基于随机森林特征优选的雪茄烟叶晾制过程含水率预测

针对雪茄烟叶晾制过程含水率人工判断主观性强、准确度低等不足,以及对影响雪茄烟叶晾制过程含水率预测的重要表观特征尚不明确等问题,该研究基于图像特征提取以及机器学习技术实现雪茄烟叶晾制过程含水率的预测。试验以雪茄烟品种“云雪2号”为试验材料,获取晾制过程的烟叶图像的颜色、轮廓、纹理以及部位四类特征并筛选出雪茄烟叶含水率预测的优选图像特征子集。在此基础上,构建了随机森林（random forest, RF）、支持向量机（support vector regression, SVR）与反向传播神经网络（back propagation neural network, BPNN）模型,并利用遗传算法（genetic algorithm, GA）对各模型超参数进行优化,将原始图像特征集与优选图像特征集输入3个机器学习模型,构建出6种模型-特征组合方案,依据晾制时期对原始数据集进行划分,并对测试集进行预测。最终结果显示：GA-SVR模型+优选图像特征子集的组合方案在测试集上表现最优,其决定系数（coefficient of determination,r²）与均方误差（mean square error,MSE）分别为0.980和0.001,且运行时间最短（运行时长=0.128 s）。研究结果可为雪茄烟叶晾制过程智能化控制提供理论依据。     

灰色系统理论在柽柳属植物扦插繁殖筛选中的应用

采用灰色系统关联度分析方法,分析并计算了8个柽柳属植物种之间的关联度以及它们扦插繁殖中的7个观测指标值间的关联度大小,结果表明:柽柳枝条扦插繁殖观测指标间的关联度大小顺序是茎粗>地上生物量>主根长>株高>侧根数>一级分枝数;柽柳种间的关联度大小顺序是中国柽柳>甘肃柽柳>甘蒙柽柳>刚毛柽柳>短穗柽柳>长穗柽柳>紫杆柽柳>多枝柽柳,关联度的大小可以反映出柽柳种间及扦插繁殖观测指标间的主次顺序。     

Improvement of Appearance Traits of elite Rice Zhenshan 97B by Molecular Introgression of Targeted about 800 kb Interval from Indica Rice Jiafuzhan Genome

Rice appearance trait is mainly mean grain length (GL), grain width (GW), ratio of length and width (L/W), chalkiness (CH) and transparence (TR). Appearance is the first impression, and rice appearance traits effect significantly the value of commodity. Hybrid rice is relatively low quality, especially on rice appearance quality,which restricts partially its extend and badly export of hybrid seed and rice in China.Shanyou 63, the most famous hybrid rice combination of China, could not be also sustainable application because of its poor qualities. In this studies, We attempt to improve appearance quality of the elite rice maintainer of Zhenshan 97B by using molecular approach of genomic interval targeted introgression. Three F2 populations were constructed to study the classical and molecular genetic of rice appearance traits, at the same time, molecular marker-asisted toimprove the main maintainer line, Zhenshan 97B were performed. There some following results:Three F2 populations were constructed based on crosses of Guangluai 4×Jiafuzhan (GJ popu.), Minghui 86×Jiafuzhan (MJ popu.) and Zhenshan 97B×Jiafuzhan (ZJ popu.). ZJ popu and GJ popu were produced to reconstruct the linkage maps related with rice appearance traits based on BSA, and detect QTL of target traits based on IM.In ZJ popu, 9 QTLs of target traits were detected. The interval, RM169～RM516 on Chromosome 5, was genetic locus of GW, L/W, CH and BW, and the explained variances were 10.9%, 14.9%, 12.0% and 14.2%, respectively.RM214 on chromosome 7, RM339 on chromosome 8 were genetic loci if CH and BW, and the explained variances were 9.4%, 10.0%, 11.0% and 12.1%. besides there is a genetic locus, RM347, of G/W on chromosome 3, and the explained varance was 10.3%. In GJ popu, 5 QTLs of rice appearance traits were detected. The interval, RM169-RM516 on Chromosome 5, were also the genetic loci of GW, CH and BW, and the explained variances were 9.0%, 12.5%, and 13.6%, respectively. RM264～RM80 on chromosome 8 was the genetic loci of GW amd L/W,and the explained variances were 14.7% and 13.4%. The genotypes of all QTLs, except RM214, from Jiafuzhan contributed to improving riee appearance traits.The research was to improve the rice appearance quality of Zhenshan 97B by introgressing QTLs of rice appearance traits from Jiafuzhan, a donor parent, by means of MAS in the process of recurrent backcrossing, 4 SSR markers were used to detect the target genotypes from donor parent, and 70 SSR primers to identify the genetic background of recurrent parent. Consequently, there were 19 target individuals in BC3, in which the mean value of GL, GW, L/W, CH and BW were 6.06±0.04mm, 2.50±0.02mm, 2.43±0.02, 29.5±2.7 and 29.4±2.7%, respectively,and the mean homologous degree (HD) to recurrent parent is up to 98.22%. Compared to Zhenshan 97B, GL, CH and BW decreased 0.17 mm, 34.9% and 34.5% respectively and however L/W increased 0.19. which accounted separately for 25.37%, 54.79%, 54.57% and 10.50% of thedifference of every trait between two parents. It is very luckly to find a individual, 13BC2-3BC3 line, whose GL, GW, G/W, CH and BW were 6.04 mm, 2.43 mm, 2.49,2.5% and 2.5% separately, There is very important signification for it to be used in hybrid rice breeding improving appearance traits. In the research, MAS efficiency of 3 loci (with 4 markers ) was 5.68% and coincident degree was 73.08%.     

