Selection of tree species by principal component analysis for abandoned farmland in southeastern Horqin Sandy Land,China

With changes in global climate and land use,the area of desertified farmland in southeastern Horqin Sandy Land(HSL)has increased in recent years,and farmlands are being abandoned.These abandoned farmlands(AFs)nega-tively impact the local ecology.Therefore,the aim of the present study was to select suitable trees and shrubs for those AFs to prevent and control the desertification tendency.In this study,three AFs were fenced for 2 years,then 37 arbor and shrub species or varieties of 21 families were planted in the fenced AFs and grown for 10 years.The ecological adaptability of the species was evaluated and ranked using a principal component analysis.The results showed that the biodiversity of the AFs significantly improved after 2 years of fencing;the Shannon-Wiener index and species rich-ness of perennial grasses and forbs were 1.45 and 3.6 times higher,respectively,than for the unfenced AF.Among all species planted in fenced AFs,nine tree species had posi-tive comprehensive F(CF)values;Pinus sylvestris(Russian Shira steppe provenance),Populus alba‘Berolinensis’and Gleditsia triacanthos had CF greater than 1,and the first(PC1),second(PC2)and third(PC3)principal component values(F_(1),F_(2),F_(3))were all positive.Among the shrubs,only Lespedeza bicolor and Rosa xanthina f.normalis had CF greater than 0.All these results suggest that fencing improves biodiversity and that planting trees and shrubs that have higher CF values on the basis of fencing is an effective way to green and beautify AFs in HSL.

Selection of promising chestnuts(Castanea sativa) among wild growing trees from southern Mediterranean region forests of Turkey

Turkey ranked third place in the world for chestnut production after China and South Korea and the country has unique chestnut forests including valuable and diverse chestnut genotypes. This study was conducted to select superior chestnut genotypes within seedling popu- lations found in natural wild grown chestnut forest located in Isparta province in Turkey during 2010-2011 years. A total of 2500 wild grown chestnut trees were examined on the field first year and among them the most promising 22 genotypes were chosen according to relatively high yield capacity, earliness, tolerance to chestnut blight （Cryphonectria parasitica）, ink disease （Phytopthora cambivora）, and fruit quality characteristics. The selected 22 genotypes were evaluated for their detailed morpho- logical, phenological and pomological traits in 2010 and 2011. According to average of 2 years, nut weight, the number of nut per kilogram, nut width, nut length, nut height and nut shell thickness of 22 promising genotypes ranged from 10.26 to 22.32 g, 97.47 to 44.80/kg, 26.80 to 42.47, 16.92 to 25.91, 27.74 to 39.73, and 0.26 to 1.01 mm, respectively. The ash, crude protein, and total fat content of kernels were between 0.85 to 1.94, 3.69 to 7.06 and 1.32 to 4.52, respectively. The genotypes were evaluated with weighted ranking method and the highest general quality score was observed in genotypes of IY17, IYO1, IY42, IY43 and IY12.

Evaluation and Selection of Introduced Tree Species in the Beijing-Tianjin Corridor

Based on the extensive analysis of natural and social conditions,regional development,and characteristics of tree species in the Beijing-Tianjin corridor,a comprehensive evaluation index system that consists of A,B,C,D layers was established for introduced tree species.Nine local representative introduced tree species were evaluated using the analytic hierarchy process(AHP).The results showed that Platanus orientalis,Quercus mongolicus,and Zizyphusjujube performed better comprehensively and were recommended as the dominant introduced tree species in the Beijing-Tianjin corridor.Other representative introduced tree species should be appropriately developed in the region.Main factors that should be taken into account for introduced tree species including drought tolerance,wintering habit,growth rate,leanness tolerance,pollution tolerance,saline tolerance,and disease resistance.

