Kansei evaluation and smart control of individual environment based on human sensing

2017 Fiscal Year Final Research Report

• Project/Area Number: 26330189
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: Yokohama National University
• Principal Investigator: Sugimoto Chika 横浜国立大学, 未来情報通信医療社会基盤センター, 特任教員(准教授) (40447347)
• Research Collaborator: YAMASUE Kotaro 横浜市立大学, 医学研究科, 特任講師 ; SUDO Takashi 株式会社東芝
• Project Period (FY): 2014-04-01 – 2018-03-31
• Keywords: ヒューマンセンシング / 識別モデル / 機械学習 / 特徴量 / 状態認識

Outline of Final Research Achievements

We proposed the method to estimate internal states such as human emotion and comfort using vital data and motion data in an objective way. The novel state recognition models, which depend on the state target and condition for sensing, were developed based on SVM, RF, NN, CNN, or VAE examining appropriate feature selection methods and discriminators. Moreover, human smart sensing system was developed to appropriately provide the feedback based on the individual state. The state estimation accuracy was evaluated while taking a rest, watching videos, studying or working at an office. As a result, the availability was shown under daily environments which have changes in the thermal, light, and sound conditions.

Free Research Field

生体計測工学