Deep Learning Abilities to Classify Intricate Variations in Temporal Dynamics of Multivariate Time Series

The aim of this work is to investigate the ability of deep learning (DL) architectures to learn temporal dynamics in multivariate time series. The methodology consists in using well known synthetic stochastic processes for which changes in joint temporal dynamics can be controlled. This permits to compare deep learning against classical machine learning techniques relying on documented hand-crafted wavelet-based features. First, we assess the performance of several different DL architectures and show the relevance of convolutional neural networks (CNN). Second, we test the robustness of CNN performance in classifying subtle changes in multivariate temporal dynamics with respect to learning conditions (dataset size, time series sample size, transfer learning).

[1]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[2]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[3]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[4]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[5]  G. Didier,et al.  Wavelet estimation for operator fractional Brownian motion , 2015, 1501.06094.

[6]  Yixin Chen,et al.  Multi-Scale Convolutional Neural Networks for Time Series Classification , 2016, ArXiv.

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[9]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[10]  Marcin Korytkowski,et al.  Convolutional Neural Networks for Time Series Classification , 2017, ICAISC.

[11]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  D. Applebaum.  Stable non-Gaussian random processes , 1995, The Mathematical Gazette.

[13]  Zhaozheng Yin,et al.  Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks , 2015, ACM Multimedia.

[14]  Tim Oates,et al.  Time series classification from scratch with deep neural networks: A strong baseline , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

[15]  Tim Oates,et al.  Encoding Time Series as Images for Visual Inspection and Classification Using Tiled Convolutional Neural Networks , 2014 .

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  G. Didier,et al.  Integral representations and properties of operator fractional Brownian motions , 2011, 1102.1822.

[18]  Mario Michael Krell,et al.  A Capacity Scaling Law for Artificial Neural Networks , 2017, ArXiv.

[19]  P. Abry,et al.  Bootstrap for Empirical Multifractal Analysis , 2007, IEEE Signal Processing Magazine.

[20]  Germain Forestier,et al.  Deep learning for time series classification: a review , 2018, Data Mining and Knowledge Discovery.

[21]  Patrice Abry,et al.  Assessing Cross-Dependencies Using Bivariate Multifractal Analysis , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[22]  Fan,et al.  Joint multifractal measures: Theory and applications to turbulence. , 1990, Physical review. A, Atomic, molecular, and optical physics.

[23]  Pattreeya Tanisaro,et al.  Time Series Classification Using Time Warping Invariant Echo State Networks , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[24]  E. Bacry,et al.  Multifractal random walk. , 2000, Physical review. E, Statistical, nonlinear, and soft matter physics.

[25]  Sangram Ganguly,et al.  A theoretical analysis of Deep Neural Networks for texture classification , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[26]  Yi Zheng,et al.  Exploiting multi-channels deep convolutional neural networks for multivariate time series classification , 2015, Frontiers of Computer Science.