Using crowdsourced fitness tracker data to model the relationship between slope and travel rates
Using crowdsourced fitness tracker data to model the relationship between slope and travel rates
复制标题
DOI：
10.1016/j.apgeog.2019.03.008
复制
发表时间：
2019-05-01
影响因子：
4.9
通讯作者：
Page, Wesley G.
中科院分区：
文献类型：
--
作者：
Campbell, Michael J.;Dennison, Philip E.;Page, Wesley G.
在徒步旅行、慢跑或沿着沿着跑步时，影响旅行速度的关键因素之一是底层地形的坡度。用于预测这种影响的模型已被用于各种科学和应用背景，包括娱乐规划，搜索和救援，荒地消防员安全，社会网络分析，并重建历史人类运动模式。尽管它们的广泛使用，这些模型是基于非常小的样本量的数据集，收集不使用瞬时测量的旅行率，并假设对称的最大旅行率的斜率的影响。这些模型通常也会导致一个单一的数学函数，忽略了快速和慢速个体之间或步行和跑步旅行速率之间可能发生的显著变化。在这项研究中，我们使用29，928人的GPS轨迹数据库对旅行率进行了建模，这些人代表了犹他湖城及其周边地区的421，247次徒步旅行，慢跑和跑步，时间为2016年7月1日至2017年6月30日。三个广泛使用的概率分布函数（拉普拉斯，高斯和洛伦兹）被用来预测旅行速率的基础上，地形坡度沿着段的小径具有均匀的坡度。为了说明快速和慢速移动之间旅行率的变化，生成了一系列旅行率模型来预测旅行率斜率，范围从第1到第99，从而为预测作为斜率函数的旅行率提供了灵活的基础。大量的样本使我们能够引入一个新的术语，解释上坡和下坡旅行率的不对称性。所有三个函数均表现良好，洛伦兹百分位数模型的平均R-2为0.958，平均绝对误差（MAE）为0.078 m/s，拉普拉斯的R-2为0.953，MAE为0.088 m/s，高斯的R-2为0.949，MAE为0.090 m/s。所有这三个功能在估计较低的旅行费率时都表现得明显更好（例如，第五：R-洛伦兹（2）= 0.941; R-拉普拉斯（2）= 0.940; R-高斯（2）= 0.934），与较高的（例如，第95位：R-Lorentz（2）= 0.914; R-Laplace（2）= 0.913; R-Gauss（2）= 0.908），表明步行速率比最快跑步速率具有更大的一致性。Lorentz在最大范围内（第5、30 - 90位）的预测性能优于其他函数，因此推荐用作灵活的旅行率预测函数。然而，拉普拉斯倾向于在中等低的旅行速率下（第10 - 25次）产生最好的结果，这表明两种模型的组合可以产生最高的精度。本研究结果为未来研究提供了一个坚实的基础，旨在估计旅行率，而徒步旅行或运行沿着斜坡。
One of the critical factors affecting travel rates while hiking, jogging, or running along a trail is the slope of the underlying terrain. Models for predicting this effect have been used in a wide variety of scientific and applied contexts, including recreation planning, search and rescue, wildland firefighter safety, social network analysis, and recreating historical human movement patterns. Despite their wide use, these models are based on datasets with very small sample sizes that were collected without using instantaneous measures of travel rate and assume symmetrical effects about the slope of maximum travel rate. These models also typically resulted in a single mathematical function, ignoring the significant variability that can occur between a fast and a slow individual, or between walking and running travel rates. In this study we modeled travel rates using a database of GPS tracks from 29,928 individuals representing 421,247 individual hikes, jogs, and runs on trails in and around Salt Lake City, Utah for an entire year between July 1, 2016 and June 30, 2017. Three widely-used probability distribution functions (Laplace, Gauss, and Lorentz) were used to predict travel rates based on terrain slope along segments of trails with uniform slopes. To account for the variability in travel rates between fast and slow movement, a series of travel rate models were generated to predict travel rate percentiles, ranging from the 1st to the 99th, thus providing a flexible basis for predicting travel rates as a function of slope. The large number of samples allowed us to introduce a novel term that accounts for asymmetry in travel rates on uphill and downhill slopes. All three functions performed well, with Lorentz percentile models averaging an R-2 of 0.958 and a mean absolute error (MAE) of 0.078 m/s, Laplace with R-2 of 0.953 and MAE of 0.088 m/s, and Gauss with R-2 of 0.949 and MAE of 0.090 m/s. All three functions performed notably better at estimating lower travel rate percentiles (e.g. 5th: R-Lorentz(2) = 0.941; R-Laplace(2) = 0.940; R-Gauss(2) = 0.934) as compared to higher (e.g. 95th: R-Lorentz(2) = 0.914; R-Laplace(2) = 0.913; R-Gauss(2) = 0.908), indicating greater consistency in walking rates than the fastest running rates. Lorentz outperformed the other functions for the widest range of percentiles (5th, 30th-90th), and thus is recommended for use as a flexible travel rate prediction function. However, Laplace tended to produce the best results at moderately-low travel rate percentiles (10th-25th), suggesting a combination of the two models could produce the highest accuracies. The results of this research provide a sound basis for future studies aiming to estimate travel rates while hiking or running along slopes.