Labeling sensing data for mobility modeling

详细信息    查看全文

• 作者：Jesse Read ; ^{jesse.read@aalto.fi" class="auth_mail" title="E-mail the corresponding author} ; Indrė Žliobaitė ^{indre.zliobaite@aalto.fi" class="auth_mail" title="E-mail the corresponding author} ; Jaakko Hollmé ; n ^{jaakko.hollmen@aalto.fi" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Sensory data ; Sensor fusion ; Hidden Markov models ; Multi-label
• 刊名：Information Systems
• 出版年：2016
• 出版时间：April 2016
• 年：2016
• 卷：57
• 期：Complete
• 页码：207-222
• 全文大小：1702 K

文摘

In urban environments, sensory data can be used to create personalized models for predicting efficient routes and schedules on a daily basis; and also at the city level to manage and plan more efficient transport, and schedule maintenance and events. Raw sensory data is typically collected as time-stamped sequences of records, with additional activity annotations by a human, but in machine learning, predictive models view data as labeled instances, and depend upon reliable labels for learning. In real-world sensor applications, human annotations are inherently sparse and noisy. This paper presents a methodology for preprocessing sensory data for predictive modeling in particular with respect to creating reliable labeled instances. We analyze real-world scenarios and the specific problems they entail, and experiment with different approaches, showing that a relatively simple framework can ensure quality labeled data for supervised learning. We conclude the study with recommendations to practitioners and a discussion of future challenges.