KNN数据挖掘算法在北京地区霾等级预报中的应用

利用北京地区2013年气象数据以及PM2.5浓度数据与能见度数据进行对比分析,结果发现气温、气压、相对湿度、露点温度、地面U风、地面V风以及PM2.5小时浓度这7个要素是影响北京地区霾等级的关键因素。利用气温、地面气压、相对湿度、露点温度、U风、V风分量以及PM2.5浓度作为7个属性特征,以霾等级做为标志量构建训练样本集,结合KNN（K Nearest Neighbor）数据挖掘算法构建霾等级预报分类器,并开展霾等级客观识别实验。结果表明K=3时该分类器的分类预报效果最佳,其13个站点的分类准确率高达88.2%。基于该算法构建的KNN模型预报无霾时的漏报概率很小,准确率高达91.8%;预报有轻度霾、中度霾以及重度霾时,空报的概率仅分别为4.7%、1.4%和2.6%。2014年8月29日至9月2日北京地区一次霾天气过程的预报结果表明：南郊观象台、密云和延庆3站的预报准确率分别达到74%、64%和84%,但霾等级的精度方面还有待于进一步提高。     

基于耦合相似指标的最近邻法在年径流预测中的应用

根据水文现象相似特性建立的最近邻法,避免了对研究对象相依形式和概率分布形式做某种假定,是一类基于数据驱动的预测方法。影响该方法预测成果优劣的关键因素之一是特征矢量相似程度衡量指标的选取。为了在度量相似程度时兼顾"矢"和"量"的信息,在深入分析余弦距离与欧氏距离异同的基础上,尝试将二者耦合作为相似度的技术指标,建立了基于耦合相似指标的最近邻法,并将该方法应用到宜昌水文站和唐乃亥水文站预见期为一年的年径流预测,利用不同水文特性的年径流资料进行校验,结果表明:基于耦合指标的最近邻法,能较好地进行年径流的预测分析,是一种有效、可行的方法。     

基于格网化邻域查询的海上船舶救援搜索方法

海洋渔业是高风险行业,各类海洋灾害频繁发生,海上航行、作业环境复杂,因此,海上快速救援对保护渔民的生命财产安全具有重要意义。本文基于空间剖分的格网化编码,提出一种根据有效救援距离和失事船舶位置进行邻域搜索以查找失事船只相邻和最邻近可供救援的船只的方法,其中有效救援距离通过救援船舶的类型和航速来设定,根据有效救援距离设置不同的编码搜索长度。本文将模拟实验区域设定为我国东海海域,随机生成1×10⁴个船位点,在时间检索效率和内存占用两方面,实验结果表明,与传统的船舶间距离的计算方法相比,基于格网化邻域搜索的查询方法编码后船位数据较编码转换前船位数据占用内存空间减少56.47%,同时,编码后检索运算的用户时间是编码前用户时间的17.67%,因此,基于格网化邻域搜索的查询方法占用内存小,且运算效率较高,能够有效提升对遇险船舶邻域救援船只的查询效率。     

基于高分卫星影像的复杂山区光伏电站信息提取

该文基于高分卫星资料,通过基于规则的面向对象分类、基于最邻近法的监督分类及基于CART分类器的监督分类三种不同分类方法,对复杂山区光伏电站进行提取,对比三种分类提取方法结果并完成精度验证。结果表明,合理的分割参数有利于提高光伏电站提取精度;基于规则的面向对象分类法光伏电站提取精度最佳,最邻近分类法次之,CART分类器分类法最差,可利用基于规则的面向对象分类法较为准确地进行复杂山区光伏电站信息提取,为光伏产业健康、合理发展提供一定的数据支撑。     

A neighbor decay cellular automata approach for simulating urban expansion based on particle swarm intelligence

Simulation and quantitative analysis of urban land use change are effective ways to investigate urban form evolution. Cellular Automata (CA) has been used as a convenient and useful tool for simulating urban land use change. However, the key issue for CA models is the definition of the transition rules, and a number of statistical or artificial intelligence methods may be used to obtain the optimal rules. Neighborhood configuration is a basic component of transition rules, and is characterized by a distance decay effect. However, many CA models do not consider the neighbor decay effect in cellular space. This paper presents a neighbor decay cellular automata model based on particle swarm optimization (PSO-NDCA). We used particle swarm optimization (PSO) to find transition rules and considered the decay effect of the cellular neighborhood. A negative power exponential function was used to compute the decay coefficient of the cellular neighborhood in the model. By calculating the cumulative differences between simulation results and the sample data, the PSO automatically searched for the optimal combination of parameters of the transition rules. Using Xiamen City as a case study, we simulated urban land use changes for the periods 1992–1997 and 2002–2007. Results showed that the PSO-NDCA model had a higher prediction accuracy for built-up land, and a higher overall accuracy and Kappa coefficient than the urban CA model based on particle swarm optimization. The study demonstrates that there exist optimal neighborhood decay coefficients in accordance with the regional characteristics of an area. Urban CA modelling should take into account the role of neighborhood decay.     

