Clustering Structure Analysis in Time-Series Data With Density-Based Clusterability Measure

Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algorithms force a structure in the data instead of discovering one.To avoid false structures in the relations of data,a novel clusterability assessment method called density-based clusterability measure is proposed in this paper.I measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningfu insight to the relationships in the data.This is especially useful in time-series data since visualizing the structure in time-series data is hard.The performance of the clusterability measure is evalu ated against several synthetic data sets and time-series data sets which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data.

Self-Learning of Multivariate Time Series Using Perceptually Important Points

In machine learning,positive-unlabelled(PU)learning is a special case within semi-supervised learning.In positiveunlabelled learning,the training set contains some positive examples and a set of unlabelled examples from both the positive and negative classes.Positive-unlabelled learning has gained attention in many domains,especially in time-series data,in which the obtainment of labelled data is challenging.Examples which originate from the negative class are especially difficult to acquire.Self-learning is a semi-supervised method capable of PU learning in time-series data.In the self-learning approach,observations are individually added from the unlabelled data into the positive class until a stopping criterion is reached.The model is retrained after each addition with the existent labels.The main problem in self-learning is to know when to stop the learning.There are multiple,different stopping criteria in the literature,but they tend to be inaccurate or challenging to apply.This publication proposes a novel stopping criterion,which is called Peak evaluation using perceptually important points,to address this problem for time-series data.Peak evaluation using perceptually important points is exceptional,as it does not have tunable hyperparameters,which makes it easily applicable to an unsupervised setting.Simultaneously,it is flexible as it does not make any assumptions on the balance of the dataset between the positive and the negative class.