Machine learning techniques for age at death estimation from long bone lengths

摘要

Estimating age at death of cadavers is an important ability in various subfields of forensic science and bioarchaeology. It can allow investigators to pinpoint someone's identity, more accurately locate an event of interest in time and clarify other societal or legal issues concerning a given skeletal collection. There are two main categories of methods for estimating age at death: biochemical methods - which use various biological or chemical processes to obtain an estimation -, and mathematical methods - which employ the use of data mining tools such as regression in order to estimate age from various numerical features. In this paper, we propose two machine learning approaches for the age estimation problem and prove that they outperform existing mathematical approaches on a number of case studies derived from publicly available data used for this task. Moreover, our methods are more robust and easier to reuse on new data.