id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_5kks6ebnnbfdhpdqj4inpbgo6e	Julien Rabatel	Anomaly detection in monitoring sensor data for preventive maintenance	2011	14	.pdf	application/pdf	11316	1325	67	We thus obtain knowledge classes that describe very precisely normal train behavior and also provide us with essential The data resulting from sensors for train maintenance is complex for the two following reasons: (i) very often errors and noisy Note that the numerical values collected by the sensors are then discretized to obtain a set of data more suited to Data collected from a train constitutes a list of readings describing its behavior over time. In this section, we focus on the data mining step in the knowledge discovery process and more precisely on the extraction of patterns characterizing normal behavior. a data sequence as normal or abnormal, but provides also very precise information about the anomaly detected: the localization of Anomaly detection in monitoring sensor data for preventive maintenance Anomaly detection in monitoring sensor data for preventive maintenance Anomaly detection in monitoring sensor data for preventive maintenance	./cache/work_5kks6ebnnbfdhpdqj4inpbgo6e.pdf	./txt/work_5kks6ebnnbfdhpdqj4inpbgo6e.txt