| Project/Area Number |
17K00373
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Kansei informatics
|
|---|
| Research Institution | Muroran Institute of Technology |
|---|
Principal Investigator |
Okada Yoshifumi 室蘭工業大学, 大学院工学研究科, 准教授 (00443177)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 心電図 / 連鎖パタンマイニング / 畳み込みニューラルネットワーク / 2D-CNN / 心室期外収縮 / 連鎖パタン / 異常検出 / 系列パタンマイニング |
|---|
| Outline of Final Research Achievements |
The aim of this study was to develop a linkage pattern mining method for automatically detecting abnormal waveform region in ECG data. First, the existing linkage pattern mining method was improved to a faster and more accurate method. In an experiment of applying a program implementing the improved method to real ECG data, it was shown that normal/abnormal ECG regions were partitioned adequately and displayed visually. Furthermore, it was presented that the normal/abnormal ECG waveforms can be available as an effective training dataset in classification model construction based on machine learning.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究で開発した技術は，医療現場のスタッフが心電図を用いて心疾患を迅速に診断するための有効な支援ツールとなりえる．また，既存の機械学習を用いた心電図解析では正常／異常の訓練データは手作業で収集されており，この作業には専門的な知識と多大な時間が必要とされていた．一方，本研究で開発した技術は，正常／異常な心電図波形を自動で高速に特定できるため，今後の心電図解析研究を大きく加速・進展できると期待される．
|
