Waterlogging risk assessment based on self-organizing map(SOM)artificial neural networks:a case study of an urban storm in Beijing

Due to rapid urbanization, waterlogging induced by torrential rainfall has become a global concern and a potential risk affecting urban habitant's safety. Widespread waterlogging disasters haveoccurred almost annuallyinthe urban area of Beijing, the capital of China. Based on a selforganizing map(SOM) artificial neural network(ANN), a graded waterlogging risk assessment was conducted on 56 low-lying points in Beijing, China. Social risk factors, such as Gross domestic product(GDP), population density, and traffic congestion, were utilized as input datasets in this study. The results indicate that SOM-ANNis suitable for automatically and quantitatively assessing risks associated with waterlogging. The greatest advantage of SOM-ANN in the assessment of waterlogging risk is that a priori knowledge about classification categories and assessment indicator weights is not needed. As a result, SOM-ANN can effectively overcome interference from subjective factors,producing classification results that are more objective and accurate. In this paper, the risk level of waterlogging in Beijing was divided into five grades. The points that were assigned risk grades of IV or Vwere located mainly in the districts of Chaoyang, Haidian, Xicheng, and Dongcheng.

Software Reusability Classification and Predication Using Self-Organizing Map (SOM)

Due to rapid development in software industry, it was necessary to reduce time and efforts in the software development process. Software Reusability is an important measure that can be applied to improve software development and software quality. Reusability reduces time, effort, errors, and hence the overall cost of the development process. Reusability prediction models are established in the early stage of the system development cycle to support an early reusability assessment. In Object-Oriented systems, Reusability of software components (classes) can be obtained by investigating its metrics values. Analyzing software metric values can help to avoid developing components from scratch. In this paper, we use Chidamber and Kemerer (CK) metrics suite in order to identify the reuse level of object-oriented classes. Self-Organizing Map (SOM) was used to cluster datasets of CK metrics values that were extracted from three different java-based systems. The goal was to find the relationship between CK metrics values and the reusability level of the class. The reusability level of the class was classified into three main categorizes (High Reusable, Medium Reusable and Low Reusable). The clustering was based on metrics threshold values that were used to achieve the experiments. The proposed methodology succeeds in classifying classes to their reusability level (High Reusable, Medium Reusable and Low Reusable). The experiments show how SOM can be applied on software CK metrics with different sizes of SOM grids to provide different levels of metrics details. The results show that Depth of Inheritance Tree (DIT) and Number of Children (NOC) metrics dominated the clustering process, so these two metrics were discarded from the experiments to achieve a successful clustering. The most efficient SOM topology [2 × 2] grid size is used to predict the reusability of classes.

基于mRMR-SOM的异步电机轴承故障诊断研究

针对异步电机轴承故障诊断问题,提出了一种融合最大相关最小冗余特征选择算法(mRMR)和自组织映射神经网络(SOM)的故障诊断方法,并将其应用于轴承故障诊断的不同阶段。首先,在实验室环境下搭建了异步电机故障诊断试验平台,在不同电机状态下分别采集振动、电流和电压信号,利用统计学方法获取了高维混合特征集;然后,以互信息为背景,利用mRMR根据特征与状态标签间的相关性和特征间的冗余性,筛选了具备强区分能力的特征,以避免计算冗余和后验诊断性能下降;最后,采用SOM对异步电机健康和轴承故障状态进行了分类识别,验证了SOM对异步电机轴承故障诊断的有效性,以及mRMR对故障诊断结果的影响。研究结果表明:基于mRMR-SOM的异步电机轴承故障诊断方法能够准确地区分健康和故障状态,测试集分类准确率达到89%;使用mRMR特征筛选能够将154维特征降低至17维,缩短23.5%的网络收敛时间,并将分类准确率由89%提升至98%;试验结果验证了基于mRMR-SOM的异步电机轴承故障诊断方法对于异步电机轴承故障诊断问题的有效性,且证实其具备良好的诊断效果。

Intraseasonal variability of the equatorial Pacific Ocean and its relationship with ENSO based on Self-Organizing Maps analysis

