http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Lightweight Multivariate LSTM for Industrial Power Prediction in Smart Grid
Made Adi Paramartha Putra,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
This paper proposes a lightweight multivariate long short-term memory (LSTM) look-back model to predict smart grid (SG) power consumption with an industrial approach. Since the power demand increases continuously and the previous studies use a complex architecture, a lightweight prediction that provides low loss and computing time is needed. We reduce the number of layers and utilize multivariate features to improve the prediction performances from previous research. Based on the simulation results, the proposed approach outperforms the existing approach in terms of prediction loss.
Adaptive LRFU replacement policy for named data network in industrial IoT
Made Adi Paramartha Putra,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2022 ICT Express Vol.8 No.2
In this paper, an adaptive least recently frequently used (LRFU) replacement policy is proposed for named data network (NDN) in the industrial internet of things (IIoT) environment. Low-latency network communication has become the main focus in IIoT development. By applying NDN architecture with the proposed replacement policy, the system can minimize the network latency of IIoT due to the NDN router’s capabilities to cache content. The simulation result shows that the proposed adaptive LRFU outperforms other popular replacement policies based on various network performances metrics. In addition, future research trends regarding the testbed implementation NDN replacement policy are suggested.
Fault Detection in 3D Printers using an Improved YOLOv5 with Hyperparameter Tuning
Made Adi Paramartha Putra,Mark Verana,Revin Naufal Alief,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.11
In this study, a modification of you only look once version 5 (YOLOv5) is presented to detect an error during the printing process of the fused filament fabrication (FDM) 3D printer. The improvement has been made in hyperparameter selection. The existing YOLOv5 uses the COCO dataset as the default hyperparameter, which is unsuitable for the 3D printing process. Therefore, we captured the image dataset using an FDM 3D printer to improve the detection result generated by the YOLOv5 model. The results show that the improved YOLOv5 with hyperparameter tuning is better than the traditional version of YOLOv5 based on the mean absolute precision (mAP).
Towards Delay Aware Data Recovery using Deep Learning in Embedded IoT Application
Made Adi Paramartha Putra,Adinda Riztia Putri,Mark Verana,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
Data recovery technique in internet of things (IoT) network able to improve the devices longevity by reducing data retransmission. Most of existing research mainly focused on improving the prediction accuracy based on simulation work. Therefore, this study evaluate the data recovery in real world environment using deep learning (DL) and embedded devices by considering the processing time delay. The main goals is to ensure the low latency by applying data recovery in IoT network with low computational resource. A low complexity of deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) network were compared. Based on experimental results, the DNN network model is able to maintain low processing delay with average of 5.18 ms and 98.85% accuracy to recover single missing data.
Machine Learning-based 3D Printer Fault Detection on Edge Device
Mark Verana,Made Adi Paramartha Putra,Revin Naufal Alief,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.11
The 3D printer is a new manufacturing technique that becoming popular in the fields of industry. However, the rapid development of 3D printing technology needs fault detection in the printing process. In this paper, a fault detection based on stacked convolutional neural network (CNN) for 3D printer is proposed. Moreover, a dataset of 3D printer for fault diagnosis is also provided. The result presented in this paper shows that, a stacked-CNN is better than the single CNN and the other methods for fault detection.