%0 Journal Article %1 Schäfer2016 %A Schäfer, Patrick %D 2016 %J Data Mining and Knowledge Discovery %K analysis bow series time toread %N 5 %P 1273--1298 %R 10.1007/s10618-015-0441-y %T Scalable time series classification %U http://dx.doi.org/10.1007/s10618-015-0441-y %V 30 %X Time series classification tries to mimic the human understanding of similarity. When it comes to long or larger time series datasets, state-of-the-art classifiers reach their limits because of unreasonably high training or testing times. One representative example is the 1-nearest-neighbor dynamic time warping classifier (1-NN DTW) that is commonly used as the benchmark to compare to. It has several shortcomings: it has a quadratic time complexity in the time series length and its accuracy degenerates in the presence of noise. To reduce the computational complexity, early abandoning techniques, cascading lower bounds, or recently, a nearest centroid classifier have been introduced. Still, classification times on datasets of a few thousand time series are in the order of hours. We present our Bag-Of-SFA-Symbols in Vector Space classifier that is accurate, fast and robust to noise. We show that it is significantly more accurate than 1-NN DTW while being multiple orders of magnitude faster. Its low computational complexity combined with its good classification accuracy makes it relevant for use cases like long or large amounts of time series or real-time analytics.

@article{Schäfer2016, abstract = {Time series classification tries to mimic the human understanding of similarity. When it comes to long or larger time series datasets, state-of-the-art classifiers reach their limits because of unreasonably high training or testing times. One representative example is the 1-nearest-neighbor dynamic time warping classifier (1-NN DTW) that is commonly used as the benchmark to compare to. It has several shortcomings: it has a quadratic time complexity in the time series length and its accuracy degenerates in the presence of noise. To reduce the computational complexity, early abandoning techniques, cascading lower bounds, or recently, a nearest centroid classifier have been introduced. Still, classification times on datasets of a few thousand time series are in the order of hours. We present our Bag-Of-SFA-Symbols in Vector Space classifier that is accurate, fast and robust to noise. We show that it is significantly more accurate than 1-NN DTW while being multiple orders of magnitude faster. Its low computational complexity combined with its good classification accuracy makes it relevant for use cases like long or large amounts of time series or real-time analytics.}, added-at = {2017-01-12T14:37:49.000+0100}, author = {Sch{\"a}fer, Patrick}, biburl = {https://www.bibsonomy.org/bibtex/209ea3a81eee066937b0856fdc109bfc6/hotho}, doi = {10.1007/s10618-015-0441-y}, interhash = {6e33e074a200f315456986ed0be8a81d}, intrahash = {09ea3a81eee066937b0856fdc109bfc6}, issn = {1573-756X}, journal = {Data Mining and Knowledge Discovery}, keywords = {analysis bow series time toread}, number = 5, pages = {1273--1298}, timestamp = {2017-01-12T14:37:49.000+0100}, title = {Scalable time series classification}, url = {http://dx.doi.org/10.1007/s10618-015-0441-y}, volume = 30, year = 2016 }