Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Sensor Data Fusion For Air Quality Monitoring
Since traditional air quality monitoring methods often rely on geographically sparse and costly air quality monitoring stations, image-based air quality method- ologies are recently offering a compelling alternative that utilizes images from sources like satellites, traffic cameras, and even smartph...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2025
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | Since traditional air quality monitoring methods often rely on geographically sparse and costly air quality monitoring stations, image-based air quality method- ologies are recently offering a compelling alternative that utilizes images from sources like satellites, traffic cameras, and even smartphones to monitor pollution levels by using estimation models, image-processing techniques, and deep-learning models. In this thesis, we first conduct a systematic review, in which we categorize and discuss the existing literature work. Moreover, we introduce a novel, multi- modal dataset designed to address the limitations of existing datasets, which are restricted in size, geographical coverage, and fixed-scene imagery, impeding the generalization of existing deep-learning prediction models. Our AirFusion dataset comprises 9,411 images paired with synchronized meteorological and geospatial readings, collected by a portable commercial air quality sensor, from 179 diverse locations. lastly, we introduce AirFusionNet, which leverages transfer learning of the pre-trained ResNet50 and use an attention mechanism to extract features from both image and numerical data to predict five key air quality parameters: PM1, PM2.5, PM10, temperature, and humidity. Our analysis of AirFusionNet estab- lishes baseline results on this challenging dataset. Our model achieves an RMSE of 10.44, 11.56, 13.18, 2.98, and 9.02 for PM1, PM2.5, PM10, temperature, and humidity, respectively, on the filtered day dataset and achieves RMSE of 9.08, 9.75, 10.69, 2.63, and 8.49 for the same parameters respectively, on the filtered combined day-night dataset. These results establish a new baseline for outdoor air quality prediction, demonstrating good performance for normal pollution levels. However, during high pollution events the RMSE increases, suggesting the need for more high-pollution data samples to improve model performance. |
|---|