In the process of introducing an analytics application to an existing production, projects typically follow a process model for guidance and orientation. Most of the project consider a process like CRISP-DM that contains steps like business case analysis, data preparation, model building and testing. It is also very common to adopt some sort of iterative …
Data Preparation and User Labelling for Time Series Classification
In this article I want to share practical experience on applying classification algorithms for segmenting a large data set of industrial time series data. The data set used contains approx 100 sensors sampled parallel and equidistant, so we have a good source for our machine learning experiment. We are using the vectors representing the system …
kMeans for time series segmentation
In this post, we want to look at using k-Means to segment a multivariate time series. We consider the vector of the scalar values of the variables sampled at the same time as the system vector. The clustering will be executed in the feature space spanned by the variables; e.g. each variable provides one dimension …