Multimodal Belief Integration by HMM/SVM-Embedded Bayesian Network: Applications to Ambulating PC Operation by Body Motions and Brain Signals

@inproceedings{Matsuyama2009MultimodalBI,
  title={Multimodal Belief Integration by HMM/SVM-Embedded Bayesian Network: Applications to Ambulating PC Operation by Body Motions and Brain Signals},
  author={Y. Matsuyama and Fumiya Matsushima and Youichi Nishida and T. Hatakeyama and Nimiko Ochiai and Shogo Aida},
  booktitle={ICANN},
  year={2009}
}
  • Y. Matsuyama, Fumiya Matsushima, +3 authors Shogo Aida
  • Published in ICANN 2009
  • Computer Science
  • Methods to integrate multimodal beliefs by Bayesian Networks (BNs) comprising Hidden Markov Models (HMMs) and Support Vector Machines (SVMs) are presented. The integrated system is applied to the operation of ambulating PCs (biped humanoids) across the network. New features in this paper are twofold. First, the HMM/SVM-embedded BN for the multimodal belief integration is newly presented. Its subsystem also has a new structure such as a committee SVM array. Another new fearure is with the… CONTINUE READING
    4 Citations
    Brain signal's low-frequency fits the continuous authentication
    • 15
    • Highly Influenced
    Brain Signal Based Continuous Authentication: Functional NIRS Approach
    Advances in Computational Intelligence
    • Highly Influenced
    • PDF

    References

    SHOWING 1-8 OF 8 REFERENCES
    Artificial Intelligence: A Modern Approach
    • 24,559
    • PDF
    A note on stochastic modeling of shunting inhibition
    • 7
    Pattern Recognition and Machine Learning
    • 9,099
    • PDF
    On some properties of stochastic information processes in neurons and neuron populations
    • 13
    The Nature of Statistical Learning Theory
    • V. N. Vapnik
    • Mathematics, Political Science
    • Statistics for Engineering and Information Science
    • 2000
    • 36,550
    Recognition of Multi-Font Printed Chinese Characters
    • 36