Demographics of cattle positive for Mycobacterium avium subspecies paratuberculosis by faecal culture,from submissions to the Cork Regional Veterinary Laboratory

The demography of bovine infections caused by Mycobacterium avium subspecies paratuberculosis (MAP) in Ireland is poorly defined. The objective of this study was to describe the demographics of cattle positive to MAP on faecal culture, based on submissions to the Cork Regional Veterinary Laboratory (Cork RVL) from 1994 to 2006. The study focused on all available faecal samples from adult cattle with non-responsive chronic diarrhoea that were submitted by private veterinary practitioners to Cork RVL for MAP culture. For each MAP-positive by faecal culture animal, data were collated from Cork RVL and Cattle Movement Monitoring Scheme (CMMS) records. Johne's disease (JD) was confirmed in 110 animals from 86 herds by the Cork RVL between 1994 and 2006, with a rate of positive cases between 15% and 18% over last four years of the study. Two breeds (Holstein/Friesian or Limousin) made up 78% of submissions. Movements were assessed for the 57 study animals with available movement information, 90% died within one year of the test and 26% tested positive in the herd they were born into. The study provides preliminary information about movement trends and demographics of animals with MAP positive submissions. Although the study area is restricted, it includes the most intensive (and economically-important) dairy region in Ireland. The demographics of JD infection from the study area are in agreement with international reports. Further work is required to determine demographic trends, incidence and prevalence of JD throughout Ireland. It is hoped this work may contribute to the development of a surveillance strategy for MAP by regional veterinary laboratories.     

大学生网络道德问题的诊断及调控对策

网络的迅猛发展带来了丰富的资源和交往的便利,也造成部分大学生网络道德情感冷漠、网络道德意识薄弱、网络道德信念缺失及网络道德行为失范等一系列问题。而网络主体、网络外部环境及网络技术是造成网络道德问题的根源。加强大学生的道德教育,构建社会、学校、家庭"三位一体"网络道德教育模式,加快网络信息技术研究,加强网络道德教育监管,强化网络道德规范,是加强大学生网络道德教育的有效措施。     

Egg production forecasting: Determining efficient modeling approaches

Several mathematical or statistical and artificial intelligence models were developed to compare egg production forecasts in commercial layers. Initial data for these models were collected from a comparative layer trial on commercial strains conducted at the Poultry Research Farms, Auburn University. Simulated data were produced to represent new scenarios by using means and SD of egg production of the 22 commercial strains. From the simulated data, random examples were generated for neural network training and testing for the weekly egg production prediction from wk 22 to 36. Three neural network architectures-back-propagation-3, Ward-5, and the general regression neural network-were compared for their efficiency to forecast egg production, along with other traditional models. The general regression neural network gave the best-fitting line, which almost overlapped with the commercial egg production data, with an R(2) of 0.71. The general regression neural network-predicted curve was compared with original egg production data, the average curves of white-shelled and brown-shelled strains, linear regression predictions, and the Gompertz nonlinear model. The general regression neural network was superior in all these comparisons and may be the model of choice if the initial overprediction is managed efficiently. In general, neural network models are efficient, are easy to use, require fewer data, and are practical under farm management conditions to forecast egg production.     

BP人工神经网络在家蚕杂交组合预测中的应用初探

利用前馈神经网络(BPANN)建立了家蚕杂种一代的6个经济性状的预测模型,通过验证得出,以双亲成绩作为输入神经元,利用BPANN模型预测杂种一代6个经济性状的平均预测误差均在5%左右。表明利用神经网络模型用来预测杂种一代成绩具有研究应用前景。     

PERT网络模型在家禽规模养殖项目管理中的运用

本文针对农业科技专家大院草科鸡规模养殖项目运行和管理中存在的问题,就优化农业科技项目管理与提高项目运行的效用和功能,提出采用PERT网络模型管理农业科技项目的思路,并对项目管理过程、方法及注意事项等问题提出了建议。本文指出,运用科学的管理方法制定合理的项目运行计划,是进行科技项目组织管理、科学地配置资源和促进科研项目顺利完成的重要途径。     

基于ResNet-CA的鱼群饱腹程度识别方法

投喂作为水产养殖过程中的一个关键环节,饵料的投喂量直接影响水产品的质量和养殖成本。然而,目前的投喂方法包括人工投喂和机器定时定量投喂,大多依靠人工经验,很难实现精准投喂。本文基于改进的ResNet34识别鱼群不同的饱腹程度。根据鱼群在不同饱腹阶段表现的摄食行为创建了含有5种不同饱腹程度的数据集,并采用数据增强操作对图像进行预处理。其次在原始模型ResNet34的基础上,本文提出使用坐标注意力机制,使模型在对图像进行特征提取的过程中能够做到专注于更大区域范围。并且使用深度可分离卷积的方式来代替传统卷积,减少模型参数量。为了评估改进的有效性,分析了改进后的模型在鱼群饱腹程度数据集上的性能,并将其与原模型ResNet34、AlexNet、VGG16、MobileNet-v2、GoogLeNet等经典卷积神经网络架构进行比较。综合实验结果表明,该模型相较于原模型参数量减少46.7%,准确率达到93.4%,相较于原模型提升3.4个百分点,同时改进后的模型在准确率、精确度、召回率等方面也都优于其他卷积神经网络。综上所述,本模型实现了性能与参数量之间的良好平衡,为后续模型在实际养殖环境中的部署并指导养殖户改善和制定投喂策略提供了可能。     

