An Intelligent Cognition Method of Human Health States Based on a Variant Knowledge Granularity Feedback Mechanism

Abstract

Human health has become a social and personal focus. Targeting the problems of the heterogeneity and randomness of crowd samples, diversity of health features and randomness of health feature values, an intelligent cognition method of human health states based on a variant knowledge granularity feedback mechanism is explored in this paper to imitate the human cognition process with repeated comparison and inference, and evaluate the human health state quickly and accurately. First, an intelligent cognition model of human health states with interconnection between the granularity decision layer, training layer, and cognition layer is proposed, and the corresponding variant knowledge granularity feedback mechanism is established. Second, based on bag of words, latent semantic analysis, and entropy, the estimated index of uncertain health states and the regulative index of knowledge granularity are constructed. Third, based on the proposed model and indexes, the optimal feedback cognition of human health states with variant knowledge granularity is achieved in the sense of pattern classification. Finally, for the collected bioelectrical impedance signals of random crowd samples, the simulated experiment has been carried out to validate the proposed method. Experimental results indicate that our method can effectively improve the accuracy of human health states compared with the existing open-loop methods.