Phylogenetic modelling scripts for identifying script versions

Abstract

As the digital and physical worlds connect, machine-learning tools are increasingly being used by businesses and institutions, including archaeological research institutes and museums. The article presents research that, based on the evolution of human scripts, provides a tool for identifying script variants used in old manuscripts and stone inscriptions. This makes the work of paleography institutes and individual researchers more efficient. Using this research, it is possible to provide some information about millions of hitherto unidentified inscriptions using machine learning. The developed and tested method applies the biological phylogenetics tool to script evolution, an area that has yet to be investigated with machine learning tools. The final aim of the research is to use these tools to clarify the connections between many Arabic, Aramaic and Central Iranian script variants. The described procedure gives a new solution to one of the fundamental issues of phylogenetic analysis, feature selection, the effectiveness of which is verified with test runs. The paper presents a new feature selection method to identify the strength or effect of features before phylogenetic processing. This type of dimensionality reduction removes unnecessary features from the dataset for these analyses and interpretations. The method was applied to some versions of Arabic, Aramaic and Middle Iranian scripts, but the procedure is not script-specific.