| Project/Area Number |
16K00182
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Information security
|
|---|
| Research Institution | Nagaoka National College of Technology |
|---|
Principal Investigator |
YANO SHOUHEI 長岡工業高等専門学校, 電気電子システム工学科, 准教授 (90332006)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
南部 功夫 長岡技術科学大学, 工学研究科, 准教授 (40553235)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2016: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
|
|---|
| Keywords | バイオメトリクス / 耳音響認証 / 機械学習 / 等誤り率 / インパルス応答 / 外耳道形状 / 温度補完法 / ペアワイズ法 / バイオメトリクス認証 / 外耳道音響特性 / マルチエンロールメント / 観測揺らぎ |
|---|
| Outline of Final Research Achievements |
We have proposed an innovative authentication method that uses the acoustic characteristics of the ear canal for constant authentication.In this research, we examined a robust sound signal observation method and a method to calculate sound features with high authentication system.We proposed and examined the frequency error diffusion method.As a result, it has been possible to propose a method for improving the discrimination accuracy even if the noise level is equal due to the degradation of the discrimination accuracy together with the error and the error frequency diffusion method.In addition, with the aim of establishing acoustic feature calculation means with high authentication accuracy, we examined an optimal feature quantity design method from biometrics information obtained from both ears.As a result, we verified experimentally and theoretically that the method of linking time series data is effective.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究では急成長が予測されるバイオメトリクス市場に注目した技術開発を実施した。本研究は従来のバイオメトリクス認証の問題点を解決し、ネット社会におけるトラストを確立することが可能な画期的なバイオメトリクス認証である。イノベーションを引き起こす可能性が高く、社会的に大きな意義のある研究である。
|
