Geochemical and Geostatistical Studies for Estimating Gold Grade in Tarq Prospect Area by K-Means Clustering Method

Tarq geochemical 1:100,000 Sheet is located in Isfahan province which is investigated by Iran’s Geological and Explorations Organization using stream sediment analyzes. This area has stratigraphy of Precambrian to Quaternary rocks and is located in the Central Iran zone. According to the presence of signs of gold mineralization in this area, it is necessary to identify important mineral areas in this area. Therefore, finding information is necessary about the relationship and monitoring the elements of gold, arsenic, and antimony relative to each other in this area to determine the extent of geochemical halos and to estimate the grade. Therefore, a well-known and useful K-means method is used for monitoring the elements in the present study, this is a clustering method based on minimizing the total Euclidean distances of each sample from the center of the classes which are assigned to them. In this research, the clustering quality function and the utility rate of the sample have been used in the desired cluster (S(i)) to determine the optimum number of clusters. Finally, with regard to the cluster centers and the results, the equations were used to predict the amount of the gold element based on four parameters of arsenic and antimony grade, length and width of sampling points.

Classification of Northeast China Cold Vortex Activity Paths in Early Summer Based on K-means Clustering and Their Climate Impact

The classification of the Northeast China Cold Vortex(NCCV)activity paths is an important way to analyze its characteristics in detail.Based on the daily precipitation data of the northeastern China(NEC)region,and the atmospheric circulation field and temperature field data of ERA-Interim for every six hours,the NCCV processes during the early summer(June)seasons from 1979 to 2018 were objectively identified.Then,the NCCV processes were classified using a machine learning method(k-means)according to the characteristic parameters of the activity path information.The rationality of the classification results was verified from two aspects,as follows:(1)the atmospheric circulation configuration of the NCCV on various paths;and(2)its influences on the climate conditions in the NEC.The obtained results showed that the activity paths of the NCCV could be divided into four types according to such characteristics as the generation origin,movement direction,and movement velocity of the NCCV.These included the generation-eastward movement type in the east of the Mongolia Plateau(eastward movement type or type A);generation-southeast longdistance movement type in the upstream of the Lena River(southeast long-distance movement type or type B);generationeastward less-movement type near Lake Baikal(eastward less-movement type or type C);and the generation-southward less-movement type in eastern Siberia(southward less-movement type or type D).There were obvious differences observed in the atmospheric circulation configuration and the climate impact of the NCCV on the four above-mentioned types of paths,which indicated that the classification results were reasonable.

Application of K-means and PCA approaches to estimation of gold grade in Khooni district(central Iran)

Grade estimation is an important phase of mining projects, and one that is considered a challenge due in part to the structural complexities in mineral ore deposits.To overcome this challenge, various techniques have been used in the past. This paper introduces an approach for estimating Au ore grades within a mining deposit using k-means and principal component analysis(PCA). The Khooni district was selected as the case study. This region is interesting geologically, in part because it is considered an important gold source. The study area is situated approximately 60km northeast of the Anarak city and 270km from Esfahan. Through PCA, we sought to understand the relationship between the elements of gold,arsenic, and antimony. Then, by clustering, the behavior of these elements was investigated. One of the most famous and efficient clustering methods is k-means, based on minimizing the total Euclidean distance from each class center. Using the combined results and characteristics of the cluster centers, the gold grade was determined with a correlation coefficient of 91%. An estimation equation for gold grade was derived based on four parameters: arsenic and antimony content, and length and width of the sampling points. The results demonstrate that this approach is faster and more accurate than existing methodologies for ore grade estimation.

Three Indication Variables and Their Performance for the Troubled-Cell Indicator using K-Means Clustering

In Zhu,Wang and Gao(SIAM J.Sci.Comput.,43(2021),pp.A3009–A3031),we proposed a new framework of troubled-cell indicator(TCI)using K-means clustering and the numerical results demonstrate that it can detect the troubled cells accurately using the KXRCF indication variable.The main advantage of this TCI framework is its great potential of extensibility.In this follow-up work,we introduce three more indication variables,i.e.,the TVB,Fu-Shu and cell-boundary jump indication variables,and show their good performance by numerical tests to demonstrate that the TCI framework offers great flexibility in the choice of indication variables.We also compare the three indication variables with the KXRCF one,and the numerical results favor the KXRCF and the cell-boundary jump indication variables.

