TY - GEN
T1 - A Study of Throughput Prediction using Convolutional Neural Network over Factory Environment
AU - Hou, Yafei
AU - Yano, Kazuto
AU - Suga, Norisato
AU - Webber, Julian
AU - Nii, Eiji
AU - Higashimori, Toshihide
AU - Denno, Satoshi
AU - Suzuki, Yoshinori
N1 - Funding Information:
ACKNOWLEDGMENT This work includes results of the project entitled “R&D on Technologies to Densely and Efficiently Utilize Radio Resources of Unlicensed Bands in Dedicated Areas,” which is supported by the Ministry of Internal Affairs and Communications as part of the research program “R&D for Expansion of Radio Wave Resources (JPJ000254)”.
Publisher Copyright:
© 2022 Global IT Research Institute-GiRI.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85127488079&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127488079&partnerID=8YFLogxK
U2 - 10.23919/ICACT53585.2022.9728893
DO - 10.23919/ICACT53585.2022.9728893
M3 - Conference contribution
AN - SCOPUS:85127488079
T3 - International Conference on Advanced Communication Technology, ICACT
SP - 429
EP - 434
BT - 24th International Conference on Advanced Communication Technology
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 24th International Conference on Advanced Communication Technology, ICACT 2022
Y2 - 13 February 2022 through 16 February 2022
ER -