Title:
ABNORMAL SOUND DETECTING DEVICE, ABNORMALITY MODEL LEARNING DEVICE, ABNORMALITY DETECTING DEVICE, ABNORMAL SOUND DETECTING METHOD, ABNORMAL SOUND GENERATING DEVICE, ABNORMAL DATA GENERATING DEVICE, ABNORMAL SOUND GENERATING METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2019/049688
Kind Code:
A1
Abstract:
The objective of the present invention is to improve accuracy of unsupervised abnormal sound detection using a small number of items of abnormal sound data. A threshold setting unit (13) uses a normal model that has learned using normal sound data, and an abnormal model representing abnormal sound data to calculate a degree of abnormality for each of a plurality of items of abnormal sound data, and sets the minimum value thereof as a threshold. A weighting updating unit (14) uses a plurality of items of normal sound data, the abnormal sound data and the threshold to update weightings in the abnormal model such that all the abnormal sound data are determined to be abnormal and the probability that normal sound data are determined to be abnormal is minimized.
Inventors:
KOIZUMI YUMA (JP)
KAWACHI YUTA (JP)
HARADA NOBORU (JP)
SAITO SHOICHIRO (JP)
NAKAGAWA AKIRA (JP)
MURATA SHIN (JP)
KAWACHI YUTA (JP)
HARADA NOBORU (JP)
SAITO SHOICHIRO (JP)
NAKAGAWA AKIRA (JP)
MURATA SHIN (JP)
Application Number:
PCT/JP2018/031345
Publication Date:
March 14, 2019
Filing Date:
August 24, 2018
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G01M99/00; G05B23/02; G06N99/00
Foreign References:
| JPH0972596A | 1997-03-18 | |||
| JP2017062713A | 2017-03-30 | |||
| JP2010092266A | 2010-04-22 | |||
| US20150219530A1 | 2015-08-06 | |||
| US20160300126A1 | 2016-10-13 |
Other References:
NAMBA, MUNEHIRO: "On the quality inspection of motors by detecting abnormal noise", 22 August 2007 (2007-08-22), pages 243 - 244, XP009519284, Retrieved from the Internet
17 March 2017, article KOIZUMI, YUUMA ET AL.: "Detection of abnormal sound of equi0nent operation sound using depth learning", pages: 473 - 476, XP009519285
KOIZUMI, YUUMA ET AL.: "2-7-5 Automatic design of acoustic features for detecting abnormal sounds in machine operation sounds", PROCEEDINGS OF THE ACOUSTICAL SOCIETY OF JAPAN MEETING, THE ACOUSTICAL SOCIETY OF JAPAN, 1880-7658, vol. 2016, 31 August 2016 (2016-08-31) - 16 September 2016 (2016-09-16), 1880-7658, pages 365 - 368, XP009515527
TSUYOSHI IDEMASASHI SUGIYAMA: "Anomaly Detection and Change Detection", 2015, KODANSHA, pages: 6 - 7
A. P. BRADLEY: "The Use of the Area Under the ROC Curve in the Evaluation of Machine Learning Algorithms", PATTERN RECOGNITION, 1996, pages 1145 - 1159
Y. KOIZUMI ET AL.: "Optimizing Acoustic Feature Extractor for Anomalous Sound Detection Based on Neyman-Pearson Lemma", EUSIPCO, 2017
See also references of EP 3680639A4
17 March 2017, article KOIZUMI, YUUMA ET AL.: "Detection of abnormal sound of equi0nent operation sound using depth learning", pages: 473 - 476, XP009519285
KOIZUMI, YUUMA ET AL.: "2-7-5 Automatic design of acoustic features for detecting abnormal sounds in machine operation sounds", PROCEEDINGS OF THE ACOUSTICAL SOCIETY OF JAPAN MEETING, THE ACOUSTICAL SOCIETY OF JAPAN, 1880-7658, vol. 2016, 31 August 2016 (2016-08-31) - 16 September 2016 (2016-09-16), 1880-7658, pages 365 - 368, XP009515527
TSUYOSHI IDEMASASHI SUGIYAMA: "Anomaly Detection and Change Detection", 2015, KODANSHA, pages: 6 - 7
A. P. BRADLEY: "The Use of the Area Under the ROC Curve in the Evaluation of Machine Learning Algorithms", PATTERN RECOGNITION, 1996, pages 1145 - 1159
Y. KOIZUMI ET AL.: "Optimizing Acoustic Feature Extractor for Anomalous Sound Detection Based on Neyman-Pearson Lemma", EUSIPCO, 2017
See also references of EP 3680639A4
Attorney, Agent or Firm:
NAKAO, Naoki et al. (JP)
Download PDF: