Multiple-Criteria Decision-Making Based on Probabilistic Estimation with Contextual Information for Physiological Signal Monitoring

We propose a multiple-criteria decision-making (MCDM) method based on Maximum A Posteriori (MAP) estimation to analyze users’ physiological status either normal or abnormal. The decision-making problem is formulated using MAP estimation and is turned out to be MCDM problem given the assumption that all probability density functions (pdfs) follow exponential forms, especially Gaussian. It indicates that this MCDM equation is decomposed into direct sum of group’s physiological status distribution. Group distribution is estimated by probabilistic approach using population from the same age or same sex. For verification, we applied the proposed method to public heart rate database. According to experimental results, the proposed method considering group context reduced overall classification errors by 20.42% compared to typical decision-making (TDM) method. This method is applicable to various personalized health monitoring applications, which estimates user’s physiological status by referring other group distribution without prior knowledge about previous health records.