宝龙店水曲柳无性系生长早期评价

以28个水曲柳无性系为材料,测定其树高、胸径生长性状,进行变异分析,筛选出优良无性系.结果表明:各无性系的树高、胸径极显著相关(P<0.01),无性系间树高、胸径差异均达极显著差异水(P<0.01).以20％的入选率,初选出无性系1333、1311、1322、1312、1321和1323为优良无性系,6个无性系平均树高...     

羊链球菌CVCC55001、CVCC55002株的制备与鉴定

为研究羊链球菌CVCC55001、CVCC55002株的菌种特性,制备了新的菌种批并对其形态及生化特性、培养特性、血清学特性、真空度、纯粹、剩余水分、毒力及免疫原性等进行鉴定,对其适宜培养基进行了筛选.试验结果表明,该冻干菌种的形态及生化特性、培养特性、血清学特性、真空度、纯粹、剩余水分、毒力及免疫原性均符合《中华人民...     

Use of genomic recursions and algorithm for proven and young animals for single‐step genomic BLUP analyses – a simulation study

The purpose of this study was to examine accuracy of genomic selection via single‐step genomic BLUP (ssGBLUP) when the direct inverse of the genomic relationship matrix ( G ) is replaced by an approximation of G ^?1 based on recursions for young genotyped animals conditioned on a subset of proven animals, termed algorithm for proven and young animals (APY). With the efficient implementation, this algorithm has a cubic cost with proven animals and linear with young animals. Ten duplicate data sets mimicking a dairy cattle population were simulated. In a first scenario, genomic information for 20k genotyped bulls, divided in 7k proven and 13k young bulls, was generated for each replicate. In a second scenario, 5k genotyped cows with phenotypes were included in the analysis as young animals. Accuracies (average for the 10 replicates) in regular EBV were 0.72 and 0.34 for proven and young animals, respectively. When genomic information was included, they increased to 0.75 and 0.50. No differences between genomic EBV (GEBV) obtained with the regular G ^?1 and the approximated G ^?1 via the recursive method were observed. In the second scenario, accuracies in GEBV (0.76, 0.51 and 0.59 for proven bulls, young males and young females, respectively) were also higher than those in EBV (0.72, 0.35 and 0.49). Again, no differences between GEBV with regular G ^?1 and with recursions were observed. With the recursive algorithm, the number of iterations to achieve convergence was reduced from 227 to 206 in the first scenario and from 232 to 209 in the second scenario. Cows can be treated as young animals in APY without reducing the accuracy. The proposed algorithm can be implemented to reduce computing costs and to overcome current limitations on the number of genotyped animals in the ssGBLUP method.     

