Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms.
Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms.
复制标题
DOI：
10.3389/fpubh.2014.00036
复制
发表时间：
2014
影响因子：
5.2
通讯作者：
Kerr J
中科院分区：
文献类型：
--
作者：
Ellis K;Godbole S;Marshall S;Lanckriet G;Staudenmayer J;Kerr J
背景：主动出行是体力活动研究的一个重要领域，但对主动出行的客观测量仍然很困难。衡量出行行为的自动化方法将促进这一领域的研究。本文提出了一种利用全球定位系统(GPS)和加速度计数据进行交通方式预测的有监督机器学习方法。方法：我们从两名研究助理那里收集了大约150 h的全球定位系统和加速度计数据，按照规定的行程方案进行，包括五项活动：骑自行车、骑车、走路、坐着和站着。我们从这些数据的1分钟窗口中提取了49个特征。比较了几种机器学习算法的性能，选择了随机森林算法对交通方式进行分类。我们使用移动平均输出过滤器来平滑随时间推移的输出预测。结果：随机森林算法在该数据集上的交叉验证准确率达到89.8%。加入移动平均滤波平滑产量预测，交叉验证准确率提高到91.9%。结论：机器学习方法是自动测量主动旅行的一种可行方法，特别是对于传统加速度计数据处理方法错误分类的旅行活动，如骑自行车和车辆旅行。
Background: Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. Methods: We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. Results: The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Conclusion: Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel.