Machine Learning and Possibility of its Application for Forensic Researches on Firearms
DOI:
https://doi.org/10.32353/khrife.2.2024.03Keywords:
forensic firearm examination; shooting distance estimation; machine learning; neural network; classification; clustering; regression.Abstract
Role of machine learning in modern society cannot be over-estimated, especially given its steadily increasing importance in recent years. Various machine learning models are applied not only in everyday life but also in solving practical, engineering, and scientific challenges. However, the methods and capabilities of machine learning remain relatively obscure to most professionals across various fields of knowledge, including specialists in forensic firearm examination. The article discusses basic tasks that machine learning methods can facilitate and provides examples of tasks faced by forensic experts during firearm examinations that can be solved utilizing these methods. The article purpose is to familiarize professionals in the field of forensic science with be-sic capabilities of machine learning methods. The research paper demonstrates which specific types of tasks in forensic firearms examination it is advisable to apply these methods to, and what is required for this purpose. In order to achieve this goal, general scientific methods (dialectical, comparative, analysis, synthesis, induction, deduction) and special scientific methods (formal-logical, systemic-structural) have been employed. Specific expertise and skills in forensic identification methods (including ballistics, microscopic comparative analysis of traces on bullets and casings, detection and examination of gunshot residue to estimate shooting distance, etc.), principles of machine learning, and mathe-matical algorithms used to construct various models have been applied.
References
Banno, A. (2004). Estimation of Bullet Striation Similarity Using Neural Networks. Journal of Forensic Sciences. Vol. 49. Is. 3. DOI: 10.1520/ JFS2002361.
Barash, M., McNevin, D., Fedorenko, V., Giverts, P. (2024). Machine learning applications in forensic DNA profiling: A critical review. Forensic Science International: Genetics. Vol. 69. Art. 102994. DOI: 10.1016/j. fsigen.2023.102994.
Carriquiry A., Hofmann H., Tai X. H., Van derPlas S. (2019). Machine learning in forensic applications. Significance. Vol. 16. Is. 2. DOI: 10.1111/j.17409713.2019.01252.x.
Chen, Zh., Chu, W., Soons, J. A., Thompson, R. M., Song, J., Zhao, X. (2019). Fired bullet signature correlation using the Congruent Matching Profile Segments (CMPS) method. Forensic Science International. Vol. 305. Art. 109964. DOI: 10.1016/j.forsciint.2019.109964.
Chen, Zh., Song, J., Soons, J. A., Thompson, R. M., Zhao, X. (2020). Pilot study on deformed bullet correlation. Forensic Science International. Vol. 306. Art. 110098. DOI: 10.1016/j. forsciint.2019.110098.
Chu, W., Tong, M., Song, J. (2013). Validation Tests for the Congruent Matching Cells (CMC) Method Using Cartridge Cases Fired with Consecutively Manufactured Pistol Slides. Journal of the Association of Firearms and Toolmarks Examiners. Vol. 45. Is. 4. URL: https://www.nist.gov/publications/validationtestscongruentmatchingcellscmcmethodusingcartridgecasesfired.
Chugh, T., Cao, K., Zhou, J., Tabassi, E., Jain, A. K. (2018). Latent Fingerprint Value Prediction: CrowdBased Learning. IEEE Transactions on Information Forensics and Security. Vol. 13. Is. 1. DOI: 10.1109/ TIFS.2017.2721099.
Cuellar, M., Gonzalez, C., Dror, I. E. (2022). Human and machine similarity judgments in forensic firearm comparisons. Forensic Science International: Synergy. Vol. 5. DOI: 10.1016/j.fsisyn.2022.100283.
Dror, I. E. (2023). The most consistent finding in forensic science is inconsistency. Journal of Forensic Sciences. Vol. 68. Is. 6. DOI: 10.1111/15564029.15369.
Dror, I. E., Scurich, N. (2020). (Mis) use of scientific measurements in forensic science. Forensic Science International: Synergy. Vol. 2. DOI: 10.1016/j.fsisyn.2020.08.006.
