Toktamış, DilekEr, Mehmet BilalIşık, Esme2022-03-192022-03-192022Toktamis, D., Er, M. B., & Isik, E. (2022). Classification of thermoluminescence features of the natural halite with machine learning. Radiation Effects and Defects in Solids, 1-12.1042-01501029-4953https://doi.org/10.1080/10420150.2022.2039927https://hdl.handle.net/20.500.12899/709Radiation dosimeters are used to measure the absorbed radiation dose of any living organism during the time intervals. They include defective crystals that store radiation until they are stimulated. Thermoluminescence (TL) is a way to see the absorbed dose of the dosimeters. The irradiated crystal is heated up to 500°C to reveal the absorbed dose as a luminescence light. The TL dosimetric properties of natural halite (rock-salt) crystals extracted from Meke crater lake in Konya, Turkey, were investigated in this study. Support Vector Machine (SVM), Artificial Neural Network (ANN) and K-Nearest Neighbor (K-NN) were also examined utilizing machine learning for categorization of TL characteristics. According to the experimental output, the TL glow curve has two main peaks located at 100 and 270°C with good dosimetric properties. In the three classifiers, SVM has the biggest accuracy and precision. High training-low testing and results from normalized data give the best accuracy, precision, sensitivity and F-score.eninfo:eu-repo/semantics/openAccessHaliteThermoluminescenceMachine learningPreprint10.1080/10420150.2022.20399271122-s2.0-85125469506Q3WOS:000758633600001Q4