A Fast Iteration Method for Mixture Regression Problem

In this paper, we propose a Fast Iteration Method for solving mixture regression problem, which can be treated as a model-based clustering. Compared to the EM algorithm, the proposed method is faster, more flexible and can solve mixture regression problem with different error distributions (i.e. Laplace and t distribution). Extensive numeric experiments show that our proposed method has better performance on randomly simulations and real data.

Incident Detection Based on Differential Analysis

Internet services and web-based applications play pivotal roles in various sensitive domains, encompassing e-commerce, e-learning, e-healthcare, and e-payment. However, safeguarding these services poses a significant challenge, as the need for robust security measures becomes increasingly imperative. This paper presented an innovative method based on differential analyses to detect abrupt changes in network traffic characteristics. The core concept revolves around identifying abrupt alterations in certain characteristics such as input/output volume, the number of TCP connections, or DNS queries—within the analyzed traffic. Initially, the traffic is segmented into distinct sequences of slices, followed by quantifying specific characteristics for each slice. Subsequently, the distance between successive values of these measured characteristics is computed and clustered to detect sudden changes. To accomplish its objectives, the approach combined several techniques, including propositional logic, distance metrics (e.g., Kullback-Leibler Divergence), and clustering algorithms (e.g., K-means). When applied to two distinct datasets, the proposed approach demonstrates exceptional performance, achieving detection rates of up to 100%.

移动网络隐私信息库未知访问源安全性预警

针对互联网信息安全预警过程中,受信息数据规模大、种类多影响,导致预警精度低、耗时长的问题,为提高预警效率,提出移动网络隐私信息库未知访问源安全性预警。利用主成分分析法对信息库数据进行降维处理,降低检测难度;利用迭代多元自回归预测(IMAP:Iterative Multivariate AutoRegressive Modelling and Prediction)算法进行数据聚类处理,提取离散性孤立数据点,完成信息库未知访问源数据筛查。将未知访问源数据输入到支持向量机中,利用时间窗口将信息库安全预警模型的构建问题转化为支持向量机学习的凸优化问题,输出安全性预警结果,并对预警模型的构建参数进行全局寻优,提高安全预警模型的预警输出能力。实验结果表明,所提方法对信息库的安全检测效率较高,且面对多类型信息库入侵攻击能做到稳定、精准预警输出。

An improved probabilistic load flow in distribution networks based on clustering and Point estimate methods

Clustering approaches are one of the probabilistic load flow(PLF)methods in distribution networks that can be used to obtain output random variables,with much less computation burden and time than the Monte Carlo simulation(MCS)method.However,a challenge of the clustering methods is that the statistical characteristics of the output random variables are obtained with low accuracy.This paper presents a hybrid approach based on clustering and Point estimate methods.In the proposed approach,first,the sample points are clustered based on the𝑙-means method and the optimal agent of each cluster is determined.Then,for each member of the population of agents,the deterministic load flow calculations are performed,and the output variables are calculated.Afterward,a Point estimate-based PLF is performed and the mean and the standard deviation of the output variables are obtained.Finally,the statistical data of each output random variable are modified using the Point estimate method.The use of the proposed method makes it possible to obtain the statistical properties of output random variables such as mean,standard deviation and probabilistic functions,with high accuracy and without significantly increasing the burden of calculations.In order to confirm the consistency and efficiency of the proposed method,the 10-,33-,69-,85-,and 118-bus standard distribution networks have been simulated using coding in Python®programming language.In simulation studies,the results of the proposed method have been compared with the results obtained from the clustering method as well as the MCS method,as a criterion.

