Applying Machine Learning Techniques to Estimate Post-Mortem Interval From Decomposition Stages
- DOI
- 10.2991/978-94-6463-716-8_21How to use a DOI?
- Keywords
- Forensic Entomology; Death Time Estimation; Feature Extraction; Deep learning; neural networks; Regression Models; Image Processing in Forensics; Time Series Analysis; Big Data in Forensics; Automated Forensic Analysis; Data-Driven Forensic Science
- Abstract
Forensic investigations rely on precise estimations of the Post-Mortem Interval (PMI). Conventional approaches that rely on external factors to determine decomposition accuracy—such as body temperature, livor mortis, and rigor mortis—are notoriously flawed. This research explores the use of machine learning algorithms to forecast PMI by examining different stages of decomposition, environmental conditions, and biological markers. This study investigates various machine learning models, including decision trees, random forests, support vector machines (SVMs), and artificial neural networks (ANNs), using datasets from controlled decomposition scenarios. Machine learning techniques, especially neural networks and random forests, outperform traditional forensic methods when it comes to PMI estimation, according to our results. The random forest model outperformed the others with an MAE of 4.5 hours, indicating its superior accuracy. The most important parameters that emerged as predictors were microbiological data and environmental factors like humidity and temperature. By tackling the problems caused by environmental variability and offering a more consistent and efficient method to PMI calculation, this study demonstrates the potential of machine learning in forensic science. The goal of future research is to strengthen the models and increase the variety of data sources available for use in practical forensic investigations.
- Copyright
- © 2025 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Ankita Chourasia AU - Pankaj Malik AU - Akshit Harsola AU - Riddhima Kaushal AU - Rimi Singh PY - 2025 DA - 2025/05/26 TI - Applying Machine Learning Techniques to Estimate Post-Mortem Interval From Decomposition Stages BT - Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025) PB - Atlantis Press SP - 250 EP - 261 SN - 1951-6851 UR - https://doi.org/10.2991/978-94-6463-716-8_21 DO - 10.2991/978-94-6463-716-8_21 ID - Chourasia2025 ER -