Challenge on estimation of pleasantness for wind based on brain decoding using machine learning

2023 Fiscal Year Final Research Report

• Project/Area Number: 22K18842
• Research Category: Grant-in-Aid for Challenging Research (Exploratory)
• Allocation Type: Multi-year Fund
• Review Section: Medium-sized Section 23:Architecture, building engineering, and related fields
• Research Institution: Tokyo Institute of Technology
• Principal Investigator: Okaze Tsubasa 東京工業大学, 環境・社会理工学院, 准教授 (40709739)
• Co-Investigator(Kenkyū-buntansha): 吉村 奈津江 東京工業大学, 情報理工学院, 教授 (00581315) ; 丸山 裕恒 東京工業大学, 科学技術創成研究院, 特任助教 (50913258) ; 玄 英麗 東京工芸大学, 工学部, 助教 (20770564)
• Project Period (FY): 2022-06-30 – 2024-03-31
• Keywords: 脳波 / 風環境 / 心地よさ感 / 機械学習 / 信号源推定 / 人工気候室実験 / 屋外実験 / 独立成分分析

Outline of Final Research Achievements

This study aims to estimate the pleasantness of wind under thermoneutral conditions based on machine learning. The analyzed brain wave was collected through an experiment performed in an artificial climate chamber and an outdoor field measurement. After removing noise from measured brain wave in the chamber experiment, the power spectral density in each brain region were calculated. The power values of the four frequency bands in all regions were used as the features for the classification analysis using machine learning. This study we applied support vector machine (SVM) as the classifier. The mean classification accuracy was 55.2%. Further discussion of applicability of SVM established using the data in the chamber experiment to that in outdoor measurement is expected.

Free Research Field

建築環境工学

Academic Significance and Societal Importance of the Research Achievements

従来の在室者の主観評価とは異なる、脳波という数値情報に基づき、最善の気流環境を推定できるなど、建築空間の気流制御を抜本的に変える可能性がある。コミュニケーションを介さず、対象者の快適感を脳活動から判定し気流の制御ができる可能性は、新たなヒューマンインタフェースの創出などにもつながり、誰もが快適に感じる風環境の実現に貢献できる。また、風という物理的刺激を用いるため、従来の動画視聴などによる感情誘発法とは異なり記憶や先入観に左右されない感情が誘発される可能性があり、感情推定精度向上のブレイクスルーともなり得る。