Time Series Imputation via Integration of Revealed Information Based on the Residual Shortcut Connection
Recovering missing values plays a significant role in time series tasks in practical applications. How to replace the missing data and build the dependency relations from the incomplete sample set is still a challenge. The previous research has found that residual network (ResNet) helps to form a de...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8762121/ |
| _version_ | 1819078595546447872 |
|---|---|
| author | Jinjin Zhang Xiaodong Mu Jiansheng Fang Yue Yang |
| author_facet | Jinjin Zhang Xiaodong Mu Jiansheng Fang Yue Yang |
| author_sort | Jinjin Zhang |
| collection | DOAJ |
| description | Recovering missing values plays a significant role in time series tasks in practical applications. How to replace the missing data and build the dependency relations from the incomplete sample set is still a challenge. The previous research has found that residual network (ResNet) helps to form a deep network and cope with degradation problem by shortcut connection. Gated recurrent unit (GRU) can improve network model and reduce training parameters by update gate which takes the place of forgetting gate and output gate in long short-term memory (LSTM). Inspired by this finding, we observe that shortcut connection and mean of global revealed information can model the relationship among missing items, the previous and overall revealed information. Hence, we design an imputation network with decay factor for shortcut connection and mean of the global revealed information in GRU, called decay residual mean imputation GRU (DRMI-GRU). We introduce a decay residual mean unit (DRMU), which takes full advantage of the previous and global revealed information to model incomplete time series; and the decay factor is applied to balance the previous long-term dependencies and all non-missing values in the sample set. In addition, a mask unit is designed to check the missing data existing or not. An extensive body of empirical comparisons with other existing imputation algorithms over real-world data and public dataset with different ratio of missing data verifies the performance of our model. |
| first_indexed | 2024-12-21T19:15:36Z |
| format | Article |
| id | doaj.art-a70d4869933b4158a02b9092e9c2a8f3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-21T19:15:36Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a70d4869933b4158a02b9092e9c2a8f32022-12-21T18:53:04ZengIEEEIEEE Access2169-35362019-01-01710239710240510.1109/ACCESS.2019.29286418762121Time Series Imputation via Integration of Revealed Information Based on the Residual Shortcut ConnectionJinjin Zhang0https://orcid.org/0000-0002-7385-5718Xiaodong Mu1Jiansheng Fang2Yue Yang3Department of Computer Science, Xi’an High-Tech Research Institution, Xi’an, ChinaDepartment of Computer Science, Xi’an High-Tech Research Institution, Xi’an, ChinaGuangzhou Shiyuan Electronic Technology Company Limited, Guangzhou, ChinaGuangzhou Shiyuan Electronic Technology Company Limited, Guangzhou, ChinaRecovering missing values plays a significant role in time series tasks in practical applications. How to replace the missing data and build the dependency relations from the incomplete sample set is still a challenge. The previous research has found that residual network (ResNet) helps to form a deep network and cope with degradation problem by shortcut connection. Gated recurrent unit (GRU) can improve network model and reduce training parameters by update gate which takes the place of forgetting gate and output gate in long short-term memory (LSTM). Inspired by this finding, we observe that shortcut connection and mean of global revealed information can model the relationship among missing items, the previous and overall revealed information. Hence, we design an imputation network with decay factor for shortcut connection and mean of the global revealed information in GRU, called decay residual mean imputation GRU (DRMI-GRU). We introduce a decay residual mean unit (DRMU), which takes full advantage of the previous and global revealed information to model incomplete time series; and the decay factor is applied to balance the previous long-term dependencies and all non-missing values in the sample set. In addition, a mask unit is designed to check the missing data existing or not. An extensive body of empirical comparisons with other existing imputation algorithms over real-world data and public dataset with different ratio of missing data verifies the performance of our model.https://ieeexplore.ieee.org/document/8762121/Gated recurrent unitmissing valuestime series imputationshortcut connection |
| spellingShingle | Jinjin Zhang Xiaodong Mu Jiansheng Fang Yue Yang Time Series Imputation via Integration of Revealed Information Based on the Residual Shortcut Connection IEEE Access Gated recurrent unit missing values time series imputation shortcut connection |
| title | Time Series Imputation via Integration of Revealed Information Based on the Residual Shortcut Connection |
| title_full | Time Series Imputation via Integration of Revealed Information Based on the Residual Shortcut Connection |
| title_fullStr | Time Series Imputation via Integration of Revealed Information Based on the Residual Shortcut Connection |
| title_full_unstemmed | Time Series Imputation via Integration of Revealed Information Based on the Residual Shortcut Connection |
| title_short | Time Series Imputation via Integration of Revealed Information Based on the Residual Shortcut Connection |
| title_sort | time series imputation via integration of revealed information based on the residual shortcut connection |
| topic | Gated recurrent unit missing values time series imputation shortcut connection |
| url | https://ieeexplore.ieee.org/document/8762121/ |
| work_keys_str_mv | AT jinjinzhang timeseriesimputationviaintegrationofrevealedinformationbasedontheresidualshortcutconnection AT xiaodongmu timeseriesimputationviaintegrationofrevealedinformationbasedontheresidualshortcutconnection AT jianshengfang timeseriesimputationviaintegrationofrevealedinformationbasedontheresidualshortcutconnection AT yueyang timeseriesimputationviaintegrationofrevealedinformationbasedontheresidualshortcutconnection |