J
Ju-Bong Kim
Researcher at Korea University of Technology and Education
Publications - 19
Citations - 222
Ju-Bong Kim is an academic researcher from Korea University of Technology and Education. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 6, co-authored 13 publications receiving 80 citations.
Papers
More filters
Proceedings ArticleDOI
Packet-based Network Traffic Classification Using Deep Learning
TL;DR: This study generates packet-based datasets through their own network traffic pre-processing, and trains five deep learning models using the convolutional neural network (CNN) and residual network (ResNet) to perform network traffic classification.
Journal ArticleDOI
Federated Reinforcement Learning for Training Control Policies on Multiple IoT Devices
TL;DR: The actor–critic proximal policy optimization (Actor–Critic PPO) algorithm is incorporated into each agent in the proposed collaborative architecture and an efficient procedure for the gradient sharing and the model transfer is proposed.
Journal ArticleDOI
Time Series Classification of Cryptocurrency Price Trend Based on a Recurrent LSTM Neural Network
TL;DR: Through the comparison of the f1-score values, the LSTM model outperforms the gradient boosting model, a general machine learning model known to have relatively good prediction performance, for the time series classification of the cryptocurrency price trend.
Journal ArticleDOI
Payload-Based Traffic Classification Using Multi-Layer LSTM in Software Defined Networks
TL;DR: This study proposes a traffic classification scheme using a deep learning model in software defined networks, and shows the superiority of the multi-layer LSTM model for network packet classification.
Journal ArticleDOI
Imitation Reinforcement Learning-Based Remote Rotary Inverted Pendulum Control in OpenFlow Network
TL;DR: From the authors' CPS-based experimental system, it is verified that a deep reinforcement learning agent can successfully control the real device located remotely from the agent, and the imitation learning strategy can make the learning time reduced effectively.