A Study of Throughput Prediction using Convolutional Neural Network over Factory Environment

Yafei Hou, Kazuto Yano, Norisato Suga, Julian Webber, Eiji Nii, Toshihide Higashimori, Satoshi Denno, Yoshinori Suzuki

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, using the time-series throughput data generated from a simulated factory scenario, we study throughput prediction using convolutional neural network (CNN). Different with image or numerical recognition using CNN, in which the distribution of the prediction target during training stage usually has the similar level, the distribution of the throughput data concentrates only on several values. This centralized distribution may degrade the prediction accuracy. Therefore, we will propose a new CNN prediction method employing target vectorization which can mitigate the centralization of distribution. This method makes training process of CNN hold more possibility and improves the prediction accuracy of the throughput.

Original languageEnglish
Title of host publication24th International Conference on Advanced Communication Technology
Subtitle of host publicationArtificial Intelligence Technologies toward Cybersecurity!!, ICACT 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages429-434
Number of pages6
ISBN (Electronic)9791188428090
DOIs
Publication statusPublished - 2022
Event24th International Conference on Advanced Communication Technology, ICACT 2022 - Virtual, Online, Korea, Republic of
Duration: 13 Feb 202216 Feb 2022

Publication series

NameInternational Conference on Advanced Communication Technology, ICACT
Volume2022-February
ISSN (Print)1738-9445

Conference

Conference24th International Conference on Advanced Communication Technology, ICACT 2022
Country/TerritoryKorea, Republic of
CityVirtual, Online
Period13/02/2216/02/22

Fingerprint

Dive into the research topics of 'A Study of Throughput Prediction using Convolutional Neural Network over Factory Environment'. Together they form a unique fingerprint.

Cite this