Open Access

ARTICLE

Image-Based Air Quality Estimation by Few-Shot Learning

Duc Cuong Pham¹, Tien Duc Ngo², Hoai Nam Vu^1,3,*

1 Faculty of Artificial Intelligence, Posts and Telecommunications Institute of Technology, Nguyen Trai, Ha Noi, 100000, Viet Nam
2 Faculty of Information Technology, Posts and Telecommunications Institute of Technology, Nguyen Trai, Ha Noi, 100000, Viet Nam
3 Young Innovation Research Laboratory on Digital Technology (YIRLoDT), Posts and Telecommunications Institute of Technology, Nguyen Trai, Ha Noi, 100000, Viet Nam

* Corresponding Author: Hoai Nam Vu. Email:

Computers, Materials & Continua 2025, 84(2), 2959-2974. https://doi.org/10.32604/cmc.2025.064672

Received 21 February 2025; Accepted 06 May 2025; Issue published 03 July 2025

Abstract

Air quality estimation assesses the pollution level in the air, supports public health warnings, and is a valuable tool in environmental management. Although air sensors have proven helpful in this task, sensors are often expensive and difficult to install, while cameras are becoming more popular and accessible, from which images can be collected as data for deep learning models to solve the above task. This leads to another problem: several labeled images are needed to achieve high accuracy when deep-learning models predict air quality. In this research, we have three main contributions: (1) Collect and publish an air quality estimation dataset, namely PTIT_AQED, including environmental image data and air quality; (2) Propose a deep learning model to predict air quality with few data, called PTIT_FAQE (PTIT Few-shot air quality estimation). We build PTIT_FAQE based on EfficientNet-a CNN architecture that ensures high performance in deep learning applications and Few-shot Learning with Prototypical Networks. This helps the model use only a few training data but still achieve high accuracy in air quality estimation. And (3) conduct experiments to prove the superiority of PTIT_FAQE compared to other studies on both PTIT_AQED and APIN datasets. The results show that our model achieves an accuracy of 0.9278 and an F1-Score of 0.9139 on the PTIT_AQED dataset and an accuracy of 0.9467 and an F1-Score of 0.9371 on the APIN dataset, which demonstrate a significant performance improvement compared to previous studies. We also conduct detailed experiments to evaluate the impact of each component on model performance.

---

Keywords

---