随机森林算法在空气质量评价中的应用

为了更好地反映空气质量的变化趋势,加强大气污染的防治,开展城市环境空气质量评价的意义重大。有效的空气质量评价方法可以提高评价体系的科学性,督促各个城市环保工作的稳步推进,从而对大气污染治理做出贡献,而空气质量评价算法是空气质量评价的核心。根据影响空气质量的几个基本要素:二氧化硫年平均浓度、二氧化氮年平均浓度、可吸入颗粒物年平均浓度等,创新性地采用随机森林算法对我国113个重点城市的空气质量进行了评价。通过评价指标将模型的评价结果与其他分类算法进行比较,发现随机森林分类模型,无论是在二分类还是多分类中都能够对各个城市地区的空气质量作出较为准确的评估,并进一步得出空气中PM10、PM2.5和O3的浓度是影响各大城市空气质量好坏的主要因素。     

Aggregate nonparametric safety analysis of traffic zones

Exploring the significant variables related to specific types of crashes is vitally important in the planning stage of a transportation network. This paper aims to identify and examine important variables associated with total crashes and severe crashes per traffic analysis zone (TAZ) in four counties of the state of Florida by applying nonparametric statistical techniques such as data mining and random forest. The intention of investigating these factors in such aggregate level analysis is to incorporate proactive safety measures in transportation planning. Total and severe crashes per TAZ were modeled to provide predictive decision trees. The variables which carried higher weight of importance for total crashes per TAZ were – total number of intersections per TAZ, airport trip productions, light truck productions, and total roadway segment length with 35 mph posted speed limit. The other significant variables identified for total crashes were total roadway length with 15 mph posted speed limit, total roadway length with 65 mph posted speed limit, and non-home based work productions. For severe crashes, total number of intersections per TAZ, light truck productions, total roadway length with 35 mph posted speed limit, and total roadway length with 65 mph posted speed limit were among the significant variables. These variables were further verified and supported by the random forest results.     

Wood characterization for energy application proceeding from pruning Morus alba L., Platanus hispanica Münchh. and Sophora japonica L. in urban areas

Pruning urban forests generates significant amounts of lignocellulosic biomass every year. The energy potential of this biomass is unclear. The aim of this research was direct analysis of the gross calorific value (GCV), elemental composition and moisture content of Morus alba L., Platanus hispanica Münchh. and Sophora japonica L. by means of laboratory equipment. This analysis allowed for further development of indirect GCV prediction models which are economically attractive and less time consuming to direct analysis. These models presented high coefficients of determination (R² 0.66–0.96). It has been determined that the species with highest mean GCV is S. japonica L. (19615.68 kJ/kg-dry sample) whereas the one with the lowest is the M. alba L. (18192.87 kJ/kg-dry sample). Elemental analysis showed highest carbon (48.22%), hydrogen (6.17%) and nitrogen (1.16%) content in S. japonica L. in dry samples. Sulfur was constant at the level 0.05% for all analyzed species. Also percentage of bark and wood density were determined. Mean percentage of bark was highest for P. hispanica Münchh. (13.05%) while wood density was highest for S. japonica L. (0.86 g cm⁻³). This way the research has proven that the biomass produced by pruning urban forests appears to be an interesting source of renewable energy.     

化学分离法分析大型纸浆发电厂废渣中生物质底灰和飞灰成分(英文)

采用三步分离法,其中第一步用水,第二步用乙酸铵,第三步用盐酸,提取纸浆发电厂生物质飞灰和底灰的组分,以评估这些残渣的浸出行为。除了Mo、S、Na以及那些浓度低于检测范围的元素外,在这两种灰份中,对于其他元素这三种浸出剂的浸出能力从弱到强的顺序为:水、乙酸铵和盐酸。采用三步分离法处理的废渣中元素浓度比前期用BCR连续提取法得到的低。     

基于“3S”技术林业有害生物预警预报系统设计与实现

林业有害生物预警预报系统以"3S"技术为核心,以C#、ARC ENGINE、WEBGIS技术为手段建立,应用GIS中缓冲区分析和叠加分析等方法预测病虫害发生的范围,在空间位置上高亮度标识病虫害发生位置、扩散区域、危害程度,关联出相关预防方法和防治技术,并实现实时信息发布和视频上传。     

Assessment of resistance spot welding quality based on ultrasonic testing and tree-based techniques

Classification and regression tree (CART) and random forest techniques were proposed as pattern recognition tools for classification of ultrasonic oscillograms of resistance spot welding (RSW) joints. The results showed that CART models produced an acceptable error rate with high interpretability. These features may be used to understand and control the decision processes, instruct other human operators, compare margins of safety or modify them depending on the criticality of the industrial process. Compared with CART trees, random forests reduced the error rate at the cost of decreasing decision interpretability. The use of the agreement of the forest was proposed as a measure to reduce the workload of human operators, who would only have to focus on the analysis of ultrasonic oscillograms that are difficult to interpret.     

