基于粗糙集和BP神经网络的粮食产量预测研究

为提高粮食产量的预测精度,提出一种基于粗糙集和BP神经网络的粮食产量预测方法。该方法以吉林省粮食总产量的历史数据作为研究对象,利用粗糙集理论的属性约简特性,识别与粮食产量相关性较大的影响因素,剔除非主要影响因素,利用约简后数据建立RSBP神经网络预测模型。结果表明,粗糙集理论能有效减少数据的维数及噪声,减少神经网络的计算量,结合两种方法能有效提高预测速度和精度。     

高校青年教师加强自身修养刍议

高校是培养高层次人才的摇篮，教师是造就人才的特殊劳动者。青年教师作为教师队伍中最具活力的群体，它的思想道德和内在素质将直接影响教师队伍的稳定，发展和提高。本文试图透视社会发展，社会劳动和阶级属性诸多方面，剖析了社会主义市场经济条件下，高校青年教师自身修养的深层次问题，寻求加强青年教师自身修养的途径和方法。     

属性识别方法在水资源系统可持续发展程度综合评价中的应用

以汉中盆地平坝区为例,探讨了水资源系统可持续发展程度的综合评价方法,并将属性识别理论应用于该研究,建立了可持续发展系统的综合评价模型.与模糊综合评价模型相对照,结果表明该方法的评价结果与模糊评价法相一致,同时该方法简单、易懂,更适合于有标准的系统质量评价问题.     

Effects of Feed Withdrawal Periods on Carcass Yield and Breast Meat Quality of Chickens Reared Using an Alternative System

The purpose of this work was to evaluate the effects of different feed withdrawal (FW) periods (3, 6, 9, 12, 15, and 18 h) on live broiler weight loss, dressed and chilled carcass yields, and chilled breast meat quality attributes of chickens reared in an alternative system, without the use of any antibiotics, growth promoters, coccidiostats, or ingredients from animal sources. Live weight loss and dressed and chilled carcass yields after FW were determined, and also fillet color, water-holding capacity (WHC), pH, shear value, cooking loss, and proximate composition, and a sensory analysis was conducted. Longer FW periods resulted in significant (P ≤ 0.05) increases in live broiler weight losses, from 1.3 to 5.3% in the 18-h period. The drops in dressed and chilled carcass yields became statistically significant at 12 h of FW, with dressed carcass yields of 65.2% after 3 h of FW and 63.8% after 12 h. Chilled carcass yields dropped from 68.8% after 3 h of FW to 67.0% after 12 h. Fillet color, as indicated by the L* values, became darker with longer FW periods, as shown by regression analysis. No statistical differences were observed for the a* values, b* values, WHC, cooking losses, and proximate composition of the fillets for the different FW periods. The Pearson correlation values showed a significant but low negative correlation between fillet pH and shear force, which varied with FW period. The highest carcass yields were obtained for broilers submitted to FW periods of between 3 and 9 h.     

土壤资源和生态环境信息系统的设计与应用: 以三峡地区秭归县为例

The design and applications of a land information system built upon ARC/INFO and ArcView are presented. The proposed system not only maintains all the advantages of the more conventional implementations but also enhances them in the following ways: 1) the application program interfaces (API) are used to transmit data and messages among different parts of the system; 2) the integrated system can support studies on land evaluations and ecological analyses by efficient management of attribute and spatial data and 3) correspondingly, spatial records and attributive records are linked by the same identifiers (ID). A case study application in Zigui County of the Three Gorges Area in China demonstrates that the system could employ land-use maps and land property data to predicate and analyze the land utilization changes in the past, present and future. The ecological environment analysis can be carried out with the data of land, economics and terrain map used, showing that the system can be widely applied, especially to survey land and environment resources in the countryside area.     

基于Fishbein 模型和产品属性对农民购买化肥意愿的分析

中国城乡差异显著,城镇和农村居民的消费行为也存在很大差异,应该对其消费行为分开进行研究。以农民消费者为对象,将化肥的二维属性(消费属性和投资属性)作为新变量引入Fishbein合理行为模型,构建了农民化肥购买意愿模型,考察化肥二维属性对他们购买意愿的影响。经过方差分析和结构方程分析发现,化肥的消费属性只能通过农民的态度影响其购买意愿;投资属性可以通过农民的态度对购买意愿产生正向影响,也可以通过从众心理对其购买意愿产生正向影响;并且投资属性对农民从众心理的影响更大,从众心理对购买意愿的影响比态度对购买意愿的影响更强。     

