The Development of Artificial Intelligence (AI) System for Forensic Investigation of Sex Crimes
Keywords:
Forensic investigation system, Artificial Intelligence (AI), SpermAbstract
This research aimed to develop an Artificial Intelligence (AI) system for sperm identification to be used as an evidence or an important indicator in sexual offense cases, and to study the feasibility of the system. The research was divided into two parts. The first part was to develop an Artificial Intelligence system for sperm detection and a website for sperm detection, using applied research method. The second part included the tool familiarization training for forensic scientists. The study found that the Artificial Intelligence system could lessen the steps of sperm detection process. If the digital scanned image from microscope slides shown more than two sperm heads, it could be assumed that a sexual abuse happened. Developed on the YOLOv5m, the precision of the system was up to 97.4%. It could also be accessed on website. Forensic scientists who were trained were satisfied with the system as it could accelerate forensic investigation service, increase chances for proving an offender’s guilt, and reduce opportunities of the offender to commit other crimes. In addition, waste of time and human resources could be avoided.
References
คณะวิทยาศาสตร์ประยุกต์ มหาวิทยาลัยธุรกิจบัณฑิตย์. (2559). การพัฒนาแนวทางการรับฟังพยานหลักฐานทางนิติวิทยาศาสตร์เพื่อพิสูจน์ความจริงในคดี. สถาบันวิจัยและพัฒนารพีพัฒนศักดิ์. https://rabi.coj.go.th/th/content/category/detail/id/39/iid/176580
ฉัตรสุมน พฤฒิภิญโญ และนิทัศน์ ศิริโชติรัตน์. (2557). กระบวนการสอบสวนและหลักฐานคดีความผิดทางเพศ. Journal of Thai Justice System, 7(1), 17-33. https://so04.tci-thaijo.org/index.php/JTJS /article/view/246204
เปิดสถิติความรุนแรงทางเพศของสังคมไทยยังน่าเป็นห่วง. (2561). BLT BANGKOK. https://www.bltbangkok.com/news/4510/
สำนักข่าวไทย. (2563). สถิติความผิดเกี่ยวกับเพศ ปี 2560-2563. https://tna.mcot.net/crime-530217
อานนท์ จำลองกุล. (2560). การดูแลผู้ถูกล่วงละเมิดทางเพศ: ร่างกาย จิตใจ และการเยียวยาทางกฎหมาย. Chulalongkorn Medical Journal, 61(5), 603-618. https://digital.car.chula.ac.th/clmjournal/vol61/ iss5/7/
Allery, J. P., Telmon, N., Mieusset, R., Blanc, A., & Rougé, D. (2001). Cytological detection of spermatozoa: comparison of three staining methods. Journal of forensic sciences, 46(2), 349-351. https://pubmed.ncbi.nlm.nih.gov/11305439/
Dobrovolny, M., Benes, J., Langer, J., Krejcar, O., & Selamat, A. (2023). Study on sperm-cell detection using YOLOv5 architecture with labaled dataset. Genes 2023, 14(2), 451. https://doi.org/10.3390/genes14020451
Feng, L., Xu, C., Zeng, X., Zhang, H., Yang, F., Li, W., Tu, Z., Li, C., & Hu, L. (2014). Y-chromosomal haplotyping of single sperm cells isolated from semen mixtures - a successful identification of three perpetrators in a multi-suspect sexual assault case. Croatian Medical Journal, 55(5), 537-41. https://doi.org/10.3325/cmj.2014.55.537
Golomingi, R., Haas, C., Dobay, A., Kottner, S., & Ebert, L. (2022). Sperm hunting on optical microscope slides for forensic analysis with deep convolutional networks – a feasibility study. Forensic Science International: Genetics, 56, 102602. https://doi.org/10.1016/j.fsigen.2021.102602
Hicks, S. A., Andersen, J. M., Witczak, O., Thambawita, V., Halvorsen, P., Hammer, H. L., Haugen, T. B., & Riegler, M. A. (2019). Machine learning-based analysis of sperm videos and participant data for male fertility prediction. Scientific Reports, 9, 1-10. https://doi.org/10.1038/s41598-019-53217-y
Iqbal, I., Ghulam, M., & Jinwen, M. (2020). Deep learning-based morphological classification of human sperm heads. Diagnostics, 10(5), 325. https://www.mdpi.com/2075-4418/10/5/325
Javadi, S., & Mirroshandel, S. A. (2019). A novel deep learning method for automatic assessment of human sperm images. Computers in biology and medicine, 106, 182-194. https://doi.org/10.1016/j.compbiomed.2019.04.030
Mohammadi, M. R., Rahimzadeh, M., & Attar, A. (2020). Sperm detection and tracking in phase-contrast microscopy image sequences using deep learning and modified CSR-DCF. arXiv. https://doi.org/10.48550/arXiv.2002.04034
Ramachandram, D., & Taylor, G. W. (2017). Deep multimodal learning: a survey on recent advances and trends. IEEE Signal Processing Magazine, 34(6), 96–108. https://ieeexplore.ieee.org/document/8103116
Tobón, D. P., Hossain, M. S., Muhammad, G., Bilbao, J., & Saddik, A. E. (2022). Deep learning in multimedia healthcare applications: a review. Multimedia Systems, 28(4), 1465-1479. https://doi.org/10.1007/s00530-022-00948-0
World Health Organization, HRP. (2021). WHO laboratory manual for the examination and processing of human semen (6th ed.). Geneva: World Health Organization. https://www.who.int/publications/i/item/9789240030787
World Population Review. (2021). Rape statistics by country 2023. https://worldpopulationreview.com/country-rankings/rape-statistics-by-country
Xu, C., & Jiang, X. (2022). iMedBot: A web-based intelligent agent for healthcare related prediction and deep learning. arXiv. https://doi.org/10.48550/arXiv.2210.05671
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 NBTC Journal
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The Office of the NBTC holds the copyright of articles appearing in the journal. The Office of the NBTC allows the public or individuals to distribute, copy, or republish the work under a Creative Commons license (CC), with attribution (BY), No Derivatives (ND) and NonCommercial (NC); unless written permission is received from the Office of the NBTC.
Text, tables, and figures that appear in articles accepted for publication in this journal are personal opinion and responsibility of the author, and not binding on the NBTC and the Office of the NBTC. In case of errors, each author is solely responsible for their own article, and not concerning the NBTC and the NBTC Office in any way.
