Deep learning for time series classification: a review

By Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, Pierre-Alain Muller. Data mining and knowledge discovery, 2018

3,323 citations recorded by the source corpus.

Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition. In this article, we study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets. By training 8730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.

Subfields: Artificial Intelligence, Biomedical Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/1c2efb418f79b5d29913e014a1dfd78865221c39

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Signal Processing

Citations in the corpus

MiniRocket: A Very Fast (Almost) Deterministic Transform for Time Series Classification (2020, methodology): “Figures showing mean ranks were produced using code from [15].”
One Fits All: Power General Time Series Analysis by Pretrained LM (2023, methodology): “…al. (2022), such as retail sales forecasting Böse et al. (2017); Courty & Li (1999) , imputation of missing data for economic time series Friedman (1962) anomaly detection for industrial maintenance Gao et al. (2020), and classification of time series from various domain Ismail Fawaz et al. (2019).”
A CNN–LSTM model for gold price time-series forecasting (2020, background): “Long short-term memory (LSTM) networks and convolutional neural networks (CNNs) are probably the most popular, efﬁcient and widely used deep learning techniques [11].”
RWKV: Reinventing RNNs for the Transformer Era (2023, background): “These applications often involve complex sequential data processing tasks that include nat-ural language understanding, conversational AI, time-series analysis, and even indirect modalities that can be reframed as sequences, such as images and graphs (Brown et al., 2020; Ismail Fawaz et al., 2019; W”
ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels (2019, methodology): “A kernel is convolved with an input time series through a sliding dot product operation, to produce a featuremapwhich is, in turn, used as the basis for classification (see Ismail Fawaz et al. 2019a).”
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection (2023, background): “The analysis of time series not only provides insights into past trends but also facilitates a multitude of tasks such as forecasting [4], classiﬁcation [5], anomaly detection [6], and data imputation [7].”
Tslearn, A Machine Learning Toolkit for Time Series Data (2020, methodology): “It includes pre-processing routines, feature extractors, and machine learning models for classiﬁcation (Bagnall et al., 2017; Fawaz et al., 2019), regression and clustering (Aghabozorgi et al., 2015).”
ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions (2022, methodology): “We report both the raw comparison results and the critical difference (CD) plots to show statistical difference [55], [56], where it visualize the statistical comparison by Wilcoxon signed-rank test with Holm’s correction.”
ADBench: Anomaly Detection Benchmark (2022, methodology): “Besides, the critical difference diagram (CD diagram) [34, 70] based on the Wilcoxon-Holm method is used for comparing groups of AD methods statistically ( p ≤ 0 .”
Unsupervised Scalable Representation Learning for Multivariate Time Series (2019, background): “Those results are incomplete as Ismail Fawaz et al. (2019) performed their experiments on the old version of the archive, whereas ours are performed on its most recent release where some datasets were changed.”