水深测量成果相邻图幅拼接质量评估方法研究

在利用搜索重合点水深比对法检查相邻两水深测量成果拼接质量过程中,通过展现重合点在拼接区域的分布情况,发现搜索的重合点存在相对总点数较少且分布不均匀的缺点,影响评估质量.针对上述问题,建立了网格选取剖面比对法,系统阐述了该方法的操作原理及其应用并通过实例验证取得了较好的结果,为水深测量成果相邻图幅拼接质量评估提供新的思路.     

3种经典机器学习算法在火山岩测井岩性识别中的对比

岩性识别一直是火山岩油气勘探中的重要课题,基于测井数据的岩性识别也逐渐成为火山岩研究的需要,大数据背景下的机器学习算法为测井岩性识别提供了一个新方向。为提高某研究区火山岩岩性识别符合率,本文采用K近邻、支持向量机和自适应增强3种经典机器学习算法,对研究区内的粗面岩、非致密粗面岩、辉绿岩、辉长岩、玄武岩和非致密玄武岩等6类中基性火山岩进行岩性识别。从常规测井系列中优选对研究区岩性敏感的自然伽马、声波时差、补偿中子、深侧向电阻率和补偿密度等5种测井参数作为岩性识别模型的输入向量,从研究区内5口有岩心样品或薄片鉴定资料的目标层中选取测井数据点1 440个,其中960个作为训练样本,其余480个作为测试样本。以识别符合率和时间作为评价指标,对3种算法的识别结果进行对比分析,实验表明：自适应增强算法的分类准确率最高,6类岩性平均识别符合率达到82.10%;支持向量机算法表现良好,平均识别符合率为81.04%;K近邻算法平均识别符合率为76.04%。     

多主体框架下基于FCM的彩色遥感图像分割

为解决大尺度高分辨率遥感图像的数据量大及局部非均匀问题,提出一种在多主体系统（MAS）框架下基于模糊C均值（FCM）的彩色遥感图像分割方法。首先利用规则划分技术将图像域划分为若干个子块,每个分割主体控制一个子块;然后在MAS框架下,分割主体通过FCM算法实现对应子块的初始分割,将初始结果与全局模型协作,确定其区域正确类别数和标号统一;最后通过协调主体协调各分割主体及其邻域分割主体的聚类中心,从而消除遥感图像的局部非均匀性,以实现彩色遥感图像分割。利用提出算法和FCM算法分别对真实彩色遥感图像和合成图像进行了分割试验,并对其分割结果进行定性、定量评价,其结果说明了提出方法的可行性和有效性。     

A novel method for discovering spatio-temporal clusters of different sizes,shapes, and densities in the presence of noise

The discovery of spatio-temporal clusters in complex spatio-temporal data-sets has been a challenging issue in the domain of spatio-temporal data mining and knowledge discovery. In this paper, a novel spatio-temporal clustering method based on spatio-temporal shared nearest neighbors (STSNN) is proposed to detect spatio-temporal clusters of different sizes, shapes, and densities in spatio-temporal databases with a large amount of noise. The concepts of windowed distance and shared nearest neighbor are utilized to define a novel spatio-temporal density for a spatio-temporal entity with definite mathematical meanings. Then, the density-based clustering strategy is employed to uncover spatio-temporal clusters. The spatio-temporal clustering algorithm developed in this paper is easily implemented and less sensitive to density variation among spatio-temporal entities. Experiments are undertaken on several simulated data-sets to demonstrate the effectiveness and advantage of the STSNN algorithm. Also, the real-world applications on two seismic databases show that the STSNN algorithm has the ability to uncover foreshocks and aftershocks effectively.     

Modeling blocky nonlinear mechanics behavior on plasticity and progressive fractures with the enriched mesh free DDA method

This study explores a new form of Discontinuous Deformation Analysis (DDA) method, which uses mesh free displacement functions instead of linear polynomial ones adopted in the original DDA, hence it can effectively describe complex block displacements and deformations. Moreover, the capability of describing a block’s nonlinear mechanical behaviors, i.e., plasticity and fracture, are developed under classical fracture and increment plasticity mechanics theories. With consideration of computation efficiency and convenience, the Sibson natural neighbor interpolation technique for block plasticity analysis and the enriched Moving Least-Squares (MLS) approximation for block fracture analysis are employed, respectively. Numerical results show the applicability of the proposed mesh free DDA method.