图牧吉自然保护区白鹤秋季觅食地生境初步研究

2004年8～9月采用定点观察法、GPS定位法和样方法对内蒙古扎赉特旗图牧吉国家级自然保护区白鹤的秋季停歇期的觅食地生境进行了调查研究,数据分析结果显示：在201个实验样方和201个对照样方中,苔草高度、芦苇高度、香蒲高度、植被盖度和植被密度的t值均小于0．05,存在显著或极显著差异;另外,主成分分析结果显示,前4个主成分的累积贡献率达到56．652％,在第一主成分中,水稗草高度和水流状况的贡献率较高;在第二主成分中,水深和水透明度的贡献率较高;在第三主成分中,香蒲高度和植被密度的贡献率较高：在第4主成分中,苔草高度的贡献率较高。     

Short communication: investigation of the feasibility of genomic selection in Icelandic Cattle

Icelandic Cattle is a local dairy cattle breed in Iceland. With about 26,000 breeding females, it is by far the largest among the indigenous Nordic cattle breeds. The objective of this study was to investigate the feasibility of genomic selection in Icelandic Cattle. Pedigree-based best linear unbiased prediction (PBLUP) and single-step genomic best linear unbiased prediction (ssGBLUP) were compared. Accuracy, bias, and dispersion of estimated breeding values (EBV) for milk yield (MY), fat yield (FY), protein yield (PY), and somatic cell score (SCS) were estimated in a cross validation-based design. Accuracy (r^) was estimated by the correlation between EBV and corrected phenotype in a validation set. The accuracy (r^) of predictions using ssGBLUP increased by 13, 23, 19, and 20 percentage points for MY, FY, PY, and SCS for genotyped animals, compared with PBLUP. The accuracy of nongenotyped animals was not improved for MY and PY, but increased by 0.9 and 3.5 percentage points for FY and SCS. We used the linear regression (LR) method to quantify relative improvements in accuracy, bias (Δ^), and dispersion (b^) of EBV. Using the LR method, the relative improvements in accuracy of validation from PBLUP to ssGBLUP were 43%, 60%, 50%, and 48% for genotyped animals for MY, FY, PY, and SCS. Single-step GBLUP EBV were less underestimated (Δ^), and less overdispersed (b^) than PBLUP EBV for FY and PY. Pedigree-based BLUP EBV were close to unbiased for MY and SCS. Single-step GBLUP underestimated MY EBV but overestimated SCS EBV. Based on the average accuracy of 0.45 for ssGBLUP EBV obtained in this study, selection intensities according to the breeding scheme of Icelandic Cattle, and assuming a generation interval of 2.0 yr for sires of bulls, sires of dams and dams of bulls, genetic gain in Icelandic Cattle could be increased by about 50% relative to the current breeding scheme.     

比较机器学习等算法对肉鸡产蛋性状育种值估计的准确性

我国白羽肉鸡育种中,通过遗传途径提高产蛋数和控制合适的蛋重是培育优良品系的一个重要方面。为探索适合我国白羽肉鸡育种中的基因组选择模型,本研究以2 474只白羽肉鸡品系的产蛋性状为研究对象,主要分析了机器学习算法KAML、BLUP(包括：PBLUP、GBLUP、SSGBLUP)和Bayes(包括：Bayes A、Bayes B和Bayes Cπ)方法对产蛋数和蛋重性状的预测准确性,准确性以5倍交叉验证进行评估。利用系谱以及基因组信息估计了产蛋数和蛋重性状的遗传力和遗传相关。结果表明,产蛋数性状遗传力为0.061~0.16,属于低遗传力性状;蛋重遗传力为0.28~0.39,属于中等遗传力性状;产蛋数与蛋重是中等遗传负相关(-0.518~-0.184),不同阶段产蛋数之间是强的遗传正相关(0.736~0.998)。不同模型预测43周产蛋数和52周蛋重的育种值估计准确性结果表明,KAML方法对两者的预测准确性分别为0.115和0.266,与GBLUP方法(准确性分别为0.118和0.283)和SSGBLUP方法(准确性分别为0.136和0.259)的准确性差异显著,同时显著低于Bayes方法(准确性分别为0.230~0.239、0.336~0.340)的预测准确性, PBLUP方法预测准确性最低(准确性分别为0.095和0.246)。因此,在白羽肉鸡产蛋数和蛋重性状中应用Bayes方法将获得最高的育种值估计准确性。     

草坪草引种观察与筛选

为满足绿化和水土保持对优良草坪草的需求，引进了草坪草种进行田间种植，并对其生物性状和抗逆性能进行观察，以从中筛选出优良的草坪草种。经过２年的观察，初步筛选出优良草坪草种－台湾草坪草；既可饲用、又可固土的优良草种－百喜草；饲用、草坪兼用的优良草种－早熟禾；饲用、草坪、固土多用型的优良草种－苇状羊茅。这几种草坪草种均具有绿化和水土保持作用。