A Comparative Study on Prediction of PM2.5 Level Using Optimization Techniques

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Atmospheric particulate matter which is generally known as PM2.5 and its variants consists of solid as well as liquid components suspending in stagnant air in our environment. If concentration of PM2.5 like particulate matter which is made up of very minute particles exceeds its limit leading to serious health problems like lungs problems in Humans as well as adverse impacts on Environment. Machine learning techniques can be used to efficiently train a model on data and improve its efficiency using Optimization Techniques. This work aims to Predict PM2.5 levels accurately in minimum time; Multiple Optimization techniques are explored here mainly Gradient Descent variants are applied using Linear Regression on meteorological data collected from a weather station in India. Our Study has showed that the AdaGrad achieve better performance with least error rate than other Optimization techniques.

Original languageEnglish
Title of host publicationProceedings of CONECCT 2021
Subtitle of host publication7th IEEE International Conference on Electronics, Computing and Communication Technologies
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665428491
DOIs
Publication statusPublished - 2021
Event7th IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2021 - Bangalore, India
Duration: 09-07-202111-07-2021

Publication series

NameProceedings of CONECCT 2021: 7th IEEE International Conference on Electronics, Computing and Communication Technologies

Conference

Conference7th IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2021
Country/TerritoryIndia
CityBangalore
Period09-07-2111-07-21

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Instrumentation
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'A Comparative Study on Prediction of PM2.5 Level Using Optimization Techniques'. Together they form a unique fingerprint.

Cite this