Title:	A proposal of anomaly detection method based on natural data augmentation in the Eigenspace
Authors:	Murakami, Naoki Hiramatsu, Naoto Kobayashi, Hiroki Akizuki, Shuichi Hashimoto, Manabu
Citation:	Journal of WSCG. 2024, vol. 32, no. 1-2, p. 91-100.
Issue Date:	2024
Publisher:	Václav Skala - UNION Agency
Document type:	článek article
URI:	http://hdl.handle.net/11025/57348
ISSN:	1213 – 6972 1213 – 6980 (CD-ROM) 1213 – 6964 (on-line)
Keywords:	detekce anomálií;strojové učení;generování obrazu;augmentace dat;analýza hlavních komponent;vlastní prostor
Keywords in different language:	anomaly detection;machine learning;image generation;data augmentation;principal component analysis;eigenspace
Abstract in different language:	This paper proposes a natural data augmentation method and an anomaly removal artificial neural network for accurate anomaly detection. Anomaly detection is important because the provision of high-quality products is vital in the manufacturing industry. However, it is difficult to obtain a sufficient number of anomaly samples for the detection, which represents a significant challenge when it comes to achieving accurate anomaly detection by machine learning. General data augmentation methods generate new anomaly images by combining normal images and anomaly images. As an alternative, this paper describes a method that generates new anomaly images by using the Eigenspace. More natural anomaly images are generated than with general data augmentation methods. This paper also proposes an anomaly removal neural network that utilizes this natural data augmentation. The results of an anomaly detection experiment showed that the AUC of 94.7% was achieved for the capsule dataset when using anomaly images generated by the proposed data augmentation for training the anomaly removal neural network. This is 1.3% higher than the state-of-the-art data augmentation method that has been utilized for training the neural network. In the case of the pill dataset, AUC of 99.4% was achieved by proposed method. This is 3.0% higher than the state-of-the-art data augmentation method that has been utilized for training the neural network. The results of a series of experiments demonstrated that anomaly images generated by the proposed data augmentation are effective for training the neural network.
Rights:	© Václav Skala - UNION Agency © Václav Skala - UNION Agency
Appears in Collections:	Volume 32, number 1-2 (2024)

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.