Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/122754
Citations | ||
Scopus | Web of ScienceĀ® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Simulating time-series data for improved deep neural network performance |
Author: | Yeomans, J. Thwaites, S. Robertson, W.S.P. Booth, D. Ng, B. Thewlis, D. |
Citation: | IEEE Access, 2019; 7:131248-131255 |
Publisher: | Institute of Electrical and Electronics Engineers |
Issue Date: | 2019 |
ISSN: | 2169-3536 2169-3536 |
Statement of Responsibility: | Jordan Yeomans, Simon Thwaites, William S. P. Robertson, David Booth, Brian Ng, Dominic Thewlis |
Abstract: | Deep learning algorithms have shown remarkable performance in classification tasks, however, they typically perform poorly with small training datasets due to overfitting. Overfitting occurs for all data types, although for the purposes of this study we are interested in time-based signals. This study introduces a novel technique to simulate time series signals from a dataset of categorically labeled data which can be used to train a deep neural network. The objective is to improve the predictive accuracy of a deep neural network on a separate validation dataset. To demonstrate the simulation methodology and improvements to the model's performance, a small dataset of ground reaction forces was used with the goal of identifying a person based on the raw signal. Our results show that the simulation method presented improves validation accuracy and reduces model training time for each of the three signal types. |
Keywords: | Deep learning; deep neural networks; data simulation; data augmentation; time-series classification; time-series data augmentation; transfer learning, LSTM; 1D CNN; ground reaction force; personal identification; small dataset; overfitting |
Rights: | This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0/ |
DOI: | 10.1109/ACCESS.2019.2940701 |
Grant ID: | http://purl.org/au-research/grants/nhmrc/1126229 |
Published version: | http://dx.doi.org/10.1109/access.2019.2940701 |
Appears in Collections: | Aurora harvest 4 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
hdl_122754.pdf | Published version | 11.04 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.