图 书 馆
识别移动数据中的事件Identifying events in mobility data |
|
| 课程网址: | http://videolectures.net/sikdd2019_kavsek_mobility_data/ |
| 主讲教师: | Branko Kavšek |
| 开课单位: | 约瑟夫·斯特凡学院 |
| 开课时间: | 2019-11-14 |
| 课程语种: | 英语 |
| 中文简介: |  今天，我们习惯于通过智能手机进行互连，并通过不同的应用程序跟踪手机的位置。 ICT技术可以实时监控和处理来自手机GPS坐标的用户位置数据。基于观察用户的移动性，人工智能方法可用于改善交通运输，主动提供移动性建议并使用用户上下文获取知识。本文介绍了机器学习算法在用户移动性数据上的应用，以识别和理解潜在的有趣事件。这项研究的数据来自同意通过我们内部开发的智能手机应用程序进行监视的用户样本。一项对227个用户进行了7年跟踪跟踪的初步研究在确定事件的预测准确性方面产生了相当积极的评估结果，但成功地识别了与用户去办公室或从办公室来的用户相关的“知名”事件/或午餐。这表明机器学习方法可能是识别移动数据中事件的合适选择，但仍有改进的空间。 |
| 课程简介: | Today we are used to being interconnected via our smartphones and having our phone location tracked by different apps. ICT technology enables real-time monitoring and processing the user location data from GPS coordinates of a phone. Based on observing the user mobility, Artificial Intelligence methods can be used to improve transportation, proactively provide mobility recommendations and acquire knowledge using the user context. This paper describes the application of machine learning algorithms on user mobility data to identify and understand potentially interesting events. The data for this research was collected from a sample of users consenting to be monitored through our in-house developed smart phone app. A pilot study that includes 227 users that were tracked over a period of 7 years yields fairly positive evaluation results in terms of predictive accuracy of identified events but succeeds in identifying exclusively “well-known” events related to users going to or coming from the office and/or lunch. This shows that machine learning methods can be a suitable choice for identifying events in mobility data but there is still room for improvement. |
| 关 键 词: | 机器学习算法; 移动数据; 事件识别 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-11-29：cjy |
| 最后编审: | 2021-01-08：yumf |
| 阅读次数: | 28 |