SmartOffice: Smart room based an architecture of non-intrusive sensors and computational intelligence techniques

• Hyuri Maciel UFAL
• André Aquino UFAL

DOI: https://doi.org/10.5753/sbcup.2019.6595

Abstract

Information about the occupation of an environment is necessary to implement advanced energy efficiency optimizations. In this sense, this work presents a monitoring and actuation system for intelligent buildings, detecting in a non-intrusive way whether the environment is occupied or not. The system consists of a low cost wireless network that monitors data of temperature, humidity, luminosity and the electric charge of the room while controlling both the illumination and temperature of the environment, a data analysis is performed to characterize the behavior of the environment. Finally, we obtain a 99.7% accuracy in detecting the environment using classification techniques in the sensed environmental data.

Keywords: Smart buildings, sensors network, machine learning, room occupation

References

Banavar, G., Morris, R., Naphade, M., Harrison, C., and Paraszczak, J. (2011). Smarter cities and their innovation challenges. Computer, 44:32–39.

Candanedo, L. M. and Feldheim, V. (2016). Accurate occupancy detection of an office room from light, temperature, humidity and co2 measurements using statistical lear- ning models. Energy and Buildings, 112:28–39.

EPE - Empresa de Pesquisa Energética (2017). Anuário Estatı́stico de Energia Elétrica 2017, volume 1. http://www.eia.gov/totalenergy/data/annual.

Ghai, S. K., Thanayankizil, L. V., Seetharam, D. P., and Chakraborty, D. (2012). Oc- cupancy detection in commercial buildings using opportunistic context sources. In 2012 IEEE International Conference on Pervasive Computing and Communications Workshops.

Hastie, T., Tibshirani, R., and Friedman, J. (2017). The Elements of Statistical Learning. Springer, second edition.
Integrated, M. (2015). Ds1307 64 x 8, serial, i2 c real-time clock.

Kleiminger, W., Beckel, C., Staake, T., and Santini, S. (2013). Occupancy detection from electricity consumption data. Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings, pages 1–8.

Lantz, B. (2015). Machine Learning with R. Packt Publishing Ltd, second edition.

Ltd., A. E. (2010). Dht11 humidity e temperature sensor.

Nikolaou, T. G., Kolokotsa, D. S., Stavrakakis, G. S., and Skias, I. D. (2012). On the application of clustering techniques for office buildings’ energy and thermal comfort classification. IEEE Transactions on Smart Grid, 3(4):2196 – 2210.

Nordic semiconductor (2008). nrfl24l01+ prelimirary product specification.

Quindai, R., Barbosa, B. M., Almeida, C. M. P., Ramos, H. S., Rodrigues, J. J. P. C., and Aquino, A. L. L. (2018). A non-intrusive low-cost kit for electric power measuring and energy disaggregation. Journal of Communications Software and Systems, 14(1):9–17.

Technologies, S. (2010). Light dependent resistor ldr.

United Nations (2014). World Urbanization Prospects 2014: Highlights. Department of Economic and Social Affairs. United Nations Environment Programme.