Çok Seviyeli Yerel İkili Dört Desenler ve İteratif ReliefF Tabanlı Yeni Bir Araç İçi Ses Sınıflandırma Yöntemi

Abstract

Ses sınıflandırması, makine öğrenimi ve ses adli bilişiminde önemli çalışma alanlarından biridir. Ancak, dijital adli bilişim literatüründe ses adli bilişimi veya ses tabanlı suç soruşturmaları üzerine sınırlı sayıda çalışma bulunmaktadır. Bu çalışmada, ses adli bilişiminde yeni bir alan sunulmaktadır: araç içi ses sınıflandırması (CISC). CISC’nin temel amacı, araçların iç ortam seslerini kullanarak tanımlanmasıdır. Bu amaçla, 10 farklı araç modeli kullanılarak bir araç içi ses veri seti oluşturulmuştur. CISC modeli, yerel ikili dört desen ve tek boyutlu çok seviyeli ayrık dalgacık dönüşümü (DWT) ile özellik çıkarımını, iteratif ReliefF tabanlı özellik seçimini ve sınıflandırmayı içermektedir. Modelin genel başarısını göstermek için k-en yakın komşu (kNN) ve destek vektör makinesi (SVM) sınıflandırıcıları kullanılmıştır. kNN ve SVM ile elde edilen doğruluk oranları sırasıyla %93,72 ± 0,37 ve %95,04 ± 0,30 olarak hesaplanmıştır. Bu sonuçlar, önerilen yöntemin başarısını ortaya koymaktadır

Keywords

• Araba iç ses sınıflandırması
• döngüsel rölyef
• yerel ikili dört desen
• çevresel ses sınıflandırması
• ses adli bilişimi analizi
• siber suç

A Novel Car Interior Sound Classification Method based on Multileveled Local Binary Four Patterns and Iterative ReliefF

Abstract

Sound classification is one of the crucial study areas in machine learning and sound forensics. However, there are limited studies on sound forensics or sound-based crime investigations in the digital forensics literature. In this work, a novel area of sound forensics is presented: car interior sound classification (CISC). The main aim of CISC is to identify a car using its interior environmental sound. A car interior sound dataset was collected using 10 car models. This CISC model includes feature generation using the local binary four pattern and one-dimensional multilevel discrete wavelet transform (DWT), iterative ReliefF-based feature selection, and classification. k-nearest neighbors (kNN) and support vector machine (SVM) were utilized as classifiers to demonstrate the general success of the proposed learning model for CISC. The accuracy rates were calculated as 93.72% ± 0.37 and 95.04% ± 0.30 with kNN and SVM, respectively. These results demonstrate the success of the proposed method.

Keywords

• Car interior sound classification
• Iterative ReliefF
• Local Binary Four Pattern
• Environmental sound classification
• Sound forensics Analysis
• Cyber Crime

References

1. Lou SC, Chao RM, Ko SH, Lin KM and Zhong JX. A simplified signal analysis algorithm for the development of a low cost underwater echo-sounder. Measurement 2011; 44(9):1572-1581.
2. Liu S. Measurement and analysis of vibration and noise in the ambient environment of metro. Measurement 2020; 107998.
3. Amarnath M, Sugumaran V and Kumar H. Exploiting sound signals for fault diagnosis of bearings using decision tree. Measurement 2013; 46(3):1250-1256.
4. Lara R, Jimenez-Romero R, Perez-Hidalgo F and Redel-Macias M D. Influence of constructive parameters and power signals on sound quality and airborne noise radiated by inverter-fed induction motors. Measurement 2015; 73:503-514.
5. Ye S, Zhang J, Xu B, Song W, and Zhu S. Experimental studies of the vibro-acoustic characteristics of an axial piston pump under run-up and steady-state operating conditions. Measurement 2019; 133: 522-531.
6. Zhang D, Stewart E, Entezami M, Roberts C and Yu D. Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network. Measurement 2020; 156:107585.
7. Xiang M, Zang J, Wang J, Wang H, Zhou C, Bi R and Xue C. Research of heart sound classification using two-dimensional features. Biomed Signal Proces 2023; 79:104190.
8. Chen J, Guo Z, Xu X, Zhang L B, Teng Y, Chen Y and Wang W. A robust deep learning framework based on spectrograms for heart sound classification. IEEE/ACM Trans Comput Biol Bioinform 2023; 21(4): 936-947.

