Photoplethysmography (PPG) has shown to be a simple noninvasive tool for cardiac function assessment and is applied to detect mental disorders. However, it is still challenging to model PPG signal that can be helpful in mental disease classification. The current study aims to establish an approach for modeling the plethysmograms using hidden Markov model (HMM). PPG waveforms were measured from mentally ill patients and healthy individuals. Patients were diagnosed as varied mental disorders including depression, bipolar disorder, schizophrenia, social phobia, etc. Linear predictive coding (LPC) and sample entropy (SampEn) were used to extract features from the PPG waves. Vector quantization (VQ) method was applied to convert extracted features to prototype vectors, and the output indices were utilized to estimate parameters for HMMs. In results, the proposed HMMs succeeded in recognition of individuals who have mental disorders which indicate the ability of the proposed modeling for disease recognition. © Springer-Verlag Berlin Heidelberg 2014.
CITATION STYLE
Chen, Y., Oyama-Higa, M., & Pham, T. D. (2014). Identification of Mental Disorders by Hidden Markov Modeling of Photoplethysmograms. In Communications in Computer and Information Science (Vol. 404 CCIS, pp. 29–39). Springer Verlag. https://doi.org/10.1007/978-3-642-54121-6_3
Mendeley helps you to discover research relevant for your work.