Short-term feeding behaviour sound classification method for sheep using LSTM networks

Aim: Multiple sclerosis (MS) is a disease, which can affect the brain and/or spinal cord, leading to a wide range of potential symptoms. This method aims to propose a novel MS recognition method.Methods: First, the bior4.4 wavelet is used to extract multiscale coefficients. Second, three types of biorthogonal wavelet features are proposed and calculated. Third, fitness-scaled adaptive genetic algorithm (FAGA)—a combination of standard genetic algorithm, adaptive mechanism, and power-rank fitness scaling—is harnessed as the optimization algorithm. Fourth, multiple-way data augmentation is utilized on the training set under the setting of 10 runs of 10-fold cross-validation. Our method is abbreviated as BWF-FAGA.Results: Our method achieves a sensitivity of 98.00 ± 0.95%, a specificity of 97.78 ± 0.95%, and an accuracy of 97.89 ± 0.94%. The area under the curve of our method is 0.9876.Conclusion: The results show that the proposed BWF-FAGA method is better than 10 state-of-the-art MS recognition methods, including eight artificial intelligence-based methods, and two deep learning-based methods.

show abstract

Section: Methodsmentioning

confidence: 99%

“…F1 score considers both the precision and the sensitivity. It is the harmonic mean of the previous two measures: precision and sensitivity (van der Goot and van Noord, 2017;Duan et al, 2021). F1 score is defined as Two other measures: Matthews correlation coefficient (MCC) and Fowlkes-Mallows index (FMI) are defined as:…”

Section: Methodsmentioning

confidence: 99%

RETRACTED: Multiple Sclerosis Recognition by Biorthogonal Wavelet Features and Fitness-Scaled Adaptive Genetic Algorithm

2021

View full text Add to dashboard Cite

show abstract

“…The comprehensive performance of the audio classification model was indicated by the four commonly used evaluation metrics [24,48], i.e. precision, recall, F1 score and accuracy:Precision=true0TPTP+FP ×100%,Recall=true0TPTP+FN ×100%,F1 score=true02TP2TP+FP+FN ×100%normaland2emAccuracy=true0TP+TNTP+TN+FP+FN ×100%,where TP, FP, TN and FN were the number of true positives, false positives, true negatives and false negatives, respectively.…”

Section: Methodsmentioning

confidence: 99%

“…The comprehensive performance of the audio classification model was indicated by the four commonly used evaluation metrics [24,48], i.e. precision, recall, F1 score and accuracy:…”

Section: Evaluation Metricsmentioning

confidence: 99%

Automated identification of chicken distress vocalizations using deep learning models

Mao

Giraudet

Liu

et al. 2022

J. R. Soc. Interface.

View full text Add to dashboard Cite

The annual global production of chickens exceeds 25 billion birds, which are often housed in very large groups, numbering thousands. Distress calling triggered by various sources of stress has been suggested as an ‘iceberg indicator’ of chicken welfare. However, to date, the identification of distress calls largely relies on manual annotation, which is very labour-intensive and time-consuming. Thus, a novel convolutional neural network-based model, light-VGG11, was developed to automatically identify chicken distress calls using recordings (3363 distress calls and 1973 natural barn sounds) collected on an intensive farm. The light-VGG11 was modified from VGG11 with significantly fewer parameters (9.3 million versus 128 million) and 55.88% faster detection speed while displaying comparable performance, i.e. precision (94.58%), recall (94.89%), F1-score (94.73%) and accuracy (95.07%), therefore more useful for model deployment in practice. To additionally improve light-VGG11's performance, we investigated the impacts of different data augmentation techniques (i.e. time masking, frequency masking, mixed spectrograms of the same class and Gaussian noise) and found that they could improve distress calls detection by up to 1.52%. Our distress call detection demonstration on continuous audio recordings, shows the potential for developing technologies to monitor the output of this call type in large, commercial chicken flocks.

show abstract

“…The comprehensive performance of the audio classification model was indicated by the four commonly used evaluation metrics [24,47], i . e ., precision, recall, F1score, and accuracy: where TP, FP, TN , and FN were the number of true positives, false positives, true negatives, and false negatives, respectively.…”

Section: Methodsmentioning

confidence: 99%

Automated identification of chicken distress vocalisations using deep learning models

Mao

Giraudet

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

The annual global production of chickens exceeds 25 billion birds, and they are often housed in very large groups, numbering thousands. Distress calling triggered by various sources of stress has been suggested as an “iceberg indicator” of chicken welfare. However, to date, the identification of distress calls largely relies on manual annotations, which is very labour-intensive and time-consuming. Thus, a novel light-VGG11 was developed to automatically identify chicken distress calls using recordings (3,363 distress calls and 1,973 natural barn sounds) collected on intensive chicken farms. The light-VGG11 was modified from VGG11 with a significantly smaller size in parameters (9.3 million vs 128 million) and 55.88% faster detection speed while displaying comparable performance, i.e., precision (94.58%), recall (94.89%), F1-score (94.73%), and accuracy (95.07%), therefore more useful for model deployment in practice. To further improve the light-VGG11’s performance, we investigated the impacts of different data augmentation techniques (i.e., time masking, frequency masking, mixed spectrograms of the same class, and Gaussian noise) and found that they could improve distress calls detection by up to 1.52%. In terms of precision livestock farming, our research opens new opportunities for developing technologies used to monitor the output of distress calls in large, commercial chicken flocks.

show abstract

Short-term feeding behaviour sound classification method for sheep using LSTM networks

Cited by 14 publications

References 39 publications

RETRACTED: Multiple Sclerosis Recognition by Biorthogonal Wavelet Features and Fitness-Scaled Adaptive Genetic Algorithm

RETRACTED: Multiple Sclerosis Recognition by Biorthogonal Wavelet Features and Fitness-Scaled Adaptive Genetic Algorithm

Automated identification of chicken distress vocalizations using deep learning models

Automated identification of chicken distress vocalisations using deep learning models

Contact Info

Product

Resources

About