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 contribution

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 publication23rd International Conference on Advanced Communication Technology
Subtitle of host publicationOn-Line Security in Pandemic Era!, ICACT 2021 - Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages429-434
Number of pages6
ISBN (Electronic)9791188428069
DOIs
Publication statusPublished - Feb 7 2021
Event23rd International Conference on Advanced Communication Technology, ICACT 2021 - Virtual, PyeongChang, Korea, Republic of
Duration: Feb 7 2021Feb 10 2021

Publication series

NameInternational Conference on Advanced Communication Technology, ICACT
Volume2021-February
ISSN (Print)1738-9445

Conference

Conference23rd International Conference on Advanced Communication Technology, ICACT 2021
CountryKorea, Republic of
CityVirtual, PyeongChang
Period2/7/212/10/21

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

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