Driver-less skill assessment and analysis using explainable AI

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K19769
• Research Category: Grant-in-Aid for Challenging Research (Exploratory)
• Allocation Type: Multi-year Fund
• Review Section: Medium-sized Section 60:Information science, computer engineering, and related fields
• Research Institution: Osaka University
• Principal Investigator: Maekawa Takuya 大阪大学, 大学院情報科学研究科, 准教授 (50447025)
• Project Period (FY): 2021-07-09 – 2024-03-31
• Keywords: 行動認識 / 行動分析 / ウェアラブルセンサ

Outline of Final Research Achievements

The ultimate goal of this study is to use AI to automatically uncover differences between works by skilled and unskilled workers and to have AI explain the meaning of those differences, and we have developed the basic technology and collected and published a data set to achieve this goal. Specifically, we tackled the following research themes in this study: automatic extraction of sensor data segments related to skills from work activity data; construction of a large-scale work activity dataset to enable work behavior analysis; work activity recognition method to enable basic analysis of work activities.

Free Research Field

ユビキタスコンピューティング

Academic Significance and Societal Importance of the Research Achievements

本研究で行った取り組みの一つとして、産業分野の行動認識・分析のための最大規模のデータセットであるOpenPackデータセットを構築し、公開を行った。作業の際の加速度データやスケルトンデータを収めた50時間以上にわたるデータセットであり、産業行動認識・分析研究の促進に大きな貢献を果たすことが期待される。上記を含む研究成果が当該分野の最難関国際会議であるUbicompやPercomに多数の論文が採択されるなど、顕著な成果を得た。