Machine learning for clustering of cognitive characteristics

2021 Fiscal Year Final Research Report

• Project/Area Number: 20K22273
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Multi-year Fund
• Review Section: 0110:Psychology and related fields
• Research Institution: Waseda University
• Principal Investigator: Miyazaki Atsushi 早稲田大学, グローバルエデュケーションセンター, 助教 (40880323)
• Project Period (FY): 2020-09-11 – 2022-03-31
• Keywords: 認知機能 / 個人差 / 機械学習 / 機能的MRI

Outline of Final Research Achievements

This study aimed to understand human cognitive characteristics from the large-scale brain and behavioral data. Therefore, multiple cognitive tasks were clustered. As a result, the clusters were classified into three cognitive characteristics. Furthermore, brain activity during multiple cognitive tasks using functional MRI showed that these clusters had significant differences in activity in the lateral prefrontal cortex, medial prefrontal cortex, anterior insular cortex, and parietal cortex. These results suggest that these regions play an important role in cognitive control.

Free Research Field

認知脳科学

Academic Significance and Societal Importance of the Research Achievements

本研究では、近年発展を遂げてきている人工知能やビッグデータ、脳画像解析技術の研究を統合的に捉えることで、従来の研究では難しかった複数の脳機能画像と認知機能の統合的分析が可能となった。本研究によって得られた成果は、個人の認知機能の特性を把握し、脳の変化の予兆を捉えるための重要な知見となり得る．今後，医療や教育，他にも車の運転などの日常的な社会課題における応用に期待される．