Air Quality Prediction Based on Machine Learning
IEEE BASE PAPER ABSTRACT:
In recent years, due to the vigorous development of industrialization, environmental protection measures cannot be effectively guaranteed. Increasingly serious environmental problems have gradually become the primary problem affecting the quality of national life. Therefore, we need to establish a relatively accurate air quality prediction model to understand the possible air pollution process in advance. According to the prediction results of the model, it is of great significance to establish and take corresponding control measures to reduce air pollution. This paper makes full use of data mining methods such as mutual information theory, neural networks, and intelligent optimization algorithm. We use the basic data of long-term air quality prediction of open monitoring points as training set and test set. Firstly, the SOM neural network model is used for unsupervised clustering of relevant pollutant data to analyze the correlation between various monitored pollutants. Aiming at the problems of a large amount of data and long calculation time of the algorithm, combined with the clustering results, and NSGA-II optimized neural network is proposed to predict the future pollution situation. The experimental results show that the prediction accuracy of pollutants can reach more than 90%.
OUR PROPOSED ABSTRACT:
In many industrial and urban regions today, assessing the air quality has become one of the most important activities for the residents. The many types of pollution brought on by the use of power, transportation, fuel, etc. have a negative impact on the quality of the air. The accumulation of dangerous gases is seriously affecting the quality of life in smart cities. We must implement effective air quality monitoring and prediction models that gather data on pollutant concentrations and provide assessments of local air pollution in order to deal with the rising levels of air pollution. Particulate matter is made up of microscopic solid or liquid droplets that are so minute that breathing them in can have major negative effects on one’s health. As a result, assessing and forecasting air quality has grown in significance. We will discuss the Random Forest Technique in this suggested system as a means of predicting and measuring pollution in large cities. The data generated by this technique includes real-time traffic data, weather information, and road data. Additionally utilised for data training and prediction is this method. Our proposed machine learning-based model for predicting air quality had a train accuracy of 99% and a test accuracy of 90%. As a result, the created model can produce better air pollution concentration forecasting performance. The approach can be used in different fields and databases due to its universality.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
Random Forest Classifier.
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED
- Input Devices : Keyboard, Mouse
- Ram : 4 GB
- Operating system : Windows 10.
- Coding Language : Python 3.8
- Web Framework : Flask
Chenghao Shi, Yu Wang, Ying Wan, Shuguang Wu, “Air Quality Prediction Based on Machine Learning”, 2022 International Conference on Machine Learning and Knowledge Engineering (MLKE), IEEE Conference, 2022.
Tag:best python projects, deep learning projects, deep learning projects for final year, ieee papers on python projects, ieee projects, ieee projects for cse, ieee projects for cse in python, machine learning projects, machine learning projects for final year, ml projects, python ai projects, python ieee projects, python ieee projects in machine learning, python machine learning projects