"[4D0F3D4CD9C1]" . . "Brno" . "Z(MSM 210000012)" . "60 ; 62" . "6"^^ . . "Nen\u00ED k dispozici"@cs . "Al-ani, T." . "Lhotsk\u00E1, Lenka" . "Cuesta Frau, D." . . . "Hamam, Y." . "Nen\u00ED k dispozici"@cs . "Nov\u00E1k, Daniel" . "RIV/68407700:21230/04:03099084" . "Unsupervised Learning of Holter ECG signals using HMM optimized by simulated annealing" . . . "We present a unsupervised learning algorithm based on continuous Hidden Markov Models (HMM) to automatically classify Holter signals based on their morphology. Our proposed method automatically detect and separate the significant beats by means of hierarchical clustering scheme. Due to the convergence and numeric problems of a classical local optimization technique, we have implemented a novel approach for the global training of HMM by simulated annealing"@en . "2"^^ . "VUTIUM Press" . "3"^^ . "Unsupervised Learning of Holter ECG signals using HMM optimized by simulated annealing"@en . "21230" . . "80-214-2633-0" . . "RIV/68407700:21230/04:03099084!RIV/2005/MSM/212305/N" . . "Unsupervised Learning of Holter ECG signals using HMM optimized by simulated annealing" . "Nen\u00ED k dispozici"@cs . . "Unsupervised Learning of Holter ECG signals using HMM optimized by simulated annealing"@en . . "2004-06-23+02:00"^^ . "We present a unsupervised learning algorithm based on continuous Hidden Markov Models (HMM) to automatically classify Holter signals based on their morphology. Our proposed method automatically detect and separate the significant beats by means of hierarchical clustering scheme. Due to the convergence and numeric problems of a classical local optimization technique, we have implemented a novel approach for the global training of HMM by simulated annealing" . . "Mico, P." . . . "Analysis of Biomedical Signals and Images" . . . "591481" . "ECG; Hidden Markov Models; Simulated Annealing"@en . . "Brno" .