一种基于k-means聚类技术的快速选择性Bagging Trees集成算法研究

选择性集成算法是目前机器学习关注的热点之一。在对一海藻繁殖案例研究的基础上,提出了一种基于k-means聚类技术的快速选择性Bagging Trees集成算法;同时与传统统计方法和一些常用的机器学习方法相比较,发现该算法具有较小的模型推广误差和更高的预测精度的优点,而且其运行的效率也得到了较大的提高。

一种基于差异思想的选择性Bagging Trees集成算法研究

本文通过对鸢尾花数据的研究,提出了一种基于分类器的分类效果差异而进行快速选择的一种改进的Bagging Trees集成算法。并通过同其他统计机器学习方法,如:CART、Bagging Trees、Random Forest以及目前流行的基于遗传算法的选择性集成算法GASEN等比较得出,该算法对于分类问题而言,具有较高的准确率,而且与GASEN算法相比,运行的效率也得到了较大的提高。

基于改进HTML-Tree的中文网页特征向量提取方法

中文网页特征向量的提取是提高中文网页分类准确度和召回度的关键。经过研究HTML网页的结构特点,提出一种基于改进的HTML-Tree及网页元素权重的中文网页文本预处理方法,并在此基础上进行网页文本特征向量的提取。该方法充分利用不同类别网页的特点,考虑了网页内各种元素权重的贡献。经过实验验证,该方法提高了网页特征向量提取的效率,有效提高了中文网页分类的准确度和召回度。

Combining spatial and economic criteria in tree-level harvest planning

Background:Modern remote sensing methods enable the prediction of tree-level forest resource data.However,the benefits of using tree-level data in forest or harvest planning is not clear given a relative paucity of research.In particular,there is a need for tree-level methods that simultaneously account for the spatial distribution of trees and other objectives.In this study,we developed a spatial tree selection method that considers tree-level(relative value increment),neighborhood related(proximity of cut trees)and global objectives(total harvest).Methods:We partitioned the whole surface area of the stand to trees,with the assumption that a large tree occupies a larger area than a small tree.This was implemented using a power diagram.We also utilized spatially explicit tree-level growth models that accounted for competition by neighboring trees.Optimization was conducted with a variant of cellular automata.The proposed method was tested in stone pine(Pinus pinea L.)stands in Spain where we implemented basic individual tree detection with airborne laser scanning data.Results:We showed how to mimic four different spatial distributions of cut trees using alternative weightings of objective variables.The Non-spatial selection did not aim at a particular spatial layout,the Single-tree selection dispersed the trees to be cut,and the Tree group and Clearcut selections clustered harvested trees at different magnitudes.Conclusions:The proposed method can be used to control the spatial layout of trees while extracting trees that are the most economically mature.

An Embedded Feature Selection Method for Imbalanced Data Classification

Imbalanced data is one type of datasets that are frequently found in real-world applications, e.g., fraud detection and cancer diagnosis. For this type of datasets, improving the accuracy to identify their minority class is a critically important issue.Feature selection is one method to address this issue. An effective feature selection method can choose a subset of features that favor in the accurate determination of the minority class. A decision tree is a classifier that can be built up by using different splitting criteria. Its advantage is the ease of detecting which feature is used as a splitting node. Thus, it is possible to use a decision tree splitting criterion as a feature selection method. In this paper, an embedded feature selection method using our proposed weighted Gini index(WGI) is proposed. Its comparison results with Chi2, F-statistic and Gini index feature selection methods show that F-statistic and Chi2 reach the best performance when only a few features are selected. As the number of selected features increases, our proposed method has the highest probability of achieving the best performance. The area under a receiver operating characteristic curve(ROC AUC) and F-measure are used as evaluation criteria. Experimental results with two datasets show that ROC AUC performance can be high, even if only a few features are selected and used, and only changes slightly as more and more features are selected. However, the performance of Fmeasure achieves excellent performance only if 20% or more of features are chosen. The results are helpful for practitioners to select a proper feature selection method when facing a practical problem.