Durou, A., AlMaadeed, S., Aref, I., Bouridane, Ah., Elbendak, M. (2019). A Comparative Study of Machine Learning Approaches for Handwriter Identification. 12th International Conference on Global Security, Safety and Sustainability (ICGS3). IEEE (London, UK, 16—18 Jan 2019). DOI:10.1109/ ICGS3.2019.8688032.
Ezeobiejesi, J. C. (2019). Deep Learning for the Analysis of Latent Fingerprint Images. University of California Riverside. URL: https://escholarship.org/uc/item/564185wc.
Giudice, O., Guarnera, L., Paratore, A. B., Farinella, G. M., Battiato, S. (2019). Siamese Ballistics Neural Network. International Conference on Image Processing (ICIP). IEEE (Taipei, Taiwan, 22—25 Sept 2019). DOI: 10.1109/ICIP.2019.8803619.
Giverc, P., Griber, A. (2021). Primenenie ma shinnogo obucheniya pri issledovanii akusticheskih signalov ognestrelnogo oruzhiya [Application of machine learning in the study of acoustic signals of firearms]. Aktualni pytannia sudovoi ekspertyzy i kryminalistyky : zb. matliv mizhnar. nauk.prakt. konf.polilohu (Kharkiv, 15—16.04.2021) Kharkiv. URL: https://www.hniise.gov. ua/uploads/files/publicfolder/2021_tezy_konference%20in%20print5.pdf [in Russian].
Giverts, P., Eckert, J., Sofer, S., Solewicz, Y. (2022). Preliminary Investigation of Acoustic Identification of Firearms Mechanisms and its Application to Case Investigations. AFTE Journal. Vol. 53. Is. 4. URL: https://www.researchgate.net/publication/358931773_Preliminary_Investigation_of_Acoustic_Identification_of_Firearms_Mechanisms_and_its_Application_to_Case_Investigation.
Giverts, P., Sofer, S., Solewicz, Y., Varer, B. (2020). Firearms identification by the acoustic signals of their mechanisms. Forensic Science International. Vol. 306. Art. 110099. DOI: 10.1016/j.forsciint.2019.110099.
Giverts, P., Sorokina, K., Fedorenko, V. (2022). Examination of the possibility to use Siamese networks for the comparison of firing pin marks. Journal of Forensic Sciences. Vol. 67. Is. 6. DOI: 10.1111/1556 4029.15143.
Jadon, Sр., Garg, A. (2020). HandsOn Oneshot Learning with Python. Birmingham : Packt Publishing Ltd.
Kamaruddin, S. B. Ah., Ghanib, N. A., Liong, Ch.Y., Jemain, A. A. (2012). Firearm Classification using Neural Networks on Ring of Firing Pin Impression Images. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal. Vol. 1. No. 3. DOI: 10.14201/ADCAIJ20121312734.
Kingston, Ch. (1992). Neural Networks in Forensic Science. Journal of Forensic Sciences. Vol. 37. Is. 1. DOI: 10.1520/jfs13232j.
Le Bouthillier, M.E., Hrynkiw, L., Beauchamp, A., Duong, L., Ratté, S. (2023). Automated detection of regions of interest in cartridge case images using deep learning. Journal of Forensic Sciences. Vol. 68. Is. 6. DOI: 10.1111/15564029.15319.
Lemos, N., Shah, K., Rade, R., Shah, D. (2018). Personality Prediction based on Handwriting using Machine Learning. International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS). IEEE (Belgaum, India, 21—22 Dec 2018). DOI: 10.1109/ CTEMS.2018.8769221.
Li, D. (2006). A New Approach for Firearm Identification with Hierarchical Neural Networks Based on Cartridge Case Images. 5th IEEE International Conference on Cognitive Informatics. IEEE (Beijing, China, 17—19 July 2006). Vol. 2. DOI: 10.1109/ COGINF.2006.365616.
Marciano, M. A., Adelman, J. D. (2017). PACE: Probabilistic Assessment for Contributor Estimation — A machine learningbased assessment of the number of contributors in DNA mixtures. Forensic Science International: Genetics. Vol. 27. DOI: 10.1016/j.fsigen.2016.11.006.
Margagliotti, G., Bollé, T. (2019). Machine learning & forensic science. Forensic Science International. Vol. 298. DOI: 10.1016/ j.forsciint.2019.02.045.
