Araştırma Makalesi
BibTex RIS Kaynak Göster

Automatic Classification of Environmental Sounds with the MFCC Method and the Proposed Deep Model

Yıl 2022, Cilt: 34 Sayı: 1, 449 - 457, 20.03.2022
https://doi.org/10.35234/fumbd.1056326

Öz

With the developing technology, the Internet of Things (IoT) is at the forefront of bringing different technologies together. The Internet of Things is also frequently used, especially in smart city applications. Smart city applications are becoming more common day by day. In this study, an application that will be used frequently in smart city applications has been realized. In this study, the UrbanSound8K dataset, which consists of environmental sounds and is one of the largest datasets in the literature, was used. A new deep one-dimensional (1D-CNN) model is proposed to classify environmental sounds to contribute to smart city applications. In the developed model, firstly, the feature maps of the environmental sounds in the data set were obtained by using the MFCC method. A high accuracy value was obtained when the feature maps obtained later were classified in the developed 1D-CNN network. This accuracy value obtained shows that the proposed model can be used in the classification process of audio data.

Kaynakça

  • Ghazal, T.M., et al., IoT for smart cities: Machine learning approaches in smart healthcare—A review. Future Internet, 2021. 13(8): p. 218.
  • Teng, H., et al., A low-cost physical location discovery scheme for large-scale Internet of things in smart city through joint use of vehicles and UAVs. Future Generation Computer Systems, 2021. 118: p. 310-326.
  • Sarkar, N.I. and S. Gul, Green computing and internet of things for smart cities: technologies, challenges, and implementation, in Green Computing in Smart Cities: Simulation and Techniques. 2021, Springer. p. 35-50.
  • Mandalapu, H., et al., Audio-visual biometric recognition and presentation attack detection: A comprehensive survey. IEEE Access, 2021. 9: p. 37431-37455.
  • Luz, J.S., et al., Ensemble of handcrafted and deep features for urban sound classification. Applied Acoustics, 2021. 175: p. 107819.
  • Eroglu, Y., et al., Diagnosis and grading of vesicoureteral reflux on voiding cystourethrography images in children using a deep hybrid model. Computer Methods and Programs in Biomedicine, 2021. 210: p. 106369.
  • Cengil, E., A. Çinar, and M. Yildirim. A Case Study: Cat-Dog Face Detector Based on YOLOv5. in 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT). 2021. IEEE.
  • BİNGOL, H. and B. ALATAS, Classification of Brain Tumor Images using Deep Learning Methods. Turkish Journal of Science and Technology, 2021. 16(1): p. 137-143.
  • Karmakar, G., et al., Assessing Trust Level of a Driverless Car Using Deep Learning. IEEE Transactions on Intelligent Transportation Systems, 2021.
  • Ullah, I. and Q.H. Mahmoud, Design and development of a deep learning-based model for anomaly detection in IoT networks. IEEE Access, 2021. 9: p. 103906-103926.
  • Sarma, M.S., et al., Traditional Bangladeshi Sports Video Classification Using Deep Learning Method. Applied Sciences, 2021. 11(5): p. 2149.
  • Sang, J., S. Park, and J. Lee. Convolutional recurrent neural networks for urban sound classification using raw waveforms. in 2018 26th European Signal Processing Conference (EUSIPCO). 2018. IEEE.
  • Chen, Y., et al., Environmental sound classification with dilated convolutions. Applied Acoustics, 2019. 148: p. 123-132.
  • Demir, F., et al., A new pyramidal concatenated CNN approach for environmental sound classification. Applied Acoustics, 2020. 170: p. 107520.
  • Davis, N. and K. Suresh. Environmental sound classification using deep convolutional neural networks and data augmentation. in 2018 IEEE Recent Advances in Intelligent Computational Systems (RAICS). 2018. IEEE.
  • Piczak, K.J. Environmental sound classification with convolutional neural networks. in 2015 IEEE 25th international workshop on machine learning for signal processing (MLSP). 2015. IEEE.
  • Salamon, J. and J.P. Bello, Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal processing letters, 2017. 24(3): p. 279-283.
  • Salamon, J., C. Jacoby, and J.P. Bello. A dataset and taxonomy for urban sound research. in Proceedings of the 22nd ACM international conference on Multimedia. 2014.
  • Davis, S. and P. Mermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE transactions on acoustics, speech, and signal processing, 1980. 28(4): p. 357-366.
  • Eser, S., A deep learning based approach for the detection of diseases in pepper and potato leaves. Anadolu Tarım Bilimleri Dergisi, 2021. 36(2): p. 167-178.
  • Chang, V., An ethical framework for big data and smart cities. Technological Forecasting and Social Change, 2021. 165: p. 120559.
  • Chen, D., P. Wawrzynski, and Z. Lv, Cyber security in smart cities: a review of deep learning-based applications and case studies. Sustainable Cities and Society, 2021. 66: p. 102655.

