Classification of Environmental Sounds With Deep Learning

Öz

Today, with the development of technology, environmental destruction is increasing day by day. For this reason, it is inevitable to take different measures to prevent the damage caused by environmental destruction. It is possible to prevent environmental damage by identifying the sounds that harm the environment and transferring them to the relevant units. In the study carried out, a data set of saw, rain, lightning, bark and broom sound data obtained from open access websites was created. Rain, barking and broom sounds in the data set were determined as the sounds that do not harm the environment, while saw and lightning were determined as the data set that harms the environment. The dataset was classified using VGG-13BN, ResNet-50 and DenseNet-121 deep learning architectures. When used, all three deep learning accuracy are due to over 95% study. Among these models, the VGG-13 BN model emerged as the most successful model with an accuracy rate of 99.72%.

Anahtar Kelimeler

• Deep Learning
• Transfer Learning
• Spectrogram
• Environmental Sound Detection

Kaynakça

1. Önder S, Gülgün B. “Gürültü Kirliliği Ve Alınması Gereken Önlemler: Bitkisel Gürültü Perdeleri”. Ziraat Mühendisliği, 35, 54-64, 2010.
2. Felipe G Z, Maldonado Y, da Costa G, Helal L G. “Acoustic scene classification using spectrograms”. In 2017 36th International Conference of the Chilean Computer Science Society (SCCC), 1-7, 2017.
3. Olah C. (2020). Understanding lstm networks, August 2015. URL https://colah. github. io/posts/2015-08-Understanding-LSTMs. Accessed on, 10.
4. Nwe T L, Dat T H, Ma B. “Convolutional neural network with multi-task learning scheme for acoustic scene classification”. In 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 1347-1350, 2017.
5. Kodaloğlu G. Segmentation of snore sounds and detection of sleep apnea with statistical change detection algorithms. MSc Thesis, Ankara University, Ankara, Turkey, 2019.
6. Başbuğ A M. Sound event recognition and acoustic scenes retrieval. MSc Thesis, Başkent University, Ankara, Turkey, 2019.
7. Toraman S, Arslan Tuncer S, Balgetir F. “Is it possible to detect cerebral dominance via EEG signals by using deep learning?” Medical Hypotheses, Elazığ: Fırat University, 131, 2019.
8. Talo M. “Meme Kanseri Histopatolojik Görüntülerinin Konvolüsyonal Sinir Ağları ile Sınıflandırılması”. Fırat University Journal of Engineering Science, 31(2), 391-398, 2019.

9. Adapa S. “Urban sound tagging using convolutional neural networks”. arXiv preprint arXiv:1909.12699v1, 2019.
10. Huzaifah M. “Comparison of time-frequency representations for environmental sound classification using convolutional neural networks”. arXiv preprint arXiv:1706.07156, 2017.
11. Zhang Z, Xu S, Cao S, Zhang S. “Deep convolutional neural network with mixup for environmental sound classification”. In Chinese conference on pattern recognition and computer vision (prcv), 356-367, 2018.
12. Salamon J, Bello J P. “Deep convolutional neural networks and data augmentation for environmental sound classification”. IEEE Signal processing letters, 24(3), 279-283, 2017.
13. Li J, Dai W, Metze F, Qu S, Das S. “A comparison of deep learning methods for environmental sound detection”. In 2017 IEEE International conference on acoustics, speech and signal processing (ICASSP), 126-130, 2017.
14. Özkaya U, Seyfi L. “Yere Nüfuz Eden Radar B Tarama Görüntülerinin Az Parametreye Sahip Konvolüsyonel Sinir Ağı İle Değerlendirilmesi”. Geomatik, 6(2), 84-92, 2021.
15. Bozkurt F, Yağanoğlu M. “Derin Evrişimli Sinir Ağları Kullanarak Akciğer X-Ray Görüntülerinden COVID-19 Tespiti”. Veri Bilimi, 4(2), 1-8, 2021.
16. Turhan C G, Bilge H Ş. “Çekişmeli üretici ağ ile ölçeklenebilir görüntü oluşturma ve süper çözünürlük”. Journal of the Faculty of Engineering and Architecture of Gazi University, 35(2), 953-966, 2020.
17. Akılotu B N, Kadiroğlu Z, Şengür A, Kayaoğlu M. “Evrişimsel Sinir Ağları ve Transfer Öğrenme Yöntemi Kullanılarak Sıtma Tespiti”. International Engineering and Science Symposium, Siirt, 2019.
18. Bozkurt F. “Derin Öğrenme Tekniklerini Kullanarak Akciğer X-Ray Görüntülerinden COVID-19 Tespiti”. Avrupa Bilim ve Teknoloji Dergisi, 24, 149-156, 2021.
19. Kumar R. “Adding binary search connections to improve densenet performance”. In 5th International Conference on Next Generation Computing Technologies (NGCT-2019), 2020.
20. Korfiatis P, Kline T L, Lachance D H, Parney I F, Buckner J C, Erickson B J. “Residual deep convolutional neural network predicts MGMT methylation status”. Journal of digital imaging, 30(5), 622-628, 2017.
21. Fu Y, Aldrich C. “Flotation froth image recognition with convolutional neural networks’’. Minerals Engineering, 132, 183-190, 2019.
22. Huang G, Liu Z, van der Maaten L, Weinberger K Q. “Densely connected convolutional networks”. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4700-4708, 2017.
23. Li X, Shen X, Zhou Y, Wang X, Li T Q. “Classification of breast cancer histopathological images using interleaved DenseNet with SENet (IDSNet)’’, PloS one, Hangzhou: China Jiliang University, 15(5), e0232127, 2020.
24. Duman E, Akın F. “Yüz Tanima Sürecinde Farkli Cnn Modellerinin Performans Karşilaştirmasi’’. Uluslararası Mardin Artuklu Multidisipliner Çalışmalar Kongresi, 35-42, 2019.
25. Narin A. “Meme Kanserinin Evrişimsel Sinir Ağı Modelleriyle Tespitinde Farklı Görüntü Büyütme Oranlarının Etkisi’’. Karaelmas Fen ve Mühendislik Dergisi, 10(2), 186-194, 2020.
26. Tan Z. Vehicle classification with deep learning. MSc Thesis, Fırat University, Elazığ, Turkey, 2019.
27. Deng X, Liu Q, Deng Y, Mahadevan S. “An improved method to construct basic probability assignment based on the confusion matrix for classification problem”. Information Sciences, 340, 250-261, 2016.
28. Orman A, Köse U, Yiğit T. “Açıklanabilir Evrişimsel Sinir Ağları ile Beyin Tümörü Tespiti”. El-Cezeri, 8(3), 1323-1337, 2021.
29. Sokolova M, Lapalme G. “A systematic analysis of performance measures for classification tasks”. Information processing & management, 45(4), 427-437, 2009.
30. Ballabio D, Grisoni F, Todeschini R. “Multivariate comparison of classification performance measures”. Chemometrics and Intelligent Laboratory Systems, 174, 33-44, 2018.