A Multi-Scale Convolutional Residual Time-Frequency Calibration Method for Low-Accuracy Air Pollution Data
Air pollution concerns have led to the widespread deployment of air quality monitoring stations. While high-cost government stations provide accurate data, their deployment is limited, whereas low-cost sensors offer widespread coverage but with lower accuracy. To enhance the accuracy of measurement...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/935 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589179801829376 |
|---|---|
| author | Jiahao Liu Fei Shi Zhenhong Jia Jiwei Qin |
| author_facet | Jiahao Liu Fei Shi Zhenhong Jia Jiwei Qin |
| author_sort | Jiahao Liu |
| collection | DOAJ |
| description | Air pollution concerns have led to the widespread deployment of air quality monitoring stations. While high-cost government stations provide accurate data, their deployment is limited, whereas low-cost sensors offer widespread coverage but with lower accuracy. To enhance the accuracy of measurement data from low-cost air monitoring sensors, this study proposes a Multi-Scale Convolutional Residual Time-Frequency Calibration Method (MCRTF-CM), focusing on the PM<sub>2.5</sub> sensor as an example. This method leverages multi-scale convolution in the feature extractor to capture diverse features at various scales using parallel convolutional kernels. Residual connections merge the original and multi-scale features, preserving the initial input for enhanced stability. The calibration module employs Gated Recurrent Units (GRUs) to capture long-term dependencies in time-series data through reset and update gates. Additionally, the Frequency Enhanced Channel Attention Mechanism (FECAM) uses Discrete Cosine Transform (DCT) to convert time-domain data to frequency-domain, assigning weights to different frequency components to enhance key features and suppress irrelevant ones. Experimental results demonstrate that MCRTF-CM outperforms optimal Long Short-Term Memory (LSTM) networks, reducing RMSE, MAE, MSE, and MAPE by 13.59%, 14.04%, 25.33%, and 8.22%, respectively, indicating its better performance. |
| format | Article |
| id | doaj-art-475dfd2b89bb4395bb185db3a76e74ee |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-475dfd2b89bb4395bb185db3a76e74ee2025-01-24T13:21:23ZengMDPI AGApplied Sciences2076-34172025-01-0115293510.3390/app15020935A Multi-Scale Convolutional Residual Time-Frequency Calibration Method for Low-Accuracy Air Pollution DataJiahao Liu0Fei Shi1Zhenhong Jia2Jiwei Qin3School of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaSchool of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaSchool of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaSchool of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaAir pollution concerns have led to the widespread deployment of air quality monitoring stations. While high-cost government stations provide accurate data, their deployment is limited, whereas low-cost sensors offer widespread coverage but with lower accuracy. To enhance the accuracy of measurement data from low-cost air monitoring sensors, this study proposes a Multi-Scale Convolutional Residual Time-Frequency Calibration Method (MCRTF-CM), focusing on the PM<sub>2.5</sub> sensor as an example. This method leverages multi-scale convolution in the feature extractor to capture diverse features at various scales using parallel convolutional kernels. Residual connections merge the original and multi-scale features, preserving the initial input for enhanced stability. The calibration module employs Gated Recurrent Units (GRUs) to capture long-term dependencies in time-series data through reset and update gates. Additionally, the Frequency Enhanced Channel Attention Mechanism (FECAM) uses Discrete Cosine Transform (DCT) to convert time-domain data to frequency-domain, assigning weights to different frequency components to enhance key features and suppress irrelevant ones. Experimental results demonstrate that MCRTF-CM outperforms optimal Long Short-Term Memory (LSTM) networks, reducing RMSE, MAE, MSE, and MAPE by 13.59%, 14.04%, 25.33%, and 8.22%, respectively, indicating its better performance.https://www.mdpi.com/2076-3417/15/2/935air qualitylow-cost sensorscalibrationMCRTF-CMGRUFECAM |
| spellingShingle | Jiahao Liu Fei Shi Zhenhong Jia Jiwei Qin A Multi-Scale Convolutional Residual Time-Frequency Calibration Method for Low-Accuracy Air Pollution Data Applied Sciences air quality low-cost sensors calibration MCRTF-CM GRU FECAM |
| title | A Multi-Scale Convolutional Residual Time-Frequency Calibration Method for Low-Accuracy Air Pollution Data |
| title_full | A Multi-Scale Convolutional Residual Time-Frequency Calibration Method for Low-Accuracy Air Pollution Data |
| title_fullStr | A Multi-Scale Convolutional Residual Time-Frequency Calibration Method for Low-Accuracy Air Pollution Data |
| title_full_unstemmed | A Multi-Scale Convolutional Residual Time-Frequency Calibration Method for Low-Accuracy Air Pollution Data |
| title_short | A Multi-Scale Convolutional Residual Time-Frequency Calibration Method for Low-Accuracy Air Pollution Data |
| title_sort | multi scale convolutional residual time frequency calibration method for low accuracy air pollution data |
| topic | air quality low-cost sensors calibration MCRTF-CM GRU FECAM |
| url | https://www.mdpi.com/2076-3417/15/2/935 |
| work_keys_str_mv | AT jiahaoliu amultiscaleconvolutionalresidualtimefrequencycalibrationmethodforlowaccuracyairpollutiondata AT feishi amultiscaleconvolutionalresidualtimefrequencycalibrationmethodforlowaccuracyairpollutiondata AT zhenhongjia amultiscaleconvolutionalresidualtimefrequencycalibrationmethodforlowaccuracyairpollutiondata AT jiweiqin amultiscaleconvolutionalresidualtimefrequencycalibrationmethodforlowaccuracyairpollutiondata AT jiahaoliu multiscaleconvolutionalresidualtimefrequencycalibrationmethodforlowaccuracyairpollutiondata AT feishi multiscaleconvolutionalresidualtimefrequencycalibrationmethodforlowaccuracyairpollutiondata AT zhenhongjia multiscaleconvolutionalresidualtimefrequencycalibrationmethodforlowaccuracyairpollutiondata AT jiweiqin multiscaleconvolutionalresidualtimefrequencycalibrationmethodforlowaccuracyairpollutiondata |