Deep learning for time series classification: a review
From MaRDI portal
Publication:69113
DOI10.1007/S10618-019-00619-1zbMATH Open1458.68196arXiv1809.04356OpenAlexW2892035503WikidataQ128277525 ScholiaQ128277525MaRDI QIDQ69113FDOQ69113
Pierre-Alain Muller, Germain Forestier, Lhassane Idoumghar, Pierre-Alain Muller, Jonathan Weber, Hassan Ismail Fawaz, Hassan Ismail Fawaz, Lhassane Idoumghar, Germain Forestier, Jonathan Weber
Publication date: 2 March 2019
Published in: Data Mining and Knowledge Discovery (Search for Journal in Brave)
Abstract: 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 8,730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.
Full work available at URL: https://arxiv.org/abs/1809.04356
Recommendations
- The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances
- Time series classification based on AdaBoost and deep residual network
- End-to-end deep representation learning for time series clustering: a comparative study
- Scalable time series classification
- Recurrent neural networks for time series classification
Classification and discrimination; cluster analysis (statistical aspects) (62H30) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Artificial neural networks and deep learning (68T07)
Cites Work
- Learning a symbolic representation for multivariate time series classification
- Time series classification with ensembles of elastic distance measures
- The BOSS is concerned with time series classification in the presence of noise
- Using dynamic time warping distances as features for improved time series classification
- Improving time series similarity measures by integrating preprocessing steps
- Speeding up similarity search under dynamic time warping by pruning unpromising alignments
- A cycle deep belief network model for multivariate time series classification
- Functional echo state network for time series classification
- Should we really use post-hoc tests based on mean-ranks?
- Time-series data mining
- A run length transformation for discriminating between auto regressive time series
- Title not available (Why is that?)
- A Primer on Neural Network Models for Natural Language Processing
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Time series shapelets: a novel technique that allows accurate, interpretable and fast classification
- Title not available (Why is that?)
- Classification of time series by shapelet transformation
- A time series forest for classification and feature extraction
- Title not available (Why is that?)
- Ridge Regression: Applications to Nonorthogonal Problems
Cited In (40)
- Deep learning-based state prediction of the Lorenz system with control parameters
- Embedding and learning with signatures
- End-to-end deep representation learning for time series clustering: a comparative study
- A performance analysis of Basin Hopping compared to established metaheuristics for global optimization
- Solving inverse problems of obtaining super-resolution using neural networks
- ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels
- Nonlinear time series classification using bispectrum-based deep convolutional neural networks
- Efficient visibility algorithm for high-frequency time-series: application to fault diagnosis with graph convolutional network
- Multichannel convolution neural network for gas mixture classification
- Time Series Clustering and Classification
- Nonlinear neural-like P model for time series classification
- On the impact of deep learning-based time-series forecasts on multistage stochastic programming policies
- Bake off redux: a review and experimental evaluation of recent time series classification algorithms
- Time series clustering with random convolutional kernels
- Series2vec: similarity-based self-supervised representation learning for time series classification
- Functional classwise principal component analysis: a classification framework for functional data analysis
- Time series extrinsic regression. Predicting numeric values from time series data
- $$\kappa $$-Circulant Maximum Variance Bases
- Deep order flow imbalance: Extracting alpha at multiple horizons from the limit order book
- A Nonautonomous Equation Discovery Method for Time Signal Classification
- Can deep learning distinguish chaos from noise? Numerical experiments and general considerations
- Dynamical pattern recognition for univariate time series and its application to an axial compressor
- Learning dynamical systems in noise using convolutional neural networks
- Stochastic physics-informed neural ordinary differential equations
- Imputation of clinical covariates in time series
- sits
- Neural-symbolic temporal decision trees for multivariate time series classification
- Supervised time series classification for anomaly detection in subsea engineering
- Time series classification with echo memory networks
- Tropical Time Series, Iterated-Sums Signatures, and Quasisymmetric Functions
- HIVE-COTE 2.0: a new meta ensemble for time series classification
- Optimal survival trees
- Co-eye: a multi-resolution ensemble classifier for symbolically approximated time series
- Interpretable time series classification using linear models and multi-resolution multi-domain symbolic representations
- Research and application of deep neural network architectures for classification on multidimensional time series
- Macroeconomic forecasting based on LSTM-conditioned normalizing flows
- The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances
- Continuous ordinal patterns: creating a bridge between ordinal analysis and deep learning
- TS-CHIEF: a scalable and accurate forest algorithm for time series classification
- Online Evidential Nearest Neighbour Classification for Internet of Things Time Series
Uses Software
This page was built for publication: Deep learning for time series classification: a review
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q69113)
