| Project/Area Number |
26750003
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Design science
|
|---|
| Research Institution | Kogakuin University |
|---|
Principal Investigator |
ZHANG JUE 工学院大学, 情報工学部, 講師 (90458993)
|
|---|
| Research Collaborator |
SASAO Kento
MATSUZAKI Kento
OGAWARA Riku
OGI Kazuki
|
|---|
| Project Period (FY) |
2014-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2014: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 歩きスマホ / アプリ開発 / 加速度センサー / インカメラ識別 / 顔角度認識 / GPS / ながら歩き / アプリケーション開発 / 加速度 / 顔認識 / カスケード分類器 |
|---|
| Outline of Final Research Achievements |
Texting while walking has become a social problem.Users’ behaviors are open to improvement by building potential user experiences (UXs) in which the system automatically detects the user’s behavior and issues a warning on their smartphone to remind them to stop.
We used a smartphone’s accelerometer, which can detect swinging and vibration during its use, to recognize normal walking conditions. Because acceleration-based determination provided insufficiently accurate detection, single-element trial applications were developed based on additional elements, such as walking speed (GPS) and the user’s gazing at the smartphone (face authentication) employing the built-in camera, with the aim of reducing false positives.
During walking experiments under various conditions, our multi-element decision-making application successfully determined whether or not a person was using their smartphone while walking,and reduced false positives at other times.
|