Android malware detection based on improved random forest

Aiming at the defect of vote principle in random forest algorithm which is incapable of distinguishing the differences between strong classifier and weak classifier,a weighted voting improved method was proposed,and an improved random forest classification (IRFCM) was proposed to detect Android malware on the basis of this method.The IRFCM chose Permission information and Intent information as attribute features from AndroidManifest.xml files and optimized them,then applied the model to classify the final feature vectors.The experimental results in Weka environment show that IRFCM has better classification accuracy and classification efficiency.     

草原石林：东北亚早白垩世花岗岩伸展穹隆和岩浆成矿爆发的地质遗迹及其形成过程

东北亚地区至少发育9个大型草原石林,属花岗岩石林的一种,是东北亚早白垩世巨量伸展和第四系冰川、风化作用的共同产物,主要特点是发育密集的近水平节理。本文通过整理岩浆岩专题填图和构造研究发现,这些石林的主体是早白垩世东北亚地区巨量伸展过程中形成众多的不对称花岗岩穹隆或同减薄岩体,岩体边部发育韧性剪切带,核部发布近水平岩浆流动面理,伸展和岩浆多期侵位导致与成矿密切相关的岩浆热液大量上涌,岩体抬升至地表,沿岩浆面理发育密集的近水平节理和部分垂直节理,后期沿这些构造面理发生的物理风化和化学作用(包括风蚀、冰川以及盐风化等)造就了千奇百怪的形态。草原石林是花岗岩地貌中的“另类”,不仅具有指示东北亚地区花岗岩形成时代(早白垩世)的特点,也是寻找晚中生代中国北方大规模成矿的良好标志体,而且风化形成的千姿百态的景色极具观赏价值,可以作为整个蒙古草原地区和大兴安岭南段地区特色的地学科普和生态旅游资源。     

Biodiesel potential of the seed oils from some Brazilian native Euphorbiaceae species

In the present study, the oil content, fatty acid composition and physicochemical properties of seed oils and biodiesel from seven species of Euphorbiaceae were analyzed. The oil content from seven Brazilian native Euphorbiaceae species ranged from 25.4 to 48.5%. Nine primarily unsaturated fatty acids were identified in seed oils. Actinostemon concolor and Stillingia trapezoidea seeds accumulated mainly oleic and linoleic acids, whereas in the seeds of Croton floribundus, Croton nepetifolius, Euphorbia comosa and Microstachys corniculata, linoleic and linolenic acids were the main constituents identified. Palmitic and oleic acids were predominantly detected in the seeds of Sapium glandulosum. In general, the oils showed low acidity, viscosity and free fatty acids. The results suggest that the seed oils from A. concolor, S. glandulosum and S. trapezoidea might be a viable alternative for biodiesel production, while those from C. floribundus, C. nepetifolius, E. comosa and M. corniculata seeds have great potential for application in the paint, varnish and lubricant industries. Due to the high content of saturated fatty acids, the seeds of S. glandulosum could also be used to produce soaps and detergents. For most species analyzed, the biodiesel specifications are in accordance with EN 14214 and ASTM D6751 standards.     

随机森林算法在温度分布重建中的应用

为提高温度分布重建精度,提出了使用随机森林算法对温度测点进行优化布置的新方法。 将测点位置作为样本特征, 以不同的测点布置方式及其对应的重建误差作为样本数据集。 使用样本数据集构建随机森林模型,评估样本特征重要性,根据 特征重要性排序实现温度测点的优化布置。 设定仿真实验与燃烧实验验证优化布置算法的可行性与有效性。 分析实验数据, 所提出的优化布置算法相对于原有算法,重建精度提升了 20%以上。 研究结果表明,随机森林算法在温度分布重建中具有良好 的应用价值,并为解决工业实际问题提供了新思路。