燃气轮机稳态试验数据异常值剔除方法研究

为确保燃气轮机整机性能评定的准确性,需对台架和机载性能测试数据进行稳态平均值求解。然而实际试验数据存在较多异常值,其对稳态平均值计算结果产生了较大的干扰。介绍了3种燃气轮机稳态试验数据异常值剔除的方法及其原理,包括莱茵达准则、均值迭代法及C模糊聚类方法,并以燃气轮机试验数据为对象,采用上述3种异常值剔除方法对试验数据进行了处理。计算结果表明:莱茵达准则、均值迭代法和C模糊聚类方法的数据处理精度基本一致,均适用于燃气轮机稳态试验数据异常值的剔除。研究成果可以为燃气轮机整机稳态试验数据处理提供参考。

基于迭代剪枝VGGNet的火星图像分类

VGGNet能提供高精度的火星图像分类,但需消耗大量内存资源。鉴于器载计算机内存资源有限,为解决这一矛盾,本文提出了基于迭代剪枝VGGNet的火星图像分类方法。首先,采用迁移学习训练网络的连通性,以便评估神经元的重要性;其次,通过迭代剪枝方法修剪不重要的神经元,以便将全连接层的参数量和内存占用量减少;最后,采用K-means++聚类实现权重参数的量化,利用霍夫曼编码压缩迭代剪枝与量化后的VGGNet权重参数,达到减少存储量和浮点数运算量的作用。此外,通过5种数据增强方法进行数据扩充,目的是解决类别不平衡的问题。实验结果表明,压缩后的VGGNet模型的所占内存、Flops和准确率分别为62.63 Mb、150.6 MFlops和96.15%。与ShuffleNet、MobileNet和EfficientNet等轻量级图像分类算法相比,所提模型具有更好的性能。

基于能量迭代模型和蜂群优化的异构无线传感器网络节能分簇路由算法

针对无线传感器网络节能分簇路由通信时存在数据传输节点死亡数量较多、传输能耗输出较大的问题,提出一种基于能量迭代模型和蜂群优化的异构无线传感器网络节能分簇路由算法.首先构建网络通信能耗模型,以缩减能耗为目标结合差分蜂群算法及时优化网络节点分布;然后基于网络节点分布优化结果,制定异构无线传感器网络节能分簇方法,使用能量迭代选簇方法确定簇头,获取簇头半径完成异构无线传感器网络的通信节点节能分簇;最后设定通信簇头节点与基站之间的距离,确定节点通信时的路由等级,并结合多跳的路由通信方式,实现异构无线传感器网络的节能路由通信.实验结果表明,利用该方法进行网络节能分簇路由通信时,数据传输节点死亡数量最多为22个,节点传输最大能耗为21 nJ/bit,表明该方法节点通信节能效果较好.

High-quality development of China’s power industry: Measurement, spatial pattern, and improvement paths

As the largest manufacturing country,China is striving to improve the development quality of its power industry with the goal of Carbon Peaking and Carbon Neutrality,in order to sustain its high-quality economic growth.In this regard,it is of importance to reveal both the regional development level of China’s power sector and its characteristics in terms of inspiring the next improvement direction.Motived by this purpose,this paper constructs an evaluation indicator system from three dimensions at the province level based on the connotation of high-quality development of the power industry(HDPI).Next,it calculates the HDPI indexes of 30 provinces and explore their development trend and spatial pattern.The results indicate that the total comprehensive performance of all regions was improved in general in the recent decade,but the spatial distribution characteristics of clean,low-carbon,safe and efficient are different.In the aspects of improvement space in future,not only do actively ameliorate the related management regimes or technical fields so as to improve the corresponding indicators’value,but also passively rely on the macro-development such as China’s urbanization level improvement,technological level improvement,and industrial structure upgrading as usual.

基于迭代式聚类的审计疑点发现——以上市公司财报数据为例

数据库查询技术作为目前计算机审计的主要方法,是一种通过审计人员先验知识发现审计疑点的方法。但当缺乏相关审计知识时,便难以给出从海量数据中发现疑点的方法。为破解这一难题,提出基于迭代式聚类的审计疑点发现方法。该方法可在无先验知识的情形下,通过对审计指标的分析,将与大多数被审计对象行为明显相异的少数对象自主识别为审计疑点。利用多种非结构化信息及网络爬取技术,从140份审计报告中自动提取出高频审计问题并据此选定财务指标;归集2008—2012年913家上市公司的财报数据,应用迭代式聚类方法,挖掘出68家疑点公司进行分析。并利用证监会等机构的非结构化网络信息,验证了此方法的有效性。验证结果表明:迭代式聚类方法有助于从海量数据中自主发现审计疑点,缩小疑点筛查范围,提高审计效率。

结合SLIC超像素和DBSCAN聚类的眼底图像硬性渗出检测方法

为自动检测出眼底图像中的硬性渗出,结合简单线性迭代聚类(SLIC)超像素分割算法和基于密度的聚类算法(DBSCAN),提出一种对眼底图像硬性渗出的检测方法.首先,采用SLIC超像素分割算法对彩色眼底图像进行过分割;然后,采用DBSCAN对上述分割得到的超像素进行聚类,形成簇;最后,分割出目标图像,并选用标准糖尿病视网膜病变数据库(DIARETDB0和DIARETDB1)的眼底图像验证上述组合算法的可行性.实验结果表明:算法能够快速、可靠地检测出眼底图像中的硬性渗出,具有可直接对彩色图像进行分割、特征提取的特点.