We investigated the intraseasonal variability of equatorial Pacific subsurface temperature and its relationship with El Nino-Southern Oscillation(ENSO) using Self-Organizing Maps(SOM) analysis.Variation in intraseasonal subsurface temperature is mainly found along the thermocline.The SOM patterns concentrate in basin-wide seesaw or sandwich structures along an east-west axis.Both the seesaw and sandwich SOM patterns oscillate with periods of 55 to 90 days,with the sequence of them showing features of equatorial intraseasonal Kelvin wave,and have marked interannual variations in their occurrence frequencies.Further examination shows that the interannual variability of the SOM patterns is closely related to ENSO;and maxima in composite interannual variability of the SOM patterns are located in the central Pacific during CP El Nino and in the eastern Pacific during EP El Nino.The se results imply that some of the ENSO forcing is manife sted through changes in the occurrence frequency of intraseasonal patterns,in which the change of the intraseasonal Kelvin wave plays an important role.

Study of TSP based on self-organizing map

Self-organizing map(SOM) proposed by Kohonen has obtained certain achievements in solving the traveling salesman problem(TSP).To improve Kohonen SOM,an effective initialization and parameter modification method is discussed to obtain a faster convergence rate and better solution.Therefore,a new improved self-organizing map(ISOM)algorithm is introduced and applied to four traveling salesman problem instances for experimental simulation,and then the result of ISOM is compared with those of four SOM algorithms:AVL,KL,KG and MSTSP.Using ISOM,the average error of four travelingsalesman problem instances is only 2.895 0%,which is greatly better than the other four algorithms:8.51%(AVL),6.147 5%(KL),6.555%(KG) and 3.420 9%(MSTSP).Finally,ISOM is applied to two practical problems:the Chinese 100 cities-TSP and102 counties-TSP in Shanxi Province,and the two optimal touring routes are provided to the tourists.

Visualization of Pareto Solutions by Spherical Self-Organizing Map and It’s acceleration on a GPU

In this study, we visualize Pareto-optimum solutions derived from multiple-objective optimization using spherical self-organizing maps (SOMs) that lay out SOM data in three dimensions. There have been a wide range of studies involving plane SOMs where Pareto-optimal solutions are mapped to a plane. However, plane SOMs have an issue that similar data differing in a few specific variables are often placed at far ends of the map, compromising intuitiveness of the visualization. We show in this study that spherical SOMs allow us to find similarities in data otherwise undetectable with plane SOMs. We also implement and evaluate the performance using parallel sphere processing with several GPU environments.

采用SOM算法的软体机械臂三维形状实时感知

为实现软体机械臂精确的三维形状实时估计,奠定变形控制与应用的基础性工作,针对三段式软体机械臂,提出了一种基于自组织映射(Self-organizing map,SOM)算法的三维空间形状实时感知方法。首先,对ZED双目相机捕捉到的左、右图像帧进行图像预处理,得到左、右二值图像,并实时提取软体机械臂的二维轮廓数据。然后,采用SOM算法对轮廓数据进行聚类,有序得到软体机械臂二维中心线的多个骨干点,并与K均值,高斯混合模型以及细化3种中心线提取算法进行了对比研究,进一步表明SOM算法更适用于解决软体机械臂复杂形状的中心线辨识。最后,通过基于双目视差的三角测距模型完成软体机械臂的三维形状重构。该算法还采用数据降采样、SOM参数优化等方法,提高算法框架的实时性能。针对软体机械臂连续形变过程,进行了实时形状传感实验和对比验证实验。实验结果表明,该算法具有较高的形状感知精度和较好的实时跟踪效果。不仅如此,与其他文献中提出的形状检测算法相比,该算法也具有较好的性能。

自组织映射神经网络(SOM)降尺度方法对江淮流域逐日降水量的模拟评估

利用1961-2002年ERA-40逐日再分析资料和江淮流域56个台站逐日观测降水量资料,引入基于自组织映射神经网络（Self-Organizing Maps,简称SOM）的统计降尺度方法,对江淮流域夏季（6-8月）逐日降水量进行统计建模与验证,以考察SOM对中国东部季风降水和极端降水的统计降尺度模拟能力。结果表明,SOM通过建立主要天气型与局地降水的条件转换关系,能够再现与观测一致的日降水量概率分布特征,所有台站基于概率分布函数的Brier评分（Brier Score）均近似为0,显著性评分（Significance Score）全部在0.8以上;模拟的多年平均降水日数、中雨日数、夏季总降水量、日降水强度、极端降水阈值和极端降水贡献率区域平均的偏差都低于11%;并且能够在一定程度上模拟出江淮流域夏季降水的时间变率。进一步将SOM降尺度模型应用到BCCCSM1.1（m）模式当前气候情景下,评估其对耦合模式模拟结果的改善能力。发现降尺度显著改善了模式对极端降水模拟偏弱的缺陷,对不同降水指数的模拟较BCC-CSM1.1（m）模式显著提高,降尺度后所有台站6个降水指数的相对误差百分率基本在20%以内,偏差比降尺度前减小了40%-60%;降尺度后6个降水指数气候场的空间相关系数提高到0.9,相对标准差均接近1.0,并且均方根误差在0.5以下。表明SOM降尺度方法显著提高日降水概率分布,特别是概率分布曲线尾部特征的模拟能力,极大改善了模式对极端降水场的模拟能力,为提高未来预估能力提供了基础。

