{"title":"Web Scraping Technique for Prediction of Air Quality through Comparative Analysis of Machine Learning and Deep Learning Algorithm","authors":"G. Kalaivani, S. Kamalakkannan","doi":"10.1109/ICAISS55157.2022.10010968","DOIUrl":null,"url":null,"abstract":"Air contamination has turned into a significant and difficult issue all over the planet and its direct impact with human well-being has drawn a lot of consideration from numerous analysts. Individuals are turning out to be known better ways of checking air quality data which are essential to safeguard human wellbeing from the genuine medical conditions brought about via air contamination. Numerous specialists are working on current air quality observation and expectations to carry out different government arrangements connected with the climate or air contamination and give precise outcomes to assist with settling on significant choices. This paper employs a machine learning method to implement predictive analytics and create a more accurate prediction model. These models are created by analysing trends and patterns using historical time series data and then creating a prediction model to forecast future values. These prediction models will be used to execute our suggested approach, the Air Quality Prediction Model (AQPM). This model yields a prediction model that accurately predicts the Air Quality Index (AQI) through the data collected. The information will be scraped from the Central Pollution Control Board (CPCB) website using the web scraping technique. The comparative analysis of ML and DL suggests that Long Short-Term Memory (LSTM) is the best fit model to measure air quality using three different accuracy metrics. Finally, the data are analysed using the predicted AQI in the LSTM model.","PeriodicalId":243784,"journal":{"name":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","volume":"41 1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAISS55157.2022.10010968","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Air contamination has turned into a significant and difficult issue all over the planet and its direct impact with human well-being has drawn a lot of consideration from numerous analysts. Individuals are turning out to be known better ways of checking air quality data which are essential to safeguard human wellbeing from the genuine medical conditions brought about via air contamination. Numerous specialists are working on current air quality observation and expectations to carry out different government arrangements connected with the climate or air contamination and give precise outcomes to assist with settling on significant choices. This paper employs a machine learning method to implement predictive analytics and create a more accurate prediction model. These models are created by analysing trends and patterns using historical time series data and then creating a prediction model to forecast future values. These prediction models will be used to execute our suggested approach, the Air Quality Prediction Model (AQPM). This model yields a prediction model that accurately predicts the Air Quality Index (AQI) through the data collected. The information will be scraped from the Central Pollution Control Board (CPCB) website using the web scraping technique. The comparative analysis of ML and DL suggests that Long Short-Term Memory (LSTM) is the best fit model to measure air quality using three different accuracy metrics. Finally, the data are analysed using the predicted AQI in the LSTM model.