基于模糊神经网络的池塘溶解氧预测模型

在分析了池塘溶解氧影响因素的基础上,利用模糊神经网络良好的非线性逼近能力建立了池塘溶解氧的模糊神经网络预测模型。神经网络模型如采用常规的BP或其它梯度算法,常导致训练时间较长且易陷入局部极小点,本实验采用快速的粒子群优化算法对模糊神经网络进行训练,收敛速度明显加快。实验结果表明采用该方法预报溶解氧的预测精度较常规BP递推算法的预测精度明显提高,所采用的模型能对溶解氧进行可靠的预测,该方法为研制开发智能水质检测仪以及工厂化养殖工作奠定了基础,对实际生产具有一定的指导意义。     

基于“3S”技术的辽宁省某尾矿库扩容工程生态影响预测与评价

以辽宁省某尾矿库为例,基于GIS技术,利用2010年的TM遥感影像及地形图,预测该尾矿库扩容后的生态影响。分析结果显示:尾矿库扩容工程对生态的影响主要体现在土地利用、植被、生态景观和地形地貌的变化4个方面。     

Bioinformatics Analysis of Bone Morphogenetic Protein 4 (BMP4) of Sheep

The assay was aimed to explore the biological characteristics of bone morphogenetic protein 4 (BMP4) of sheep,NCBI,DNAMAN DNAStar,TMHMM Server v.2.0,PsortⅡ,SignalP various bioinformatical softwares were used to speculate the physical and chemical properties,hydrophobic property,phosphorylation site,conservative structure domain,protein secondary structure of BMP4 protein.Also,the three-dimensional structure was forecasted with the SWISS-MODEL Workspace software.The results indicated that the BMP4 of sheep had high homologies with the BMP4 of various species.The encoded protein was a hydrophilic protein which was unstable.There was no transmembrane regions and it was likely to be located in the nucleus.What was more,there was signal peptide and eighteen phosphorylation sites.Through the forecast of functional domains,the protein had two functional domains,including the transforming growth factor-beta (TGF-beta) superfamily and TGF-beta propeptide superfamily.The result was consistent with the function of BMP4 gene family,it also demonstrated that BMP4 was a growth factor and it had the function of signal transduction.The amino acid homology between the predicted 3D structure of protein and template 3bmp.1.A was 88.29%.The bioinformatics analysis of BMP4 gene could provide reference for the further study in practice.     

基于贡献度随机森林模型的公司债信用风险实证分析

运用贡献度随机森林方法（CRF）方法探讨公司债财务指标比率与其违约率的关系.运用连续属性离散化方法（OB）进行财务指标最优降维；运用WOE变换进行模型变量约简.研究表明，CRF模型的分类性能显著优于其他模型，测试集评估总体正确率达90.47%，AUC统计量、AR比率及K-S值分别提升了2.6%、7.6%、4.38%，变量贡献度量化了各财务指标对违约率影响，为诠释随机森林预测机制提供了依据.     

基于Lasso和BP神经网络的组合预测及其应用——以居民消费支出预测为例

在变量选择的基础上，构建基于Lasso方法和BP神经网络的预测模型，并对我国城乡居民的消费支出进行预测，结果显示：基于Lasso方法和BP神经网络的组合预测精度要明显高于BP神经网络、Lasso方法的预测精度；在2014~2020年，我国农村居民消费增长率有所提升，城镇居民消费增长率减缓，城乡居民消费增长率之间的差距呈下降趋势，但短期内城乡居民消费差距依然难以缓和。     

花生黄曲霉生长预测模型的研究

通过对分离自花生的黄曲霉LYYSS03-3在不同温度(15-35℃)、不同相对湿度(水活度分别为0.5,0.7,0.9)下的菌落生长特性进行检测,采用Boltzmann和Logistic 模型对黄曲霉的生长曲线进行拟合,结果表明,在适宜温湿度阶段,花生黄曲霉的生长曲线更适合用Boltzmann模型拟合.     

土耳其斯坦裂体吸虫23kDa蛋白基因的序列分析及抗原表位预测

为研究土耳其斯坦裂体吸虫23 kDa蛋白的生物学特性,以土耳其斯坦裂体吸虫cDNA为模版,利用PCR对23 kDa基因进行扩增,并将其克隆到T-easy载体后进行序列测定。利用生物信息学对其结构、抗原指数进行分析,并对其抗原表位进行预测。序列分析结果表明,该虫体的23 kDa基因长度为657 bp,A+T含量为57.38%,与曼氏血吸虫、埃及血吸虫和日本血吸虫的23 kDa基因的相似性分别为85.24%、83.71%和81.89%。蛋白二级结构分析表明,23 kDa蛋白经过4次跨膜,主要由6个α-螺旋、3个β-折叠、7个β转角和若干个无规则卷曲构成。抗原表位预测结果表明,该蛋白有3个B细胞抗原表位。综合分析土耳其斯坦裂体吸虫23 kDa蛋白是一种较好的抗原分子,是土耳其斯坦裂体吸虫疫苗的重要候选分子。     

湘西北长果安息香种群数量与分布格局

对湖南石门壶瓶山景关门、桑植龙潭坪茅垭村样地的长果安息香(Changiostyrax raxdolichocarpa)种群数量和分布格局进行调查和分析。结果表明：长果安息香种群的年龄结构呈衰退型，个体数量主要集中在小树(IV龄段)，幼龄级株数和老龄级株数匮乏；长果安息香种群在进入生理死亡年龄前有2个死亡高峰，第1个峰值产生于幼树(II、III龄段)，主要原因是种内和种间竞争(主要是光照)，第2个峰值产生于中树长成大树阶段(V、VI龄段)，除种内、种间对环境的竞争外，生长地土层浅薄、大树倒伏及人为砍伐亦加剧了该峰值的产生；种群整体呈聚集分布类型，小树向中树、大树变化过程表现出聚集分布向随机分布转变，导致长果安息香濒危的主要原因是种子萌发率极低、种群竞争能力较差以及人为干扰等。     

Analysis on Target Genes with Mutation in microRNA of Blue-shelled Chicken and White Leghorn

The study was conducted to explore the potential different characters between Blue-shelled chicken and White leghorn.Global genome microRNA was combined the identified microRNA with complementary lab-predicted microRNA.Then the two breed chicken's SNP data got by GGRS were mapped to the microRNA and focused on SNP that deliberately located in mature-microRNA.Bioinformatics method was adopted for target prediction on microRNA which had SNPs.By further gene enrichment analysis,the study found these genes enriched in 22 GO terms,10 KEGG pathways,and 3 IPA important networks.And they enriched in traits which associated with growth,such as mTOR signaling pathways,Wnt signaling pathways,growth hormone receptor networks and insulin-like growth factor Ⅰ receptor networks.And they also enriched in some laying traits,such as oocyte meiotic signaling pathways and progesterone mature oocytes signaling pathways.The methods and the results might provide references for further studies.     

抗旱、耐盐碱、矮秆陆地棉数量性状的遗传相关及主成份分析

对从国内外引进的抗旱、耐盐碱、矮杆棉花资源材料 ,经抗旱、耐盐碱、矮杆性鉴定和比较 ,选取了其中表现较好的 1 9份材料 ,进行了遗传相关和主成份分析 ,结果表明 :在 5 0 mmol· L- 1Na Cland1 0 0 mmol· L- 1Na Cl胁迫下的出苗率间呈正相关 ,抗盐性与产量间呈负相关 ;第一棉铃高度与纤维品质性状呈正相关。抗旱、耐盐碱、矮杆棉花材料的前 6个因子贡献率达 86.5 % ,其分别为第一棉铃高度因子、果枝数因子、单株结铃数因子、矮杆因子、单铃重因子等