“…In its development phase, the framework was used and tested on several toy datasets, including (but not limited to) iris, wine, breast cancer, and MNIST. However, it was designed with the goal of being applied in the field of affective computing, mainly on multimodal data for the emotion and depression classification tasks [10,11,21]. Thus, some utilities were left in the published source code to address these tasks, although they do not alter the genericity of the algorithm.…”