Osterburg, J. W. (1969). The Evaluation of Phisical Еvidenve in Сriminalistics: Subjective or Objective Process? The Journal of Criminal Law, Criminalogy and Police Science. Vol. 60. No. 1. DOI: 10.2307/1141742.
Petraco, N. D. K, Chan, H., De Forest, P. R., Diaczuk, P., Gambino, C., Hamby, J., Kammerman, F. L., Kammrath, B. W., Ku bic, T. A., Kuo, L., et al. (2011). Application of Machine Learning to Toolmarks: Statistical ly Based Methods for Impression Pattern Comparisons. Final Report. U. S. Department of Justice. URL: https://www.ojp.gov/ pdffiles1/nij/grants/239048.pdf.
Pisantanaroj, P., Tanpisuth, P., Sinchavanwat, P., Phasuk, S., Phienphanich, Ph., Jangtawee, P., Yakoompai, K., Donphoongpi, M., Ekgasit, S., Tantibundhit, Ch. (2020). Automated Firearm Classification From Bullet Markings Using Deep Learning. IEEE Access. Vol. 8. Art. 78236—78251. DOI: 10.1109/ ACCESS.2020.2989673.
Report to the President’s. Forensic Science in Criminal Courts: Ensuring Scientific Validity of FeatureComparison Methods. (2016). URL: https://obamawhitehouse.archives.gov/sites/ default/files/microsites/ostp/PCAST/pcast_forensic_science_report_final.pdf.
Sharma, A., Kaur, M. (2018). Automatic segmentation for separation of overlapped latent fingerprints. International Journal of Computer Sciences and Engineering. Vol. 6. Is. 7. DOI: 10.26438/ijcse/v6i7.484490.
Song, J., Song, H. (2023). Reporting likelihood ratio for casework in firearm evidence identification. Journal of Forensic Sciences. Vol. 68. Is. 2. Pp. 399—406. DOI: 10.1111/1556 4029.15186.
Stojanović, B., Marques, O., Nešković, A., Puzović, S. (2016). Fingerprint ROI segmentation based on deep learning. 24th Telecommunications Forum (TELFOR). IEEE (Belgrade, Serbia,22—23 Nov 2016). DOI: 10.1109/TELFOR.2016.7818799.
Strengthening Forensic Science in the United States: A Path Forward. (2009). Washington, D. C. DOI: 10.17226/12589.
Tong, M., Song, J., Chu, W., Thompson, R. M. (2014). Fired Cartridge Case Identification Using Optical Images and the Congruent Matching Cells (CMC) Method. Journal of Research of the National Institute of Standards and Technology. Vol. 119. Art. 575. DOI: 10.6028/jres.119.023.
Varer, B., Giverts, P. (2021). The Comparison of Feature Engineering Methods Used for Acoustic Identification of Firearms. International Conference on Information and Telecommunication Technologies and Radio Electronics (UkrMiCo). IEEE (Odesa, Ukraine, 29 Nov 2021). DOI: 10.1109/ UkrMiCo52950.2021.9716587.
Wang, S., Jia, Sh. (2019). Signature handwriting identification based on generative adversarial networks. Journal of Physics: Conference Series. Vol. 1187. Is. 4. Art. 042047. DOI: 10.1088/1742 6596/1187/4/042047.
Wen, Zh., Curran, J. M., Harbison, S.A., Wevers, G. E. (2023). Classification of firing pin impressions using HOGSVM. Journal of Forensic Sciences. Vol. 68. Is. 6. DOI: 10.1111/15564029.15377.
Wong, W. J., Lai, Sh.H. (2020). Multitask CNN for restoring corrupted fingerprint images. Pattern Recognition. Vol. 101. Art. 107203. DOI: 10.1016/j.patcog.2020.107203.
Yih, Ch.H., Hung, J.L., Wu, J.A., Chen, L.M. (2018). Overlapped Fingerprint Separation Based on Deep Learning. International Conference on Digital Medicine and Image Processing (Okinawa, Japan, Nov 12—14, 2018). DOI: 10.1145/3299852.3299857.
