An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound Classification
With the growth of deep learning in various classification problems, many researchers have used deep learning methods in environmental sound classification tasks. This paper introduces an end-to-end method for environmental sound classification based on a one-dimensional convolution neural network w...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/10/4660 |
| _version_ | 1827692041787670528 |
|---|---|
| author | Mohammed Gamal Ragab Said Jadid Abdulkadir Norshakirah Aziz Hitham Alhussian Abubakar Bala Alawi Alqushaibi |
| author_facet | Mohammed Gamal Ragab Said Jadid Abdulkadir Norshakirah Aziz Hitham Alhussian Abubakar Bala Alawi Alqushaibi |
| author_sort | Mohammed Gamal Ragab |
| collection | DOAJ |
| description | With the growth of deep learning in various classification problems, many researchers have used deep learning methods in environmental sound classification tasks. This paper introduces an end-to-end method for environmental sound classification based on a one-dimensional convolution neural network with Bayesian optimization and ensemble learning, which directly learns features representation from the audio signal. Several convolutional layers were used to capture the signal and learn various filters relevant to the classification problem. Our proposed method can deal with any audio signal length, as a sliding window divides the signal into overlapped frames. Bayesian optimization accomplished hyperparameter selection and model evaluation with cross-validation. Multiple models with different settings have been developed based on Bayesian optimization to ensure network convergence in both convex and non-convex optimization. An UrbanSound8K dataset was evaluated for the performance of the proposed end-to-end model. The experimental results achieved a classification accuracy of 94.46%, which is 5% higher than existing end-to-end approaches with fewer trainable parameters. Four measurement indices, namely: sensitivity, specificity, accuracy, precision, recall, F-measure, area under ROC curve, and the area under the precision-recall curve were used to measure the model performance. The proposed approach outperformed state-of-the-art end-to-end approaches that use hand-crafted features as input in selected measurement indices and time complexity. |
| first_indexed | 2024-03-10T11:14:53Z |
| format | Article |
| id | doaj.art-1e68335d60a34bfc857c6691d936ce61 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T11:14:53Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1e68335d60a34bfc857c6691d936ce612023-11-21T20:27:16ZengMDPI AGApplied Sciences2076-34172021-05-011110466010.3390/app11104660An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound ClassificationMohammed Gamal Ragab0Said Jadid Abdulkadir1Norshakirah Aziz2Hitham Alhussian3Abubakar Bala4Alawi Alqushaibi5Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32610, MalaysiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32610, MalaysiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32610, MalaysiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32610, MalaysiaElectrical and Electronics Engineering Department, Universiti Teknologi PETRONAS, Seri Iskandar 32610, MalaysiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32610, MalaysiaWith the growth of deep learning in various classification problems, many researchers have used deep learning methods in environmental sound classification tasks. This paper introduces an end-to-end method for environmental sound classification based on a one-dimensional convolution neural network with Bayesian optimization and ensemble learning, which directly learns features representation from the audio signal. Several convolutional layers were used to capture the signal and learn various filters relevant to the classification problem. Our proposed method can deal with any audio signal length, as a sliding window divides the signal into overlapped frames. Bayesian optimization accomplished hyperparameter selection and model evaluation with cross-validation. Multiple models with different settings have been developed based on Bayesian optimization to ensure network convergence in both convex and non-convex optimization. An UrbanSound8K dataset was evaluated for the performance of the proposed end-to-end model. The experimental results achieved a classification accuracy of 94.46%, which is 5% higher than existing end-to-end approaches with fewer trainable parameters. Four measurement indices, namely: sensitivity, specificity, accuracy, precision, recall, F-measure, area under ROC curve, and the area under the precision-recall curve were used to measure the model performance. The proposed approach outperformed state-of-the-art end-to-end approaches that use hand-crafted features as input in selected measurement indices and time complexity.https://www.mdpi.com/2076-3417/11/10/4660Bayesian optimizationconvolutional neural networksdeep learningensemble learningenvironmental sound classificationoptimization |
| spellingShingle | Mohammed Gamal Ragab Said Jadid Abdulkadir Norshakirah Aziz Hitham Alhussian Abubakar Bala Alawi Alqushaibi An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound Classification Applied Sciences Bayesian optimization convolutional neural networks deep learning ensemble learning environmental sound classification optimization |
| title | An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound Classification |
| title_full | An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound Classification |
| title_fullStr | An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound Classification |
| title_full_unstemmed | An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound Classification |
| title_short | An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound Classification |
| title_sort | ensemble one dimensional convolutional neural network with bayesian optimization for environmental sound classification |
| topic | Bayesian optimization convolutional neural networks deep learning ensemble learning environmental sound classification optimization |
| url | https://www.mdpi.com/2076-3417/11/10/4660 |
| work_keys_str_mv | AT mohammedgamalragab anensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT saidjadidabdulkadir anensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT norshakirahaziz anensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT hithamalhussian anensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT abubakarbala anensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT alawialqushaibi anensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT mohammedgamalragab ensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT saidjadidabdulkadir ensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT norshakirahaziz ensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT hithamalhussian ensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT abubakarbala ensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification AT alawialqushaibi ensembleonedimensionalconvolutionalneuralnetworkwithbayesianoptimizationforenvironmentalsoundclassification |