MFCC Yöntemi ve Önerilen Derin Model ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması

Yıl 2022, Cilt: 34 Sayı: 1, 449 - 457, 20.03.2022
https://doi.org/10.35234/fumbd.1056326

Öz

Gelişen teknoloji ile birlikte Nesnelerin İnterneti (IoT), farklı teknolojileri bir araya getirmenin ön saflarında yer almaktadır. Nesnelerin interneti özellikle akıllı şehir uygulamalarında da sıklıkla kullanılmaktadır. Akıllı şehir uygulamaları her geçen gün daha da yaygın bir hale gelmektedir. Yapılan bu çalışmada da akıllı şehir uygulamalarında sıklıkla kullanılacak bir uygulama gerçekleştirilmiştir. Bu çalışmada çevre seslerinden oluşan ve bu konuda literatürdeki en büyük veri setlerinden biri olan UrbanSound8K veri seti kullanılmıştır. Akıllı şehir uygulamalarına katkıda bulunmak amacıyla çevresel sesleri sınıflandırmak için yeni bir derin tek boyutlu (1D-CNN) model önerilmiştir. Geliştirilen modelde ilk olarak MFCC yöntemi kullanılarak veri setindeki çevresel seslerin öznitelik haritaları elde edilmiştir. Daha sonra elde edilen öznitelik haritaları geliştirilen 1D-CNN ağında sınıflandırıldığında yüksek bir doğruluk değeri elde edilmiştir. Elde edilen bu doğruluk değeri önerilen modelin ses verilerini sınıflandırma işleminde kullanılabileceğini göstermektedir.