一种基于加速迭代的大数据集谱聚类方法

传统谱聚类算法的诸多优点只适合小数据集。根据Laplacian矩阵的特点重新构造新的Gram矩阵,输入新构造矩阵的若干列,然后利用加速迭代法解决大数据集的谱聚类特征提取问题,使得在大数据集条件下,谱聚类算法只需要很小的空间复杂度就可达到非常快的计算速度。

基于混合距离学习的双指数模糊C均值算法

提出了一种基于DI-FCM(double indices fuzzy C-means)算法框架的无监督距离学习算法——基于混合距离学习的双指数模糊C均值算法HDDI-FCM(double indices fuzzy C-m eans with hybrid distance).数据集未知距离度量被表示为若干已有距离的线性组合,然后执行HDDI-FCM,在对数据集进行有效聚类的同时进行距离学习.为了保证迭代算法收敛,引入了Steffensen迭代法来改进计算簇中心点的迭代公式.讨论了算法中参数的选择.基于UCI(University of California,Irvine)数据集的实验结果表明该算法是有效的.

浙江省水利管理与服务能力现代化发展水平评价

遵循独立、科学、系统、层次和可操作性的原则,在充分分析国内外大量相关指标的基础上,结合浙江省实际情况,提出了包括防汛防台抗旱管理、水利工程管理、水行政管理、水利工程完好率、人才保障能力、资金保障能力等6项准则层的浙江省水利管理与服务能力现代化发展水平评估指标体系,在此基础上利用模糊聚类循环迭代法科学确定指标权重,并构建了发展水平综合评估模型。对浙江省2015年的水利管理与服务能力现代化水平进行评价,将结果与2020年的预期值进行对比,查找问题和薄弱环节并提出对策建议。

基于改进遗传小波神经网络的雷暴预报方法

为了进一步提高雷暴预报的准确率,在分析研究雷暴预报方法的基础上,提出了一种了基于改进遗传算法优化小波神经网络的雷暴预报方法(IGAWNN).该方法利用聚类分析和牛顿迭代法对多种群遗传算法的收敛方向和精度进行改进,避免了种群同质化与局部最优问题,采用改进的遗传算法对小波神经网络的初始权值阈值进行了优化.选用南京地区2008—2009年6—8月的探空和闪电定位资料,使用灰关联法挖掘出关联程度较大的对流参数作预报因子,归一化处理后输入模型,采用独立样本进行预报检验.结果表明,与BP神经网络等方法相比,IGA-WNN预报准确率更高,具有更好的非线性处理能力和泛化性.

基于聚类的单帧图像超分辨率重建方法

为解决单幅图像的超分辨重建问题,提出一种基于聚类的单帧图像超分辨率重建方法。从高分辨率样本图像中学习一个结构聚类型的高分辨率字典,利用迭代收缩算法优化目标方程,求得高分辨率图像的表示系数,使用学习到的高分辨率字典对低分辨率图像进行重构。实验结果表明,与总变分方法、软切割方法和稀疏表示方法相比,该方法的单帧图像超分辨率重建效果较好。

模糊聚类分析在低频振荡主导模式辨识中的应用

互联系统中,利用振荡曲线提取多机振荡信息,需要选择合适的曲线才能快速得到系统主导振荡模式。文章首先提出了一种基于模糊划分的迭代自组织数据分析技术的聚类方法;然后在一些基本假设的基础上,形成了模糊集合,并运用模糊聚类分析法将系统分区;最后用Prony分析算法从合适的低频振荡信号曲线中准确地提取区域主导振荡模式。通过对中国电力科学研究院8机36节点系统的算例仿真验证了该方法的可行性和有效性。