Time Series Classification
121 papers with code • 29 benchmarks • 5 datasets
Time Series Classification is a general task that can be useful across many subject-matter domains and applications. The overall goal is to identify a time series as coming from one of possibly many sources or predefined groups, using labeled training data. That is, in this setting we conduct supervised learning, where the different time series sources are considered known.
This problem is especially hard to solve for time series classification and regression in industrial applications such as predictive maintenance or production line optimization, for which each label or regression target is associated with several time series and meta-information simultaneously.
In order to assess the methods and implementations, we run a benchmark on a wide variety of representative (time series) data sets, with in-depth analysis of empirical results, and strive to provide a reference ranking for which method(s) to use for non-expert practitioners.
Our in-lab study shows that GesturePod achieves 92% gesture recognition accuracy and can help perform common smartphone tasks faster.
Ranked #1 on Gesture Recognition on GesturePod
FastRNN addresses these limitations by adding a residual connection that does not constrain the range of the singular values explicitly and has only two extra scalar parameters.
Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices
We propose a method, EMI-RNN, that exploits these observations by using a multiple instance learning formulation along with an early prediction technique to learn a model that achieves better accuracy compared to baseline models, while simultaneously reducing computation by a large fraction.
ROCKET achieves state-of-the-art accuracy with a fraction of the computational expense of most existing methods by transforming input time series using random convolutional kernels, and using the transformed features to train a linear classifier.
Thus, XCM architecture enables a good generalization ability on both small and large datasets, while allowing the full exploitation of a faithful post-hoc model-specific explainability method (Gradient-weighted Class Activation Mapping) by precisely identifying the observed variables and timestamps of the input data that are important for predictions.
For time series classification task using 1D-CNN, the selection of kernel size is critically important to ensure the model can capture the right scale salient signal from a long time-series.
ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels
Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger datasets.