Mi SciELO
Servicios Personalizados
Articulo
Indicadores
Citado por SciELO
Links relacionados
Similares en SciELO
Compartir
Ingeniería Electrónica, Automática y Comunicaciones
versión On-line ISSN 1815-5928
Resumen
GONZALEZ RUBIO, Tahimy et al. Proposal for the monitoring of sedation states in electroencephalographic signals. EAC [online]. 2019, vol.40, n.3, pp. 16-27. Epub 08-Sep-2019. ISSN 1815-5928.
During a surgical procedure it is essential induce to the patient, unconsciousness states, amnesia, analgesia and muscle relaxation, however, cases of intraoperative awareness are reported for the inaccuracy in monitoring anesthesia. Due the incidence of this phenomenon, the Center for Neuroscience Studies, Images and Signals Processing from Universidad de Oriente, Cuba, is carried out the development of an anesthesia monitor prototype, based on automatic recognition of sedation states in electroencephalographic signals using Artificial Intelligence techniques. To achieve the proposed objective, were evaluated the performance of a Naive Bayes classifier and three Machines Learning: Artificial Neural Networks with five different topologies, Adaptive Network Based Fuzzy Inference System and Support Vector Machines to recognize three sedation states characterized by nine power parameters obtained from the frequency spectrum of the signals recorded by two electroencephalographic channels front F4 and Fz. As results of the experiments, the states Profound Sedation, Moderate Sedation and Mild Sedation were recognized with an Accuracy of 96.12%, 90.06% and 90.24% respectively using Support Vector Machines and the registers of F4 electroencephalographic channel.
Palabras clave : Machines Learning; Sedation States; Electroencephalographic Signals.