作者: Yi-Cheng Chen , Chien-Chih Chen , Wen-Chih Peng , Wang-Chien Lee
DOI: 10.1007/978-3-319-06605-9_19
关键词:
摘要: Since the great advent of sensor technology, usage data appliances in a house can be logged and collected easily today. However, it is challenge for residents to visualize how these are used. Thus, mining algorithms much needed discover appliance patterns. Most previous studies on pattern discovery mainly focused analyzing patterns single rather than correlation among appliances. In this paper, novel algorithm, namely, Correlation Pattern Miner (CoPMiner), developed capture correlations probabilistically. With several new optimization techniques, CoPMiner reduce search space effectively efficiently. Furthermore, proposed algorithm applied real-world dataset show practicability mining.