Study of Improving Accuracy of MIMOSYS by Bayesian Inference.

DOI
  • Takano Takeshi
    Mathematical Engineering of Morality Emotions, Dept. of Bioengneering, Graduate School of Engineering, The University of Tokyo PST Inc.
  • Shinohara Shuji
    Mathematical Engineering of Morality Emotions, Dept. of Bioengneering, Graduate School of Engineering, The University of Tokyo
  • Mitsuyoshi Shunji
    Mathematical Engineering of Morality Emotions, Dept. of Bioengneering, Graduate School of Engineering, The University of Tokyo
  • Omiya Yasuhiro
    PST Inc.
  • Higuchi Masakazu
    Voice analysis and measurement of pathophysiology, Department of Bioengineer ing, Graduate School of Engineering, The University of Tokyo
  • Nakamura Mitsuteru
    Department of Pharmacology, School of Medicine, The University of Texas Health Science Center at San Antonio, Texas, USA
  • Saito Taku
    Department of Psychiatry, National Defense Medical College
  • Yoshino Aihide
    Department of Psychiatry, National Defense Medical College
  • Toda Hiroyuki
    Department of Psychiatry, National Defense Medical College
  • Tokuno Shinichi
    Voice analysis and measurement of pathophysiology, Department of Bioengineer ing, Graduate School of Engineering, The University of Tokyo School of Health Innovation, Kanagawa University of Human Services

Bibliographic Information

Other Title
  • ベイズ推定を用いたMIMOSYSの精度改善の検討

Abstract

<p>In today's stressful age, early detection of mental health problems is an issue. We have developed MIMOSYS (Mind Monitoring System), which estimates a human's mental health condition by voice. This technology has the advantage of being noninvasive and easy to measure. On the other hand, MIMOSYS has a property that specificity of mental health index is low with short term speech data. In this study, we collected speech data of patients with major depressive disorder, found the likelihood distribution of Vitality of mild and severe individuals, calculated the posterior probability using Bayes' theorem from Vitality which obtained from the subject's utterance and estimated patients' severity. As a result, we confirmed that the separation performance improves more than Vitality itself. This result shows that it is possible to estimate mental health conditions with high precision from short term MIMOSYS data.</p>

Journal

Details 詳細情報について

  • CRID
    1390848250134349568
  • NII Article ID
    130007884976
  • DOI
    10.11239/jsmbe.annual58.230
  • ISSN
    18814379
    1347443X
  • Text Lang
    ja
  • Data Source
    • JaLC
    • CiNii Articles
  • Abstract License Flag
    Disallowed

Report a problem

Back to top