RAEF: An Imputation Framework Based on a Gated Regulator Autoencoder for Incomplete IIoT Time-Series Data
The number of intelligent applications available for IIoT environments is growing, but when the time-series data these applications rely on are incomplete, their performance suffers. Unfortunately, incomplete data are all too frequent to a phenomenon in the world of IIoT. A common workaround is to u...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/3320402 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832557135414689792 |
|---|---|
| author | Jianyong Zhao Jiachen Qiu Danfeng Sun Baiping Chen |
| author_facet | Jianyong Zhao Jiachen Qiu Danfeng Sun Baiping Chen |
| author_sort | Jianyong Zhao |
| collection | DOAJ |
| description | The number of intelligent applications available for IIoT environments is growing, but when the time-series data these applications rely on are incomplete, their performance suffers. Unfortunately, incomplete data are all too frequent to a phenomenon in the world of IIoT. A common workaround is to use imputation. However, the current methods are largely designed to reconstruct a single missing pattern, where a robust and flexible imputation framework would be able to handle many different missing patterns. Hence, the framework presented in this study, RAEF, is capable of processing multiple missing patterns. Based on a recurrent autoencoder, RAEF houses a novel neuron structure, called a gated regulator, which reduces the negative impact of different missing patterns. In a comparison of the state-of-the-art time-series imputation frameworks at a range of different missing rates, RAEF yielded fewer errors than all its counterparts. |
| format | Article |
| id | doaj-art-eb91a5c276f24a8ba38cdf6473ef2701 |
| institution | Kabale University |
| issn | 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-eb91a5c276f24a8ba38cdf6473ef27012025-02-03T05:43:35ZengWileyComplexity1099-05262021-01-01202110.1155/2021/3320402RAEF: An Imputation Framework Based on a Gated Regulator Autoencoder for Incomplete IIoT Time-Series DataJianyong Zhao0Jiachen Qiu1Danfeng Sun2Baiping Chen3Institute of Intelligent and Software TechnologyInstitute of Intelligent and Software TechnologyInstitut f. Automation und KommunikationInstitute of Intelligent and Software TechnologyThe number of intelligent applications available for IIoT environments is growing, but when the time-series data these applications rely on are incomplete, their performance suffers. Unfortunately, incomplete data are all too frequent to a phenomenon in the world of IIoT. A common workaround is to use imputation. However, the current methods are largely designed to reconstruct a single missing pattern, where a robust and flexible imputation framework would be able to handle many different missing patterns. Hence, the framework presented in this study, RAEF, is capable of processing multiple missing patterns. Based on a recurrent autoencoder, RAEF houses a novel neuron structure, called a gated regulator, which reduces the negative impact of different missing patterns. In a comparison of the state-of-the-art time-series imputation frameworks at a range of different missing rates, RAEF yielded fewer errors than all its counterparts.http://dx.doi.org/10.1155/2021/3320402 |
| spellingShingle | Jianyong Zhao Jiachen Qiu Danfeng Sun Baiping Chen RAEF: An Imputation Framework Based on a Gated Regulator Autoencoder for Incomplete IIoT Time-Series Data Complexity |
| title | RAEF: An Imputation Framework Based on a Gated Regulator Autoencoder for Incomplete IIoT Time-Series Data |
| title_full | RAEF: An Imputation Framework Based on a Gated Regulator Autoencoder for Incomplete IIoT Time-Series Data |
| title_fullStr | RAEF: An Imputation Framework Based on a Gated Regulator Autoencoder for Incomplete IIoT Time-Series Data |
| title_full_unstemmed | RAEF: An Imputation Framework Based on a Gated Regulator Autoencoder for Incomplete IIoT Time-Series Data |
| title_short | RAEF: An Imputation Framework Based on a Gated Regulator Autoencoder for Incomplete IIoT Time-Series Data |
| title_sort | raef an imputation framework based on a gated regulator autoencoder for incomplete iiot time series data |
| url | http://dx.doi.org/10.1155/2021/3320402 |
| work_keys_str_mv | AT jianyongzhao raefanimputationframeworkbasedonagatedregulatorautoencoderforincompleteiiottimeseriesdata AT jiachenqiu raefanimputationframeworkbasedonagatedregulatorautoencoderforincompleteiiottimeseriesdata AT danfengsun raefanimputationframeworkbasedonagatedregulatorautoencoderforincompleteiiottimeseriesdata AT baipingchen raefanimputationframeworkbasedonagatedregulatorautoencoderforincompleteiiottimeseriesdata |