TY - JOUR
T1 - Dissimilarity-based representations for one-class classification on time series
AU - Mauceri, Stefano
AU - Sweeney, James
AU - McDermott, James
N1 - Publisher Copyright:
© 2019
PY - 2020/4
Y1 - 2020/4
N2 - In several real-world classification problems it can be impractical to collect samples from classes other than the one of interest, hence the need for classifiers trained on a single class. There is a rich literature concerning binary and multi-class time series classification but less concerning one-class learning. In this study, we investigate the little-explored one-class time series classification problem. We represent time series as vectors of dissimilarities from a set of time series referred to as prototypes. Based on this approach, we evaluate a Cartesian product of 12 dissimilarity measures, and 8 prototype methods (strategies to select prototypes). Finally, a one-class nearest neighbor classifier is used on the dissimilarity-based representations (DBR). Experimental results show that DBR are competitive overall when compared with a strong baseline on the data-sets of the UCR/UEA archive. Additionally, DBR enable dimensionality reduction, and visual exploration of data-sets.
AB - In several real-world classification problems it can be impractical to collect samples from classes other than the one of interest, hence the need for classifiers trained on a single class. There is a rich literature concerning binary and multi-class time series classification but less concerning one-class learning. In this study, we investigate the little-explored one-class time series classification problem. We represent time series as vectors of dissimilarities from a set of time series referred to as prototypes. Based on this approach, we evaluate a Cartesian product of 12 dissimilarity measures, and 8 prototype methods (strategies to select prototypes). Finally, a one-class nearest neighbor classifier is used on the dissimilarity-based representations (DBR). Experimental results show that DBR are competitive overall when compared with a strong baseline on the data-sets of the UCR/UEA archive. Additionally, DBR enable dimensionality reduction, and visual exploration of data-sets.
KW - Dissimilarity-based representations
KW - One-class classification
KW - Time series
UR - http://www.scopus.com/inward/record.url?scp=85075502805&partnerID=8YFLogxK
U2 - 10.1016/j.patcog.2019.107122
DO - 10.1016/j.patcog.2019.107122
M3 - Article
AN - SCOPUS:85075502805
SN - 0031-3203
VL - 100
JO - Pattern Recognition
JF - Pattern Recognition
M1 - 107122
ER -