Indonesian Journal of Electrical Engineering and Computer Science Vol. 19, No. 2, August 2020, pp. 775~783 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v19.i2.pp775-783  775 Journal homepage: http://ijeecs.iaescore.com Simulation and optimization of genetic algorithm-artificial neural network based air quality estimator Shirish Pandey, S.Hasan Saeed, N.R. Kidwai Department of ECE, Integral University, India Article Info ABSTRACT Article history: Received Jan4, 2020 Revised Mar6, 2020 Accepted Mar21, 2020 In this work intelligent model for estimation of the concentration of carbon monoxide in a polluted environment is developed on mat Lab platform. The results are validated using data collected from repository linked to University of California. The data records are over the duration of one year using E nose sensor placed in main city of Italy. The records are rectified and segmented at different length to extract the Base and Divergence Values features. An Artificial Neural Network Model (ANN) is developed and the result is validated manually.Another optimized Genetic Algorithm- Artificial Neural Network based air quality estimation model is developed which validate the result using artificial intelligence technique to get a better performance network. Keywords: Artificial neuralnetwork Genetic algorithm Copyright © 2020 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: ShirishPandey, Departmentof ECE,Integral University, Kursi Road Lucknow226021,India. Email: Shirish109@gmail.com 1. INTRODUCTION The environment air pollution affects the human life. Therefore it is necessary to predict the air quality exactly. In the present time it will be rather easy to use digital signal processing technique for research purpose and so far generating result. The geographical information system (G.I.S.) a power technique to process polluted data. Though the G.I.S based data mining technique is very popular but it is not much accurate. People involved in environmental research also use a number of numeric factors to achieve desired result. It is easier to define certain attributes for each data sample using numeric factors. Due to these attributes it is possible to identify variation in pollution. The attributes are ordinal-scale variable. Ordinal-scale variable are obtained by literature review.Ordinal scale variable are not easy to define[1]. A number of other methods were also proposed for the estimation and monitoring air quality. A method was proposed to monitor air quality in environment using concept that in a vehicle the air quality is similar to the outer environment if the windows are open. They detected air exchange rate within and outside of vehicle before and after window is open on an internet of things (Iot) platform [2]. Another IoT application using ANN is proposed by overcoming the limitation of existing approaches which have lengthyshort term memory based artificial intelligence technique using neural network for prediction of contaminants concentration in a polluted environment [3-5]. Different methods for monitoring environment quality in manufacturing industry using wireless sensor network with Zigbee were proposed to collect data for various toxic gases along with temperature, and humidity [6-11]. A unique method to predict the air quality using neural network based on multiple locations, outcome from correlations between nearby locations and among similar locations in temporary domain at the location in Taiwan and Beijing [12]. An electronic nose method used to predict the environmental pollution.They employed three type of e-nose system based on amperometric gas sensors [13-15]. A method using wireless sensor network is presented using deployment of sensors at various