Kaynakça

  • Ghazal, T.M., et al., IoT for smart cities: Machine learning approaches in smart healthcare—A review. Future Internet, 2021. 13(8): p. 218.
  • Teng, H., et al., A low-cost physical location discovery scheme for large-scale Internet of things in smart city through joint use of vehicles and UAVs. Future Generation Computer Systems, 2021. 118: p. 310-326.
  • Sarkar, N.I. and S. Gul, Green computing and internet of things for smart cities: technologies, challenges, and implementation, in Green Computing in Smart Cities: Simulation and Techniques. 2021, Springer. p. 35-50.
  • Mandalapu, H., et al., Audio-visual biometric recognition and presentation attack detection: A comprehensive survey. IEEE Access, 2021. 9: p. 37431-37455.
  • Luz, J.S., et al., Ensemble of handcrafted and deep features for urban sound classification. Applied Acoustics, 2021. 175: p. 107819.
  • Eroglu, Y., et al., Diagnosis and grading of vesicoureteral reflux on voiding cystourethrography images in children using a deep hybrid model. Computer Methods and Programs in Biomedicine, 2021. 210: p. 106369.
  • Cengil, E., A. Çinar, and M. Yildirim. A Case Study: Cat-Dog Face Detector Based on YOLOv5. in 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT). 2021. IEEE.
  • BİNGOL, H. and B. ALATAS, Classification of Brain Tumor Images using Deep Learning Methods. Turkish Journal of Science and Technology, 2021. 16(1): p. 137-143.
  • Karmakar, G., et al., Assessing Trust Level of a Driverless Car Using Deep Learning. IEEE Transactions on Intelligent Transportation Systems, 2021.
  • Ullah, I. and Q.H. Mahmoud, Design and development of a deep learning-based model for anomaly detection in IoT networks. IEEE Access, 2021. 9: p. 103906-103926.
  • Sarma, M.S., et al., Traditional Bangladeshi Sports Video Classification Using Deep Learning Method. Applied Sciences, 2021. 11(5): p. 2149.
  • Sang, J., S. Park, and J. Lee. Convolutional recurrent neural networks for urban sound classification using raw waveforms. in 2018 26th European Signal Processing Conference (EUSIPCO). 2018. IEEE.
  • Chen, Y., et al., Environmental sound classification with dilated convolutions. Applied Acoustics, 2019. 148: p. 123-132.
  • Demir, F., et al., A new pyramidal concatenated CNN approach for environmental sound classification. Applied Acoustics, 2020. 170: p. 107520.
  • Davis, N. and K. Suresh. Environmental sound classification using deep convolutional neural networks and data augmentation. in 2018 IEEE Recent Advances in Intelligent Computational Systems (RAICS). 2018. IEEE.
  • Piczak, K.J. Environmental sound classification with convolutional neural networks. in 2015 IEEE 25th international workshop on machine learning for signal processing (MLSP). 2015. IEEE.
  • Salamon, J. and J.P. Bello, Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal processing letters, 2017. 24(3): p. 279-283.
  • Salamon, J., C. Jacoby, and J.P. Bello. A dataset and taxonomy for urban sound research. in Proceedings of the 22nd ACM international conference on Multimedia. 2014.
  • Davis, S. and P. Mermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE transactions on acoustics, speech, and signal processing, 1980. 28(4): p. 357-366.
  • Eser, S., A deep learning based approach for the detection of diseases in pepper and potato leaves. Anadolu Tarım Bilimleri Dergisi, 2021. 36(2): p. 167-178.
  • Chang, V., An ethical framework for big data and smart cities. Technological Forecasting and Social Change, 2021. 165: p. 120559.
  • Chen, D., P. Wawrzynski, and Z. Lv, Cyber security in smart cities: a review of deep learning-based applications and case studies. Sustainable Cities and Society, 2021. 66: p. 102655.
Toplam 22 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Bölüm MBD
Yazarlar

Muhammed Yıldırım 0000-0003-1866-4721

Yayımlanma Tarihi 20 Mart 2022
Gönderilme Tarihi 11 Ocak 2022
Yayımlandığı Sayı Yıl 2022 Cilt: 34 Sayı: 1

Kaynak Göster

APA Yıldırım, M. (2022). MFCC Yöntemi ve Önerilen Derin Model ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 34(1), 449-457. https://doi.org/10.35234/fumbd.1056326
AMA Yıldırım M. MFCC Yöntemi ve Önerilen Derin Model ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi. Mart 2022;34(1):449-457. doi:10.35234/fumbd.1056326
Chicago Yıldırım, Muhammed. “MFCC Yöntemi Ve Önerilen Derin Model Ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması”. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 34, sy. 1 (Mart 2022): 449-57. https://doi.org/10.35234/fumbd.1056326.
EndNote Yıldırım M (01 Mart 2022) MFCC Yöntemi ve Önerilen Derin Model ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 34 1 449–457.
IEEE M. Yıldırım, “MFCC Yöntemi ve Önerilen Derin Model ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması”, Fırat Üniversitesi Mühendislik Bilimleri Dergisi, c. 34, sy. 1, ss. 449–457, 2022, doi: 10.35234/fumbd.1056326.
ISNAD Yıldırım, Muhammed. “MFCC Yöntemi Ve Önerilen Derin Model Ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması”. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 34/1 (Mart 2022), 449-457. https://doi.org/10.35234/fumbd.1056326.
JAMA Yıldırım M. MFCC Yöntemi ve Önerilen Derin Model ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi. 2022;34:449–457.
MLA Yıldırım, Muhammed. “MFCC Yöntemi Ve Önerilen Derin Model Ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması”. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, c. 34, sy. 1, 2022, ss. 449-57, doi:10.35234/fumbd.1056326.
Vancouver Yıldırım M. MFCC Yöntemi ve Önerilen Derin Model ile Çevresel Seslerin Otomatik Olarak Sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi. 2022;34(1):449-57.