SOM神经网络算法的研究与进展

自组织映射(Self-organizingMaps,SOM)算法是一种无导师学习方法,具有良好的自组织、可视化等特性,已经得到了广泛的应用和研究。该文系统地介绍了SOM算法的产生背景、基本算法。同时对SOM算法的参数设置和其不足进行了分析。重点归纳了其发展过程中的各种改进算法,并对其研究热点及应用领域作了简要的综述,最后展望了该算法的发展方向。

SOM神经网络改进及在遥感图像分类中的应用

针对自组织特征神经网络自身算法的特点和缺陷,采用遗传算法对网络进行改进,形成了基于遗传算法的自组织特征神经网络,并从输入向量、竞争层神经元数量设置和初始权向量设定三方面,结合遥感图像的特性对自组织特征映射网络遥感图像分类的方法进行了改进。将该方法应用于选择西安地区的ETM+卫星遥感图像进行分类实验。结果表明,基于遗传算法的自组织特征映射网络使得遥感图像的分类精度更高,且该算法实现简单,具有一定的工程应用价值。

基于SOM-DB-PAM混合聚类算法的电力客户细分

针对电力客户具有客户数量大、存在孤立点等特点,提出一种适用于对大量电力客户进行快速聚类的SOM-DB-PAM混合聚类算法。该算法利用自组织映射神经网络训练输入数据,以获取代表输入模式且数据量远小于输入数据量的原型向量,使用围绕中心点的切分(PAM)对该原型向量聚类并用Davies-Bouldin指标判定最优聚类个数以保证聚类效果。实验结果表明,与传统聚类算法相比,该算法具有更高的分类正确率,当客户数量较大时,能实现对客户的快速、有效聚类,并减少人为指定聚类个数的盲目性和主观性。

基于混合AIS/SOM的入侵检测模型

针对异常检测信息获取不足的缺点,提出基于混合人工免疫系统(AIS)/自组织映射(SOM)的入侵检测模型。该模型采用人工免疫系统检测网络异常,对检测到的异常连接用自组织映射进行分类,应用KDDCUP99实验数据集进行仿真。结果表明该检测方法是有效的,能够将检测到的异常连接分类并给出异常连接的更多信息,检测和分类效率较高、误报率低。

竞争层结构可调SOM网络在中药模式识别中的应用

针对经典SOM算法无法准确反映原始数据的特征信息,提出了竞争层结构可调的SOM算法——CSA-SOM算法。该算法增加了竞争层神经元动态调节的步骤,调节的依据是不断比较原数据的位置信息和映射后低维空间的位置信息,使两者最终能趋于一致。因此降维后的数据能够较好地保持原数据的特征,包括距离信息、角度信息以及分布信息。该算法有效地实现了红景天药材的准确清晰分类。算法理论分析和实验结果均表明,CSA-SOM算法是一种快速、准确的数据内在规律映射可视化算法,与SOM算法相比,CSA-SOM算法的特征映射效果比较好,解决了SOM算法会使映射后数据结构发生扭曲的问题。

应用于光伏阵列故障诊断的DA-SOM算法研究

针对自组织映射SOM(self-organizing map)神经网络聚类性能易受其初始权值的影响,采用蜻蜓算法DA(dragonfly algorithm)优化SOM神经网络的局部权重失真指数LWDI(locally weighted distortion index),对神经网络的初始权值进行寻优。以光伏阵列故障数据样本为研究对象,将正常与故障状态下的输出特性进行对比分析,建立故障诊断模型,并利用诊断模型诊断和输出故障类型。仿真结果表明,与基本SOM神经网络及反向传播BP(back propagation)、DA-BP神经网络相比较,DA-SOM神经网络能够得到较优的聚类效果,可有效地提高光伏阵列故障诊断的准确率。

