Drug usage duration classification using Extreme Learning Machine based on personality features

Determining the duration of drug consumption is essential for the success of treatment for drug abuse since the effectivity of such a program depends on the duration of the treatment. One promising set of features to identify the duration of drug consumption is personality features called Revised NEO Personality Inventory (NEO PI-R). In this paper, the Extreme Learning Machine model is employed to perform the classification. The model is trained and tested using 10- fold mechanism to verify the effectivity of the classification. The accuracy of the classifier differs, depending on the type of drug, with the maximum accuracy of 86.31% and the minimum one of 36.65%.