Publication Type : Conference Proceedings
Publisher : IEEE
Source : 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), Kirtipur, Nepal, 2024, pp. 1597-1603, doi: 10.1109/I-SMAC61858.2024.10714872. 28.10.2024-xplore
Url : https://ieeexplore.ieee.org/document/10714872
Campus : Bengaluru
School : School of Engineering
Department : Electrical and Electronics
Year : 2024
Abstract : Quality of all living beings depends on the five basic elements of which air is one element. Due to rapid industrialization and overgrowing vehicle numbers, the air is being polluted to a greater extent. This work aims in assessing the air quality using machine learning and deep learning algorithms. Air quality dataset is taken from an open source. Four artificial intelligent based regressors are used. Two machine learning models based on ensemble technique viz., random forest and gradient boost algorithm are used. Two models are based on neural network namely, Artificial Neural Network and Long Short-Term Memory (LSTM) regression models, two ensemble methods viz. Random Forest and Gradient Boost methods are used. The random forest model provides better estimation of air quality compared to other three methods with R2-score of 0.959, with least Mean Squared Error (MSE) of 0.042, Mean Absolute Error (MAE) of 0.13 and Root Mean Squared Error (RMSE) of 0.0205.
Cite this Research Publication : Swara Sameer Pawaneka, Jagadish S. Kallimani, Geetanjali Udgirkar, M. R. Rashmi, Sanitha Michail C., and Hoong Pin Lee, "Efficient AQI Prediction: A Comparative Study of Artificial Neural Networks, LSTM, Random Forest, and Gradient Boosting Techniques," 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), Kirtipur, Nepal, 2024, pp. 1597-1603, doi: 10.1109/I-SMAC61858.2024.10714872. (28.10.2024-xplore)