Pesquisa de referências

Smart monitoring of electrical circuits for distinction of connected devices through current pattern analysis using machine learning algorithms

Smart monitoring of electrical circuits for distinction of connected devices through current pattern analysis using machine learning algorithms
Recurso electrónico / Electronic resource
Registro MARC
Tag12Valor
LDR  00000cab a2200000 4500
001  MAP20200037262
003  MAP
005  20220911190415.0
008  201123e20201201esp|||p |0|||b|por d
040  ‎$a‎MAP‎$b‎spa‎$d‎MAP
084  ‎$a‎922.134
100  ‎$0‎MAPA20200022954‎$a‎Oliveira Lima, Jean Phelipe de
24510‎$a‎Smart monitoring of electrical circuits for distinction of connected devices through current pattern analysis using machine learning algorithms‎$c‎Jean Phelipe de Oliveira Lima, Carlos Maurício Seródio Figueiredo
500  ‎$a‎Artículo en portugués
520  ‎$a‎Energy Monitoring is a crucial activity in Energy Eciency, which involves the study of techniques to supervise the energy consumption in a power grid, regarding the main purpose is to assure a good level of detail, to achieve consumption quotas for each connected device, for a low infrastructure cost. This paper presents the evaluation of dierent Machine Learning models to classify electric current patterns to identify and monitor electric charges present in circuits with a single sensing device. The models were trained and validated by a database created from signal samples of 4 electrical devices: Notebook Charger, Refrigerator, Blender and Fan. The models that presented the best metrics achieved, respectively, 97% and 100% Accuracy and 98% and 100% F1-Score, surpassing results obtained in related researches.
650 4‎$0‎MAPA20080611200‎$a‎Inteligencia artificial
650 4‎$0‎MAPA20170005476‎$a‎Machine learning
650 4‎$0‎MAPA20110029234‎$a‎Eficiencia energética
650 4‎$0‎MAPA20080584269‎$a‎Consumo energético
7001 ‎$0‎MAPA20200023012‎$a‎Seródio Figueiredo, Carlos Maurício
7730 ‎$w‎MAP20200034445‎$t‎Revista Iberoamericana de Inteligencia Artificial‎$d‎IBERAMIA, Sociedad Iberoamericana de Inteligencia Artificial , 2018-‎$x‎1988-3064‎$g‎31/12/2020 Volumen 23 Número 66 - diciembre 2020 , p. 36-50
856  ‎$q‎application/pdf‎$w‎1108791‎$y‎Recurso electrónico / Electronic resource