期刊名称：International Journal of Multimedia and Ubiquitous Engineering
印刷版ISSN：1975-0080
出版年度：2015
卷号：10
期号：2
页码：129-136
DOI：10.14257/ijmue.2015.10.2.12
出版社：SERSC
摘要：Sensors perform various activities to detect in a recent environment of Internet of things and ubiquitous sensor network. A single sensor detects multi-events in some cases while multi-sensors detect a single event and report in some other cases. The study presented a way of data clustering to classify events detected by a single sensor in circumstances where information is obtained by a form of data stream. Data was grouped in three types of events when clustering was applied for sensor data detected and reported. The following results also showed that clustering distinguished the events in the consequent time timeslots. The clusters displayed changing patterns with time. This result would contribute to the study field of context inference based on data stream.
关键词：Data Stream Mining; Internet of Things; Data Clustering
