Title :
Hierarchical Linear Dynamical Systems: A new model for clustering of time series
Author :
Cinar, Goktug T. ; Loza, Carlos A. ; Principe, Jose C.
Author_Institution :
Comput. NeuroEngineering Lab. (CNEL), Univ. of Florida, Gainesville, FL, USA
Abstract :
The auditory cortex in the brain does effortlessly a better job of extracting information from the acoustic world than our current generation of signal processing algorithms. The proposed architecture, Hierarchical Linear Dynamical System (HLDS), is based on Kalman filters with hierarchically coupled state models that stabilize the input dynamics and provide a representation space. This approach extracts information from the input and self-organizes it in the higher layers leading to an algorithm capable of clustering time series in an unsupervised manner. In this paper we further investigate the properties of HLDS, demonstrate its performance on music rather than isolated notes and propose the time domain implementation to overcome one of its current bottlenecks.
Keywords :
Kalman filters; information retrieval; music; pattern clustering; signal representation; time series; Kalman filters; hierarchical linear dynamical systems; hierarchically coupled state models; information extraction; music; representation space; signal processing algorithms; unsupervised time series clustering; Accuracy; Brain modeling; Convergence; Equations; Estimation; Mathematical model; Time series analysis; Kalman filters; Music information retrieval; clustering; cognitive models; dynamical systems; hierarchical systems; time series;
Conference_Titel :
Neural Networks (IJCNN), 2014 International Joint Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-6627-1
DOI :
10.1109/IJCNN.2014.6889858