Dynamical system classification with diffusion embedding for ECG-based person identification
详细信息 查看全文
- 作者：Jeremias Sulama ; jsulam@cs.technion.ac.il" class="auth_mail" title="E-mail the corresponding author ; Yaniv Romanob ; Ronen Talmonb
- 关键词：Classification ; Manifold learning ; Person identification ; ECG
- 刊名：Signal Processing
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：130
- 期：Complete
- 页码：403-411
- 全文大小：1338 K
文摘
- class="listitem" id="list_li0005">
- class="label">•
A novel signal classification method for dynamical systems is proposed.
- class="label">•
Diffusion Maps is applied on stable representations of sensor observations.
- class="label">•
Three variations are proposed, with different motivations and implications.
- class="label">•
Person identification from ECG signals is studied on a free available database.
- class="label">•
Our method achieves the highest reported accuracy on this dataset.