An Enhanced Algorithm of RNN Using Trend in Time-Series
The concept of trend in data and a novel neural network method for the forecasting of upcoming time-series data are proposed in this paper. The proposed method extracts two data sets—the trend and the remainder—resulting in two separate learning sets for training. This method wor...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/11/7/912 |
| _version_ | 1798040850091999232 |
|---|---|
| author | Dokkyun Yi Sunyoung Bu Inmi Kim |
| author_facet | Dokkyun Yi Sunyoung Bu Inmi Kim |
| author_sort | Dokkyun Yi |
| collection | DOAJ |
| description | The concept of trend in data and a novel neural network method for the forecasting of upcoming time-series data are proposed in this paper. The proposed method extracts two data sets—the trend and the remainder—resulting in two separate learning sets for training. This method works sufficiently, even when only using a simple recurrent neural network (RNN). The proposed scheme is demonstrated to achieve better performance in selected real-life examples, compared to other averaging-based statistical forecast methods and other recurrent methods, such as long short-term memory (LSTM). |
| first_indexed | 2024-04-11T22:13:21Z |
| format | Article |
| id | doaj.art-19c7666791ca444e9b3c516fb02deb89 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-11T22:13:21Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-19c7666791ca444e9b3c516fb02deb892022-12-22T04:00:30ZengMDPI AGSymmetry2073-89942019-07-0111791210.3390/sym11070912sym11070912An Enhanced Algorithm of RNN Using Trend in Time-SeriesDokkyun Yi0Sunyoung Bu1Inmi Kim2DU College, Daegu University, Kyungsan 38453, KoreaDepartment of Liberal Arts, Hongik University, Sejong 04066, KoreaDU College, Daegu University, Kyungsan 38453, KoreaThe concept of trend in data and a novel neural network method for the forecasting of upcoming time-series data are proposed in this paper. The proposed method extracts two data sets—the trend and the remainder—resulting in two separate learning sets for training. This method works sufficiently, even when only using a simple recurrent neural network (RNN). The proposed scheme is demonstrated to achieve better performance in selected real-life examples, compared to other averaging-based statistical forecast methods and other recurrent methods, such as long short-term memory (LSTM).https://www.mdpi.com/2073-8994/11/7/912time seriestrendmachine learningRNNLSTM |
| spellingShingle | Dokkyun Yi Sunyoung Bu Inmi Kim An Enhanced Algorithm of RNN Using Trend in Time-Series Symmetry time series trend machine learning RNN LSTM |
| title | An Enhanced Algorithm of RNN Using Trend in Time-Series |
| title_full | An Enhanced Algorithm of RNN Using Trend in Time-Series |
| title_fullStr | An Enhanced Algorithm of RNN Using Trend in Time-Series |
| title_full_unstemmed | An Enhanced Algorithm of RNN Using Trend in Time-Series |
| title_short | An Enhanced Algorithm of RNN Using Trend in Time-Series |
| title_sort | enhanced algorithm of rnn using trend in time series |
| topic | time series trend machine learning RNN LSTM |
| url | https://www.mdpi.com/2073-8994/11/7/912 |
| work_keys_str_mv | AT dokkyunyi anenhancedalgorithmofrnnusingtrendintimeseries AT sunyoungbu anenhancedalgorithmofrnnusingtrendintimeseries AT inmikim anenhancedalgorithmofrnnusingtrendintimeseries AT dokkyunyi enhancedalgorithmofrnnusingtrendintimeseries AT sunyoungbu enhancedalgorithmofrnnusingtrendintimeseries AT inmikim enhancedalgorithmofrnnusingtrendintimeseries |