Assessment of gully erosion susceptibility using different DEM-derived topographic factors in the black soil region of Northeast China

As a primary sediment source, gully erosion leads to severe land degradation and poses a threat to food and ecological security. Therefore, identification of susceptible areas is critical to the prevention and control of gully erosion. This study aimed to identify areas prone to gully erosion using four machine learning methods with derived topographic attributes. Eight topographic attributes (elevation, slope aspect, slope degree, catchment area, plan curvature, profile curvature, stream power index, and topographic wetness index) were derived as feature variables controlling gully occurrence from digital elevation models with four different pixel sizes (5.0 m, 12.5 m, 20.0 m, and 30.0 m). A gully inventory map of a small agricultural catchment in Heilongjiang, China, was prepared through a combination of field surveys and satellite imagery. Each topographic attribute dataset was randomly divided into two portions of 70% and 30% for calibrating and validating four machine learning methods, namely random forest (RF), support vector machines (SVM), artificial neural network (ANN), and generalized linear models (GLM). Accuracy (ACC), area under the receiver operating characteristic curve (AUC), root mean square error (RMSE), and mean absolute error (MAE) were calculated to assess the performance of the four machine learning methods in predicting spatial distribution of gully erosion susceptibility (GES). The results suggested that the selected topographic attributes were capable of predicting GES in the study catchment area. A pixel size of 20.0 m was optimal for all four machine learning methods. The RF method described the spatial relationship between the feature variables and gully occurrence with the greatest accuracy, as it returned the highest values of ACC (0.917) and AUC (0.905) at a 20.0 m resolution. The RF was also the least sensitive to resolutions, followed by SVM (ACC = 0.781–0.891, AUC = 0.724–0.861) and ANN (ACC = 0.744–0.808, AUC = 0.649–0.847). GLM performed poorly in this study (ACC = 0.693–0.757, AUC = 0.608–0.703). Based on the spatial distribution of GES determined using the optimal method (RF + pixel size of 20.0 m), 16% of the study area has very high level susceptibility classes, whereas areas with high, moderate, and low levels of susceptibility make up approximately 24%, 30%, and 31% of the study area, respectively. Our results demonstrate that GES assessment with machine learning methods can successfully identify areas prone to gully erosion, providing reference information for future soil conservation plans and land management. In addition, pixel size (resolution) is the key consideration when preparing suitable datasets of feature variables for GES assessment.     

压缩根瘤菌分类属性空间的聚类方法研究

用系统聚类方法(R 技术),分析了性状对偶间的相似性,并结合比较检测方法的特异性、稳定性、安全性和材料来源的难易等因素,把253株根瘤菌的248维分类属性空间压缩到130。经两组抽样验证。聚类分析结果基本保持了原分类体系的主体结构。可以认为,选定的性状能够满足目前根瘤菌数值分类的要求。这不仅减少了今后根瘤菌数值分类的工作量,还有助于为根瘤菌分类、鉴定特征的标准化建立基础。     

基于样点个体代表性的大尺度土壤属性制图方法

大空间尺度范围的土壤属性分布信息是陆地表层过程模拟的基础信息.基于野外样点进行空间插值是获得土壤属性空间分布信息的重要手段.现有的空间插值方法通常要求所用样点对研究区土壤属性空间分布规律具有良好的全局代表性.然而,受采样经费和野外采样条件的限制,所采集的样点往往难以全面地反映研究区土壤属性的空间分布规律.基于这样的样点用现有空间插值方法得到的土壤属性分布图通常精度较低,并且由样点全局代表性差带来的推测不确定性也无法得到度量.为了合理利用这些已采集的但全局代表性不好的样点,本文提出了基于样点“个体代表性”推测土壤属性空间分布并度量推测不确定性的方法.该方法在两点环境条件越相似、土壤属性就越相似的假设下,认为每一样点可以代表与其环境条件相似的地区,并且代表程度可以由两点的环境相似度度量;通过分析环境相似度计算推测不确定性,并以环境相似度为权重计算样点可代表地区的土壤属性值.将该方法应用于推测新疆伊犁地区土壤表层有机质含量,经验证,本文方法能够有效地利用全局代表性差的样点推测样点能够代表地区的土壤属性空间分布,并且所得的推测不确定性与预测残差呈现正向关系,能够有效地指示推测结果的可靠程度.