An extension of the FURIA classification algorithm to low quality data through fuzzy rankings and its application to the early diagnosis of dyslexia

An early detection and reeducation of dyslexic children is critical for their integration in the classroom. Parents and instructors can help the psychologist to detect potential cases of dyslexia before the children׳s writing age. Artificial intelligence tools can also assist in this task. Dyslexia symptoms are detected with tests whose results may be vague or ambiguous, thus machine learning techniques for low quality data are advised. In particular, in this paper it is suggested that a new extension to vague datasets of the classification algorithm FURIA (Fuzzy Unordered Rule Induction Algorithm) has advantages over other approaches in both the computational effort during the learning stage and the linguistic quality of the induced classification rules. The new approach is benchmarked with different test problems and compared to other artificial intelligence tools for dyslexia diagnosis in the literature.