9. Petošić A, Djurek I, Suhanek M and Grubeša S. Interlaboratory comparisons’ measurement uncertainty in the field of environmental noise. Measurement 2019; 148: 106932.
10. Muhammad G and Alghathbar K. Environment recognition for digital audio forensics using MPEG-7 and mel cepstral features. J Electr Eng 2011; 62(4):199-205.
11. Ratcliffe JH, Lattanzio M, Kikuchi G, Thomas K. A partially randomized field experiment on the effect of an acoustic gunshot detection system on police incident reports. J Exp Criminol 2019; 15(1):67-76.
12. Nanda MA, Seminar KB, Nandika D, Maddu A. Development of termite detection system based on acoustic and temperature signals. Measurement 2019; 147: 106902.
13. Glowacz A, Glowacz W, Glowacz Z, Kozik J. Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals. Measurement 2018; 113:1-9.
14. Kane P and Andhare A. Critical evaluation and comparison of psychoacoustics, acoustics and vibration features for gear fault correlation and classification. Measurement 2020;107495.
15. Mohaimenuzzaman M, Bergmeir C, West I T, Meyer B. Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices. Pattern Recognit 2023;133:109025.
16. Abdoli S, Cardinal P, Koerich AL. End-to-end environmental sound classification using a 1d convolutional neural network. Expert Syst Appl 2019; 136:252-263.
17. Ahmad S, Agrawal S, Joshi S, Taran S, Bajaj V, Demir F, Sengur A. Environmental sound classification using optimum allocation sampling based empirical mode decomposition. Phys A Stat 2020; 537: 122613.
18. Bardou D, Zhang K, Ahmad SM. Lung sounds classification using convolutional neural networks. Artif Intell Med 2018; 88: 58-69.
19. Beltrán J, Chávez E, Favela J. Scalable identification of mixed environmental sounds, recorded from heterogeneous sources. Pattern Recognit Lett 2015;68:153-160.
20. İnik Ö, CNN hyper-parameter optimization for environmental sound classification. Appl Acoust 2023; 202:109168.
21. Khunarsal P, Lursinsap C, Raicharoen T. Very short time environmental sound classification based on spectrogram pattern matching. Inf Sci 2013; 243:57-74.
22. Piczak, KJ. ESC: Dataset for environmental sound classification. In: Proceedings of the 23rd ACM international conference on Multimedia; 2015; New York, NY, USA, pp. 1015-1018.
23. Muhammad G and Alghathbar K. Environment Recognition for Digital Audio Forensics Using MPEG-7 and Mel Cepstral Features. Int Arab J Inf Technol 2013; 10(1).
24. Kraetzer C, Oermann A, Dittmann J, Lang A. Digital audio forensics: a first practical evaluation on microphone and environment classification. In: 9th workshop on Multimedia & security; 2007; pp.63-74.
25. Oermann A, Lang A and Dittmann J. Verifier-tuple for audio-forensic to determine speaker environment. In: 7th workshop on Multimedia and security; 2005; pp.57-62.
26. Serizel R, Bisot V, Essid S, Richard G. Machine listening techniques as a complement to video image analysis in forensics. In: IEEE International Conference on Image Processing; 2016; IEEE, pp. 948-952.
27. Güner A, Alçin ÖF Şengür A. Automatic digital modulation classification using extreme learning machine with local binary pattern histogram features. Measurement 2019;145: 214-225.
28. Gupta D, Arora J, Agrawal U, Khanna A, Albuquerque VHC. Optimized Binary Bat algorithm for classification of white blood cells. Measurement 2019; 143:180-190.
29. Hu Q, Ohata EF, Silva FH, Ramalho GL, Han T, Reboucas Filho PP. A new online approach for classification of pumps vibration patterns based on intelligent IoT system. Measurement 2020;151: 107138.
30. Ma C, An Y, Shen E, Yu D, Zhang J. Car Interior Sound Field Zoning Using Optimal Loudspeaker Array and Double Iteration Method. J Audio Eng Soc 2024; 72(4): p. 247-256.
31. Zaman K, Sah M, Direkoglu C, Unoki M. A survey of audio classification using deep learning. IEEE Access 202;11: 106620-106649.
32. Li F, Pang X, Yang Z. Motor current signal analysis using deep neural networks for planetary gear fault diagnosis. Measurement 2019; 145:45-54.
33. Xue Y, Dou D, Yang J, Multi-fault diagnosis of rotating machinery based on deep convolution neural network and support vector machine. Measurement 2020; 156:107571.
34. Lu Y, Wang M, Wu W, Han Y, Zhang Q, Chen S, Dynamic entropy-based pattern learning to identify emotions from EEG signals across individuals. Measurement 2020; 150: 107003.
35. Sudhagar S, Sakthivel M, Ganeshkumar P. Monitoring of friction stir welding based on vision system coupled with Machine learning algorithm. Measurement 2019; 144:135-143.
