An Experimental Evaluation of Nearest Neighbour Time Series Classification
This work addresses the validity of baseline methods in time series classification for researchers, providing empirical evidence that challenges common assumptions, though it is incremental in nature.
The study evaluated the standard practice of using 1-NN with Euclidean or DTW distance for time series classification, finding that 1-NN with Euclidean is easy to beat, but 1-NN with DTW is not when window size is optimized through cross-validation, based on experiments across 77 problems.
Data mining research into time series classification (TSC) has focussed on alternative distance measures for nearest neighbour classifiers. It is standard practice to use 1-NN with Euclidean or dynamic time warping (DTW) distance as a straw man for comparison. As part of a wider investigation into elastic distance measures for TSC~\cite{lines14elastic}, we perform a series of experiments to test whether this standard practice is valid. Specifically, we compare 1-NN classifiers with Euclidean and DTW distance to standard classifiers, examine whether the performance of 1-NN Euclidean approaches that of 1-NN DTW as the number of cases increases, assess whether there is any benefit of setting $k$ for $k$-NN through cross validation whether it is worth setting the warping path for DTW through cross validation and finally is it better to use a window or weighting for DTW. Based on experiments on 77 problems, we conclude that 1-NN with Euclidean distance is fairly easy to beat but 1-NN with DTW is not, if window size is set through cross validation.