• Corpus ID: 16409971

Encoding Time Series as Images for Visual Inspection and Classification Using Tiled Convolutional Neural Networks

  title={Encoding Time Series as Images for Visual Inspection and Classification Using Tiled Convolutional Neural Networks},
  author={Zhiguang Wang and Tim Oates},
Inspired by recent successes of deep learning in computer vision and speech recognition, we propose a novel framework to encode time series data as different types of images, namely, Gramian Angular Fields (GAF) and Markov Transition Fields (MTF). This enables the use of techniques from computer vision for classification. Using a polar coordinate system, GAF images are represented as a Gramian matrix where each element is the trigonometric sum (i.e., superposition of directions) between… 

Figures and Tables from this paper

Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images

The proposed framework encodes multivariate time series data into two-dimensional colored images, and concatenate the images into one bigger image for classification through a Convolutional Neural Network (ConvNet).

Inertial Sensor Data to Image Encoding for Human Action Recognition

Four types of spatial domain methods for transforming inertial sensor data to activity images, which are then utilized in a novel fusion framework for improving the accuracy of human action recognition are used.

Multivariate Time Series Data Transformation for Convolutional Neural Network

The preliminary results of the experiments find that encoding time series data into images and aggregating the images by the appending method are helpful on increasing classification accuracy.

Sequence-to-Sequence Model with Attention for Time Series Classification

This paper proposes a novel model incorporating a sequence-to-sequence model that consists two LSTMs, one encoder and one decoder that is competitive with the state-of-the-art in real world tasks such as human activity recognition and calls it S2SwA, as the short for Sequence- to-Sequence with Attention.

Lagged encoding for image‐based time series classification using convolutional neural networks

A novel, deep learning approach to time series classification based on a lagged time series representation stored as images and Convolutional Neural Network used to image classification, which is particularly suitable for systems that need to store sensitive information.

Deep learning and time series-to-image encoding for financial forecasting

This paper exploits an ensemble of CNNs, trained over Gramian angular fields images, generated from time series related to the Standard & Poor ʼ s 500 index future; the aim is the prediction of the future trend of the U.S. market.

Encoding Time Series as Multi-Scale Signed Recurrence Plots for Classification Using Fully Convolutional Networks

This paper tackles the problem using Multi-scale Signed Recurrence Plots (MS-RP), an improvement of RP, and proposes a novel method based on MS-RP images and Fully Convolutional Networks (FCN) for TSC.

Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review

This review, which focuses on the application of CNNs to image classification tasks, covers their development, from their predecessors up to recent state-of-the-art deep learning systems.

Effective Processing of Convolutional Neural Networks for Computer Vision: A Tutorial and Survey

This work reviews the major advances on ConvNets for effective processing in computer vision from some dimensions which include, convolutional layer design configurations, pooling layer strategies, network activation functions, loss functions, network regularization techniques, and ConvNet optimization methods.



Time Series Classification Using Multi-Channels Deep Convolutional Neural Networks

A novel deep learning framework for multivariate time series classification is proposed that is not only more efficient than the state of the art but also competitive in accuracy and demonstrates that feature learning is worth to investigate for time series Classification.

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

Tiled convolutional neural networks

This paper proposes tiled convolution neural networks (Tiled CNNs), which use a regular "tiled" pattern of tied weights that does not require that adjacent hidden units share identical weights, but instead requires only that hidden units k steps away from each other to have tied weights.

Face recognition: a convolutional neural-network approach

A hybrid neural-network for human face recognition which compares favourably with other methods and analyzes the computational complexity and discusses how new classes could be added to the trained recognizer.

Convolutional networks and applications in vision

New unsupervised learning algorithms, and new non-linear stages that allow ConvNets to be trained with very few labeled samples are described, including one for visual object recognition and vision navigation for off-road mobile robots.

Learning Convolutional Feature Hierarchies for Visual Recognition

This work proposes an unsupervised method for learning multi-stage hierarchies of sparse convolutional features and trains an efficient feed-forward encoder that predicts quasi-sparse features from the input.

Exploring convolutional neural network structures and optimization techniques for speech recognition

This paper investigates several CNN architectures, including full and limited weight sharing, convolution along frequency and time axes, and stacking of several convolution layers, and develops a novel weighted softmax pooling layer so that the size in the pooled layer can be automatically learned.

Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition

The proposed CNN architecture is applied to speech recognition within the framework of hybrid NN-HMM model to use local filtering and max-pooling in frequency domain to normalize speaker variance to achieve higher multi-speaker speech recognition performance.

A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion

We develop and present a novel deep convolutional neural network architecture, where heterogeneous pooling is used to provide constrained frequency-shift invariance in the speech spectrogram while

Gradient-based learning applied to document recognition

This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.