Classification of Time Series Utilizing Temporal and Decision Fusion

Dietrich, Christian; Schwenker, Friedhelm; Palm, Günther

doi:10.1007/3-540-48219-9_38

Cited by 26 publications

(12 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in a series of papers, Dietrich et al introduce several classification methods for insect sounds, some of which require up to eighteen parameters, and which are trained on a dataset containing just 108 exemplars (Dietrich et al 2001).…”

Section: General Animal Sound Classificationmentioning

confidence: 99%

“…However, we argue that most current tools are severely limited. They often require the careful tuning of many parameters (as many as eighteen (Dietrich et al 2001)) and thus huge amounts of training data, are too computationally expensive for deployment with resource-limited sensors that will be deployed in the field (Dang et al 2010), are specialized for a notably small group of species, or are simply not accurate enough to be useful.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Monitoring and Mining Animal Sounds in Visual Space

2012

View full text Add to dashboard Cite

Monitoring animals by the sounds they produce is an important and challenging task, whether the application is outdoors in a natural habitat, or in the controlled environment of a laboratory setting.In the former case, the density and diversity of animal sounds can act as a measure of biodiversity. In the latter case, researchers often create control and treatment groups of animals, expose them to different interventions, and test for different outcomes. One possible manifestation of different outcomes may be changes in the bioacoustics of the animals.With such a plethora of important applications, there have been significant efforts to build bioacoustic classification tools. However, we argue that most current tools are severely limited. They often require the careful tuning of many parameters (and thus huge amounts of training data), are either too computationally expensive for deployment in resource-limited sensors, specialized for a very small group of species, or are simply not accurate enough to be useful.In this work we introduce a novel bioacoustic recognition/classification framework that mitigates or solves all of the above problems. We propose to classify animal sounds in the visual space, by treating the texture of their sonograms as an acoustic fingerprint using a recently introduced parameter-free texture measure as a distance measure. We further show that by searching for the most representative acoustic fingerprint, we can significantly outperform other techniques in terms of speed and accuracy.

show abstract

Section: General Animal Sound Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Monitoring and Mining Animal Sounds in Visual Space

2012

View full text Add to dashboard Cite

show abstract

“…Many other approaches have been attempted in the last decade. For example, in a series of papers, Dietrich et al introduce several classification methods for insect sounds, some of which require up to eighteen parameters, and which were trained on a dataset containing just 108 exemplars [8].…”

Section: General Animal Sound Classificationmentioning

confidence: 99%

“…However, we argue that current tools are severely limited. They often require the careful tuning of many parameters (as many as eighteen [8]) and thus huge amounts of training data, they are too computationally expensive for use with resourcelimited sensors that will be deployed in the field [7], they are specialized for a very small group of species, or they are simply not accurate enough to be useful. In this work we introduce a novel bioacoustic recognition/classification framework that mitigates or solves all of the above problems.…”

Section: Introductionmentioning

confidence: 99%

Monitoring and Mining Insect Sounds in Visual Space

Hao

Campana

Keogh

2012

Proceedings of the 2012 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Monitoring animals by the sounds they produce is an important and challenging task, whether the application is outdoors in a natural habitat, or in the controlled environment of a laboratory setting. In the former case the density and diversity of animal sounds can act as a measure of biodiversity. In the latter case, researchers often create control and treatment groups of animals, expose them to different interventions, and test for different outcomes. One possible manifestation of different outcomes may be changes in the bioacoustics of the animals. With such a plethora of important applications, there have been significant efforts to build bioacoustic classification tools. However, we argue that most current tools are severely limited. They often require the careful tuning of many parameters (and thus huge amounts of training data), they are too computationally expensive for deployment in resource-limited sensors, they are specialized for a very small group of species, or they are simply not accurate enough to be useful. In this work we introduce a novel bioacoustic recognition/classification framework that mitigates or solves all of the above problems. We propose to classify animal sounds in the visual space, by treating the texture of their spectrograms as an acoustic fingerprint using a recently introduced parameter-free texture measure as a distance measure. We further show that by searching for the most representative acoustic fingerprint we can significantly outperform other techniques in terms of speed and accuracy.

show abstract

“…Dietrich et al [19,21] There are weaknesses to this approach. First, the determination of the parameters such as the size of the sliding window is data-dependent.…”

Section: Dynamic Time Warping (Dtw)mentioning

confidence: 99%