SKLBP14: Kare çekirdekli yerel ikili modele dayalı yeni bir dokusal çevresel ses sınıflandırma modeli

Öz

Günümüzde ileri-ileri (FF) algoritması, makine öğrenimi toplumunda çok popülerdir ve kare tabanlı bir aktivasyon işlevi kullanır. Bu araştırmada, FF algoritmasından ilham aldık ve yerel ikili örüntü için yeni bir çekirdek sunduk ve bu, kare çekirdekli yerel ikili örüntü (SKLBP) olarak adlandırıldı. Önerilen tek boyutlu SKLBP'yi konuşlandırarak, yeni bir özellik mühendisliği modeli sunulmuştur. Önerilen SKLBP tabanlı modelin sınıflandırma yeteneğini ölçmek için, yeni bir dokusal çevresel ses sınıflandırması (ESC) veri seti topladık. Toplanan veri seti dengeli bir veri seti olup 15 sınıf içermektedir. Her sınıfta 100 ses vardır. Önerdiğimiz model derin öğrenme yapısını taklit etmiştir. Bu nedenle, ayrık dalgacık dönüşümü kullanarak çok düzeyli öznitelik çıkarma metodolojisini kullanır. Oluşturulan özellikler, yinelemeli özellik seçicinin girdisi olarak kabul edilmiştir. Seçilen öznitelik vektörü k en yakın komşu sınıflandırıcının girdisi olarak kullanılmıştır. Önerilen SKLBP tabanlı sinyal sınıflandırma modeli, %90'ın üzerinde doğruluğa ulaştı. Bu bağlamda, yeni dokusal ESC veri setini toplayarak ve SKLBP tabanlı ESC modelini önererek ESC metodolojisine katkıda bulunduk.

Anahtar Kelimeler

• Textural ESC dataset
• Square-kernelled local binary pattern
• Signal classification
• Advanced signal processing
• Textural feature extraction

SKLBP14: A new textural environmental sound classification model based on a squarekernelled local binary pattern

Öz

Nowadays, the forward-forward (FF) algorithm is very popular in the machine learning society, and it uses a square-based activation function. In this research, we inspired the FF algorithm and presented a new kernel for a local binary pattern named square-kernelled local binary pattern (SKLBP). By deploying the proposed one-dimensional SKLBP, a new feature engineering model has been presented. To measure the classification ability of the proposed SKLBP-based model, we have collected a new textural environmental sound classification (ESC) dataset. The collected dataset is a balanced dataset, and it contains 15 classes. There are 100 sounds in each class. Our proposed model has mimicked the deep learning structure. Therefore, it uses multileveled feature extraction methodology by using discrete wavelet transform. The features generated have been considered as input for the iterative feature selector. The chosen feature vector has been utilized as input of the k nearest neighbor classifier. The proposed SKLBP-based signal classification model reached 94% classification accuracy. In this aspect, we contributed to the ESC methodology by collecting the new textural ESC dataset and proposing the SKLBP-based ESC model.

Anahtar Kelimeler

• Dokusal ESC veri seti
• Kare çekirdekli yerel ikili model
• Sinyal sınıflandırması
• Gelişmiş sinyal işleme
• Dokusal özellik çıkarma

Kaynakça

1. [1] Demir K, Berna A, Demir F. "Detection of brain tumor with a pre-trained deep learning model based on feature selection using MR images". Firat University Journal of Experimental and Computational Engineering, 2(1), 23-31, 2023.
2. [2] Sevinç A, Özyurt F. "Classification of recyclable waste using deep learning architectures". Firat University Journal of Experimental and Computational Engineering, 1(3), 122-128, 2022.
3. [3] Matwin S, Kouznetsov A, Inkpen D, Frunza O, O'Blenis P. "A new algorithm for reducing the workload of experts in performing systematic reviews". Journal of the American Medical Informatics Association, 17(4), 446-453, 2010.
4. [4] Salamon J, Bello JP. "Deep convolutional neural networks and data augmentation for environmental sound classification". IEEE Signal processing letters, 24(3), 279-283, 2017.
5. [5] Abdoli S, Cardinal P, Koerich AL. "End-to-end environmental sound classification using a 1D convolutional neural network". Expert Systems with Applications, 136, 252-263, 2019.
6. [6] Okaba M, Tuncer T. "An automated location detection method in multi-storey buildings using environmental sound classification based on a new center symmetric nonlinear pattern: CS-LBlock-Pat". Automation in Construction, 125, 103645, 2021.
7. [7] Zhang Y, Zeng J, Li Y, Chen D. "Convolutional neural network-gated recurrent unit neural network with feature fusion for environmental sound classification". Automatic Control and Computer Sciences, 55, 311-318, 2021.
8. [8] Demir F, Abdullah DA, Sengur A. "A new deep CNN model for environmental sound classification". IEEE Access, 8, 66529-66537, 2020.

9. [9] Ojala T, Pietikainen M, Maenpaa T. "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns". IEEE Transactions on pattern analysis and machine intelligence, 24(7), 971-987, 2002.
10. [10] Ahonen T, Hadid A, Pietikäinen M. "Face recognition with local binary patterns". in European conference on computer vision, 2004: Springer, 469-481.
11. [11] Hinton G. "The forward-forward algorithm: Some preliminary investigations". arXiv preprint arXiv:2212.13345, 2022.
12. [12] Kotsiopoulos T, Sarigiannidis P, Ioannidis D, Tzovaras D. "Machine learning and deep learning in smart manufacturing: The smart grid paradigm". Computer Science Review, 40, 100341, 2021.
13. [13] Hall O, Dompae F, Wahab I, Dzanku FM. "A review of machine learning and satellite imagery for poverty prediction: Implications for development research and applications". Journal of International Development, 2023.
14. [14] Tuncer T, Dogan S, Baygin M, Acharya UR. "Tetromino pattern based accurate EEG emotion classification model". Artificial Intelligence in Medicine, 123, 102210, 2022.
15. [15] Tuncer T, Dogan S, Pławiak P, Acharya UR, "Automated arrhythmia detection using novel hexadecimal local pattern and multilevel wavelet transform with ECG signals". Knowledge-Based Systems, 186, 104923, 2019.
16. [16] Tuncer T, Dogan S, Özyurt F, Belhaouari SB, Bensmail H. "Novel Multi Center and Threshold Ternary Pattern Based Method for Disease Detection Method Using Voice". IEEE Access, 8, 84532-84540, 2020.
17. [17] L. E. Peterson, "K-nearest neighbor," Scholarpedia, vol. 4, no. 2, p. 1883, 2009.
18. [18] Maillo J, Ramírez S, Triguero I, Herrera F. "kNN-IS: An Iterative Spark-based design of the k-Nearest Neighbors classifier for big data". Knowledge-Based Systems, 117, 3-15, 2017.
19. [19] Carrington AM. et al. "Deep ROC analysis and AUC as balanced average accuracy, for improved classifier selection, audit and explanation". IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 329-341, 2022.
20. [20] Powers DM. "Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation". arXiv preprint arXiv:2010.16061, 2020.