基于主成分分析和径向基网络的水稻胡麻斑病严重度估测

对植被病害严重度的精确预测是采取植保措施的关键,同时对减少农药使用量也具有积极意义。该研究首先对叶片光谱反射数据进行重采样和求一阶、二阶微分,再用主成分分析PCA技术对上述变换光谱进行分析,最后结合径向基函数神经网络RBFN对水稻胡麻叶斑病严重度进行预测。将全部的光谱数据和病害严重度分为两组,75％用于网络训练,25％用作网络性能测试。文中对预测结果准确性有重要影响的径向基函数扩展速率和不同的数据处理方法进行了讨论,研究发现,一阶微分光谱经PCA压缩后,获得主分量光谱,输入RBN,病害严重度的预测均方根误差仅有7.73％。表明：主成分分析和径向基函数神经网络（PCA-RBFN）相结合,可以对水稻胡麻斑病严重度进行快速、精确的估算。     

考虑损失厌恶型顾客的产品推荐方法研究

随着电子商务和社交网络的快速发展,在线商品和服务的数量日益增长,顾客越来越难以依据在线信息制定其购买决策。本文基于数据体量较大的在线数值评分,构建产品推荐模型,帮助顾客成功定位所需商品。首先,引入直觉梯形模糊数进行数值评分转换,以处理历史用户给定评分数据的不确定性特征;其次,引入经典前景理论来刻画现实决策过程中顾客的损失厌恶心理。最后,通过汽车之家网站的汽车购买案例及与完全理性顾客推荐结果的对比分析,验证了该模型的实用性和有效性。     

基于指数标度的G1-概率系数法和熵的需求重要度修正

顾客需求重要度的获取是进行顾客需求综合分析过程的一个重要环节,它的确定对质量屋的优化以及之后的优化决策有着重要的作用.科学准确地计算顾客需求重要度有助于企业有针对性的生产满足顾客需求的产品,从而提高顾客满意度,增强市场竞争力.基于QFD理论,文章从顾客和专家双视角出发收集数据,采用指数标度的G1-概率系数法代替传统的权重概率综合系数法来确定顾客初始需求权重,并结合市场竞争性因素对初始需求权重进行修正,简单准确地确定了顾客需求重要度,并通过IT外包案例验证了该方法的实效性.     

多噪声源共同作用下的总烦恼度评价与预测

主要研究了多噪声源共同作用下的混合噪声烦恼度的评价过程与预测方法. 首先, 设计并完成了固定播放时长噪声样本作用下的烦恼度主观评价实验, 获得了人工合成的混合噪声样本作用下的混合噪声烦恼度(亦称总烦恼度) α_T 评价数据与构成混合噪声样本的所有单一噪声样本单独作用时的烦恼度α_i (i=1, 2, 3, ···, K; K为混合噪声样本中单一噪声样本的总数) 评价数据. 随后, 细致分析了两组评价数据之间的关系, 提出在已知α_i 的基础上利用多元线性回归模型预测α_T. 最后, 解决了如何确定模型中对应各α_i的权值ω_i (i=1, 2, 3, ···, K) 的问题. 研究表明, 以所提出的权值确定方法建立的多元线性回归预测模型 能够较为成功地预测混合噪声样本作用下的总烦恼度评价值.     

基于Matlab短时闪变严重度计算方法研究

随着电力市场的商品化发展，电能质量受到广泛关注．电压波动和闪变是电能质量的重要指标之一．按照国际电工标准规定．分析了电压波动与闪变检测的各个环节，在simulink下建立了闪变仪模型,依据生成视感度系数序列的大小，编制计算短时阗变严重度的程序，结果表明该算法简单．相对误差小，方法简便实用，统计精度高．     

基于索赔额与应负责任的奖惩系统

在机动车保险中，仅仅基于索赔次数的奖惩系统对那些有着小索赔的保单持有人不公平。在本文，我们考虑索赔额的大小及责任归属，建立一个基于索赔额与应负责任的奖惩系统。     

中子活化分析实验

本文给出一个关于中子活化分析的简易的实验方法。     

Tire load rating to reduce soil compaction

Both experience and research warn that heavily loaded wheels of agricultural transport vehicles and heavy machinery may cause severe compaction damage to the farmland. A remedy consists of reducing both the wheel load and the contact pressure.Early in the 1990s, the author suggested an experimental examination of the problem of soil compaction under fully controlled conditions. The ensuing research program, which was sponsored by the Grant Agency of the Czech Republic, included a series of experiments with loaded wheels carried out in the experimental grounds of the Czech University of Agriculture and, subsequently, their physical modelling in the laboratory of the Department of Motor Vehicles, Technical faculty. This program has corroborated the idea that physical modelling under controlled conditions, complemented by an adequate evaluation procedure, has a promising potential to predict full-scale ground compaction and become a sound basis for practical measures. This paper describes the laboratory equipment, testing technique, and the way of evaluating the compaction potential of tires in terms of soil dry bulk density, leading to a Compaction Number (CN) rating of individual tires. Practically, the CN rating is supposed to be included in agricultural tire catalogues to complement the load capacity/inflation pressure values for hard ground (e.g., ETRTO specifications based on tire strength and wear).     

Tail negative dependence and its applications for aggregate loss modeling

Tail order of copulas can be used to describe the strength of dependence in the tails of a joint distribution. When the value of tail order is larger than the dimension, it may lead to tail negative dependence. First, we prove results on conditions that lead to tail negative dependence for Archimedean copulas. Using the conditions, we construct new parametric copula families that possess upper tail negative dependence. Among them, a copula based on a scale mixture with a generalized gamma random variable (GGS copula) is useful for modeling asymmetric tail negative dependence. We propose mixed copula regression based on the GGS copula for aggregate loss modeling of a medical expenditure panel survey dataset. For this dataset, we find that there exists upper tail negative dependence between loss frequency and loss severity, and the introduction of tail negative dependence structures significantly improves the aggregate loss modeling.