosphate (P<sub>2</sub>O<sub>5</sub>) since the apatite is the main source of REEs in this particular research. Four clusters were determined as an optimal number of clusters using silhouette criterion as well as k-means clustering method and SOM. Therefore, using self-organizing map, study area was subdivided in four zones. These four zones can be described as phosphate type, albitofyre type, metasomatic and phosphorus iron ore, and Iron Ore type. Phosphate type is the most prone to rare earth elements. Eventually, results were validated with laboratory analysis.
基金supported by National Natural Science Foundation of China(Nos.11171367 and 61502068)the Fundamental Research Funds for the Central Universities of China(No.3132014094)+1 种基金the China Postdoctoral Science Foundation(Nos.2013M541213 and 2015T80239)Fundacao da Amaro a Pesquisa do Estado de Sao Paulo(FAPESP)Brazil(No.2012/23329-5)
文摘The convergence analysis of MaxMin-SOMO algorithm is presented. The SOM-based optimization (SOMO) is an optimization algorithm based on the self-organizing map (SOM) in order to find a winner in the network. Generally, through a competitive learning process, the SOMO algorithm searches for the minimum of an objective function. The MaxMin-SOMO algorithm is the generalization of SOMO with two winners for simultaneously finding two winning neurons i.e., first winner stands for minimum and second one for maximum of the objective function. In this paper, the convergence analysis of the MaxMin-SOMO is presented. More specifically, we prove that the distance between neurons decreases at each iteration and finally converge to zero. The work is verified with the experimental results.
基金supported by the Program for New Century Excellent Talents in University (NCET-06-0236)
文摘An improved clustering method based on artificial immune is proposed. To obtain the better initial solution, the initial antibody network is introduced by self organizing map （SOM） method. In the process of the clustering iteration, a series of optimization and evolution strategies are designed, such as clustering satisfaction, the threshold design of scale compression, the learning rate, the clustering monitoring points and the clustering evaluations indexes. These strategies can make the clustering thresholds be quantified and reduce the operator’s subjective factors. Thus, the local optimal and the global optimal clustering simultaneously are proposed by the synthesized function of these strategies. Finally, the experiment and the comparisons demonstrate the proposed method effectiveness.
文摘针对基因表达数据样本少,维数高的特点,尤其是在样本分型缺乏先验知识的情况下,结合自组织特征映射的优点提出了基于代表熵的双向聚类算法。该算法首先通过自组织特征映射网络(SOM)对基因聚类,根据波动系数挑选特征基因。然后根据代表熵的大小判断基因聚类的好坏,并确定网络的神经元个数。最后采用FCM(Fuzzy C Means)聚类算法对挑选出的特征基因集进行样本分型。将该算法用于两组公开的基因表达数据集,实验结果表明该算法在降低特征维数的同时,得出了较高的聚类准确率。
文摘于2007—2008年对象山港23个站点(包括10个电厂站点)的水质样品进行连续2年的季节性采集,采用SOM(Self-Organizing Map)工具箱,结合k-nn(knearest neighbors)神经元聚类对15个水质参数进行分析,以探明象山港海域水质时空变化并识别敏感的影响区域.结果显示,象山港海域N/P(物质的量比)平均值为27.0.水体污染指数(AI)和海水营养指数(NI)分别指示整个象山港水质处于严重污染和富营养化状态,但水质加权指数(WDX)显示,加权水质标准未超过3类水质,说明传统的AI和NI指数不能反映象山港的实际水质状况.经SOM分析发现,象山港海域各取样站点按季节和空间格局可分为8个聚类组.从季节上看,pH和油类含量在春季最低;夏季水温、COD、NO2--N最高,而DO最低.NO3--N、DIN、DIP在秋冬季节高于春夏季节,但透明度相反.Chl-a含量以夏季最高,冬季最低.GLM(General Linear Model)方差分析显示,不同季节的安全性指数(SFT)和N/P无显著差异(p>0.05),而NI、AI和WDX差异极显著(p<0.01).空间分析显示,象山港水体可分为港底区和口中部区,其中,港底区盐度、pH显著低于口中部区(p<0.01),而NO2--N、NH4+-N、DIN、DIP、Chl-a则显著高于口中部区(p<0.05).除WDX无显著差异外,港底区的N/P显著低于口中部区(p<0.01),而NI、AI、SFT相反(p<0.05).建议港区底部宜采用养殖大型海藻方式以减轻富营养化,此外,冬季黄墩港的水体中粪大肠菌群严重超标,生食该季节贝类产品时需要检测.
