Statistical method for prediction of gait kinematics with Gaussian process regression

We propose a novel methodology for predicting human gait pattern kinematics based on a statistical and stochastic approach using a method called Gaussian process regression (GPR). We selected 14 body parameters that significantly affect the gait pattern and 14 joint motions that represent gait kinematics. The body parameter and gait kinematics data were recorded from 113 subjects by anthropometric measurements and a motion capture system. We generated a regression model with GPR for gait pattern prediction and built a stochastic function mapping from body parameters to gait kinematics based on the database and GPR, and validated the model with a cross validation method. The function can not only produce trajectories for the joint motions associated with gait kinematics, but can also estimate the associated uncertainties. Our approach results in a novel, low-cost and subject-specific method for predicting gait kinematics with only the subject's body parameters as the necessary input, and also enables a comprehensive understanding of the correlation and uncertainty between body parameters and gait kinematics.     

Predicting walnut (Juglans spp.) crop yield using meteorological and airborne pollen data

Crop yield determines economy by influencing prices on the trade market, and so accurate forecasts of the yield are important for planning various aspects of agricultural production. The main aim of this study is to construct a model for predicting walnut yield in an important walnut production area (the region of Novi Sad in Northern Serbia). Relationships between the amount of walnuts produced annually (2000–2011) and abiotic (e.g. meteorological) and biotic (e.g. airborne pollen data) factors were examined using Pearson correlation analysis. Walnut yield data were then entered into linear regression models with variables that had the highest correlations. The models were constructed using 10 years of data, and tested using 2 years of data not included in constructing the model. This paper has shown that walnut yield is greatly dependent on weather conditions, particularly during fertilisation and seed growth, but the amount of available airborne pollen also plays an important role. The introduction of the seasonal pollen index, as a proxy for the amount of pollen available for fertilisation, improved the performance of models predicting walnut yield.     

Energy–water and seasonal variations in climate underlie the spatial distribution patterns of gymnosperm species richness in China

Studying the pattern of species richness is crucial in understanding the diversity and distribution of organisms in the earth. Climate and human influences are the major driving factors that directly influence the large‐scale distributions of plant species, including gymnosperms. Understanding how gymnosperms respond to climate, topography, and human‐induced changes is useful in predicting the impacts of global change. Here, we attempt to evaluate how climatic and human‐induced processes could affect the spatial richness patterns of gymnosperms in China. Initially, we divided a map of the country into grid cells of 50 × 50 km² spatial resolution and plotted the geographical coordinate distribution occurrence of 236 native gymnosperm taxa. The gymnosperm taxa were separated into three response variables: (a) all species, (b) endemic species, and (c) nonendemic species, based on their distribution. The species richness patterns of these response variables to four predictor sets were also evaluated: (a) energy–water, (b) climatic seasonality, (c) habitat heterogeneity, and (d) human influences. We performed generalized linear models (GLMs) and variation partitioning analyses to determine the effect of predictors on spatial richness patterns. The results showed that the distribution pattern of species richness was highest in the southwestern mountainous area and Taiwan in China. We found a significant relationship between the predictor variable set and species richness pattern. Further, our findings provide evidence that climatic seasonality is the most important factor in explaining distinct fractions of variations in the species richness patterns of all studied response variables. Moreover, it was found that energy–water was the best predictor set to determine the richness pattern of all species and endemic species, while habitat heterogeneity has a better influence on nonendemic species. Therefore, we conclude that with the current climate fluctuations as a result of climate change and increasing human activities, gymnosperms might face a high risk of extinction.     

Relationships between taxonomic and functional components of diversity: implications for conservation of tropical freshwater fishes

相似文献   

MONITORING THE TREND OF HARBOR SEALS IN PRINCE WILLIAM SOUND,ALASKA, AFTER THE EXXON VALDEZ OIL SPILL

We used aerial counts to monitor the trend in numbers of harbor seals, Phoca vitulina richardsi, in Prince William Sound, Alaska, following the 1989 Exxon Valdez oil spill. Repetitive counts were made at 25 haul-out sites during the annual molt period each year from 1990 through 1997. A generalized linear model indicated that time of day, date, and time relative to low tide significantly affected seal counts. When Poisson regression was used to adjust counts to a standardized set of survey conditions, results showed a highly significant decline of 4.6% per year. Unadjusted counts indicated a slight, but not statistically significant, decline in the number of seals. The number of harbor seals on the trend-count route in eastern and central PWS has been declining since at least 1984, with an overall population reduction of 63% through 1997. Programs to monitor long-term changes in animal population sizes should account for factors that can cause short-term variations in indices of abundance. The inclusion of such factors as covariates in models can improve the accuracy of monitoring programs.     

