一种基于可见-近红外光谱快速鉴别茶叶品种的新方法

提出了一种用可见-近红外光谱技术快速无损鉴别茶叶品种的新方法。应用可见-近红外光谱仪测定5个品种茶叶的光谱曲线,用主成分分析法对不同品种茶叶进行聚类分析并获得茶叶的可见-近红外光谱数据的主成分,再结合人工神经网络技术建立模型进行品种鉴别。主成分分析表明,以主成分1和2对所有建模样本的得分值做出的得分图,对不同种类茶叶具有较好的聚类作用,可以定性分析茶叶种类。把主成分分析得到的前6个主成分作为神经网络的输入,茶叶品种值作为神经网络的输出,通过5个茶叶品种共125个样本的训练和学习,建立了茶叶品种鉴别的3层BP人工神经网络模型,对未知的25个样本进行鉴别,品种识别准确率达到100%。说明本文提出的方法具有很好的分类和鉴别作用,为茶叶的品种快速鉴别提供了一种新方法。     

Top Varieties of Generalized MV-Algebras and Unital Lattice-Ordered Groups

In spite of the well-know fact that the system of ?-groups with strong unit (unital ?-groups) does not form a variety, there is a categorical connection between the category of unital ?-groups and the variety of generalized MV-algebras which enables us to naturally export equational machinery and terminology like “variety” from the latter category to the former.

Using this categorical equivalence, we study varieties, or equationally defined classes, and top varieties, varieties above the normal valued variety, of both structures. We generalize Chang's Completeness Theorem for generalized MV-algebras, and formulate some open questions for both structures.     

Periods of generalized Fermat curves

Let $k,n\ge 2$ be integers. A generalized Fermat curve of type $(k,n)$ is a compact Riemann surface S that admits a subgroup of conformal automorphisms $H\le \text{Aut}(S)$ isomorphic to ${\mathbb{Z}}_k^n$, such that the quotient surface $S/H$ is biholomorphic to the Riemann sphere $\stackrel{?}{\mathbb{C}}$ and has $n+1$ branch points, each one of order k. There exists a good algebraic model for these objects, which makes them easier to study. Using tools from algebraic topology and integration theory on Riemann surfaces, we find a set of generators for the first homology group of a generalized Fermat curve. Finally, with this information, we find a set of generators for the period lattice of the associated Jacobian variety.     

On ordered categories as a framework for fuzzification of algebraic and topological structures

Using the framework of ordered categories, the paper considers a generalization of the fuzzification machinery of algebraic structures introduced by Rosenfeld as well as provides a new approach to fuzzification of topological structures, which amounts to fuzzifying the underlying “set” of a structure in a suitably compatible way, leaving the structure itself crisp. The latter machinery allows the so-called “double fuzzification”, i.e., a fuzzification of something that is already fuzzified.     

基于DS算法的玉米近红外定性分析光谱校正方法研究

从校正的角度出发,研究了近红外定性分析中模型稳定性问题。以13个玉米品种为研究对象,针对数据采集时间不同带来的模型失效问题,借鉴近红外光谱定量分析中两台仪器间模型传递的思想,将直接模型传递(Direct Standardization)算法用于校正同一仪器不同时间采集的光谱, 使得一次建立的品种鉴别模型,能用于其余时间测试数据的鉴别。首先采用Kennard/Stone算法在主光谱集中选取校正样品集,按照对应的编号从从光谱集中取出对应的数据,然后对校正样品集采用DS算法求取两组数据间的变换关系,再对剩余的从光谱集进行相应的变换得到适用于模型的光谱。实验中对比了校正样本数和模型校正位置对校正结果的影响,分别从品种定性鉴别准确性和校正前后主光谱数据和从光谱数据分布距离两方面分析了实验结果。结果表明,该方法能有效地解决同一仪器随着采样时间推移产生的光谱偏移现象,对采样时间不同的测试集均得到较高的识别率,提高了模型的鲁棒性和适用范围,由实验结果可见,校正位置处于特征提取之后时,校正效果最佳。     

玉米品种近红外光谱鉴别技术中的参数漂移问题研究

以13个玉米品种鉴别为研究对象,提出了一种解决光谱仪参数漂移问题的有效方法。使用同一台光谱仪分不同时间重复采集数据,用一天数据建模,其余测试,发现不同时间采集的数据有较大偏移,严重时正确识别率仅为7.69%。为此,提出一种有监督学习特征提取的多天联合建模方法,首先挑选具有代表性的多个时间段样本数据共同组成建模集,其次采用PLS+LDA特征提取算法,提取出与仪器参数漂移无关的品种特征信息, 然后采用BPR方法建立品种鉴别模型。实验结果表明,该方法对于不同时间数据的偏移均能有较好的校正效果,得到较高的识别率和稳定性。     

基于独立组分分析和BP神经网络的可见/近红外光谱蜂蜜品牌的鉴别

提出了一种基于独立组分分析的可见/近红外光谱透射技术快速鉴别蜂蜜品牌的新方法。用独立组分分析方法获取蜂蜜的可见/近红外光谱载荷图,将载荷图中相关性最大的波段,作为人工神经网络的输入建立蜂蜜品牌的鉴别模型。建立了一个三层的BP神经网络模型,各层传递函数采用S型(Sigmoid)函数,并设置网络输入层节点数为9,隐含层节点数为10,输出层节点数为3。每个品牌25个样本,3个品牌共75个样本,用来建立BP神经网络模型,剩余的3个品牌各５个样本用于预测,鉴别准确率达100%,模型的拟合残差为8.245 365×10-5。说明基于独立组分分析的方法具有很好的鉴别效果,为蜂蜜的品牌鉴别提供了一种新方法。     

Hypersolvable Groups

Call a group G hypersolvable if it has an ascending series with G/C_G(A) solvable for each factor A of the series. In this article we establish some basic facts about hypersolvable groups. We also prove that if G is a perfect Fitting p-group such that every proper subgroup is contained in a proper normal subgroup, then G has a proper non-hypersolvable subgroup.     

Varieties of semigroups with non-trivial identities on subsemigroup lattices

The present notice is devoted to the characterization up to the group case of varieties of semigroups whose subsemigroup lattices satisfy non-trivial identities. Received November 2, 1999; accepted in final form April 23, 2000.