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.

Comparison of Electric Load Forecasting between Using SOM and MLP Neural Network

Electric load forecasting has been a major area of research in the last decade since the production of accurate short-term forecasts for electricity loads has proven to be a key to success for many of the decision makers in the energy sector, from power generation to operation of the system. The objective of this research is to analyze the capacity of the MLP （multilayer perceptron neural network） versus SOM （self-organizing map neural network） for short-term load forecasting. The MLP is one of the most commonly used networks. It can be used for classification problems, model construction, series forecasting and discrete control. On the other hand, the SOM is a type of artificial neural network that is trained using unsupervised data to produce a low-dimensional, discretized representation of an input space of training samples in a cell map. Historical data of real global load demand were used for the research. Both neural models provide good prediction results, but the results obtained with the SOM maps are markedly better Also the main advantage of SOM maps is that they reach good results as a network unsupervised. It is much easier to train and interpret the results.

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.

Dynamic vaccine distribution model based on epidemic diffusion rule and clustering approach

Due to the fact that the emergency medicine distribution is vital to the quick response to urgent demand when an epidemic occurs, the optimal vaccine distribution approach is explored according to the epidemic diffusion rule and different urgency degrees of affected areas with the background of the epidemic outbreak in a given region. First, the SIQR （susceptible, infected, quarantined,recovered） epidemic model with pulse vaccination is introduced to describe the epidemic diffusion rule and obtain the demanded vaccine in each pulse. Based on the SIQR model, the affected areas are clustered by using the self-organizing map （SOM） neutral network to qualify the results. Then, a dynamic vaccine distribution model is formulated, incorporating the results of clustering the affected areas with the goals of both reducing the transportation cost and decreasing the unsatisfied demand for the emergency logistics network. Numerical study with twenty affected areas and four distribution centers is carried out. The corresponding numerical results indicate that the proposed approach can make an outstanding contribution to controlling the affected areas with a relatively high degree of urgency, and the comparison results prove that the performance of the clustering method is superior to that of the non-clustering method on controlling epidemic diffusion.

Retrieval of PM10 Concentration from an AOT Passive Remote-Sensing Station between 2003 and 2007 over Northern France

A method of retrieving PM10 particles concentrations at the ground level from AOT (Aerosol Optical Thickness) measurements is presented. It uses data obtained among five years during 2003 to 2007 summers in the Lille region (northern France). As PM10 concentration strongly depends on meteorological variables, we clustered the meteorological situations provided by the MM5 meteorological model forced at the lateral boundaries by the operational NCEP model in eight classes (local weather types) for which a robust statistical relationship between AOT and PM10 was found. The meteorological situations were defined by the hourly vertical profiles of temperature and (zonal and meridian) wind components. The clustering of the weather types were obtained by a self-organizing map (SOM) followed by a hierarchical ascending classification (HAC). We were then able to retrieve the PM10 at the surface from the AERONET AOT measurements for each weather type by doing non linear regressions with dedicated SOMs. The method is general and could be extended to other regions. We analyzed the strong pollution event that occurred during August 2003 heat wave. Comparison of the results from our method with the output of the CHIMERE chemical-transport model showed the interest to tentatively combine these two pieces of information to improve particle pollution alert.

基于小波变换的动态心电图波形特征聚类研究

研究了动态心电图（Holter）中的心电波形聚类,找到了占据大部分心电波形的基本波形.以二次样条小波变换（WT）方法检测Holter中的R波,从而确定完整心动周期的波形.同时根据WT找到心电波形中极值点及其相关斜率,利用自组织映射（SOM）神经网络进行心电波形的聚类,完成特征提取.通过实验表明,Holter的R波检测率达到99.5%,相对于基于人工神经网络、线性滤波器等方法要好;24 h的Holter中所包含的106次心电基本波形的识别率达到91.4%,达到了将心电数据分析量降为5～10 %的目的.