QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism
Quick Access Recorder (QAR), an important device for storing data from various flight parameters, contains a large amount of valuable data and comprehensively records the real state of the airline flight. However, the recorded data have certain missing values due to factors, such as weather and equi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-03-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2023.9020001 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832544781600817152 |
|---|---|
| author | Jingqi Zhao Chuitian Rong Xin Dang Huabo Sun |
| author_facet | Jingqi Zhao Chuitian Rong Xin Dang Huabo Sun |
| author_sort | Jingqi Zhao |
| collection | DOAJ |
| description | Quick Access Recorder (QAR), an important device for storing data from various flight parameters, contains a large amount of valuable data and comprehensively records the real state of the airline flight. However, the recorded data have certain missing values due to factors, such as weather and equipment anomalies. These missing values seriously affect the analysis of QAR data by aeronautical engineers, such as airline flight scenario reproduction and airline flight safety status assessment. Therefore, imputing missing values in the QAR data, which can further guarantee the flight safety of airlines, is crucial. QAR data also have multivariate, multiprocess, and temporal features. Therefore, we innovatively propose the imputation models A-AEGAN (“A” denotes attention mechanism, “AE” denotes autoencoder, and “GAN” denotes generative adversarial network) and SA-AEGAN (“SA” denotes self-attentive mechanism) for missing values of QAR data, which can be effectively applied to QAR data. Specifically, we apply an innovative generative adversarial network to impute missing values from QAR data. The improved gated recurrent unit is then introduced as the neural unit of GAN, which can successfully capture the temporal relationships in QAR data. In addition, we modify the basic structure of GAN by using an autoencoder as the generator and a recurrent neural network as the discriminator. The missing values in the QAR data are imputed by using the adversarial relationship between generator and discriminator. We introduce an attention mechanism in the autoencoder to further improve the capability of the proposed model to capture the features of QAR data. Attention mechanisms can maintain the correlation among QAR data and improve the capability of the model to impute missing data. Furthermore, we improve the proposed model by integrating a self-attention mechanism to further capture the relationship between different parameters within the QAR data. Experimental results on real datasets demonstrate that the model can reasonably impute the missing values in QAR data with excellent results. |
| format | Article |
| id | doaj-art-c8d8f78ea9c14164a7cfcffba3a4d3bf |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-03-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-c8d8f78ea9c14164a7cfcffba3a4d3bf2025-02-03T09:54:47ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-03-0171122810.26599/BDMA.2023.9020001QAR Data Imputation Using Generative Adversarial Network with Self-Attention MechanismJingqi Zhao0Chuitian Rong1Xin Dang2Huabo Sun3School of Computer Science and Technology, Tiangong University, Tianjin 300387, ChinaSchool of Computer Science and Technology, Tiangong University, Tianjin 300387, ChinaSchool of Computer Science and Technology, Tiangong University, Tianjin 300387, ChinaInstitute of Aviation Safety, China Academy of Civil Aviation Science and Technology, Beijing 100028, ChinaQuick Access Recorder (QAR), an important device for storing data from various flight parameters, contains a large amount of valuable data and comprehensively records the real state of the airline flight. However, the recorded data have certain missing values due to factors, such as weather and equipment anomalies. These missing values seriously affect the analysis of QAR data by aeronautical engineers, such as airline flight scenario reproduction and airline flight safety status assessment. Therefore, imputing missing values in the QAR data, which can further guarantee the flight safety of airlines, is crucial. QAR data also have multivariate, multiprocess, and temporal features. Therefore, we innovatively propose the imputation models A-AEGAN (“A” denotes attention mechanism, “AE” denotes autoencoder, and “GAN” denotes generative adversarial network) and SA-AEGAN (“SA” denotes self-attentive mechanism) for missing values of QAR data, which can be effectively applied to QAR data. Specifically, we apply an innovative generative adversarial network to impute missing values from QAR data. The improved gated recurrent unit is then introduced as the neural unit of GAN, which can successfully capture the temporal relationships in QAR data. In addition, we modify the basic structure of GAN by using an autoencoder as the generator and a recurrent neural network as the discriminator. The missing values in the QAR data are imputed by using the adversarial relationship between generator and discriminator. We introduce an attention mechanism in the autoencoder to further improve the capability of the proposed model to capture the features of QAR data. Attention mechanisms can maintain the correlation among QAR data and improve the capability of the model to impute missing data. Furthermore, we improve the proposed model by integrating a self-attention mechanism to further capture the relationship between different parameters within the QAR data. Experimental results on real datasets demonstrate that the model can reasonably impute the missing values in QAR data with excellent results.https://www.sciopen.com/article/10.26599/BDMA.2023.9020001multivariate time seriesdata imputationself-attentiongenerative adversarial network (gan) |
| spellingShingle | Jingqi Zhao Chuitian Rong Xin Dang Huabo Sun QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism Big Data Mining and Analytics multivariate time series data imputation self-attention generative adversarial network (gan) |
| title | QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism |
| title_full | QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism |
| title_fullStr | QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism |
| title_full_unstemmed | QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism |
| title_short | QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism |
| title_sort | qar data imputation using generative adversarial network with self attention mechanism |
| topic | multivariate time series data imputation self-attention generative adversarial network (gan) |
| url | https://www.sciopen.com/article/10.26599/BDMA.2023.9020001 |
| work_keys_str_mv | AT jingqizhao qardataimputationusinggenerativeadversarialnetworkwithselfattentionmechanism AT chuitianrong qardataimputationusinggenerativeadversarialnetworkwithselfattentionmechanism AT xindang qardataimputationusinggenerativeadversarialnetworkwithselfattentionmechanism AT huabosun qardataimputationusinggenerativeadversarialnetworkwithselfattentionmechanism |