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.     

氧化法制备聚合氯化铁絮凝剂的氧化速率及其形态分布

采用氧化法制备聚合氯化铁絮凝剂，论述了不同亚铁溶液中氧化水解动力学、氧化过程PH值变化以及不同反应过程对聚合氯化铁形态分布的影响；结果表明，氯化亚铁溶液的氧化速率主要受溶液的含酸量和三价铁离子的水解聚合反应的协同效应的影响，当溶液酸量达到最低点时，亚铁氧化速度也将降至最慢；通过形态分布、稳定性及氧化速度的研究确定了制备聚合氯化铁的最佳条件。     

A One-Equation Turbulence Model for Geophysical Applications: Comparison with Data and the k−ε Model

A one-equation turbulence model is presented, in which the turbulent kinetic energy k is calculated with a transport equation whereas the turbulent length scale l is calculated with an algebraic expression. The value of l depends on the local stratification and reduces to the classical |z| scaling for unstratified flows near a wall, where |z| is the distance to the wall. The length scale decreases during stable stratification, and increases for unstable stratification compared to the neutral case. In the limit of strong stable stratification, the so-called buoyancy length scale proportional to k ^1/2 N ^–1 is obtained, where N is the buoyancy frequency. The length scale formulation introduces a single model parameter which is calibrated against experimental data. The model is verified extensively against laboratory measurements and oceanic data, and comparisons are made with the two-equation k- model. It is shown that the performance of the proposed k model is almost identical to that of the k- model. In addition, the stability functions of Launder are revisited and adjusted to obtain better agreement with recent data.     

虚拟生态产业链的稳定性研究

以虚拟产业链的稳定性作为研究的着力点,对影响虚拟产业链的稳定性的风险因素进行分析,其中包括市场风险因素、技术成本风险因素、交易风险因素等,针对这些影响因素,并给出风险防范体系,即虚拟产业链的风险防范内生体系和外生体系:内生体系是指在虚拟产业链的本身内部网络中建立的风险防范机制、对策、方法措施等,如检查机制、激励机制、利润/风险分担机制和清算机制,而外生体系是指对虚拟生态产业链的风险起防范作用的法律法规、信用和传媒等社会体系的总和。从而从生态产业链内外部整体资源的协同利用和利益相关者的协同效用两方面来提高虚拟产业链的稳定性。     

聚合铝的形态稳定性及其动电特性的研究

本文采用改进的Ａｌ－Ｆｅｒｒｏｎ快速测定法研究了混凝过程中铝盐与聚合铝水解形态的转化规律及稳定性，并对混凝反应过程中铝与聚合铝溶解－沉淀形态分布与理论溶解度进行了对比，同时采用流动电流技术直接测定了铝盐与聚合铝絮凝剂的荷电状况，最后对发生在混凝过程中铝与聚合铝最佳凝聚形态进行了讨论。     

赣州高级技工学校滑坡成因分析及稳定性评价

本文从地形地貌、岩性、降水等方面综合分析了赣州高级技工学校滑坡的成因,并通过定量计算,分析了滑坡在天然及饱和状态下的稳定性,提出了滑坡的治理方案。     

四川九寨黄龙机场高填方地基变形与稳定性系统研究

<正>随着我国西部大开发战略实施,多山的西南地区机场建设进入迅猛发展阶段。这些机场的特点是高填方、高地震烈度、场区地质条件复杂、常分布有软弱土层,且机场建设周期短。因而妥善解决机场高填方地基的稳定与变形(沉降与差异沉降)是该地     

秦岭Ⅰ号隧道围岩压力的理想弹塑性分析

影响洞室稳定性的因素很多,但岩体自身的受力情况是至关重要的。在不考虑支护反力的条件下,将弹塑性应力半径作为变量,分析秦岭Ⅰ号隧道弹塑性区应力随半径的变化规律,为隧道的施工及支护提供参考。     

城市垃圾填埋场安全稳定性分析

垃圾填埋场是一类特殊工程，其安全稳定性一直是研究的热点和难点。本文借鉴成熟的工程力学思想，将分析山谷型垃圾填埋体的安全稳定性转化为分析垃圾坝稳定性。利用已知的稳定填埋场边坡有关性状，反算出垃圾土可能最小综合内摩擦角，利用这个参数来计算填埋体在三种典型状态下对垃圾坝产生的最大作用力，从而来判断垃圾坝的稳定性。探索了一套分析山谷型填埋场填埋体稳定性的方法并提出了两个公式，对于该类型垃圾填埋场建设具有指导作用。     

基于SEM的双车道公路超车行为安全评价

为提高驾驶人在双车道公路上超车的安全性,基于tau理论适应性分析,提出超车过程中驾驶人不仅根据tau线索估计避碰时间,也利用距离、速度、加速度等判断超车是否安全的试验假设。招募12名受试者,应用驾驶模拟系统试验平台,依据试验假设采集12个与超车行为有关的驾驶行为数据,对其进行无量纲化处理,并利用Bootstrap法对数据进行扩增。结合驾驶行为问卷得分,利用AMOS软件,建立超车行为安全评价的结构方程模型。通过对初始假设模型进行多次修正与评价,得到影响超车行为安全的3个驾驶行为参数。结果表明,超车车辆在超车并道后的速度、与前导车之间的避碰时间及与对向车辆之间的避碰时间这3个驾驶行为参数可作为超车行为安全评价的有效指标。