Use of genetic algorithms to select input variables in decision tree models for the prediction of benthic macroinvertebrates

Predicting freshwater organisms based on machine learning is becoming more and more reliable due to the availability of appropriate datasets, advanced modelling techniques and the continuously increasing capacity of computers. A database consisting of measurements collected at 360 sampling sites in non-navigable watercourses in Flanders was applied to predict the absence/presence of benthic macroinvertebrate taxa by means of decision trees. The measured variables were a combination of physical–chemical (temperature, pH, dissolved oxygen concentration, conductivity, total organic carbon, Kjeldahl nitrogen and total phosphorus), structural (granulometric analysis of the sediment, width, depth and flow velocity of the river) and two ecotoxicological variables. The predictive power of decision trees was assessed on the basis of the number of Correctly Classified Instances (CCI). A genetic algorithm was introduced to compare the predictive power of different sets of input variables for the decision trees. The number of input variables was reduced from 15 to 2–8 variables without affecting the predictive power of the decision trees significantly. Furthermore, reducing the number of input variables allowed to ease the identification of general data trends.     

Zero-inflated models with application to spatial count data

Count data arises in many contexts. Here our concern is with spatial count data which exhibit an excessive number of zeros. Using the class of zero-inflated count models provides a flexible way to address this problem. Available covariate information suggests formulation of such modeling within a regression framework. We employ zero-inflated Poisson regression models. Spatial association is introduced through suitable random effects yielding a hierarchical model. We propose fitting this model within a Bayesian framework considering issues of posterior propriety, informative prior specification and well-behaved simulation based model fitting. Finally, we illustrate the model fitting with a data set involving counts of isopod nest burrows for 1649 pixels over a portion of the Negev desert in Israel.     

The Effect of Fragment Shape and Species' Sensitivity to Habitat Edges on Animal Population Size

Abstract:  Habitat fragmentation causes extinction of local animal populations by decreasing the amount of viable "core" habitat area and increasing edge effects. It is widely accepted that larger fragments make better nature reserves because core-dwelling species have a larger amount of suitable habitat. Nevertheless, fragments in real landscapes have complex, irregular shapes. We modeled the population sizes of species that have a representative range of preferences for or aversions to habitat edges at five spatial scales (within 10, 32, 100, 320, and 1000 m of an edge) in a nation-wide analysis of forest remnants in New Zealand. We hypothesized that the irregular shapes of fragments in real landscapes should generate statistically significant correlations between population density and fragment area, purely as a "geometric" effect of varying species responses to the distribution of edge habitat. Irregularly shaped fragments consistently reduced the population size of core-dwelling species by 10–100%, depending on the scale over which species responded to habitat edges. Moreover, core populations within individual fragments were spatially discontinuous, containing multiple, disjunct populations that inhabited small spatial areas and had reduced population size. The geometric effect was highly nonlinear and depended on the range of fragment sizes sampled and the scale at which species responded to habitat edges. Fragment shape played a strong role in determining population size in fragmented landscapes; thus, habitat restoration efforts may be more effective if they focus on connecting disjunct cores rather than isolated fragments.     

摩托车发动机活塞浇注模设计

根据实际生产的需要对摩托车发动机活塞的成形工艺进行分析 ,从而确定合理的浇注方案 ,然后详细地阐述活塞浇注模结构设计和工作原理 ,并介绍了模具的抽芯过程和型芯的典型加工工艺     

福建省“尤德地体”的成矿特征和找矿远景

“尤德地体”位于闽中裂谷带南端 ,与紫金山金矿处于同一成矿带。在“尤德地体”中 ,目前已发现元古界麻源群变质岩和侏罗系长林组、南园组 ,火山岩中均存在韧性剪切带型矿床和热液交代充填矿床。区域构造、地层含矿性、物化探重砂异常等表明其找矿前景很好。找矿工作重点应紧扣层控矿床 ,大断裂带 ,斑岩型金矿和红土型金矿     

GIS支持下的黄土高原地区植被生态梯度分析

在地理信息系统(GIS)支持下对黄土高原地区257个样方的植被进行了研究。DCA分析较好地反映了植被的连续性变化及植被的生态梯度与气候因子的关系。分析的结果表明．植被组成和结构沿经、纬度变化明显，分异出森林、森林草原、温性草原、荒漠半荒漠植被等不同类型，优势种替代明显，植物种类也形成了不同的生态类型。植被的梯度变化与气候因子密切相关，较好地反映了黄土高原地区环境与结构的空间变异特点。     

荧光灯管芯柱玻璃中金属铅的机械化学硫化

以硫化钠为硫化剂,机械化学硫化荧光灯管芯柱玻璃中金属铅,实现金属铅向硫化铅快速转化.通过单因素实验,考察了不同机械化学硫化条件,即球磨时间、球磨转速和球料比对硫化率的影响,并通过XRD、SEM和粒度对硫化产物进行表征.结果表明,硫化率随球磨时间和球磨转速的增大而增大,随球料比的增大先增大后减小,当球磨转速为750r/min、球磨时间为120min、球料比为50：1g/g时,荧光灯管芯柱玻璃中金属铅的硫化率可达96.18%.XRD结果表明,荧光灯管芯柱玻璃中金属铅的机械化学硫化产物为PbS、SEM和粒度结果表明,荧光灯管芯柱玻璃的粒径随球磨转速和球磨时间的增加而减小.     

Assessment of cervical range of motion,cervical core strength and scapular dyskinesia in violin players

Background. Playing the violin can lead to asymmetric postures which can affect the cervical range of motion, cervical core strength and scapular stability. Objective. The objective of the study was to assess the cervical range of motion, cervical core strength and scapular dyskinesia in violin players and non-players of the same age group. Methods. An inclinometer was used to assess the cervical range of motion, pressure biofeedback was used to assess cervical core strength and scapular dyskinesia was also assessed in 30 professional violin players (18–40 years) compared with 30 age-matched non-players. Analysis was done using an unpaired t test. Results. Significant change was seen with respect to extension (p?=?0.051), cervical core strength (p?=?0.005), right (Rt) superior angle 0° (p?=?0.004), Rt superior angle 45° (p?=?0.015) and Rt inferior angle 90° (p?=?0.013). Conclusion. This study shows a significant difference in extension range of motion and cervical core strength of violin players. Also, there was scapular dyskinesia seen at 0° and 45° right-side superior angle of the scapula and 90° right-side inferior angle of the scapula.     

济南市大气污染防治三区划定研究

根据《山东省区域性大气污染物综合排放标准》(DB37/2376-2013)实施要求,开展济南市市域范围大气污染防治三区划定。划定过程以地理信息系统空间分析技术为手段,根据各区域大气环境承载力、人口密度分布和生态环境敏感程度三个因素的空间分布差异,实现三区划分,形成划定初步方案。同时,结合相关规划和重点企业/工业园区空间布局状况,对初步划定方案进行调整,形成三区划定最终方案,并在此基础上提出各分区大气污染控制措施。