Title:
LEARNING-TYPE SIGNAL SEPARATION METHOD AND LEARNING-TYPE SIGNAL SEPARATION DEVICE
Document Type and Number:
WIPO Patent Application WO/2018/199031
Kind Code:
A1
Abstract:
A learning-type signal separation method wherein a model formulation unit is used to carry out a learning process on the basis of a training signal that contains a specific component and a training signal that does not contain the specific component, said training signals including a common characteristic. In this learning-type signal separation method, the model formulation unit is made to carry out a learning process in which there is generated a signal of a data sequence obtained by separating and removing the specific component from the data sequence of the training signal on the basis of the training signal and information indicating whether the specific component is contained in the training signal, thereby generating learned data; an arbitrary signal containing the common characteristic is obtained; and there is generated a signal of a data sequence obtained by separating and removing the specific component from the data sequence of the acquired arbitrary signal on the basis of the arbitrary signal and the learned data that has been generated.
Inventors:
KURASAWA HISASHI (JP)
OGASAWARA TAKAYUKI (JP)
YAMAGUCHI MASUMI (JP)
TSUKADA SHINGO (JP)
NAKASHIMA HIROSHI (JP)
HATA TAKAHIRO (JP)
MATSUURA NOBUHIKO (JP)
OGASAWARA TAKAYUKI (JP)
YAMAGUCHI MASUMI (JP)
TSUKADA SHINGO (JP)
NAKASHIMA HIROSHI (JP)
HATA TAKAHIRO (JP)
MATSUURA NOBUHIKO (JP)
Application Number:
PCT/JP2018/016472
Publication Date:
November 01, 2018
Filing Date:
April 23, 2018
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G06N99/00; A61B5/0452
Domestic Patent References:
| WO2017027856A1 | 2017-02-16 |
Foreign References:
| JP2007189589A | 2007-07-26 | |||
| JP2015031889A | 2015-02-16 | |||
| JP2017088717A | 2017-05-25 |
Other References:
GOODFELLOW, I. J. ET AL.: "Generative adversarial nets", THE NEURAL INFORMATION PROCESSING SYSTEMS FOUNDATION, PROCEEDINGS OF ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), 13 December 2014 (2014-12-13), pages 1 - 9, XP055468946, Retrieved from the Internet [retrieved on 20180621]
TAKAYUKI OGASAWARAKAZUYOSHI ONONOBUAKI MATSUURAMASUMI YAMAGUCHIJUNJI WATANABESHINGO TSUKADA: "Application of Wearable Electrode Inner Technology", NTT TECHNICAL JOURNAL, November 2014 (2014-11-01), pages 16 - 20
TAIGANG HEGARI CLIFFORDLIONEL TARASSENKO: "Application of independent component analysis in removing artefacts from the electrocardiogram", NEURAL COMPUT & APPLIC, 2006, pages 105 - 116, XP019381264, DOI: 10.1007/s00521-005-0013-y
MA MNEIMNEHEE YAZMT JOHNSONRJ POVINELLI: "An Adaptive Kalman Filter for Removing Baseline Wandering in ECG Signals", COMPUTERS IN CARDIOLOGY, vol. 33, 2006, pages 253 - 256, XP031248955
JUAN PABLO MARTINEZ ET AL.: "A Wavelet-Based ECG Delineator: Evaluation on Standard Databases", IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, vol. 51, no. 4, April 2004 (2004-04-01), pages 570 - 581, XP011109261, DOI: 10.1109/TBME.2003.821010
XIONG, PENG ET AL.: "ECG signal enhancement based on improved denoising auto-encoder", ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, vol. 52, 2016, pages 194 - 202, XP029530661, DOI: 10.1016/j.engappai.2016.02.015
See also references of EP 3605408A4
TAKAYUKI OGASAWARAKAZUYOSHI ONONOBUAKI MATSUURAMASUMI YAMAGUCHIJUNJI WATANABESHINGO TSUKADA: "Application of Wearable Electrode Inner Technology", NTT TECHNICAL JOURNAL, November 2014 (2014-11-01), pages 16 - 20
TAIGANG HEGARI CLIFFORDLIONEL TARASSENKO: "Application of independent component analysis in removing artefacts from the electrocardiogram", NEURAL COMPUT & APPLIC, 2006, pages 105 - 116, XP019381264, DOI: 10.1007/s00521-005-0013-y
MA MNEIMNEHEE YAZMT JOHNSONRJ POVINELLI: "An Adaptive Kalman Filter for Removing Baseline Wandering in ECG Signals", COMPUTERS IN CARDIOLOGY, vol. 33, 2006, pages 253 - 256, XP031248955
JUAN PABLO MARTINEZ ET AL.: "A Wavelet-Based ECG Delineator: Evaluation on Standard Databases", IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, vol. 51, no. 4, April 2004 (2004-04-01), pages 570 - 581, XP011109261, DOI: 10.1109/TBME.2003.821010
XIONG, PENG ET AL.: "ECG signal enhancement based on improved denoising auto-encoder", ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, vol. 52, 2016, pages 194 - 202, XP029530661, DOI: 10.1016/j.engappai.2016.02.015
See also references of EP 3605408A4
Attorney, Agent or Firm:
SHIGA INTERNATIONAL PATENT OFFICE (JP)
Download PDF:
Previous Patent: IMAGE PROCESSING DEVICE AND IMAGE FORMATION DEVICE
Next Patent: STRUCTURE-FRP MATERIAL BOND CONSTRUCTION AND BONDING METHOD
Next Patent: STRUCTURE-FRP MATERIAL BOND CONSTRUCTION AND BONDING METHOD