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

By Zhiguang Wang, Tim Oates. 2014

636 citations recorded by the source corpus.

How researchers see this paper

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

1. Jiuxiang Gu
2. Jianfei Cai
3. Amir Shahroudy
4. Jun Liu
5. Jason Kuen
6. G. Wang
7. Zhenhua Wang
8. Bing Shuai

Citations in the corpus

• Recent advances in convolutional neural networks (2015, methodology): “[24] find that Tiled CNN performs better than traditional CNN [25] on small time series datasets.”
• Deep Learning for Time-Series Analysis (2017, methodology): “Wang and Oates [59] presented an approach for Time-Series Classification using CNN-like networks.”
• Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review (2017, background): “Some of the promising recent developments along these lines include double convolution (see section 5.1.1.3), tiled convolution (Ngiam et al., 2010; Wang & Oates, 2015), and, in particular, dilated convolution (Yu & Koltun, 2015), which has shown promising results for diverse tasks such as speech…”
• Deep learning for time series classification: a review (2018, methodology): “, 2017; Tripathy and Acharya, 2018) and Markov transition fields (Wang and Oates, 2015).”
• Potential, challenges and future directions for deep learning in prognostics and health management applications (2020, background): “2, Gramian Angular Fields (GAF), Markov Transition Fields (MTF) and Recurrence Plots (RP) have been introduced in Wang and Oates (2015), Debayle 1-”