An approach frequently used to determine the time of death is Henssge's nomogram. The precision of the resulting time period is, however, impacted by uncertainties that occur from the graphical solution of the original mathematical expression. In comparison to Henssge's nomogram, we provide a more precise and adaptive method for calculating the time of death using existing machine learning techniques/tools including support vector machines (SVMs) and decision trees. The bulk of the tools we chose can estimate the time of death with low error rates even with only 3000 training cases, according to a synthetic data-driven model we developed using Python. The best outcomes for determining the time of death with the lowest error and highest estimated time of death accuracy were from an SVM with a radial basis function (RBF) kernel and AdaBoost+SVR.
HTML PDFShare this article
Journal of Forensic Medicine received 165 citations as per Google Scholar report
