Data Analytics for Home Air Quality Monitoring

  • Petya Mihaylova
  • Agata ManolovaEmail author
  • Petia Georgieva
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 283)


Modern air quality monitoring systems are characterised by high complexity and costs. The expensive embedded units such as sensor arrays, processors, power blocks, displays and communication units make them less appropriate for small indoor spaces.

In this paper we demonstrate that two widely available, in private houses, sensors (for Humidity and Temperature) are promising alternative, to the expensive indoor air quality solutions, provided with intelligent data processing tools. Our findings suggest that neural network based data analytics system can learn to discriminate unusual indoor gases from normal home air components based only on temperature and humidity measurements.


Indoor air quality Data analytics Neural network Deep Autoencoder Neural Network 



This study has been done during the traineeship program of PhD student Petya Mihaylova in University of Aveiro funded by ERASMUS+EU programme for education, training, youth and sport, supported by technical University of Sofia, Bulgaria.


  1. 1.
    Mikuckas, A., et al.: A grey model approach to indoor air quality management in rooms based on real-time sensing of particles and volatile organic compounds. Appl. Math. Model. 42, 290–299 (2017)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Jangid, S., Sharma, S.: An embedded system model for air quality monitoring. In: International Conference on Computing for Sustainable Global Development (INDIACom), pp. 303–308 (2016)Google Scholar
  3. 3.
    Clémenta, P., et al.: Gas discrimination using screen-printed piezoelectric cantilevers coated with carbon nanotubes. Sens. Actuators, B 237, 1056–1065 (2016)CrossRefGoogle Scholar
  4. 4.
    Fonollosaa, J., et al.: Human activity monitoring using gas sensor arrays. Sens. Actuators, B 199, 398–402 (2014)CrossRefGoogle Scholar
  5. 5.
    Szczurek, M.M., Flisowska-Wiercik, B.: Method of gas mixtures discrimination based on sensor array, temporal response and data driven approach. Talanta 83, 916–923 (2011)CrossRefGoogle Scholar
  6. 6.
    Penza, M., Gassano, G., Tortorella, F.: Gas recognition by activated WO3 thin-film sensors array. Sens. Actuators, B 81, 115–121 (2001)CrossRefGoogle Scholar
  7. 7.
    Chen, P.-C., Ishikawa, F.N., Chang, H.-K., Ryu, K., Zhou, Ch.: A nanoelectronic nose: a hybrid nanowire/carbon nanotube sensor array with integrated micro-machined hotplates for sensitive gas discrimination. Nanotechnology 20(12), 125503 (2009)CrossRefGoogle Scholar
  8. 8.
    Huertaa, R., Mosqueiroa, T., Fonollosab, J., Rulkova, N.F., Rodriguez-Lujand, I.: Online decorrelation of humidity and temperature in chemical sensors for continuous monitoring. Chemo-metrics Intell. Lab. Syst. 157, 169–176 (2016)CrossRefGoogle Scholar
  9. 9.
    Huerta, R., Vembu, S., Amigó, J.M., Nowotny, T., Elkan, C.: Inhibition in multiclass classification. Neural Comput. 24(9), 2473–2507 (2012)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Computer Vision and Pattern Recognition (2014)Google Scholar
  11. 11.
    Krizhevsky, A., Sutskever, I.G., Hinton, E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)Google Scholar
  12. 12.
    Hinton, G., Osindero, S., The, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Bozhkov, L., Koprinkova-Hristova, P., Georgieva, P.: Learning to decode human emotions with Echo State Networks. Neural Networks 78, 112–119 (2016)CrossRefGoogle Scholar
  14. 14.
    Bozhkov, L., Koprinkova-Hristova, P., Georgieva, P.: Reservoir computing for emotion valence discrimination from EEG signals. Neurocomputing 231, 28–40 (2017)CrossRefGoogle Scholar
  15. 15.
    UCI Machine Learning Repository: Data Sets.

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019

Authors and Affiliations

  • Petya Mihaylova
    • 2
  • Agata Manolova
    • 3
    Email author
  • Petia Georgieva
    • 1
  1. 1.Department of Electronics, Telecommunications and InformaticsUniversity of AveiroAveroPortugal
  2. 2.English Language Faculty of EngineeringTechnical University of SofiaSofiaBulgaria
  3. 3.Faculty of TelecommunicationsTechnical University of SofiaSofiaBulgaria

Personalised recommendations