Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Dias, B., Glória, A. & Sebastião, P. (2021). Prediction of link quality for IoT cloud communications supported by machine learning. In Paul R. (Ed.), 2021 IEEE World AI IoT Congress (AIIoT) . (pp. 150-154). Seattle, WA, USA: IEEE.
Exportar Referência (IEEE) 
B. Dias et al.,  "Prediction of link quality for IoT cloud communications supported by machine learning", in 2021 IEEE World AI IoT Congr. (AIIoT) , Paul R., Ed., Seattle, WA, USA, IEEE, 2021, pp. 150-154
Exportar BibTeX 
@inproceedings{dias2021_1766222678398,
	author = "Dias, B. and Glória, A. and Sebastião, P.",
	title = "Prediction of link quality for IoT cloud communications supported by machine learning",
	booktitle = "2021 IEEE World AI IoT Congress (AIIoT) ",
	year = "2021",
	editor = "Paul R.",
	volume = "",
	number = "",
	series = "",
	doi = "10.1109/AIIoT52608.2021.9454211",
	pages = "150-154",
	publisher = "IEEE",
	address = "Seattle, WA, USA",
	organization = "",
	url = "https://ieeexplore.ieee.org/xpl/conhome/9454163/proceeding"
}
Exportar RIS 
TY  - CPAPER
TI  - Prediction of link quality for IoT cloud communications supported by machine learning
T2  - 2021 IEEE World AI IoT Congress (AIIoT) 
AU  - Dias, B.
AU  - Glória, A.
AU  - Sebastião, P.
PY  - 2021
SP  - 150-154
DO  - 10.1109/AIIoT52608.2021.9454211
CY  - Seattle, WA, USA
UR  - https://ieeexplore.ieee.org/xpl/conhome/9454163/proceeding
AB  - This paper introduces a study done to evaluate the use of machine learning regression techniques to predict the link quality of communications done by IoT nodes. The proposed methodology is able to predict the link quality of the most typical cloud communication protocols, such as cellular, Wi-Fi, SigFox and LoRaWAN, based on the node location. To discover the best model to achieve this, a set of machine learning techniques were implemented, including Linear Regression, Decision Tree, Random Forest and Neural Networks, being the results compared. Results showed that Decisions Trees achieve the best efficiency, with a margin of error of 7.172 dBm, after cross-validation. This paper includes a detailed description of the methodology, its implementation and the experimental results.
ER  -