Predictive Modeling of Indoor Environmental Parameters for Assessing Comfort Conditions in a Kindergarten Setting
People tend to spend the majority of their time indoors. Indoor air properties can significantly affect humans’ comfort, health, and productivity. This study utilizes measurement data of indoor conditions in a kindergarten in Sofia, Bulgaria. Autoregressive integrated moving average (ARIMA) and long...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Toxics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2305-6304/11/8/709 |
| _version_ | 1797583152661659648 |
|---|---|
| author | Radostin Mitkov Dessislava Petrova-Antonova Petar O. Hristov |
| author_facet | Radostin Mitkov Dessislava Petrova-Antonova Petar O. Hristov |
| author_sort | Radostin Mitkov |
| collection | DOAJ |
| description | People tend to spend the majority of their time indoors. Indoor air properties can significantly affect humans’ comfort, health, and productivity. This study utilizes measurement data of indoor conditions in a kindergarten in Sofia, Bulgaria. Autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) recurrent neural network (RNN) models were developed to predict CO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2</mn></msub></semantics></math></inline-formula> levels in the educational facility over the next hour based on 2.5 h of past data and allow for near real-time decision-making. The better-performing model, LSTM, is also used for temperature and relative humidity forecasting. Global comfort is then estimated based on threshold values for temperature, humidity, and CO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2</mn></msub></semantics></math></inline-formula>. The predicted <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> values ranged between 0.938 and 0.981 for the three parameters, while the prediction of global comfort conditions achieved a 91/100 accuracy. |
| first_indexed | 2024-03-10T23:31:48Z |
| format | Article |
| id | doaj.art-923110f66c334b51935bd1a1c7769cad |
| institution | Directory Open Access Journal |
| issn | 2305-6304 |
| language | English |
| last_indexed | 2024-03-10T23:31:48Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Toxics |
| spelling | doaj.art-923110f66c334b51935bd1a1c7769cad2023-11-19T03:14:57ZengMDPI AGToxics2305-63042023-08-0111870910.3390/toxics11080709Predictive Modeling of Indoor Environmental Parameters for Assessing Comfort Conditions in a Kindergarten SettingRadostin Mitkov0Dessislava Petrova-Antonova1Petar O. Hristov2GATE Institute, Sofia University “St. Kliment Ohridski”, 1113 Sofia, BulgariaGATE Institute, Sofia University “St. Kliment Ohridski”, 1113 Sofia, BulgariaGATE Institute, Sofia University “St. Kliment Ohridski”, 1113 Sofia, BulgariaPeople tend to spend the majority of their time indoors. Indoor air properties can significantly affect humans’ comfort, health, and productivity. This study utilizes measurement data of indoor conditions in a kindergarten in Sofia, Bulgaria. Autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) recurrent neural network (RNN) models were developed to predict CO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2</mn></msub></semantics></math></inline-formula> levels in the educational facility over the next hour based on 2.5 h of past data and allow for near real-time decision-making. The better-performing model, LSTM, is also used for temperature and relative humidity forecasting. Global comfort is then estimated based on threshold values for temperature, humidity, and CO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2</mn></msub></semantics></math></inline-formula>. The predicted <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> values ranged between 0.938 and 0.981 for the three parameters, while the prediction of global comfort conditions achieved a 91/100 accuracy.https://www.mdpi.com/2305-6304/11/8/709predictive modelingmachine learningindoor environmentcomfort conditionsair quality |
| spellingShingle | Radostin Mitkov Dessislava Petrova-Antonova Petar O. Hristov Predictive Modeling of Indoor Environmental Parameters for Assessing Comfort Conditions in a Kindergarten Setting Toxics predictive modeling machine learning indoor environment comfort conditions air quality |
| title | Predictive Modeling of Indoor Environmental Parameters for Assessing Comfort Conditions in a Kindergarten Setting |
| title_full | Predictive Modeling of Indoor Environmental Parameters for Assessing Comfort Conditions in a Kindergarten Setting |
| title_fullStr | Predictive Modeling of Indoor Environmental Parameters for Assessing Comfort Conditions in a Kindergarten Setting |
| title_full_unstemmed | Predictive Modeling of Indoor Environmental Parameters for Assessing Comfort Conditions in a Kindergarten Setting |
| title_short | Predictive Modeling of Indoor Environmental Parameters for Assessing Comfort Conditions in a Kindergarten Setting |
| title_sort | predictive modeling of indoor environmental parameters for assessing comfort conditions in a kindergarten setting |
| topic | predictive modeling machine learning indoor environment comfort conditions air quality |
| url | https://www.mdpi.com/2305-6304/11/8/709 |
| work_keys_str_mv | AT radostinmitkov predictivemodelingofindoorenvironmentalparametersforassessingcomfortconditionsinakindergartensetting AT dessislavapetrovaantonova predictivemodelingofindoorenvironmentalparametersforassessingcomfortconditionsinakindergartensetting AT petarohristov predictivemodelingofindoorenvironmentalparametersforassessingcomfortconditionsinakindergartensetting |