Corpus ID: 125644

Imaging Time-Series to Improve Classification and Imputation

@article{Wang2015ImagingTT,
  title={Imaging Time-Series to Improve Classification and Imputation},
  author={Zhiguang Wang and Tim Oates},
  journal={ArXiv},
  year={2015},
  volume={abs/1506.00327}
}
Inspired by recent successes of deep learning in computer vision, we propose a novel framework for encoding time series as different types of images, namely, Gramian Angular Summation/Difference Fields (GASF/GADF) and Markov Transition Fields (MTF. [...] Key Method We used Tiled Convolutional Neural Networks (tiled CNNs) on 20 standard datasets to learn high-level features from the individual and compound GASF-GADF-MTF images. Our approaches achieve highly competitive results when compared to nine of the…Expand
Classification of time-series images using deep convolutional neural networks
TLDR
Recurrence Plots is used to transform time-series into 2D texture images and then take advantage of the deep CNN classifier to boost the recognition rate of TSC. Expand
Multivariate Time Series Data Transformation for Convolutional Neural Network
TLDR
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. Expand
Encoding Time Series as Multi-Scale Signed Recurrence Plots for Classification Using Fully Convolutional Networks
TLDR
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. Expand
Deep learning and time series-to-image encoding for financial forecasting
TLDR
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. Expand
Multivariate Time Series as Images: Imputation Using Convolutional Denoising Autoencoder
TLDR
This work proposes a modified Convolutional Denoising Autoencoder (CDA) based approach to impute multivariate time seriesData in combination with a preprocessing step that encodes time series data into 2D images using Gramian Angular Summation Field (GASF). Expand
A deep learning framework for time series classification using Relative Position Matrix and Convolutional Neural Network
TLDR
This work proposes a novel deep learning framework using Relative Position Matrix and Convolutional Neural Network (RPMCNN) for the TSC task and demonstrates that this approach achieves remarkable results and outperforms the current best TSC approaches by a large margin. Expand
Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images
  • Chao-Lung Yang, Zhi-Xuan Chen, Chen-Yi Yang
  • Computer Science, Medicine
  • Sensors
  • 2020
TLDR
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). Expand
SigNet: An Advanced Deep Learning Framework for Radio Signal Classification
TLDR
A novel deep learning framework called SigNet, where a signal-to-matrix (S2M) operator is adopted to convert the original signal into a square matrix first and is co-trained with a follow-up CNN architecture for classification, leading to the upgraded model SigNet2.0. Expand
Inertial Sensor Data to Image Encoding for Human Action Recognition
TLDR
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. Expand
Conditional-GAN Based Data Augmentation for Deep Learning Task Classifier Improvement Using fNIRS Data
TLDR
The proposed system uses a CGAN with a CNN classifier to enhance the accuracy through data augmentation and obtained a task classification accuracy of 96.67% for the CGAN-CNN combination. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 48 REFERENCES
Temporal Autoencoding Improves Generative Models of Time Series
TLDR
A new training method is proposed for both the TRBM and the CRBM, which enforces the dynamic structure of temporal datasets by treating the temporal models as denoising autoencoders, considering past frames of the dataset as corrupted versions of the present frame and minimizing the reconstruction error of thepresent data by the model. Expand
ImageNet classification with deep convolutional neural networks
TLDR
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. Expand
A Bag-of-Features Framework to Classify Time Series
TLDR
A framework to classify time series based on a bag-of-features representation (TSBF) that provides a feature-based approach that can handle warping (although differently from DTW), and experimental results show that TSBF provides better results than competitive methods on benchmark datasets from the UCR time series database. Expand
Fast time series classification using numerosity reduction
TLDR
While the idea of numerosity reduction for nearest-neighbor classifiers has a long history, it is shown here that it can leverage off an original observation about the relationship between dataset size and DTW constraints to produce an extremely compact dataset with little or no loss in accuracy. Expand
Tiled convolutional neural networks
TLDR
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. Expand
Training energy-based models for time-series imputation
TLDR
This paper presents a strategy for training energy-based graphical models for imputation directly, bypassing difficulties probabilistic approaches would face and finds that the training methods outperform the Contrastive Divergence learning algorithm. Expand
Extracting and composing robust features with denoising autoencoders
TLDR
This work introduces and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern. Expand
Generalized Denoising Auto-Encoders as Generative Models
TLDR
A different attack on the problem is proposed, which deals with arbitrary (but noisy enough) corruption, arbitrary reconstruction loss, handling both discrete and continuous-valued variables, and removing the bias due to non-infinitesimal corruption noise. Expand
Learning Convolutional Feature Hierarchies for Visual Recognition
TLDR
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. Expand
Deep Learning: Methods and Applications
TLDR
This monograph provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning. Expand
...
1
2
3
4
5
...