AN AUTOMATED GUNSHOT AUDIO CLASSIFICATION METHOD BASED ON FINGER PATTERN FEATURE GENERATOR AND ITERATIVE RELIEFF FEATURE SELECTOR

Yıl 2021, Cilt: 8 Sayı: 14, 225 - 243, 30.06.2021

Türker Tuncer Sengul Dogan Erhan Akbal Emrah Aydemir

Öz

Audio forensics applications and methods are very crucial to clarify crimes. To accelerate audio analysis process and classify audios with high accuracy, machine learning (ML) methods must be used in audio forensics. An automated gunshot audios classification method is presented in this study. To implement our automated gunshot classification method, a novel gun audios dataset was collected from YouTube with 8 classes in the first phase. A novel ML method is presented in the second phase and the proposed ML method contains three fundamental phases. These phases are a novel finger pattern (finger-pat), statistical moments and discrete wavelet transform (DWT) based feature generation network, informative/distinctive feature selection with iterative ReliefF (IRF) feature selector and classification with a k nearest neighbors (kNN) classifier (shallow) to show success of the generated and selected features by using the proposed finger-pat based feature generation network and IRF feature selector. These methods and kNN achieved 94.48% classification accuracy. These results demonstrate that our proposed method can be used in gunshot audio analysis.

Kaynakça

• Casey E. Digital evidence and computer crime: Forensic science, computers, and the internet: Academic press; 2011.
• Turner P. Unification of digital evidence from disparate sources (digital evidence bags). Digital Investigation. 2005;2(3):223-228.
• Case A, Cristina A, Marziale L, Richard GG, Roussev V. FACE: Automated digital evidence discovery and correlation. digital investigation. 2008;5:S65-S75.
• Kenneally EE, Brown CL. Risk sensitive digital evidence collection. Digital Investigation. 2005;2(2):101-119.
• Turner P. Selective and intelligent imaging using digital evidence bags. digital investigation. 2006;3:59-64.
• Maher RC. Audio forensic examination. IEEE Signal Processing Magazine. 2009;26(2):84-94.
• Raponi S, Ali I, Oligeri G. Sound of Guns: Digital Forensics of Gun Audio Samples meets Artificial Intelligence. arXiv preprint arXiv:2004.07948. 2020.
• Begault DR, Beck SD, Maher RC. Overview of forensic audio gunshot analysis techniques. Paper presented at: Audio Engineering Society Conference: 2019 AES International Conference on Audio Forensics, 2019.
• Maher RC. Acoustical characterization of gunshots. Paper presented at: 2007 IEEE Workshop on Signal Processing Applications for Public Security and Forensics, 2007.
• Sueur J, Farina A. Ecoacoustics: the ecological investigation and interpretation of environmental sound. Biosemiotics. 2015;8(3):493-502.
• Xie J, Zhu M. Handcrafted features and late fusion with deep learning for bird sound classification. Ecological Informatics. 2019;52:74-81.
• Green M, Murphy D. Environmental sound monitoring using machine learning on mobile devices. Applied Acoustics. 2020;159:107041.
• Mayer P, Magno M, Benini L. Self-sustaining acoustic sensor with programmable pattern recognition for underwater monitoring. IEEE Transactions on Instrumentation and Measurement. 2019;68(7):2346-2355.
• Pham G-T, Baron V, Finez A, Nicolas B. High resolution source localization in underwater acoustics for deep sea mining monitoring. Paper presented at: OCEANS 2019-Marseille, 2019.
• Lim SJ, Jang SJ, Lim JY, Ko JH. Classification of snoring sound based on a recurrent neural network. Expert Systems With Applications. 2019;123:237-245.
• Patil S, Saxena A, Talreja T, Bhatti V. Medical Diagnosis of Ailments Through Supervised Learning Techniques on Sounds of the Heart and Lungs. Soft Computing and Signal Processing: Springer; 2019:253-262.
• Jung M, Chi S. Human activity classification based on sound recognition and residual convolutional neural network. Automation in Construction. 2020;114:103177.
• González-Hernández FR, Sánchez-Fernández LP, Suárez-Guerra S, Sánchez-Pérez LA. Marine mammal sound classification based on a parallel recognition model and octave analysis. Applied Acoustics. 2017;119:17-28.
• Muhammad G, Alghathbar K. Environment recognition for digital audio forensics using MPEG-7 and mel cepstral features. Journal of Electrical Engineering. 2011;62(4):199-205.
• Busse C, Krause T, Ostermann J, Bitzer J. Improved Gunshot Classification by Using Artificial Data. Paper presented at: Audio Engineering Society Conference: 2019 AES International Conference on Audio Forensics, 2019.
• Khan S, Divakaran A, Sawhney HS. Weapon identification using hierarchical classification of acoustic signatures. Paper presented at: Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense VIII, 2009.
• Ahmed T, Uppal M, Muhammad A. Improving efficiency and reliability of gunshot detection systems. Paper presented at: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013.
• Djeddou M, Touhami T. Classification and modeling of acoustic gunshot signatures. Arabian journal for science and engineering. 2013;38(12):3399-3406.
• Kiktova E, Lojka M, Pleva M, Juhar J, Cizmar A. Gun type recognition from gunshot audio recordings. Paper presented at: 3rd International Workshop on Biometrics and Forensics (IWBF 2015), 2015.
• Khan S, Divakaran A, Sawhney HS. Weapon identification across varying acoustic conditions using an exemplar embedding approach. Paper presented at: Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense IX, 2010.
• Morton Jr KD, Torrione PA, Collins L. Classification of acoustic gunshot signatures using a nonparametric Bayesian signal model. Paper presented at: Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense X, 2011.
• Sánchez-Hevia HA, Ayllón D, Gil-Pita R, Rosa-Zurera M. Maximum likelihood decision fusion for weapon classification in wireless acoustic sensor networks. IEEE/ACM transactions on audio, speech, and language processing. 2017;25(6):1172-1182.
• Liao Y, Vemuri VR. Use of k-nearest neighbor classifier for intrusion detection. Computers & security. 2002;21(5):439-448.
• Robnik-Šikonja M, Kononenko I. Theoretical and empirical analysis of ReliefF and RReliefF. Machine learning. 2003;53(1-2):23-69.
• Youtube. https://www.youtube.com/. 2020.
• Shensa MJ. The discrete wavelet transform: wedding the a trous and Mallat algorithms. IEEE Transactions on signal processing. 1992;40(10):2464-2482.
• Jensen A, la Cour-Harbo A. Ripples in mathematics: the discrete wavelet transform: Springer Science & Business Media; 2001.
• Schiele J, Rabe F, Schmitt M, et al. Automated Classification of Airborne Pollen using Neural Networks. Paper presented at: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2019.
• Stuhlsatz A, Meyer C, Eyben F, Zielke T, Meier G, Schuller B. Deep neural networks for acoustic emotion recognition: Raising the benchmarks. Paper presented at: 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2011.
• 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. 2019;186:104923.
• Sallai J, Hedgecock W, Volgyesi P, Nadas A, Balogh G, Ledeczi A. Weapon classification and shooter localization using distributed multichannel acoustic sensors. Journal of systems architecture. 2011;57(10):869-885.