Discretized Linear Regression and Multiclass Support Vector Based Air Pollution Forecasting Technique

TL;DR

This paper introduces an IoT-enabled air pollution forecasting system using discretized linear regression and multiclass SVM, demonstrating improved accuracy and efficiency over existing methods in India’s air quality data.

Contribution

It presents a novel LR-MSV method for air pollution prediction within an IoT and cloud computing framework, enhancing forecasting accuracy and reducing errors.

Findings

LR-MSV outperforms existing methods in accuracy

Significant reduction in forecasting time and error rate

Effective monitoring and control of air quality data

Abstract

Air pollution is a vital issue emerging from the uncontrolled utilization of traditional energy sources as far as developing countries are concerned. Hence, ingenious air pollution forecasting methods are indispensable to minimize the risk. To that end, this paper proposes an Internet of Things (IoT) enabled system for monitoring and controlling air pollution in the cloud computing environment. A method called Linear Regression and Multiclass Support Vector (LR-MSV) IoT-based Air Pollution Forecast is proposed to monitor the air quality data and the air quality index measurement to pave the way for controlling effectively. Extensive experiments carried out on the air quality data in the India dataset have revealed the outstanding performance of the proposed LR-MSV method when benchmarked with well-established state-of-the-art methods. The results obtained by the LR-MSV method witness a significant increase in air pollution forecasting accuracy by reducing the air pollution forecasting time and error rate compared with the results produced by the other state-of-the-art methods