融合差分进化和SOM的组合文本聚类算法

自组织映射算法是一种重要的聚类模型,能够有效提高搜索引擎的精确性。为克服自组织映射网络对于初始连接权值敏感的不足,提出一种改进的差分进化和SOM相结合的组合文档聚类算法IDE-SOM,首先引入一种改进的差分进化算法对文档集进行一次粗聚类,旨在对SOM网络的初始连接权值进行优化,然后将这个连接权值初始化SOM网络进行细聚类。仿真实验表明,该算法在F-measure、熵等评价指标上都获得了较好的聚类效果。

一种改进的BSOM灰度图像轮廓提取算法

介绍一种批处理无监督的自组织映射算法(BSOM),然后对该算法的学习速率进行了改进,提出了基于模拟退火的BSOM灰度图像轮廓提取算法.仿真实验结果表明算法的有效性.同时,测试数据对比表明,在提取图像轮廓时,方法比文献[6]的BSOM方法收敛速度更快,提取的图像轮廓效果更好.

基于改进RFM模型与聚类算法的民航客户细分研究

对于传统的RFM模型客户细分而言,由于缺乏科学的指标而无法针对航空市场进行精确的细分,因此提出TLFM模型作为细分的指标,利用自组织映射(SOM)算法和“手肘法”确定k-means算法的最佳k值,从而得到航空市场客户细分的结果。最后根据客户细分的情况和各类客户的行为特征,提出差异性的服务和不同的营销策略来提高航空公司的竞争力。

基于共享介质争用访问机制的电采暖设备自适应控制方法

“煤改电”背景下大量电采暖设备的无序接入,极易造成尖峰负荷、引起电压波动甚至越限,影响电能质量与用电安全。针对这一问题,提出了基于共享介质争用访问机制的电采暖设备自适应控制方法。通过刻画电采暖功率变化与区域内电压分布关系函数,分析了各节点电压波动的关键影响因素。以此为基础,构建了以家庭为最小控制单元的电采暖设备自适应控制方法实施架构:采用自组织映射(SOM)神经网络得到家庭近期活跃的电采暖设备数量,进而借鉴通信网络中信道访问与数据传输冲突监测机制,使电采暖设备通过实时采集本地环境信息和电气信息进行自主控制和冲突规避,实现了无需通信的自适应控制。仿真结果验证了所提控制方法在减小用电尖峰负荷、平抑负荷曲线及抑制电压越限方面的有效性以及在实时控制方面的优越性。

Multi-Dimensional Traffic Flow Time Series Analysis with Self-Organizing Maps

The two important features of self-organizing maps （SOM）, topological preservation and easy visualization, give it great potential for analyzing multi-dimensional time series, specifically traffic flow time series in an urban traffic network. This paper investigates the application of SOM in the representation and prediction of multi-dimensional traffic time series. Ffrst, SOMs are applied to cluster the time series and to project each multi-dimensional vector onto a two-dimensional SOM plane while preserving the topological relationships of the original data. Then, the easy visualization of the SOMs is utilized and several exploratory methods are used to investigate the physical meaning of the clusters as well as how the traffic flow vectors evolve with time. Finally, the k-nearest neighbor （kNN） algorithm is applied to the clustering result to perform short-term predictions of the traffic flow vectors. Analysis of real world traffic data shows the effec- tiveness of these methods for traffic flow predictions, for they can capture the nonlinear information of traffic flows data and predict traffic flows on multiple links simultaneously.

A Multiscale Approach to Automatic Medical Image Segmentation Using Self-Organizing Map

In this paper, a new medical image classification scheme is proposed using selforganizing map (SOM) combined with multiscale technique. It addresses the problem of the handling of edge pixels in the traditional multiscale SOM classifiers. First, to solve the difficulty in manual selection of edge pixels, a multiscale edge detection algorithm based on wavelet transform is proposed. Edge pixels detected are then selected into the training set as a new class and a mu1tiscale SoM classifier is trained using this training set. In this new scheme, the SoM classifier can perform both the classification on the entire image and the edge detection simultaneously. On the other hand, the misclassification of the traditional multiscale SoM classifier in regions near edges is greatly reduced and the correct classification is improved at the same time.