Infant pain detection with homomorphic filter and fuzzy k-NN classifier

Abstract

Newborn pain is a non-stationary made by babies in reaction to certain circumstances. This infant facial expression can be used to recognize physical or psychology condition of newborn. The goal of this study is to evaluate the performance of illumination levels for infant pain classification. Local Binary Pattern (LBP) features are computed at Fuzzy k-NN classifier. Eight different performance measurements such as Sensitivity, Specificity, Accuracy, Area under Curve (AUC), Cohen's kappa (k), Precession, F-Measure and Time Consumption are performed. Fuzzy k-NN classifier is employed to classify the newborn pain. The outcomes accentuated that the suggested features and classification algorithms can be employed to assist the medical professionals for diagnosing pathological condition of newborn pain.