Optimal Selection of Raw Material Forest Species for Edible Fungi in Guizhou Province

A comprehensive evaluation system,which focused on optimal selection of raw material forest species for edible fungi,was established by combination of Analytic Hierarchy Process(AHP)and Experts Grading Method(EGM).The evaluation system had 4 indices of grade I and 12 indices of grade II.Among the 12 indices of grade II,the weighted values of production quality of edible fungi P2(0.2874),usable time P7(0.1873),annual average increment P8(0.1873),edible fungi production suitability P1(0.0958)were larger than the values of others.Based on the comprehensive evaluation system,this study analyzed and screened 47 broadleaf species of 40 genera of 25 families.There were 16 broadleaf species having the comprehensive evaluation scores of equal to or greater than2.4000,which were available as major tree species for edible fungi development of Guizhou Province,especially species such as Liriodendron chinense,Quercus acutissima,Alnus cremastogyne,Betula luminfera,Elaeocarpus duclouxii,Elaeocarpus sylvestris,Choerospondias axillaris.The 10 broadleaf tree species with comprehensive evaluation score of 2.1000≤Y 2.4000 were recommended as candidates for edible fungi production,while the 21 broadleaf species with the comprehensive evaluation score of less than 2.1000 were not recommended.

Which trees should be removed in thinning treatments?

Background： In economically optimal management, trees that are removed in a thinning treatment should be selected on the basis of their value, relative value increment and the effect of removal on the growth of remaining trees. Large valuable trees with decreased value increment should be removed, especially when they overtop smaller trees. Methods： This study optimized the tree selection rule in the thinning treatments of continuous cover managemen when the aim is to maximize the profitability of forest management. The weights of three criteria （stem value, relative value increment and effect of removal on the competition of remaining trees） were optimized together with thinning intervals. Results and conclusions： The results confirmed the hypothesis that optimal thinning involves removing predominantly large trees. Increasing stumpage value, decreasing relative value increment, and increasing competitive influence increased the likelihood that removal is optimal decision. However, if the spatial distribution of trees is irregular, it is optimal to leave large trees in sparse places and remove somewhat smaller trees from dense places. However, the benefit of optimal thinning, as compared to diameter limit cutting is not usually large in pure one-species stands. On the contrary, removing the smallest trees from the stand may lead to significant （30-40 %） reductions in the net present value of harvest incomes.

Tree growth performance and estimation of wood quality in plantation trials for Maesopsis eminii and Shorea spp.

Plantations of tropical species axe becoming an increasingly important source of wood. However, it is important that research trials focus not only on tree growth performance, but also on wood quality. The aims of this study were to assess the growth performance of six commercially and ecologically important tree species from separate plantation trials in Indonesia and to determine the relationships between tree growth and wood quality in terms of the dynamic modulus of elasticity （MOE） and wood density. Forty-eight 7-year Maesopsis eminii Engl. and thirty-five 9-year specimens （7 each of 5 Shorea spp.） were selected from two trials. The MOE, based on acoustic velocity, was indirectly measured to evaluate wood stiffness. Tree-growth performance was evaluated, and correlations between growth traits and acoustic velocity as well as density and wood stiffness properties were estimated. The growth performance of M. eminii in terms of tree volume was significantly different in three different cate- gories of growth （i.e. fast, medium, slow）. Of the five Shorea spp. studied, Shorea leprosula Miq. had the highest growth rate, as expected since it is known to be a fastgrowing Shorea species. Indirect measurement of wood quality by means of non-destructive ultrasonic methods showed a weak negative correlation between tree volume and acoustic velocity and dynamic MOE. Although each fast-growing tree could reach a merchantable size faster than other varieties or species, wood traits of various species tested were not significantly different based on tree growth rate performance. The findings from this study could be used to improve selection criteria in future breeding trials; indirect measurements of the dynamic modulus of elasticity can be used in mass pre-selection of genetic materials, to choose the most-promising material for in-depth evaluation.

基于XGBoost的中国上市公司违约风险预测模型

准确预测上市公司的违约风险,是企业信用风险评价的关键,也是金融机构信贷决策的重要依据。通过线性回归模型的信息量AIC遴选违约判别能力最大的指标组合,采用粒子群优化算法构建基于XGBoost的违约预测模型。选取中国A股3425家上市公司不同时间窗口的数据为样本进行违约预测,将所构建的PSO-XGBoost模型与逻辑回归、支持向量机等13种预测模型对比,验证所建模型的有效性。通过UCI数据库中的3个公开信用数据集,利用Friedman检验,验证所建模型的稳健性。研究表明:使用上市公司数据与13种模型对比,PSO-XGBoost模型提高了预测精度G-mean;使用3个公开信用数据集,在多个评价指标上,PSO-XGBoost模型的平均预测性能显著优于对比模型;通过指标对预测结果的贡献获得指标重要性得分,增强了预测模型的可解释性。研究发现:“资产负债率”“流动比率”“长期资本负债率”等财务指标对违约预测的影响最大,“行业景气指数”“社会消费品零售总额增长率”“流通中现金(M0)供应量同比增长率”等指标是影响违约预测的重要指标。本研究可以为提高违约风险预测的准确性提供有效的方法和实证证据,有助于加强上市公司违约风险的预警和防范,降低违约风险监管成本,为企业管理者、债权人及投资者提供良好的决策支持。

