Export Publication

The publication can be exported in the following formats: APA (American Psychological Association) reference format, IEEE (Institute of Electrical and Electronics Engineers) reference format, BibTeX and RIS.

Export Reference (APA) 
Coelho, J. A., Glória, A. & Sebastião, P. (2020). Precise water leak detection using machine learning and real-time sensor data. IoT. 1 (2), 474-493
Export Reference (IEEE) 
J. A. Coelho et al.,  "Precise water leak detection using machine learning and real-time sensor data", in IoT, vol. 1, no. 2, pp. 474-493, 2020
Export BibTeX 
@article{coelho2020_1766198897064,
	author = "Coelho, J. A. and Glória, A. and Sebastião, P.",
	title = "Precise water leak detection using machine learning and real-time sensor data",
	journal = "IoT",
	year = "2020",
	volume = "1",
	number = "2",
	doi = "10.3390/iot1020026",
	pages = "474-493",
	url = "https://www.mdpi.com/journal/IoT"
}
Export RIS 
TY  - JOUR
TI  - Precise water leak detection using machine learning and real-time sensor data
T2  - IoT
VL  - 1
IS  - 2
AU  - Coelho, J. A.
AU  - Glória, A.
AU  - Sebastião, P.
PY  - 2020
SP  - 474-493
SN  - 2624-831X
DO  - 10.3390/iot1020026
UR  - https://www.mdpi.com/journal/IoT
AB  - Water is a crucial natural resource, and it is widely mishandled, with an estimated one third of world water utilities having loss of water of around 40% due to leakage. This paper presents a proposal for a system based on a wireless sensor network designed to monitor water distribution systems, such as irrigation systems, which, with the help of an autonomous learning algorithm, allows for precise location of water leaks. The complete system architecture is detailed, including hardware, communication, and data analysis. A study to discover the best machine learning algorithm between random forest, decision trees, neural networks, and Support Vector Machine (SVM) to fit leak detection is presented, including the methodology, training, and validation as well as the obtained results. Finally, the developed system is validated in a real-case implementation that shows that it is able to detect leaks with a 75% accuracy. 
ER  -