Classification for Big Dataset of Bioacoustic Signals Based on Human Scoring System and Artificial Neural Network

Mohammad Pourhomayoun; Peter J. Dugan; Marian Popescu; Denise Risch; Hal Lewis; Christopher W. Clark

Classification for Big Dataset of Bioacoustic Signals Based on Human Scoring System and Artificial Neural Network

Mohammad Pourhomayoun
, Peter J. Dugan
, Marian Popescu
, Denise Risch
, Hal Lewis
, Christopher W. Clark

Producción científica: Conference contribution

Resumen

In this paper, we propose a method to improve sound classification performance by combining signal features, derived from the time-frequency spectrogram, with human perception. The method presented herein exploits an artificial neural network (ANN) and learns the signal features based on the human perception knowledge. The proposed method is applied to a large acoustic dataset containing 24 months of nearly continuous recordings. The results show a significant improvement in performance of the detection-classification system; yielding as much as 20% improvement in true positive rate for a given false positive rate.

Idioma original	Undefined/Unknown
Título de la publicación alojada	ICML 2013 Workshop on Machine Learning for Bioacoustics
Estado	Published - 15 may 2013

Citar esto

@inproceedings{c2515d0c5df14b1aa55926b7c96d1215,

title = "Classification for Big Dataset of Bioacoustic Signals Based on Human Scoring System and Artificial Neural Network",

abstract = "In this paper, we propose a method to improve sound classification performance by combining signal features, derived from the time-frequency spectrogram, with human perception. The method presented herein exploits an artificial neural network (ANN) and learns the signal features based on the human perception knowledge. The proposed method is applied to a large acoustic dataset containing 24 months of nearly continuous recordings. The results show a significant improvement in performance of the detection-classification system; yielding as much as 20\% improvement in true positive rate for a given false positive rate.",

author = "Mohammad Pourhomayoun and Dugan, \{Peter J.\} and Marian Popescu and Denise Risch and Hal Lewis and Clark, \{Christopher W.\}",

year = "2013",

month = may,

day = "15",

language = "Undefined/Unknown",

booktitle = "ICML 2013 Workshop on Machine Learning for Bioacoustics",

}

TY - GEN

T1 - Classification for Big Dataset of Bioacoustic Signals Based on Human Scoring System and Artificial Neural Network

AU - Pourhomayoun, Mohammad

AU - Dugan, Peter J.

AU - Popescu, Marian

AU - Risch, Denise

AU - Lewis, Hal

AU - Clark, Christopher W.

PY - 2013/5/15

Y1 - 2013/5/15

N2 - In this paper, we propose a method to improve sound classification performance by combining signal features, derived from the time-frequency spectrogram, with human perception. The method presented herein exploits an artificial neural network (ANN) and learns the signal features based on the human perception knowledge. The proposed method is applied to a large acoustic dataset containing 24 months of nearly continuous recordings. The results show a significant improvement in performance of the detection-classification system; yielding as much as 20% improvement in true positive rate for a given false positive rate.

AB - In this paper, we propose a method to improve sound classification performance by combining signal features, derived from the time-frequency spectrogram, with human perception. The method presented herein exploits an artificial neural network (ANN) and learns the signal features based on the human perception knowledge. The proposed method is applied to a large acoustic dataset containing 24 months of nearly continuous recordings. The results show a significant improvement in performance of the detection-classification system; yielding as much as 20% improvement in true positive rate for a given false positive rate.

M3 - Conference contribution

BT - ICML 2013 Workshop on Machine Learning for Bioacoustics

ER -