Effect of selective cutting type on the chainsaw productivity in Caspian Forests

Time and motion studies were conducted to evaluate the impact of selective cutting type on Chainsaw productivity in Caspian forests, the selective cutting performed as single and group selection cutting in the region. The selective cutting was performed on a 42-ha tract with an average slope of 30%. The results indicate that felling time for per tree is most affected by diameter at breast height, the distance among harvested trees in single-tree selection method and diameter at breast height in group selection method. The production rate in single and group selection cutting were 21.2 m^3·h^-1 and 28.4 m^3·h^-1 for one person, respectively. Considering the gross and net production rate in single and group selection cutting, the unit cost was 1.11 USD.m^-3 and 0.88 USD.m^-3, respectively. The results indicate that group selection cutting can be more profitable than single-tree selection method.

The effect of single-tree selction system on soil properties in an oriental beech stand of Hyrcanian forest, north of Iran

A case study was conducted in beech forests of northern Iran to determine the effect of the created gaps on some soil properties in beech stand. Changes of soil properties in small （60-150 mE）, medium （151-241 mE）, large （242-332 m^2） and very large （333-550 m^2） gaps, as well as under closed stands were studied eight years after-the gap creation. Soil samples were taken from three depths, 0-10, 10-20 and 20-30 cm. The gaps were different from their around undisturbed stands in terms of the following soil parameters： Mg^＋2 concentration of 0-10 cm at medium gap size, bulk density of 10-20 cm at very large gap size as well as K^＋ and Ca^＋2 concentrations at 20-30 cm at small and large gap sizes, respectively. Furthermore, the size of the gaps had no effect on soil characteristics through the whole profile. Water saturation percent （Sp %） at 0-10cm as well as P and Mg^＋2 at 20--30 cm was different amongst undisturbed stands around different gap sizes. The center and the edges of the gap were different only in terms of organic carbon at the depth of 10-20 cm. Significant differences were observed between gaps and closed canopy regarding P and Ca^＋2 at depth 0--10 cm and 10-20 cm, respectively. It can be concluded that applied silvicultural system for harvesting trees which created these gaps might be suitable for conservation and forest management in the region.

“油-稻-稻”三熟制早熟冬油菜氮高效基因型及鉴定指标筛选

【目的】旨在筛选适宜“油-稻-稻”三熟制的氮高效早熟冬油菜基因型及其简易筛选指标。【方法】利用田间小区试验,选用了生育期185 d以下的的适宜“油-稻-稻”三熟制种植的14种早熟冬油菜基因型,进行正常施氮(N_(1))和不施氮(N_(0))处理。根据不同冬油菜基因型氮肥利用率(NUE)的差异,利用树状聚类分析进行分类,形成高、中、低3种氮效率基因型。同时通过逆向溯源的方法,观察分析3种氮效率基因型在不同氮水平条件下的产量构成、主要农艺性状、干物质积累及氮素吸收等方面的表现特征。总结分析出氮高效冬油菜基因型的一些简易判断的指标。【结果】不同氮效率基因型冬油菜在产量形成、主要农艺性状等方面存在显著差异。N1处理下成熟期早熟冬油菜的主要农艺性状的表型值和变异系数基本表现大于N0处理。因此,以N1处理下不同基因型的农艺性状表现作为不同氮效率基因型的鉴别标准。N1处理下,氮高效基因型比氮中效和氮低效基因型产量高、单株角果数多、每角粒数多、株高高、主花序长、一级分枝数多、角果密度高、各部位干物质积累量高、籽粒中氮含量高、氮肥偏生产力、氮肥农学效率、氮肥生理利用率和氮收获指数均较高。【结论】沣油737是适合南方“油-稻-稻”三熟制的氮高效早熟冬油菜;正常施氮条件下,成熟期较多的单株角果数与每角粒数,以及较高株高是判断早熟冬油菜氮高效基因型的简易指标。