VPMCD: variable interaction modeling approach for class discrimination in biological systems

Data classification algorithms applied for class prediction in computational biology literature are data specific and have shown varying degrees of performance. Different classes cannot be distinguished solely based on interclass distances or decision boundaries. We propose that inter-relations among the features be exploited for separating observations into specific classes. A new variable predictive model based class discrimination (VPMCD) method is described here. Three well established and proven data sets of varying statistical and biological significance are utilized as benchmark. The performance of the new method is compared with advanced classification algorithms. The new method performs better during different tests and shows higher stability and robustness. The VPMCD is observed to be a potentially strong classification approach and can be effectively extended to other data mining applications involving biological systems.     

模糊线性回归模型在河流水体总氮浓度预测中的应用

以湘江熬洲断面为例,将该断面水体中总氮浓度及其有关影响因子用三角模糊数来表征.同时,结合己有的模糊线性回归模型成果,构造了带有三角模糊参数的水体中总氮浓度模糊线性回归预测模型.并应用所建模型预测该断面水体中2002-2005年总氮浓度,所得的预测值与已有的实测值之间的相对误差均小于20%,完全满足实际应用对误差的要求,预测合格率为100%,说明这种预测模型在预测河流水体总氮浓度变化中有一定的实用性,为今后开展河流水体中污染物浓度预测提供了新途径.     

基于土地利用及植被覆盖变化的黄河源区生境质量时空变化特征

位于青藏高原腹地的黄河源地区生态环境脆弱,面临生物多样性锐减、生态系统退化等问题,黄河源区生态系统保护及其高质量发展已成为国家的重点战略之一。土地利用与植被覆盖是影响生境质量的重要因素,定量化土地利用方式、强度及格局和植被覆盖格局对生态质量影响的研究越来越受到关注,但其对黄河源区生态质量的耦合效应尚不明确。基于2000年和2015年黄河源区土地利用类型及生长季归一化植被指数（NDVI）,采用InVEST模型探究了不同时期黄河源区生境质量时空变化,并采用地理加权回归（GWR）模型揭示了生境质量对土地利用和植被覆盖变化的空间响应特征。结果表明,2000年与2015年土地利用类型变化主要为未利用土地向草地的转移。植被覆盖变化方面,源区生长季NDVI整体上升。从生境质量的空间分布来看,黄河源区生境质量总体呈现南高北低的空间格局,高值分布在南部及中部地区,低值分布在北部布青山、东北部高海拔区及黄河乡的黄河沿岸。相较于2000年,2015年黄河源区生境质量平均提高11.47%。草地面积和NDVI与生境质量均呈显著正相关关系,其中NDVI是提高黄河源区生境质量的重要驱动因子。研究结果突出了NDVI对提高黄河源区生境质量的主导作用,可为未来源区生态保护提供借鉴。     

基于地理加权模型的南设得兰群岛北部南极磷虾渔场空间分布影响分析

结合南极磷虾渔业科学观察员收集的渔业数据和海洋环境数据,本研究利用地理加权回归模型(GWR),分析了具有空间属性的虾群深度和离岸距离两个因子,以及海水表温对南设得兰群岛北侧水域南极磷虾渔场空间分布的影响.结果表明:各年南极磷虾渔业单位捕捞努力量渔获量(CPUE)在空间上的分布无显著的集聚性;2010和2013年,3个因子之间存在空间自相关性(正相关),而2012和2016年则无自相关性.GWR模型结果显示,3个因子对CPUE的空间分布具有不同程度的影响,影响程度大小依次为虾群深度>离岸距离>温度.拟合结果发现,南设得兰群岛东、西两侧水域中表温对CPUE空间分布的影响与其他两个因子具有相反的趋势.虾群深度和离岸距离对CPUE的空间效应主要表现为负相关,但存在着年际和区域性差异.本研究结果可为南极磷虾渔场形成机制研究提供方法上的参考.