不同类型土壤的光谱特征及其有机质含量预测

 【目的】构建适合土壤有机质含量估测的高光谱参数及定量反演模型。【方法】系统分析中国中、东部地区5种不同类型土壤风干样本有机质含量与350～2 500 nm波段范围高光谱反射率之间的关系,利用特征光谱参数和BP神经网络建立土壤有机质的定量估测模型。【结果】光谱一阶导数构成的两波段光谱参数与土壤有机质含量的相关性明显优于原始光谱,尤其采用Norris平滑滤波后导数光谱效果更好。光谱参数构成形式以差值指数最好,其次为比值和归一化指数。与土壤有机质含量相关程度最高的光谱参数是由可见光区554 nm和近红外区1 398 nm两个波段的一阶导数组合而成的差值指数DI(D554,D1398),两者呈显著指数曲线关系,拟合方程为y= 184.2 ×exp[-1297×DI(D554,D1398)],决定系数为0.90。经不同类型土壤的观测资料检验,模型预测决定系数为0.84,均方根误差RMSE为3.64,相对分析误差RPD为2.98,显示估测模型具有较好的预测精度。另外,利用BP神经网络结合偏最小二乘法(PLS)对导数光谱进行分析,提取贡献率达到99.56 %的前6个主成分建立了三层BP 神经网络模型,模型决定系数为0.98,经不同类型土壤的观测资料检验,模型预测决定系数为0.96,RMSE为2.24,相对偏差RPD为4.83。比较利用DI(D554,D1398)和BP网络进行土壤有机质含量的预测结果,前者精度低于后者,但可以满足土壤有机质监测的需要。【结论】利用差值光谱指数DI(D554,D1398)和BP神经网络模型均可实现对土壤有机质的精确估测。     

An overview of animal science research 1945–2011 through science mapping analysis

The conceptual structure of the field of Animal Science (AS) research is examined by means of a longitudinal science mapping analysis. The whole of the AS research field is analysed, revealing its conceptual evolution. To this end, an automatic approach to detecting and visualizing hidden themes or topics and their evolution across a consecutive span of years was applied to AS publications of the JCR category ‘Agriculture, Dairy & Animal Science’ during the period 1945–2011. This automatic approach was based on a coword analysis and combines performance analysis and science mapping. To observe the conceptual evolution of AS, six consecutive periods were defined: 1945–1969, 1970–1979, 1980–1989, 1990–1999, 2000–2005 and 2006–2011. Research in AS was identified as having focused on ten main thematic areas: ANIMAL‐FEEDING, SMALL‐RUMINANTS, ANIMAL‐REPRODUCTION, DAIRY‐PRODUCTION, MEAT‐QUALITY, SWINE‐PRODUCTION, GENETICS‐AND‐ANIMAL‐BREEDING, POULTRY, ANIMAL‐WELFARE and GROWTH‐FACTORS‐AND‐FATTY‐ACIDS. The results show how genomic studies gain in weight and integrate with other thematic areas. The whole of AS research has become oriented towards an overall framework in which animal welfare, sustainable management and human health play a major role. All this would affect the future structure and management of livestock farming.     

苹果病害智能诊断方法研究与设计

针对传统苹果专家病害诊断系统自学习能力差、准确率低的不足,研究并设计了人工神经网络的苹果病害诊断方法.采用动态编码对苹果病害模糊知识进行量化,构建BP网络诊断模型进行诊断;采用Java语言开发基于Web的病害动态诊断平台,用白水苹果病害样本进行了实验.该方法对20种苹果病害的诊断具有较好的效果,测试准确率达到85.4%.在获得必要领域知识的前提下,用神经网络进行苹果病害诊断准确率高,系统设计灵活,基于Web的诊断平台便于推广和使用.     

基于卷积神经网络的中国北方冬小麦遥感估产

针对传统的农作物估产方法过度依赖人工经验,以及实地采样成本高等问题。该研究使用MODIS数据构建了基于卷积神经网络(convolutional neural network,CNN)的冬小麦估产模型。对2006-2016年中国北方冬小麦核心区的60个地级市进行模型训练,鲁棒性检验以及估产误差空间特征分析。结果表明:1)估产模型在训练集和验证集的均方根误差(root mean squareerror,RMSE)分别为183.82kg/hm2、689.72 kg/hm2,决定系数(R2)分别为0.98、0.71。2)以同样的神经网络结构对2006-2016年估产样本分别作为验证集,训练11个独立模型的RMSE平均值是772.03 kg/hm2,证明算法具有较高的鲁棒性。3)2007、2012和2016年不同省份的估产结果表明,模型对北方冬小麦区的平原区估产精度较高,尤其是河北和山东2省(RMSE为500 kg/hm2)。该文构建的估产模型可以实现冬小麦单产的复杂拟合,可以应用于较大尺度(范围)冬小麦产量预报。