A Green GIS Solution against Air Pollution in the Province of Bergamo: The Paulownia Tree

The paper describes a GIS approach to identify the most suitable areas for growing the Paulownia tree in the Province of Bergamo;this work will become the subject of a dissertation thesis at the School of Engineering of the University of Bergamo. Paulownia is quite an ancient tree, well known especially in the far east countries, for its wonderful flowers and the quality of the wood which is a source of certain profit. The paper is focused on the employment of the Paulownia tree against air pollution, since its big leaves absorb high amounts of CO2 in the atmosphere and can capture the small particles of pollutants in the air ten times more than any other tree species. First, the analysis identifies the most favourable areas for its growth in the Province of Bergamo. Secondly, among the latter, the analysis detects the strategic areas for its growth near the most polluted zones. Finally, a quantitative evaluation is carried out about the trees contribution against pollutants in the atmosphere.

江苏沿江防护林主要树种选择研究

通过对江苏沿江8市古树资源和长江江苏段2岸1 km范围内森林中各树种资源分布调查,结合长江防护林造林树种选择相关研究,筛选出适用于长江江苏段防护林造林树种59个。分别针对沿路区、滨水区和滩面区3种生态位特点,通过生态效益、景观效益和社会效益3类共10个指标,采用定量与定性研究相结合的方法,对这些树种进行综合评价、排序和分类。结果表明:3种生态位上各造林树种均可分为3类,第1类树种3种生态位可作为优选树种分别有15,7,7个;第2类3种生态位作为一般树种,分别有22,40,29个;其他可作为备选树种。结合沿江不同造林环境的特点和相关树种的特殊适应性,提出了相应的树种选择和配置建议。

采用VAE-CatBoost的高速公路交通事件检测框架

为解决交通事件检测中特征稀少与样本失衡的问题,提出一种基于变分自编码器(VAE)-随机森林(RF)-分类梯度提升树(CatBoost)的交通事件检测框架。依据4条规则构建较为全面的初始特征集。使用VAE进行数据平衡。之后,采用RF算法筛选出最佳输入特征集。最后,采用CatBoost算法作为分类器检测交通事件。使用真实世界的交通数据集设计实验,并选择6个有效评价指标对实验结果进行评价。结果表明:所提出的交通事件检测框架除误报率之外,各项评价指标均取得最优结果,表明在交通事件检测方面具备优异性能。

Family tree and population: Distinction and similarity of the analysis on example of hemophilia

On the basis of Hardy-Weinberg law the distinction in the philosophy of the description of a family tree and a population is considered. With the help of introduction of the equivalent constant mutagen factor both in a family tree and in a population, the analysis of hemophilia is led. Influence of selection at presence of hemophilia is considered. On the basis of idea of Danforth and Haldane about the balance mutagenesis and selection at presence of hemophilia, the inter-relation of selection parameter and the equivalent constant mutagen factor is found. It is shown, that dynamics of development of hemophilia in a family tree and in population are similar.

重庆市典型园林树种抗日灼能力评价研究

气候变化背景下,全球高温热浪增加导致夏季高温时间和日照强度增加,植物日灼问题加剧,但目前针对园林植物抗日灼性的研究较少。以重庆市为例,通过模拟光照试验,对重庆市8种常见园林树种的抗日灼指数、抗日灼程度、净光合速率、蒸腾速率等指标进行测定,并采用主成分分析综合评价园林树种的抗日灼能力。结果表明:可从形态指标和生理指标两方面来评价园林植物的抗日灼能力;依据抗日灼能力得分的高低,将8种树种分为3种类型,依次为抗日灼能力强(三角枫、香樟、金桂)、抗日灼能力中等(银杏、五角枫、鸡爪槭)和抗日灼能力弱(红枫、银桂)。