中国高技能劳动力与一般劳动力的空间分布格局及其影响因素

基于2000和2010年全国人口普查分县数据和地级行政单元数据,采用不均衡指数和空间自相关分析等方法,刻画中国高技能劳动力和一般劳动力的空间分布格局及其变化,并采用空间滞后模型,识别高技能劳动力与一般劳动力空间分布的决定因素及其变化。结果表明：① 两类劳动力总体的空间特征均为东南密集,西北稀疏;② 2000—2010年,高技能劳动力在空间分布上呈集中化的趋势,而一般劳动力呈分散化的趋势;③ 十年间高技能劳动力集聚区虹吸作用加强,其分布越发集中于沿海特大城市群,而一般劳动力集聚区回波作用加强,其分布越发均衡;④ 空间回归分析结果表明,职工平均工资、是否直辖市或省会、每万人在校高校学生、是否沿海城市、常住人口数和空间溢出效应在十年中一直都是决定高技能劳动力和一般劳动力空间分布的主要因素,而失业率、中学生师比、二氧化硫排放量和绿地率在2010年也成为影响两类劳动力空间分布的主要因素。对比两类劳动力的模型结果可得,高技能劳动力的空间分布受行政因素、高校因素和地区生活舒适度的影响更大,而一般劳动力的空间分布受劳动力市场因素的影响更大。     

毛蚶天津群体形态性状对体质量的影响研究

为探讨形态性状对体质量的影响,指导毛蚶的选育,以毛蚶天津群体为研究对象,测量壳长、壳宽、壳高、体质量,并进行统计分析。结果表明,壳宽是体质量的主要影响因子,其与体质量的相关系数为0.953,直接作用为0.505,间接作用为0.448,壳长、壳高间接作用分别为0.483、0.480,综合决定系数为0.706 6。毛蚶体质量多元回归方程为Y=-40.8+0.438X1+1.124X2+0.469X3,R2=0.924;以壳宽为自变量,体质量回归方程为:Y=5.443×10-3X22.519,R2=0.937。     

Relationships between body weight and other morphological traits in young sea cucumbers Apostichopus japonicas

Correlation, multiple regression, and path analyses were used to investigate the relationships between body weight and three other morphological traits in juvenile Japanese sea cucumbers Apostichopus japonicus . We measured live body weight (BW), body length (BL), numbers of papillae (NP), and numbers of tube feet (NF) at 60, 80, 100, and 130 days post-hatching (dph). We calculated path correlation coefficients, correlation indices ( R 2 ), and coefficients of determination with BW as the dependent variable and the other morphological traits as independent variables. The coefficient of variation for BW was high across all age groups, and all measured morphological traits were significantly correlated ( P < 0.01). BL had the greatest direct eff ect on BW across all age groups (60 dph, 0.526;80 dph, 0.404;100 dph, 0.620;and 130 dph, 0.681), while NF had the greatest indirect eff ect on BW across all age groups (60 dph, 0.528;80 dph, 0.452;100 dph, 0.666;and 130 dph, 0.603). Regression analyses between morphological traits and BW indicated that R 2 was greater than 0.85 only in the 100-dph specimens. The indirect eff ects of the other measured morphological traits on BW were age-dependent. The optimal regression equations, as determined with stepwise regression, were, for 60-dph specimens: BW 60 =10 (-3.04+0.092BL+0.014NP+0.014NF)( R 2 =0.632);for 80-dph specimens: BW 80 =10 (- 3.035+0.056BL+0.017NP+0.02NF)( R 2 =0.686);for 100-dph specimens: BW 100 =10 (- 3.742+0.069BL+0. 633 · lg (NP)+0. 464 · lg (NF))( R 2 =0.893);and for 130-dph specimens: BW 130 =10 (- 2.472+0.065BL+0.012NP)( R 2 =0.774). Our work clarified the correlation between various morphological traits and body weight of a commercially-important sea cucumber species ( A . japonicus ). Our predictive models for body weight might be useful for the aquaculture and selective breeding of A . japonicus . These models might also provide theoretical support for the indirect selection of traits that are difficult to select directly.     

Geospatial data mining for digital raster mapping

We performed an in-depth literature survey to identify the most popular data mining approaches that have been applied for raster mapping of ecological parameters through the use of Geographic Information Systems (GIS) and remotely sensed data. Popular data mining approaches included decision trees or “data mining” trees which consist of regression and classification trees, random forests, neural networks, and support vector machines. The advantages of each data mining approach as well as approaches to avoid overfitting are subsequently discussed. We also provide suggestions and examples for the mapping of problematic variables or classes, future or historical projections, and avoidance of model bias. Finally, we address the separate issues of parallel processing, error mapping, and incorporation of “no data” values into modeling processes. Given the improved availability of digital spatial products and remote sensing products, data mining approaches combined with parallel processing potentials should greatly improve the quality and extent of ecological datasets.     

