標題: Dynamic Data Driven-based Automatic Clustering and Semantic Annotation for Internet of Things Sensor Data
作者: Lin, Szu-Yin
Li, Jun-Bin
Yu, Ching-Tzu
資訊管理與財務金融系 註:原資管所+財金所
Department of Information Management and Finance
關鍵字: clustering;semantic annotation;ontology;Internet of Things;sensor data
公開日期: 1-Jan-2019
摘要: Faced with the advent of the era of smart Internet of Things (IoT), a large amount of sensor data and a large number of intelligent applications have been introduced into our lives. However, the dynamic and multimodal nature of data makes it challenging to transform them into machine-readable and machine-interpretable forms. In this study, a semantic annotation method is proposed to annotate sensor data through semantics. First, the method constructs an initial ontology based on the semantic sensor network (SSN) ontology for dynamic loT sensor data. Second, through K-means clustering, new knowledge is extracted from input data, and the semantic information is used for updating the initial ontology. The updated ontology then forms the basis of semantic annotation. In this study, an experiment is performed to analyze the data collected from sensors every 10 s for a period of one month. From the results of simulation experiments, we found useful knowledge from new data. With more available knowledge, sensor data can be annotated with higher adequacy.
URI: http://dx.doi.org/10.18494/SAM.2019.2333
http://hdl.handle.net/11536/152291
ISSN: 0914-4935
DOI: 10.18494/SAM.2019.2333
期刊: SENSORS AND MATERIALS
Volume: 31
Issue: 6
起始頁: 1789
結束頁: 1801
Appears in Collections:Articles