A Sequence-to-Sequence Air Quality Predictor Based on the n-Step Recurrent Prediction
Increasingly, more people are suffering from the effects of air pollution. This study took Beijing as an example and proposed an attention-based air quality predictor (AAQP) that could better protect people from air pollution. The AAQP is a seq2seq model, and it exploits historical air quality data...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8675934/ |
| _version_ | 1818349468401008640 |
|---|---|
| author | Bo Liu Shuo Yan Jianqiang Li Guangzhi Qu Yong Li Jianlei Lang Rentao Gu |
| author_facet | Bo Liu Shuo Yan Jianqiang Li Guangzhi Qu Yong Li Jianlei Lang Rentao Gu |
| author_sort | Bo Liu |
| collection | DOAJ |
| description | Increasingly, more people are suffering from the effects of air pollution. This study took Beijing as an example and proposed an attention-based air quality predictor (AAQP) that could better protect people from air pollution. The AAQP is a seq2seq model, and it exploits historical air quality data and weather data to predict future air quality indexes. Although existing research has promoted seq2seq for air quality prediction, there are still two problems. First, the seq2seq has a slow training speed so the original RNN in the encoder was replaced with a fully connected encoder to accelerate the training process. Position embedding was also introduced to help the fully connected encoder find the sequential relationships among source sequences. Another problem is error accumulation caused by recurrent prediction. Accordingly, the n-step recurrent prediction was proposed to solve this problem. The experimental results validated that the AAQP with n-step recurrent prediction had better performance than the related arts since the error accumulation was reduced, and the training time was significantly decreased compared with the original seq2seq attention model. |
| first_indexed | 2024-12-13T18:06:26Z |
| format | Article |
| id | doaj.art-7e14ae30e1ed4fe7870719480dddbc3a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T18:06:26Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7e14ae30e1ed4fe7870719480dddbc3a2022-12-21T23:36:03ZengIEEEIEEE Access2169-35362019-01-017433314334510.1109/ACCESS.2019.29080818675934A Sequence-to-Sequence Air Quality Predictor Based on the n-Step Recurrent PredictionBo Liu0Shuo Yan1https://orcid.org/0000-0003-0293-5443Jianqiang Li2https://orcid.org/0000-0003-1995-9249Guangzhi Qu3Yong Li4Jianlei Lang5Rentao Gu6School of Software Engineering, Faculty of Information Technology, Beijing University of Technology, Beijing, ChinaSchool of Software Engineering, Faculty of Information Technology, Beijing University of Technology, Beijing, ChinaSchool of Software Engineering, Faculty of Information Technology, Beijing University of Technology, Beijing, ChinaComputer Science and Engineering Department, Oakland University, Rochester, MI, USASchool of Software Engineering, Faculty of Information Technology, Beijing University of Technology, Beijing, ChinaKey Laboratory of Beijing on Regional Air Pollution Control, College of Environmental & Energy Engineering, Beijing University of Technology, Beijing, ChinaBeijing Laboratory of Advanced Information Networks, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, ChinaIncreasingly, more people are suffering from the effects of air pollution. This study took Beijing as an example and proposed an attention-based air quality predictor (AAQP) that could better protect people from air pollution. The AAQP is a seq2seq model, and it exploits historical air quality data and weather data to predict future air quality indexes. Although existing research has promoted seq2seq for air quality prediction, there are still two problems. First, the seq2seq has a slow training speed so the original RNN in the encoder was replaced with a fully connected encoder to accelerate the training process. Position embedding was also introduced to help the fully connected encoder find the sequential relationships among source sequences. Another problem is error accumulation caused by recurrent prediction. Accordingly, the n-step recurrent prediction was proposed to solve this problem. The experimental results validated that the AAQP with n-step recurrent prediction had better performance than the related arts since the error accumulation was reduced, and the training time was significantly decreased compared with the original seq2seq attention model.https://ieeexplore.ieee.org/document/8675934/Air qualityseq2seqattentionprediction |
| spellingShingle | Bo Liu Shuo Yan Jianqiang Li Guangzhi Qu Yong Li Jianlei Lang Rentao Gu A Sequence-to-Sequence Air Quality Predictor Based on the n-Step Recurrent Prediction IEEE Access Air quality seq2seq attention prediction |
| title | A Sequence-to-Sequence Air Quality Predictor Based on the n-Step Recurrent Prediction |
| title_full | A Sequence-to-Sequence Air Quality Predictor Based on the n-Step Recurrent Prediction |
| title_fullStr | A Sequence-to-Sequence Air Quality Predictor Based on the n-Step Recurrent Prediction |
| title_full_unstemmed | A Sequence-to-Sequence Air Quality Predictor Based on the n-Step Recurrent Prediction |
| title_short | A Sequence-to-Sequence Air Quality Predictor Based on the n-Step Recurrent Prediction |
| title_sort | sequence to sequence air quality predictor based on the n step recurrent prediction |
| topic | Air quality seq2seq attention prediction |
| url | https://ieeexplore.ieee.org/document/8675934/ |
| work_keys_str_mv | AT boliu asequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT shuoyan asequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT jianqiangli asequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT guangzhiqu asequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT yongli asequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT jianleilang asequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT rentaogu asequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT boliu sequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT shuoyan sequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT jianqiangli sequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT guangzhiqu sequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT yongli sequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT jianleilang sequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction AT rentaogu sequencetosequenceairqualitypredictorbasedonthensteprecurrentprediction |