Title:
DATA CLASSIFICATION DEVICE, DATA CLASSIFICATION METHOD, AND DATA CLASSIFICATION PROGRAM
Document Type and Number:
WIPO Patent Application WO/2021/199706
Kind Code:
A1
Abstract:
A data classification device according to the present invention comprises: a data acquisition unit which acquires data to be classified; a classification unit which classifies the data into one among a plurality of classes by using a trained model trained using a neural network; a similarity calculation unit which calculates the similarity between the data and the trained data used when generating the trained model; a determination unit which determines whether or not the data belongs to the plurality of classes on the basis of the similarity, and determines that the data belongs to an unknown class when the data does not belong to any of the plurality of classes.
Inventors:
MIZUTA SHINGO (JP)
IKEDA KEITA (JP)
IKEDA KEITA (JP)
Application Number:
PCT/JP2021/005080
Publication Date:
October 07, 2021
Filing Date:
February 10, 2021
Export Citation:
Assignee:
TORAY INDUSTRIES (JP)
International Classes:
G06N3/02; G06F16/55; G06F16/906; G06N20/00
Foreign References:
| JP2000207377A | 2000-07-28 | |||
| JP2001142868A | 2001-05-25 | |||
| JPH1074188A | 1998-03-17 | |||
| JP2019096313A | 2019-06-20 |
Other References:
KEISUKE SHIMA, JUNICHI IMAGI, HIDEAKI HAYASHI, TARO SHIBANOKI, YUICHI KURITA, TOSHIO TSUJI: "A Probabilistic Neural Network with Anomaly Detection and Related Application to an EMG-controlled Prosthetic Hand", JOURNAL OF THE ROBOTICS SOCIETY OF JAPAN, vol. 33, no. 4, 1 January 2015 (2015-01-01), pages 275 - 284, XP055946929, ISSN: 0289-1824, DOI: 10.7210/jrsj.33.275
URAKAWA YUNOSUKE : "Unknown Network Anomaly Detection Focused on Quantity of Payload Features", PROCEEDINGS OF THE COMPUTER SECURITY SYMPOSIUM 2018 (CSS2018), 22-25 OCTOBER 2018, vol. 2018, no. 2, 16 November 2018 (2018-11-16) - 25 October 2018 (2018-10-25), Japan, pages 1038 - 1045, XP009537910
URAKAWA YUNOSUKE : "Unknown Network Anomaly Detection Focused on Quantity of Payload Features", PROCEEDINGS OF THE COMPUTER SECURITY SYMPOSIUM 2018 (CSS2018), 22-25 OCTOBER 2018, vol. 2018, no. 2, 16 November 2018 (2018-11-16) - 25 October 2018 (2018-10-25), Japan, pages 1038 - 1045, XP009537910
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF: