QUANT: A Minimalist Interval Method for Time Series Classification
This provides a fast and accurate solution for time series classification tasks, though it is incremental as it simplifies existing interval-based approaches.
The paper tackles time series classification by proposing a minimalist interval method that achieves the same average accuracy as the most accurate existing interval methods using only quantile features, fixed intervals, and an off-the-shelf classifier. It achieves state-of-the-art accuracy on 142 UCR datasets with a total compute time of less than 15 minutes on a single CPU core.
We show that it is possible to achieve the same accuracy, on average, as the most accurate existing interval methods for time series classification on a standard set of benchmark datasets using a single type of feature (quantiles), fixed intervals, and an 'off the shelf' classifier. This distillation of interval-based approaches represents a fast and accurate method for time series classification, achieving state-of-the-art accuracy on the expanded set of 142 datasets in the UCR archive with a total compute time (training and inference) of less than 15 minutes using a single CPU core.