基于最小二乘支持向量机的农田水汽通量建模

支持向量机是在统计学习理论基础上发展起来的一种新型的机器学习方法,已在模式识别、非线性建模等领域中得到了应用．本文将最小二乘支持向量机方法应用于农田水汽通量的建模中,并同前馈反向传播神经网络的建模性能进行了比较．结果表明,最小二乘支持向量机方法具有可调参数少、学习速度较快等优点,具有更好的推广能力,以更高的精度建立农田水汽通量模型．模型的敏感性分析进一步显示,用最小二乘支持向量机方法建立的农田水汽通量模型是合理可行的．     

子代身高性别对父母身高的回归分析

对抽样调查的身高数据进行计量分析,建立了子代对亲代身高的回归分析模型,揭示了子代身高与亲代身高的遗传率;研究结果表明,父母身高对下一代的遗传率强度不同,母亲要强于父亲;子女接受遗传的效应也不一样,女儿要强于儿子;建立了性别遗传模型,深入研究了亲代父母之间的身高差对子代性别的影响,亲代身高差越大,则生女孩的几率就越大,反之生男孩的几率就越大．     

EXCEL在天然产物提取工艺中的应用

正交试验设计是天然产物研究中重要的方法之一,本文介绍了利用Microsoft EXCEL的内部统计函数编制天然产物提取工艺统计分析程序,并以实例说明了该程序的使用方法和应用技巧。结果表明,用户只需输入试验的原始数据,即可快速、准确地进行直观分析和方差分析,并可根据极差值得出最佳工艺条件,所得分析结果与专业统计分析软件DPS对数据进行正交分析相比,二者计算结果基本一致,且该方法不但快捷方便,操作简单,而且结果准确可靠,可大大提高天然产物提取工艺的效率。     

葡萄叶中总黄酮的提取工艺研究

目的：从葡萄叶中提取总黄酮。方法：采用正交试验法研究葡萄叶总黄酮的最佳提取工艺条件,考察了乙醇浓度、回流温度、回流时间及料液比四因素对葡萄叶总黄酮提取率的影响。结果：确立了葡萄叶总黄酮最佳提取条件为：45％的乙醇为溶剂、液料比为1：40、提取温度为60％、提取时间2h,在最佳工艺条件下葡萄叶总黄酮含量为5．329mg／g。     

海藻希瓦氏菌(Shewanella alga)发酵培养基条件优化的研究

目的:优化海藻希瓦氏菌生产河豚毒素的发酵培养基。方法:通过测定菌体密度(用OD600表示)和菌体收获量,研究了部分初始条件及添加不同营养物质对海藻希瓦氏菌生长的影响,采用单因素试验和正交试验对发酵条件进行了优化。结果:最适发酵初始pH为7.5,最适摇瓶装液量为150mL。通过正交试验找出最大影响因素为葡萄糖供应,优化后的培养基最佳配方为:在2216E培养基中添加1.0%葡萄糖、2.5%酵母粉、1.0%磷酸高铁。结论:优化后的培养基培养供试菌,菌体收获量比在2216E培养基中培养增加了2.012g.L-1。     

食用调和油中花生油含量的近红外光谱分析

采用偏最小二乘法(PLS)等方法建立了食用调和油中花生油含量定量分析的近红外光谱定标模型。采集食用调和油样品在4 000 cm-1~10 000 cm-1范围内的近红外漫反射光谱,光谱经一阶导数处理后,采用偏最小二乘法建立样品中花生油含量的定标模型,并用Leave-one-out内部交叉验证法对模型进行验证。模型相关系数为0.99961,校正均方根RMSEC为0.830%。比较不同光谱预处理方法对定标模型的影响,结果表明一阶导数Corr.coeff最好。采用不同的化学计量学方法建立的定标模型中以偏最小二乘回归法最理想。     

Quantitative structure-activity relationship study of bitter di- and tri-peptides including relationship with angiotensin I-converting enzyme inhibitory activity.

Bitterness represents a major challenge in industrial application of food protein hydrolysates or bioactive peptides and is a major factor that controls the flavor of formulated therapeutic products. The aim of this work was to apply quantitative structure-activity relationship modeling as a tool to determine the type and position of amino acids that contribute to bitterness of di- and tri-peptides. Datasets of bitter di- and tri-peptides were constructed using values from available literature, followed by modeling using partial least square (PLS) regression based on the three z-scores of 20 coded amino acids. Prediction models were validated using cross-validation and permutation tests. Results showed that a single-component model could explain 52 and 50% of the Y variance (bitterness threshold) of bitter di- and tri-peptides, respectively. Using PLS regression coefficients, it was determined that hydrophobic amino acids at the carboxyl-terminus and bulky amino acid residues adjacent to the carboxyl terminal are the major determinants of the intensity of bitterness of di- and tri-peptides. However, there was no significant (p > 0.05) correlation between bitterness of di- and tri-peptides and their angiotensin I-converting enzyme-inhibitory properties.     

用正交试验法优选二化螟人工饲料配方

采用15因子2水平正交试验,优选出1种二化螟Chilo suppressalis(Walker)人工饲料配方,筛选出影响二化螟发育的5个关键因子,分别是稻茎粉、麦芽粉、稻糠粉、酵母粉和蔗糖。其中稻茎粉、麦芽粉、酵母粉和稻糠粉影响二化螟的幼虫成活率,蔗糖和麦芽粉影响二化螟的幼虫历期,稻茎粉影响二化螟的蛹重。     

A novel bacterial community index to assess stream ecological health

相似文献   

Quantification of the effect of electrical and thermal parameters on radiofrequency ablation for concentric tumour model of different sizes

Radiofrequency ablation (RFA) has been increasingly used in treating cancer for multitude of situations in various tissue types. To perform the therapy safely and reliably, the effect of critical parameters needs to be known beforehand. Temperature plays an important role in the outcome of the therapy and any uncertainties in temperature assessment can be lethal. This study presents the RFA case of fixed tip temperature where we’ve analysed the effect of electrical conductivity, thermal conductivity and blood perfusion rate of the tumour and surrounding normal tissue on the radiofrequency ablation. Ablation volume was chosen as the characteristic to be optimised and temperature control was achieved via PID controller. The effect of all 6 parameters each having 3 levels was quantified with minimum number of experiments harnessing the fractional factorial characteristic of Taguchi’s orthogonal arrays. It was observed that as the blood perfusion increases the ablation volume decreases. Increasing electrical conductivity of the tumour results in increase of ablation volume whereas increase in normal tissue conductivity tends to decrease the ablation volume and vice versa. Likewise, increasing thermal conductivity of the tumour results in enhanced ablation volume whereas an increase in thermal conductivity of the surrounding normal tissue has a debilitating effect on the ablation volume and vice versa. With increase in the size of the tumour (i.e., 2–3 cm) the effect of each parameter is not linear. The parameter effect varies with change in size of the tumour that is manifested by the different gradient observed in ablation volume. Most important is the relative insensitivity of ablation volume to blood perfusion rate for smaller tumour size (2 cm) that is also in accordance with the previous results presented in literature. These findings will provide initial insight for safe, reliable and improved treatment planning perceptively.