• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on HCI in Mobility, Transport, and Automotive Systems;International Conference on Human-Computer Interaction >Monitoring Road Surface Conditions for Bicycles - Using Mobile Device Sensor Data from Crowd Sourcing
【24h】

Monitoring Road Surface Conditions for Bicycles - Using Mobile Device Sensor Data from Crowd Sourcing

机译：监视自行车的路面状况-使用来自人群采购的移动设备传感器数据

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper introduces an approach for monitoring cycleway conditions by collecting crowdsourced data from mobile devices. To collect the data, an application was developed and optimized to be used by many cyclists. The application uses acceleration and gyroscopic sensors to collect and upload road roughness data into a classification platform. A classification model classifies the monitored routes into three quality classes and synchronizes the results with the application. The methodology shows how to collect and classify road surface conditions of cycleways. By using the K-Nearest Neighbor machine learning algorithm as a classifier, we were able to achieve a forecast accuracy above 90% on average. We report on our experiences with classification accuracy of four different classifiers as well as the experimental evaluations of the system. The results support the potential development of a community portal that provides detected cycleway conditions from the up-to-date mobile crowdsensing application.
机译：本文介绍了一种通过收集来自移动设备的众包数据来监视自行车道状况的方法。为了收集数据，开发并优化了一个应用程序，以供许多骑自行车的人使用。该应用程序使用加速度和陀螺仪传感器来收集路面不平度数据并将其上传到分类平台。分类模型将受监视的路由分为三个质量类别，并将结果与​​应用程序同步。该方法论展示了如何收集和分类自行车道的路面状况。通过使用K最近邻机器学习算法作为分类器，我们能够实现平均90％以上的预测准确性。我们报告了我们在四个不同分类器分类精度方面的经验以及对系统的实验评估。结果支持社区门户的潜在发展，该社区门户从最新的移动人群感应应用程序提供检测到的自行车道状况。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号