Context recognition based on behavior analysis of touch operation and its application

2017 Fiscal Year Final Research Report

• Project/Area Number: 26700007
• Research Category: Grant-in-Aid for Young Scientists (A)
• Allocation Type: Partial Multi-year Fund
• Research Field: Information network
• Research Institution: Nara Institute of Science and Technology
• Principal Investigator: Arakawa Yutaka 奈良先端科学技術大学院大学, 情報科学研究科, 准教授 (30424203)
• Project Period (FY): 2014-04-01 – 2018-03-31
• Keywords: 行動認識 / コンテキスト認識 / タッチ操作 / スマートフォン

Outline of Final Research Achievements

This research aims to recognize the user context by using a smartphone. We proposed to utilize a touch panel, which is generally an input/output device, as a sensor for recognizing the context of the user from behaviors appearing in the touch operation. First of all, we developed a system called Touch Analyzer that can capture all the touch operation of any applications on a smartphone and showed that it could be acquired with nearly 100% precision. Then, we proposed an algorithm for identifying the holding style of users. Ultimately, we showed that if the length information of the user's finger is known, eight holding styles can be identified with an accuracy of 96.5%.

Free Research Field

ユビキタスコンピューティング