AUTOMATED AIR POLLUTION DETECTION AND ESTIMATION OF AQI USING ResNET
Author(s):
R.Udaya Shanmuga, Dr.G.TamilPavai
Keywords:
Abstract
Air Pollution is turning the whole world
prematurely grey. The health effects of air pollution imperil human lives especially for at-risk population and those with respiratory illness and the fact is well- documented. Many researches proposed to estimate particulate matter values from smartphone images, given that deploying highly accurate air pollution monitors throughout a city is a highly expensive. Departing from previous machine learning studies which primarily focus on pollutant estimation based on single day-time images, our proposed deep learning model integrates Residual Network (ResNet) with Long Short-Term Memory (LSTM), extracting spatial-temporal features of sequential images taken from smartphones instead for estimating PM2.5 and PM10 values of a particular location at a particular time. Our methodology is as follows: First, images are obtained constantly with regular time intervals. Second, verified experimentally that any PM2.5 and PM10 values obtained remain constant within a radius of 500 meters. Third, the proposed ResNet-LSTM was constructed and extended by incorporating meteorological information and one short path. In future, our deep-learning image-based air pollution estimation study will incorporate sequential images obtained from 24-hr operating traffic surveillance cameras distributed across all parts to provide full- day and more fine-grained image-based air pollution estimation for the city.
Article Details
Unique Paper ID: 154171
Publication Volume & Issue: Volume 8, Issue 7
Page(s): 39 - 48
Article Preview & Download
Share This Article
Conference Alert
NCSST-2021
AICTE Sponsored National Conference on Smart Systems and Technologies
Last Date: 25th November 2021
SWEC- Management
LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT