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

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.

[1]  Cristina Cattaneo,et al.  Comparison of Four Skeletal Methods for the Estimation of Age at Death on White and Black Adults * , 2007, Journal of forensic sciences.

[2]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[3]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[4]  Kazuhiro Sakaue,et al.  New Method for Diagnosis of the Sex and Age-at-death of an Adult Human Skeleton from the Patella , 2008 .

[5]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[6]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[7]  M Graw,et al.  Recommendations for the forensic diagnosis of sex and age from skeletons. , 2007, Homo : internationale Zeitschrift fur die vergleichende Forschung am Menschen.

[8]  M Y Işcan,et al.  Estimation of age at death using cortical histomorphometry of the sternal end of the fourth rib. , 1994, Journal of forensic sciences.

[9]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[10]  J. Prieto,et al.  The problem of aging human remains and living individuals: a review. , 2009, Forensic science international.

[11]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[12]  Niels Lynnerup,et al.  A method for estimating age of Danish medieval sub-adults based on long bone length. , 2012, Anthropologischer Anzeiger; Bericht uber die biologisch-anthropologische Literatur.

[13]  Thomas G. Dietterich What is machine learning? , 2020, Archives of Disease in Childhood.

[14]  Stefanie Ritz-Timme,et al.  Racemization of aspartic acid in human proteins , 2002, Ageing Research Reviews.

[15]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .

[16]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.