Decision templates for the classification of bioacoustic time series

C. Dietrich1, F. Schwenker1, G. Palm1
1Department of Neural Information Processing, University of Ulm (EBS), Ulm, Germany

Tóm tắt

The classification of time series is topic of this paper. In particular we discuss the combination of multiple classifier outputs with decision templates. The decision templates are calculated over a set of feature vectors which are extracted in local time windows. To learn characteristic classifier outputs of time series a set of decision templates is determined for the individual classes. We present algorithms to calculate multiple decision templates, and demonstrate the behaviour of this new approach on a real world data set from the field of bioacoustics.

Từ khóa

#Biomedical acoustics #Information processing #Data mining #Speech recognition #Signal processing #Speech processing #Recurrent neural networks #Hidden Markov models #Neural networks #Supervised learning

Tài liệu tham khảo

10.1016/S0031-3203(99)00223-X 10.1007/978-1-4615-3950-6 nischk, 1999, Die Grillengesellschaften zweier neotropischer Waldokosysteme in Ecuador 10.1109/MASSP.1986.1165342 10.1002/j.1538-7305.1975.tb02840.x rabiner, 1993, Fundamentals of speech recognition schwenker, 2002, Radial Basis Function Neural Networks and Temporal Fusion for the Classification of Btoacoustic Time Series, Neurocomput 10.1109/21.155943 10.1007/3-540-45014-9_20 dietrich, 2001, Classification of Bloacous-tic Time Series Utilizing Pulse Detection. Time and Frequency Features and Data Fusion, Ulmer Informatik-Berichte 2001–04 University of Ulm kadous, 2002, Temporal Classification Extending the Classification Paradigm to Multivariate Time Series ingrisch, 1997, Taxonomy. stridulation and development of Podoscirtinae from Thailand, Senckenbergiana Biology, 77, 47 kuncheva, 2000, Fuzzy Classifier Design Heidelberg New York Physica Verlag, 10.1007/978-3-7908-1850-5 10.1109/34.667881 10.1007/3-540-48219-9_38 bishop, 1995, Neural Networks for Pattern Recognition 10.1016/S0165-0114(99)00161-X