A Fuzzy-Probabilistic Representation Learning Method for Time Series Classification

Time series classification (TSC) is a supervised task in which time series data are associated with predefined classes. Time ordering and correlations of the samples should be considered and observations can have different lengths. Therefore, learning compact and useful representations is an important approach for TSC. Fuzzy time series (FTS) methods have the ability to find temporal patterns and transition rules. Probabilistic weighted FTS (PWFTS) uses the empirical probabilities to find the model of a TS. Despite its good performance, this method has been used exclusively for forecasting problems. Therefore, in this study we propose a novel TSC method using the PWFTS representation learning weights as features in conjunction to a classifier algorithm. We show that PWFTS method is able to learn useful representations for time series in low computational time. Our algorithm was tested in 24 datasets available in the UCR TSC archive and compared with state-of-the-art methods: fuzzy cognitive maps, Rocket, and TS2Vec in combination to the classifiers random forest and support vector machine. The classification accuracy and execution time required to find the features were evaluated. The results show that our fuzzy-probabilistic representation learning method is similar in accuracy to the other methods, and the time consumption for PWFTS computation was two to five orders of magnitude faster than the other methods. The results suggest that our approach can be used in time sensitive applications and in systems with hardware limitations.