A recurrent neural network using historical data to predict time series indoor PM2.5 concentrations for residential buildings
© 2021 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd..
Due to the severe outdoor PM2.5 pollution in China, many people have installed air-cleaning systems in homes. To make the systems run automatically and intelligently, we developed a recurrent neural network (RNN) that uses historical data to predict the future indoor PM2.5 concentration. The RNN architecture includes an autoencoder and a recurrent part. We used data measured in an apartment over the course of an entire year to train and test the RNN. The data include indoor/outdoor PM2.5 concentration, environmental parameters and time of day. By comparing three different input strategies, we found that a strategy employing historical PM2.5 and time of day as inputs performed best. With this strategy, the model can be applied to predict the relatively stable trend of indoor PM2.5 concentration in advance. When the input length is 2 h and the prediction horizon is 30 min, the median prediction error is 8.3 µg/m3 for the whole test set. For times with indoor PM2.5 concentrations between (20,50] µg/m3 and (50,100] µg/m3 , the median prediction error is 8.3 and 9.2 µg/m3 , respectively. The low prediction error between the ground-truth and predicted values shows that the RNN can predict indoor PM2.5 concentrations with satisfactory performance.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:31 |
|---|---|
| Enthalten in: |
Indoor air - 31(2021), 4 vom: 15. Juli, Seite 1228-1237 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Dai, Xilei [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Air Pollutants |
|---|
| Anmerkungen: |
Date Completed 25.10.2021 Date Revised 25.10.2021 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1111/ina.12794 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM320116948 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM320116948 | ||
| 003 | DE-627 | ||
| 005 | 20231225172908.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1111/ina.12794 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1067.xml |
| 035 | |a (DE-627)NLM320116948 | ||
| 035 | |a (NLM)33448484 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Dai, Xilei |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A recurrent neural network using historical data to predict time series indoor PM2.5 concentrations for residential buildings |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 25.10.2021 | ||
| 500 | |a Date Revised 25.10.2021 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2021 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd. | ||
| 520 | |a Due to the severe outdoor PM2.5 pollution in China, many people have installed air-cleaning systems in homes. To make the systems run automatically and intelligently, we developed a recurrent neural network (RNN) that uses historical data to predict the future indoor PM2.5 concentration. The RNN architecture includes an autoencoder and a recurrent part. We used data measured in an apartment over the course of an entire year to train and test the RNN. The data include indoor/outdoor PM2.5 concentration, environmental parameters and time of day. By comparing three different input strategies, we found that a strategy employing historical PM2.5 and time of day as inputs performed best. With this strategy, the model can be applied to predict the relatively stable trend of indoor PM2.5 concentration in advance. When the input length is 2 h and the prediction horizon is 30 min, the median prediction error is 8.3 µg/m3 for the whole test set. For times with indoor PM2.5 concentrations between (20,50] µg/m3 and (50,100] µg/m3 , the median prediction error is 8.3 and 9.2 µg/m3 , respectively. The low prediction error between the ground-truth and predicted values shows that the RNN can predict indoor PM2.5 concentrations with satisfactory performance | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 650 | 4 | |a artificial intelligence | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a indoor PM2.5 | |
| 650 | 4 | |a outdoor parameters | |
| 650 | 4 | |a recurrent neural network | |
| 650 | 4 | |a time series model | |
| 650 | 7 | |a Air Pollutants |2 NLM | |
| 650 | 7 | |a Particulate Matter |2 NLM | |
| 700 | 1 | |a Liu, Junjie |e verfasserin |4 aut | |
| 700 | 1 | |a Li, Yongle |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Indoor air |d 1996 |g 31(2021), 4 vom: 15. Juli, Seite 1228-1237 |w (DE-627)NLM093670826 |x 1600-0668 |7 nnns |
| 773 | 1 | 8 | |g volume:31 |g year:2021 |g number:4 |g day:15 |g month:07 |g pages:1228-1237 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1111/ina.12794 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 31 |j 2021 |e 4 |b 15 |c 07 |h 1228-1237 | ||