Application of a semi-supervised technique for identifying unstable mine slopes

This paper aims to apply a semi-supervised technique to study the stability of mine slopes, aiding in the identification of those with potential failure risks. Semi-supervised techniques are valuable when not all information about the data is known. To achieve this objective, biased random key genetic algorithm was employed to solve the constrained clustering problem. The solution to this problem involves grouping slopes based on similar characteristics while adhering to specified constraints. The obtained results demonstrate the effectiveness of the proposed technique in slope grouping.