Ríos Muñoz, Gonzalo RicardoMoreno Pino, FernandoSoto, NinaMartínez Olmos, PabloArtés Rodríguez, AntonioFernández Avilés, FranciscoArenal, Ángel2022-05-182022-05-182020-09-13Computing in Cardiology (CinC 2020), 13-16 September 2020, Rimini, Italy. V. 47. IEEE, 2020.978-1-7281-7382-52325-887Xhttps://hdl.handle.net/10016/34837Proceeding of 2020 Computing in Cardiology (CinC 2020), 13-16 September 2020, Rimini, ItalyActivity detection in atrial fibrillation (AF) electrograms (EGMs) is a key concept to understand the mechanisms of this frequent arrhythmia and design new strategies for its treatment. We present a new method that employs Hidden Markov Models (HMMs) to identify activity presence in bipolar EGMs. The method is fully unsupervised and hence it does not require labeled training data. The HMM activity detection method was validated and compared to the non-linear energy operator (NLEO) method for a set of manually annotated EGMs. The HMM performed better than the NLEO and exhibited more robustness in the presence of low voltage fragmented EGMs.4eng© 2020, IEEETrainingLow voltageNonlinear distortionHidden Markov modelsAtrial fibrillationTraining dataRobustnessconference paperBiología y BiomedicinaTelecomunicacioneshttps://doi.org/10.22489/CinC.2020.098open access14Computing in Cardiology (CinC 2020), 13-16 September 2020, Rimini, Italy47CC/0000033345