36. Navarro JM and Pita A. Machine Learning Prediction of the Long-Term Environmental Acoustic Pattern of a City Location Using Short-Term Sound Pressure Level Measurements. Appl Sci 2023; 13(3):1613.
37. Mollah A, Mahanta TK, Balide V., Intelligent Classification of Automotive Horn Sound Quality 2024; SAE Tech Pap, No: 2024-26-0204.
38. Nasim F, Masood S, Jaffar A, Ahmad U, Rashid M. Intelligent Sound-Based Early Fault Detection System for Vehicles. Comput Syst Sci Eng 2023; 46(3).
39. Fan X, Sun T, Chen W, Fan Q. Deep neural network based environment sound classification and its implementation on hearing aid app. Measurement 2020;107790.
40. Jaber MM, Abd SK, Shakeel PM, Burhanuddin MA, Mohammed MA, Yussof S. A telemedicine tool framework for lung sounds classification using ensemble classifier algorithms. Measurement 2020; 107883.
41. Shen G, Nguyen Q, Choi J, An environmental sound source classification system based on Mel-frequency cepstral coefficients and Gaussian mixture models. IFAC Proc Vol 2012; 45(6): 1802-1807.
42. Saki F, Kehtarnavaz N. Real-time hierarchical classification of sound signals for hearing improvement devices. Appl Acoust 2018;132: 26-32.
43. Salamon J, Jacoby C, Bello JP. A dataset and taxonomy for urban sound research. In: 22nd ACM international conference on Multimedia 2014;1041-1044.
44. Medhat F, Chesmore D, Robinson J, Masked Conditional Neural Networks for sound classification. Appl Soft Comput 2020; 90: 106073.
45. Chen Y, Guo Q, Liang X, Wang J, Qian Y. Environmental sound classification with dilated convolutions. Appl Acoust 2019;148:123-132.
46. Souli S, Lachiri Z. Audio sounds classification using scattering features and support vectors machines for medical surveillance. Appl Acoust 2018;130: 270-282.
47. López-Pacheco MG, Sánchez-Fernández LP, Molina-Lozano H, Sánchez-Pérez LA. Predominant environmental noise classification over sound mixing based on source-specific dictionary. Appl Acoust 2016; 112: 171-180.
48. Tuncer T, Dogan S, Ertam F. Automatic voice based disease detection method using one dimensional local binary pattern feature extraction network. Appl Acoust 2019; 155: 500-506.
49. AlQahtani MO. Environment Sound recognition for digital audio forensics using linear predictive coding features. In: International Conference on Digital Information Processing and Communications. 2011; Berlin, Heidelberg: Springer Berlin Heidelberg, pp.301-309.
50. Black J. Youtube Channel. [cited 05.04.2024; Available from: https://www.youtube.com/channel/UCRT3s4cWpEKyu2U9xPtmOiw.
51. Keerthi SS, Shevade SK, Bhattacharyya C, Murthy KR. A fast iterative nearest point algorithm for support vector machine classifier design. IEEE Trans Neural Netw Learn Syst 2000; 11(1): 124-136.
52. Kar S, Sharma KD, Maitra M, Gene selection from microarray gene expression data for classification of cancer subgroups employing PSO and adaptive K-nearest neighborhood technique. Expert Syst Appl 2015; 42(1):612-627.
53. Liao Y, Vemuri VR, Use of k-nearest neighbor classifier for intrusion detection. Comput Secur 2002; 21(5): 439-448.
54. Patel JR, Patel JM, Medical image fusion technique using singlelevel and multilevel DWT, Int J Eng Res Technol ESRSA Publications 2014; 3(1).
55. Hasan KK, Ngah UK, Salleh MFM. Multilevel decomposition Discrete Wavelet Transform for hardware image compression architectures applications. In: 2013 IEEE International Conference on Control System, Computing and Engineering 2013;pp.315-320.
56. Tian H and Ji W. A digital video watermarking scheme based on 1D-DWT. In: 2013 IEEE International Conference on Control System, Computing and Engineering IEEE, 2013;pp.315-320.
57. Ojala T, Pietikäinen M, Mäenpää T. A generalized local binary pattern operator for multiresolution gray scale and rotation invariant texture classification. In: Advances in Pattern Recognition—ICAPR 2001: Second International Conference; Rio de Janeiro, Brazil; March 11–14, 2001; 2. Springer Berlin Heidelberg, 2001; pp. 399-408.
58. Sun Y, Lou X, Bao B, A novel relief feature selection algorithm based on mean-variance model. J Inf Comput Sci 2011; 8(16): 3921-3929.
59. Robnik-Šikonja M and Kononenko I. Theoretical and empirical analysis of ReliefF and RReliefF. Mach Learn. 2003;53(1-2):23-69.
60. Tuncer T, Dogan S, Pławiak P, Acharya UR. Automated arrhythmia detection using novel hexadecimal local pattern and multilevel wavelet transform with ECG signals. Knowl Based Syst 2019;186:104923.