基于AHP-PSR模型的西南丘陵地区农用地集约利用动态评价

针对西南丘陵地区农用地利用效率低、耕地质量锐减、人地关系逐步恶化等问题构建了基于AHP-PSR模型的西南丘陵地区农用地集约利用评价系统。采用专家打分法进行指标筛选后,基于AHP-PSR模型进行农用地集约利用动态评价,对系统内部协调及稳定性进行分析、评估,较深入地研究农用地集约利用驱动因子,并采用最优子集选取策略分析集约利用驱动力,以避免仅以简单相关性就加入或剔除驱动力因素导致回归系数不符合实际内涵的现象。实验表明:可利用系统调整指标间权重,动态展示人地关系协调可持续发展关系,其分析结果可供有关部门决策参考。     

顾及局部与结构特征的稀疏多项式逻辑回归高光谱图像分类方法

稀疏多项式逻辑回归在分类中仅利用图像光谱信息,导致分类效果不太理想.本文提出了一种顾及局部与结构特征的稀疏多项式逻辑回归高光谱图像分类方法.首先利用加权均值滤波与拓展形态学多属性剖面对原始高光谱图像进行局部与结构特征提取;然后对二者进行加权平均特征级融合以获取更具唯一性的像元特征;最后由稀疏多项式逻辑回归分类器对融合结果进行分类.结果表明,本文方法能有效地提高分类精度,而且具有较强的稳健性.     

顾及空间非平稳特征的遥感干旱监测

遥感技术具备实时快速、时空连续、广覆盖尺度等独特优势,在全球气候恶化大背景下,利用遥感干旱监测方法相比于传统地面监测手段,能够提供实时、准确、稳定的旱情信息,辅助科学决策。目前常用遥感旱情监测方法大多依赖全域性数学模型建模,假定了旱情模式的空间平稳特性,因而难以准确反映旱情模式的局部差异特征。本文提出利用地理加权回归模型GWR (Geographically Weighted Regression),考虑旱情模式的空间非平稳特性,综合多种遥感地面旱情监测指数,以实现传统全域旱情监测模型的局部优化。以美国大陆为研究区,监测2002年—2011年共10年的旱情状态。研究表明,GWR模型能够提供空间变化的局部最佳估计模型参数,监测结果更加吻合标准美国旱情监测USDM (U.S Drought Monitor)验证数据,且与地面实测值的最高相关系数R达到0.8552,均方根误差RMSE达到0.972,显著优于其他遥感旱情监测模型。GWR模型具备空间非平稳探测优势,实现了旱情模式的局部精细探测,能够显著提升遥感旱情监测精度,具备较好的应用前景。     

DMSP/OLS夜间灯光数据的四川省GDP空间化分析

针对DMSP/OLS夜间灯光数据模拟省级格网GDP问题,该文选取2000、2006以及2010年DMSP/OLS稳定夜间灯光数据、辐射定标夜间灯光数据和四川省第二、三产业社会经济GDP数据,运用相关性分析、对比分析以及回归分析的方法,模拟出四川省GDP空间化密度图并分析与高程之间的关系。结果表明:在省级范围内,GDP与辐射定标灯光数据的相关性明显高于与稳定灯光数据的相关性,且前者的灯光指数CNLI与GDP相关性最高;运用3年的辐射定标灯光数据模拟得到四川省GDP密度图与GDP统计数据的拟合精度均达到0.99以上;2000-2010年四川省GDP呈现由成都市向四周不断扩张的趋势并随高程变化显著,四川省GDP高值区主要集中在高程1 000m以下的成都平原及周边区域,西部高原和山地地区GDP值较低。     

Building a model-based personalised recommendation approach for tourist attractions from geotagged social media data

When travelling, people are accustomed to taking and uploading photos on social media websites, which has led to the accumulation of huge numbers of geotagged photos. Combined with multisource information (e.g. weather, transportation, or textual information), these geotagged photos could help us in constructing user preference profiles at a high level of detail. Therefore, using these geotagged photos, we built a personalised recommendation system to provide attraction recommendations that match a user's preferences. Specifically, we retrieved a geotagged photo collection from the public API for Flickr (Flickr.com) and fetched a large amount of other contextual information to rebuild a user's travel history. We then created a model-based recommendation method with a two-stage architecture that consists of candidate generation (the matching process) and candidate ranking. In the matching process, we used a support vector machine model that was modified for multiclass classification to generate the candidate list. In addition, we used a gradient boosting regression tree to score each candidate and rerank the list. Finally, we evaluated our recommendation results with respect to accuracy and ranking ability. Compared with widely used memory-based methods, our proposed method performs significantly better in the cold-start situation and when mining ‘long-tail’ data.     

珠江流域夏半年降水的预测

采用珠江流域1954～2003年月降水资料,以及前期太平洋海温场和北半球500 hPa高度场月平均资料,利用主分量逐步回归预测模型,对该流域夏半年(4～9月)降水分布进行主分量计算和预测.结果表明:对前25个主分量的预测就能很好地预测珠江流域夏半年降水的变化,2004～2006年预测结果与实况较接近.预测因子取自500 hPa高度场和海温场的主分量,为降水的预测提供大量有用信息.该方法在实际业务中有一定的应用价值.