| Project/Area Number |
15K12112
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Soft computing
|
|---|
| Research Institution | Advanced Telecommunications Research Institute International |
|---|
Principal Investigator |
KAWANABE Motoaki 株式会社国際電気通信基礎技術研究所, 脳情報通信総合研究所, 主幹研究員 (30272389)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
兼村 厚範 国立研究開発法人産業技術総合研究所, 人間情報研究部門, 研究員 (50580297)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
KANAI Ryota 株式会社アラヤ・ブレイン・イメージング, 代表取締役兼Chief Scientist (80607177)
|
|---|
| Project Period (FY) |
2015-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2016: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2015: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | 確率的情報処理 / ライフログ / 異種データの統合解析 / 確率的情報書類 |
|---|
| Outline of Final Research Achievements |
We developed machine learning techniques to infer continuously personality traits and psychological measures useful for mental/physical health based on heterogeneous data from multiple sources in real environments. As factors affecting on heath status, we focused on attention levels and behavioural patterns. For the former, we measured simultaneously EEG and biomedical signals from several subjects during an auditory sustained attention response task (SART), and extracted features related to attention levels such as ECG R-R intervals. For the latter, we developed a tensor decomposition method to infer behavioural patterns efficiently from mobility traces. Furthermore, in order to make full use of heterogeneous multi-sensor data with complex missing patterns, we proposed completion methods of missing observations based on matrix factorisation or AR models, and improvements of propensity score estimation with deep neural networks.
|
