Transactions of the Institute of Systems, Control and Information Engineers
Online ISSN : 2185-811X
Print ISSN : 1342-5668
ISSN-L : 1342-5668
Volume 30, Issue 7
Displaying 1-4 of 4 articles from this issue
  • Takenori Obo, Toshiyuki Sawayama, Takuya Sawayama, Naoyuki Kubota
    2017 Volume 30 Issue 7 Pages 263-272
    Published: July 15, 2017
    Released on J-STAGE: October 15, 2017

    The number of drowning incident at home has been increasing steadily over time. The most common cause of the incidents is a situation that produces hemodynamic compromise during bathing. It can heighten the risk of causing a stroke, myocardial infarction, and loss of consciousness. This paper presents an inovative ultrasensitive vibration sensor for detecting viral sign that can measure micro vibration transmitted through a bathtub. Moreover, we propose a neuro-fuzzy system to extract hearbeat and estimate human states during bathing. In the experimental result, we discuss the effectiveness of the proposed system in terms of measuring precision, comparing with a pulse rate meter.

    Download PDF (3488K)
  • Masaya Nakata, Tomoki Hamagami
    2017 Volume 30 Issue 7 Pages 273-285
    Published: July 15, 2017
    Released on J-STAGE: October 15, 2017

    The XCSAM classifier system is an approach of evolutionary rule-based machine learning, which evolves rules advocating the highest-return actions at state, resulting in best classification. This paper starts with claiming a limitation that XCSAM still fails to evolutionary generate adequate rules advocating the highest-return actions. Then, under our hypothesis that this limitation is caused from the rule-deletion mechanism of XCSAM, we revisit its rule-deletion strategy in order to promote the evolution of adequate rules. Different from the existing deletion strategy which deletes two rules for each rule-evolution, our deletion strategy is modified to delete more than two rules as necessary. Experimental results on a benchmark classification task validate our modification powerfully works to evolve adequate rules, improving the performance of XCSAM. We further show our modification robustly enables XCSAM to perform well on real world classification task.

    Download PDF (1696K)
  • ―Minimal Compartments of Triglycerides and Non-esterified Fatty Acids
    Claudia Cecilia Yamamoto Noguchi, Eiko Furutani
    2017 Volume 30 Issue 7 Pages 286-292
    Published: July 15, 2017
    Released on J-STAGE: October 15, 2017

    In keeping with the recent recognition of the additive impact of dietary fat on postprandial blood glucose (BG) levels in type 1 diabetes mellitus (T1DM), we include a number of physiologically-relevant improvements to a previous conceptual minimal mixed meal model by considering independent signals for gut transit of carbohydrates and dietary fat, and explicit representation of fatty acid spillover in the compartmental representation of non-esterified fatty acids (NEFA) to represent lipid-derived insulin resistance as the complementary increase in triglycerides (TG) and NEFA levels. Simulation results of postprandial plasma lipids and BG excursion compared with clinical data in the literature demonstrate the validity and potential of the minimal mixed meal model proposed.

    Download PDF (854K)
Short Paper