2020 Fiscal Year Final Research Report
Establishment of the new polygraph testing method using brain activity data with fNIRS
Project/Area Number |
19K23389
|
Research Category |
Grant-in-Aid for Research Activity Start-up
|
Allocation Type | Multi-year Fund |
Review Section |
0110:Psychology and related fields
|
Research Institution | Chuo University |
Principal Investigator |
|
Project Period (FY) |
2019-08-30 – 2021-03-31
|
Keywords | fNIRS / 自律神経系反応 / 虚偽検出 / 隠匿情報検査 / 捜査心理学 / 機会学習 |
Outline of Final Research Achievements |
The concealed information test (CIT) with autonomic responses has been conducted in criminal investigations in Japan. The aims of this study are to establish the evaluation methods for results in the concealed information test (CIT) and to search for response patterns specific to the participants in guilty group, who committed a mock crime. As a first step toward this goal, an experimental system to simultaneously measure autonomic responses and cerebral hemodynamic response were constructed. Then, this study confirmed that both autonomic responses and cerebral hemodynamic response showed different patterns between those who performed the mock crime and those who did not. This study also examined the applicability of machine learning for discrimination between guilty and innocent participants at the individual level based on such response patterns. As a result, machine learning could discriminate with about 90% accuracy.
|
Free Research Field |
心理学
|
Academic Significance and Societal Importance of the Research Achievements |
日本における隠匿情報検査(CIT)は,理論的基盤が確立され,科学的妥当性を持った犯罪捜査手法であると世界的に高い評価を受けている。現在は学術的文脈のみならず捜査現場の実施においても,標準的な検査結果の評価手法の確立が求められている。本研究では,現行のCITにおいて使用される自律神経系反応を脳血流動態反応と時間同期して計測することができることを示し,事件の犯人が自分に不利な情報を秘匿する際に生じる反応を認知神経科学的視点で説明することを可能にした。また,自律神経系反応と脳血流動態反応の両面からの標準的な結果の評価方法の確立に向けて,機械学習を利用した個人レベルでの判別可能性も示すことができた。
|