Time series datamining based on causal relationship combining statistics model and physical model
Project/Area Number |
17K00161
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Multimedia database
|
Research Institution | Tokai University |
Principal Investigator |
|
Project Period (FY) |
2017-04-01 – 2020-03-31
|
Project Status |
Completed (Fiscal Year 2019)
|
Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2017: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
|
Keywords | マルチメディア・データベース / ビッグデータ分析・活用 / 時系列データマイニング / Prognostics / Time series motif / Predicative maintenance / ビックデータの分析・活用 / 機械学習 / IoT / 信頼性工学 / 異常検知 / 故障診断 / 寿命予測 / ビックデータ分析・活用 |
Outline of Final Research Achievements |
As IoT (Internet of Things) and BigData have been emerging, a variety of datamining technologies have been applied to predictive maintenance of equipment and facility. While these technologies are greatly successful in pattern recognition and social data analysis, they are less successful in predictive maintenance. One of the reasons is that existing machine learning methods cannot handle well unsupervised learning for detecting gradually changing states of industry systems. Therefore I proposed "time series chain extraction for detecting the gradually changing patterns" and "fast parameter-free feature extraction of magnitudes of spikes in time series" I also verified the effectiveness of our proposed methods on real industry data.
|
Academic Significance and Societal Importance of the Research Achievements |
四次産業革命やSociety 5.0を実現するために, IoT(Internet of Things)普及に伴って飛躍的に増加するセンサーデータを分析する機番技術を確立する
|
Report
(2 results)
Research Products
(6 results)