Cnn-based Dna Pattern Analysis for Missing Person Identification in Mass Casualty and Forensic Scenarios

In the aftermath of mass casualty occurrences (MCIs) and complex forensic investigations, identifying missing people quickly and accurately is crucial for humanitarian and legal reasons. Short Tandem Repeats (STRs), a type of highly variable DNA sequence, have long been considered the gold standard for determining human identification. Traditional STR analysis procedures, on the other hand, need manual interpretation and statistical comparison, which are time-consuming and error-prone, particularly when dealing with large-scale disasters or degraded DNA samples. In this work, a unique use of convolutional neural networks (CNNs) to automate the analysis of DNA patterns based on STR profiles is proposed. The algorithm gains the ability to accurately identify and match intricate DNA patterns across big datasets by transforming STR allele data into a deep learning-compatible format. Standard forensic criteria are used to assess the system after it has been trained on both simulated and real-world STR data. The suggested CNN-based framework is a useful tool for identifying missing persons in mass graves, MCIs, and other forensic situations since it drastically cuts down on identification time while preserving forensic-level accuracy. This method not only improves DNA-based identification's speed and accuracy, but it also establishes the framework for incorporating AI into forensic systems of the future.