Korištenje metoda strojnog učenja u antropološkoj problematici

Machine learning is a part of the field of computer science known as artificial intelligence that deals with the construction and analysing of systems that can learn from the data. The application of machine learning techniques in the analysis of large data sets is called data mining. In-depth analysis of data and its use in the detection of knowledge is an indispensable part of modern data analysis in scientific research, applied in many fields of science. Anthropology as interdisciplinary science in their research provides a broad space for the application of data mining, whose advantages and disadvantages, should be considered. The aim of this work was to review a few selected machine learning algorithms and to examine their use on real-world data set. Supervised and unsupervised learning was tested, with in depth analysis of decision tree algorithm (J48 classification techniques) and Naive Bayes classifier, which were used for prediction of diabetes mellitus from the PIMA Indian diabetes dataset made available by National Institute of Diabetes and Digestive and Kidney Diseases. For the processing of data and for descriptive statistics were used languages „R“ and "Python“, while machine learning algorithms were implemented in tool WEKA.