基于BP神经网络的上市公司CEO报酬实证研究

近年来的研究表明,CEO报酬不仅受公司业绩的影响,还受到其他诸多因素的影响,而且,CEO报酬与其决定因素之间往往存在着非线性关系。本文以2003-2005年沪深股市的A股上市公司为样本,采用BP神经网络对CEO总报酬、CEO年薪、CEO持股价值及其决定因素分别进行训练和学习,结果表明：（1）网络训练输出值与实际值的拟合度分别达到91.09%、97.23%和78.44%;（2）网络的预测能力相对于传统的线性回归模型分别提高了92.72%、92.08%和53.89%。因此,本文认为在分析和确定CEO报酬水平时引入神经网络模型是可行的。     

供水管网水质评价方法的探讨及其应用

利用了模糊数学评价模型和综合指数评价模型分别对南方某市部分给水管网水质进行评价。评价结果分析表明,模糊数学评价法具有评价准确性好、操作简单的特点;综合指数法具有评价结果直观、精确度较高的优点。从评价结果上看,综合指数法较模糊数学评价法更为合理。     

密云水库流域2000-2005年植被覆盖度变化监测

植被是生态系统最重要的组成部分,而植被覆盖度是衡量地表植被状况的一个最重要的指标,是生态系统健康评价的前提和必要的基础。文章利用2000和2005年2个时相的Landsat 7 ETM+遥感影像为数据源,以BP神经网络法为植被覆盖度估算模型,计算了密云水库流域内不同时期的植被覆盖度,生成了该流域2个时相内的植被覆盖度图,以此分析密云水库流域植被覆盖度的时空变化。结果表明,从2000-2005年,密云水库流域内除无植被覆盖类型外(即水域部分),其余土地利用类型的植被覆盖度都呈增加趋势,其中以沙质地和耕地最为明显,分别增长了29.5%和27.3%,并且密云水库流域的平均植被覆盖度不高,尤其西部地区植被覆盖度较差,水土流失和土地沙化情况比较严重。     

“十二五”地表水国家环境监测网络吉林省水环境国控监测点位布设的构想

根据国家环境质量监测网络,对“十二五”地表水环境质量监测断面调整工作要求,吉林省在辖区内所有水环境质量监测断面及采样点基础上,完成了松花江流域和辽河流域国控监测断面的优化调整工作。在此过程中,如何从国家尺度上,既能充分反映吉林省水环境质量状况,又能满足国家对地表水环境管理需求进行了深入思考。本文以吉林省为例,在确定国控监测断面及采样点的布设中．提出了自己的构想和建议。     

基于MATLAB的BP神经网络模型在漠阳江水质评价中的应用研究

为提高水质评价的准确性,基于MATLAB及人工神经网络理论,采用误差反向传播的BP算法建立漠阳江水质评价模型,充分利用神经网络的非线性映射特性,取7项常规地表水水质评价指标对漠阳江水质进行评价,并将BP神经网络评价结果与单因子评价法及综合指数法的评价结果进行比较,网络运行结果表明一致效果良好.同时较传统的水质评价方法,该网络具有较高的识别精度,提高了水质评价等级的准确性,使评价的结果更具有科学性.     

瑞士土壤环境监测网络构建与运行对中国的启示

“十三五”期间,中国初步构建了国家土壤环境监测网并开展了监测工作。当前,国家层面土壤环境监测网络的构建和运行还处于起步阶段,笔者选取土壤环境监测开展较为成熟的瑞士土壤环境监测网(NABO)作为研究对象,综述了NABO的技术体系及多年来的土壤环境监测结果,并结合中国土壤环境监测工作现状进行讨论,认为NABO在监测网络建立、指标选取、数据分析等方面建立了较为成熟的技术体系,未来中国国家土壤环境监测网可在此方面借鉴瑞士经验。     

FTA在城市控制爆破工程事故中的运用

城市控制爆破工程采用电雷管网路起爆,极易发生爆破事故.运用FTA方法,编制了爆破事故树,并进行了定性分析.结合工程实际,提出了爆破事故的具体预防措施,更依法采取了爆破安全管理措施.     

Source characterization of ambient fine particles at multiple sites in the Seattle area

To identify major PM_2.5 (particulate matter ≤2.5 μm in aerodynamic diameter) sources with a particular emphasis on the ship engine emissions from a major port, integrated 24 h PM_2.5 speciation data collected between 2000 and 2005 at five United State Environmental Protection Agency's Speciation Trends Network monitoring sites in Seattle, WA were analyzed. Seven to ten PM_2.5 sources were identified through the application of positive matrix factorization (PMF). Secondary particles (12–26% for secondary nitrate; 17–20% for secondary sulfate) and gasoline vehicle emissions (13–31%) made the largest contributions to the PM_2.5 mass concentrations at all of the monitoring sites except for the residential Lake Forest site, where wood smoke contributed the most PM_2.5 mass (31%). Other identified sources include diesel vehicle emissions, airborne soil, residual oil combustion, sea salt, aged sea salt, metal processing, and cement kiln. Residual oil combustion sources identified at multiple monitoring sites point clearly to the Port of Seattle suggesting ship emissions as the source of oil combustion particles. In addition, the relationship between sulfate concentrations and the oil combustion emissions indicated contributions of ship emissions to the local sulfate concentrations. The analysis of spatial variability of PM_2.5 sources shows that the spatial distributions of several PM_2.5 sources were heterogeneous within a given air shed.     

基于神经网络的洪水预报研究

人工神经网络通过神经元之间的相互作用来完成整个网络的信息处理,具有自学习和自适应等一系列优点,因而用它来进行洪水预报是可行的.对洪水预报问题,初步建立了基于神经网络的洪水预报系统,给出了应用实例.     

Application of artificial neural network approach and remotely sensed imagery for regional eco-environmental quality evaluation

Eco-environment quality evaluation is an important research theme in environment management. In the present study, Fuzhou city in China was selected as a study area and a limited number of 222 sampling field sites were first investigated in situ with the help of a GPS device. Every sampling site was assessed by ecological experts and given an Eco-environment Background Value (EBV) based on a scoring and ranking system. The higher the EBV, the better the ecological environmental quality. Then, three types of eco-environmental attributes that are physically-based and easily-quantifiable at a grid level were extracted: (1) remote sensing derived attributes (vegetation index, wetness index, soil brightness index, surface land temperature index), (2) meteorological attributes (annual temperature and annual precipitation), and (3) terrain attribute (elevation). A Back Propagation (BP) Artificial Neural Network (ANN) model was proposed for the EBV validation and prediction. A three-layer BP ANN model was designed to automatically learn the internal relationship using a training set of known EBV and eco-environmental attributes, followed by the application of the model for predicting EBV values across the whole study area. It was found that the performance of the BP ANN model was satisfactory and capable of an overall prediction accuracy of 82.4%, with a Kappa coefficient of 0.801 in the validation. The evaluation results showed that the eco-environmental quality of Fuzhou city is considered as satisfactory. Through analyzing the spatial correlation between the eco-environmental quality and land uses, it was found that the best eco-environmental areas were related to forest lands, whereas the urban area had the relatively worst eco-environmental quality. Human activities are still considered as a major impact on the eco-environmental quality in this area.