Limits...
Discerning pig screams in production environments.

Vandermeulen J, Bahr C, Tullo E, Fontana I, Ott S, Kashiha M, Guarino M, Moons CP, Tuyttens FA, Niewold TA, Berckmans D - PLoS ONE (2015)

Bottom Line: To achieve this, 7 hours of labelled data from 24 pigs was used.The developed detection method attained 72% sensitivity, 91% specificity and 83% precision.As a result, the detection method showed that screams contain the following features discerning them from other sounds: a formant structure, adequate power, high frequency content, sufficient variability and duration.

View Article: PubMed Central - PubMed

Affiliation: M3-BIORES-Measure, Model & Manage Bioresponses, KU Leuven, Leuven, Belgium.

ABSTRACT
Pig vocalisations convey information about their current state of health and welfare. Continuously monitoring these vocalisations can provide useful information for the farmer. For instance, pig screams can indicate stressful situations. When monitoring screams, other sounds can interfere with scream detection. Therefore, identifying screams from other sounds is essential. The objective of this study was to understand which sound features define a scream. Therefore, a method to detect screams based on sound features with physical meaning and explicit rules was developed. To achieve this, 7 hours of labelled data from 24 pigs was used. The developed detection method attained 72% sensitivity, 91% specificity and 83% precision. As a result, the detection method showed that screams contain the following features discerning them from other sounds: a formant structure, adequate power, high frequency content, sufficient variability and duration.

No MeSH data available.


The two ROC curves.They showing the True and False positive Rates (TPR and FPR). The numbers on the plots give the minimal required votes for the training and validation set.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4414550&req=5

pone.0123111.g006: The two ROC curves.They showing the True and False positive Rates (TPR and FPR). The numbers on the plots give the minimal required votes for the training and validation set.

Mentions: Fig 6 depicts the ROC-curve for the various numbers of votes required for classification as a scream. According to ROC the training set had consistently higher sensitivity (or TPR) values than the validation set. On average it was 0.07 (or 7%) higher. Furthermore, the desired sensitivity and specificity could be chosen based on this curve. The remainder of the results were calculated with six as the minimal number of votes required. The reason for choosing six is explained in the discussion.


Discerning pig screams in production environments.

Vandermeulen J, Bahr C, Tullo E, Fontana I, Ott S, Kashiha M, Guarino M, Moons CP, Tuyttens FA, Niewold TA, Berckmans D - PLoS ONE (2015)

The two ROC curves.They showing the True and False positive Rates (TPR and FPR). The numbers on the plots give the minimal required votes for the training and validation set.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4414550&req=5

pone.0123111.g006: The two ROC curves.They showing the True and False positive Rates (TPR and FPR). The numbers on the plots give the minimal required votes for the training and validation set.
Mentions: Fig 6 depicts the ROC-curve for the various numbers of votes required for classification as a scream. According to ROC the training set had consistently higher sensitivity (or TPR) values than the validation set. On average it was 0.07 (or 7%) higher. Furthermore, the desired sensitivity and specificity could be chosen based on this curve. The remainder of the results were calculated with six as the minimal number of votes required. The reason for choosing six is explained in the discussion.

Bottom Line: To achieve this, 7 hours of labelled data from 24 pigs was used.The developed detection method attained 72% sensitivity, 91% specificity and 83% precision.As a result, the detection method showed that screams contain the following features discerning them from other sounds: a formant structure, adequate power, high frequency content, sufficient variability and duration.

View Article: PubMed Central - PubMed

Affiliation: M3-BIORES-Measure, Model & Manage Bioresponses, KU Leuven, Leuven, Belgium.

ABSTRACT
Pig vocalisations convey information about their current state of health and welfare. Continuously monitoring these vocalisations can provide useful information for the farmer. For instance, pig screams can indicate stressful situations. When monitoring screams, other sounds can interfere with scream detection. Therefore, identifying screams from other sounds is essential. The objective of this study was to understand which sound features define a scream. Therefore, a method to detect screams based on sound features with physical meaning and explicit rules was developed. To achieve this, 7 hours of labelled data from 24 pigs was used. The developed detection method attained 72% sensitivity, 91% specificity and 83% precision. As a result, the detection method showed that screams contain the following features discerning them from other sounds: a formant structure, adequate power, high frequency content, sufficient variability and duration.

No MeSH data available.