In present scenario of the world, controlling air pollution is one of the leading challenges. Most often the educational institutes and organizations in developing countries suffer from polluted environment due to improper planning and poor infrastructure. Students and faculties in a classroom could suffer from health issues due to prolonged exposure to such environment. In this work, we have built low cost environment monitoring devices which detect different pollutant gasses like CO, CO<sub>2</sub>, NO<sub>2</sub>, particulate matters (PM<sub>10</sub>/PM<sub>2.5</sub>/PM<sub>1</sub>) with two meteorological parameters relative humidity and temperature. We have observed that the same type of sensors for the same gases give different values although the sensitivity of sensors is acceptable, so we have also tried to perform calibration of the sensors using machine learning technique. We have also detected the class duration for which a classroom environment can be considered healthy for a given number of students using our low cost environment monitoring device. We are also trying to develop a predictive model which predicts the indoor environment with given outdoor meteorological data and structure of the room.
Description
IoT based indoor environment data modelling and prediction - IEEE Conference Publication
%0 Conference Paper
%1 sharma2018iot
%A Sharma, P. K.
%A De, T.
%A Saha, S.
%B 2018 10th International Conference on Communication Systems Networks (COMSNETS)
%D 2018
%K collaborative p2map sensorbox
%P 537-539
%R 10.1109/COMSNETS.2018.8328266
%T IoT based indoor environment data modelling and prediction
%U https://ieeexplore.ieee.org/document/8328266/
%X In present scenario of the world, controlling air pollution is one of the leading challenges. Most often the educational institutes and organizations in developing countries suffer from polluted environment due to improper planning and poor infrastructure. Students and faculties in a classroom could suffer from health issues due to prolonged exposure to such environment. In this work, we have built low cost environment monitoring devices which detect different pollutant gasses like CO, CO<sub>2</sub>, NO<sub>2</sub>, particulate matters (PM<sub>10</sub>/PM<sub>2.5</sub>/PM<sub>1</sub>) with two meteorological parameters relative humidity and temperature. We have observed that the same type of sensors for the same gases give different values although the sensitivity of sensors is acceptable, so we have also tried to perform calibration of the sensors using machine learning technique. We have also detected the class duration for which a classroom environment can be considered healthy for a given number of students using our low cost environment monitoring device. We are also trying to develop a predictive model which predicts the indoor environment with given outdoor meteorological data and structure of the room.
@inproceedings{sharma2018iot,
abstract = {In present scenario of the world, controlling air pollution is one of the leading challenges. Most often the educational institutes and organizations in developing countries suffer from polluted environment due to improper planning and poor infrastructure. Students and faculties in a classroom could suffer from health issues due to prolonged exposure to such environment. In this work, we have built low cost environment monitoring devices which detect different pollutant gasses like CO, CO<sub>2</sub>, NO<sub>2</sub>, particulate matters (PM<sub>10</sub>/PM<sub>2.5</sub>/PM<sub>1</sub>) with two meteorological parameters relative humidity and temperature. We have observed that the same type of sensors for the same gases give different values although the sensitivity of sensors is acceptable, so we have also tried to perform calibration of the sensors using machine learning technique. We have also detected the class duration for which a classroom environment can be considered healthy for a given number of students using our low cost environment monitoring device. We are also trying to develop a predictive model which predicts the indoor environment with given outdoor meteorological data and structure of the room.},
added-at = {2018-09-06T17:09:22.000+0200},
author = {Sharma, P. K. and De, T. and Saha, S.},
biburl = {https://www.bibsonomy.org/bibtex/21640767362b0273f1bcd1948582ce3f2/lautenschlager},
booktitle = {2018 10th International Conference on Communication Systems Networks (COMSNETS)},
description = {IoT based indoor environment data modelling and prediction - IEEE Conference Publication},
doi = {10.1109/COMSNETS.2018.8328266},
interhash = {a66a2622712f9cc8cd4562089a27b963},
intrahash = {1640767362b0273f1bcd1948582ce3f2},
issn = {2155-2509},
keywords = {collaborative p2map sensorbox},
month = jan,
pages = {537-539},
timestamp = {2018-09-06T17:09:22.000+0200},
title = {IoT based indoor environment data modelling and prediction},
url = {https://ieeexplore.ieee.org/document/8328266/},
year = 2018
}