Abstract

Keywords

۱٫ Introduction

۲٫ Gunshot audio dataset

۳٫ The presented sleep stage classification model

۴٫ Experiments

۵٫ Discussions

۶٫ Conclusion

CRediT authorship contribution statement

Declaration of Competing Interest

Acknowledgment

References

Abstract

Background

Gun model identification (GMI) is a complex issue for digital forensics examiners/professions. Because the GMI process is a highly costed process, and it is generally detected manually. A sound classification model is presented in this research to decrease the cost of the GMI and automate this process.

Material and method

The primary objective of this research is to present a new intelligent audio forensics tool. Therefore, a new gunshot dataset was collected, and the collected dataset includes 2130 audios of the 28 gun models. This dataset can be downloaded using http://web.firat.edu.tr/sdogan/Gun_S_Dogan.rar link. The presented fractal H-tree pattern-based classification method is applied to these audios to obtain results. This method has three fundamental phases, and these are feature extraction, the most informative features selection, and classification. This method uses both a fractal textural generator and statistical features. By deploying tunable q-factor wavelet transform (TQWT), a multileveled feature generation method is created to generate both low-level and high-level features. The recommended fractal H-tree pattern and statistical feature extraction functions generate features at each level. Neighborhood component analysis (NCA) chooses the most informative features. In the classification phase, the support vector machine (SVM) and k nearest neighbor (kNN) classifiers are used.

Results

The recommended fractal H-tree pattern-based method yielded 96.10% and 90.40% by employing kNN and SVM, respectively.

Conclusion

The calculated results and findings denoted the high classification capability of the presented fractal H-tree pattern-based method for gun model classification using gunshot audios. Also, this research shows that a new audio forensic tool can be developed by employing the presented method for GMI.

۱٫ Introduction

۱٫۱٫ Background and related work

Gun model identification (GMI) is one of today’s essential research topics. GMI has a crucial role in criminalistics, and it has been mostly used in military applications. At the same time, GMI can also be used for security purposes in applications such as digital forensics and forensics [1–۳]. Each gun has a special acoustic characteristic. When these acoustic characteristics are analyzed in detail, they can provide critical support information to criminalistics. Different features such as the audios obtained from the trigger and hammer mechanism of the gun, the audio of mechanical movement, the audios of the bullet hitting solid surfaces customize the gun [4,5]. Therefore, the detection of this gun can be achieved by using the features of a gun audio signal. GMI systems with a high recognition rate are needed in the crime scene to recognize such systems automatically [6]. These systems must be capable of responding to events in different environments. In addition, systems should be less sensitive to environmental sounds. For example, a gunshot may be environmentally inadequate in acoustical evidence due to its location [7].