Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network
Author ORCID
Joyanta Jyoti Mondal 0000-0003-3113-8603
Md. Farhadul Islam 0000-0003-3249-4490
Meem Arafat Manab 0000-0002-2336-4160
Publication Date
4-29-2023
Abstract
Short Description:
In this research, we vigorously analyze the difficulties of predicting location-specific PM2.5 concentration from photos captured by smartphone cameras. Here, we particularly focus on Dhaka, the capital of Bangladesh, considering its very high level of air pollution exposure to a huge number of its dwellers. In our research, we develop a Deep Convolutional Neural Network (DCNN) and train it using more than a thousand outdoor photos captured and labeled by us. We capture the photos at various locations in Dhaka, Bangladesh, and label them based on PM2.5 concentration data extracted from the local US consulate as computed by the NowCast algorithm. During training with the dataset, our model learns a correlation index through supervised learning, which improves the model's ability to act as a Picture-based Predictor of PM2.5 Concentration (PPPC) making it capable of detecting comparable daily aggregated AQI index from a photo captured by a smartphone.
Code and More Details: https://github.com/lepotatoguy/aqi
Keywords
AQI, PM2.5
Repository
Zenodo
Distribution License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Access Instructions and Link
This data is available under the CC-BY 4.0 License
Recommended Citation
Mondal, Joyanta Jyoti; Islam, Md. Farhadul; Islam, Raima; Rhidi, Nowsin Kabir; Islam, A; Manab, Meem; and Noor, Jannatun, "Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network" (2023). UAB Research Data Catalog. 96.
https://digitalcommons.library.uab.edu/datasets/96
