Authors :
K.V.V. Ganesh; G. Sheetal; M. Sai Amith; L. Harshith Goyal; K. Srinivasa Rao
Volume/Issue :
Volume 9 - 2024, Issue 4 - April
Google Scholar :
https://tinyurl.com/bdeaj25f
Scribd :
https://tinyurl.com/mrxex6hw
DOI :
https://doi.org/10.38124/ijisrt/IJISRT24APR1706
Abstract :
The project titled "Air Quality Prediction
Using KNN and LSTM" endeavors toaddress the critical
issue of air pollutionthrough the application of advanced
computational techniques. The project aimsto develop a
robust predictive model that can forecast air quality
levels based on historical data, meteorological
parameters, and relevant environmental features.
Leveraging machine learning algorithms such as
regression, decision trees, or neural networks, the
project seeks to analyze complex relationships within the
data and enhance the accuracy of air qualitypredictions.
The methodology involves the collection and
preprocessing of extensive datasets encompassing
pollutant concentrations, weather conditions, and
geographicalinformation. The selected machine learning
algorithms will be trained on this data to recognize
patterns and correlations, enabling the model to make
accurate predictions. The project also explores the
integration of real- time data streams, satellite imagery,
and sensor networks to improve the responsiveness of
the predictive model.
Keywords :
Air Quality Prediction, Machine Learning Algorithms, Linear Regression, Decision Tree, Random Forest, K-Nearest Neighbours (KNN), Long Short-Term Memory (LSTM), Ensemble Learning,Hybrid Models.
The project titled "Air Quality Prediction
Using KNN and LSTM" endeavors toaddress the critical
issue of air pollutionthrough the application of advanced
computational techniques. The project aimsto develop a
robust predictive model that can forecast air quality
levels based on historical data, meteorological
parameters, and relevant environmental features.
Leveraging machine learning algorithms such as
regression, decision trees, or neural networks, the
project seeks to analyze complex relationships within the
data and enhance the accuracy of air qualitypredictions.
The methodology involves the collection and
preprocessing of extensive datasets encompassing
pollutant concentrations, weather conditions, and
geographicalinformation. The selected machine learning
algorithms will be trained on this data to recognize
patterns and correlations, enabling the model to make
accurate predictions. The project also explores the
integration of real- time data streams, satellite imagery,
and sensor networks to improve the responsiveness of
the predictive model.
Keywords :
Air Quality Prediction, Machine Learning Algorithms, Linear Regression, Decision Tree, Random Forest, K-Nearest Neighbours (KNN), Long Short-Term Memory (LSTM), Ensemble Learning,Hybrid Models.
