http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
DDoS Detection in Industrial Internet of Things Using Machine Learning
Esmot Ara Tuli,Dong-Seong Kim,Jae Min Lee 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.2
Ensuring security in IIoT devices is a big concern where sometimes critical infrastructure related to it, risks are not acceptable. Distributed denial of service (DDoS) attack is one of the dangerous attack which generally come from the application or network layer where effected system and attackers system are connected. An efficient detection system for DDoS attack is important. This paper propose machine learning-based DDoS detection system with Synthetic Minority Over-sampling Technique (SMOTE) for solving imbalance data problem and increase accuracy. The simulation is done with UNSW-NB 15 dataset over AdaBoost,Logistic Regression, Decision Trees, Random Forest, KNN, Naive Bayes Classifier and achieve attack detection rate higher than 99% with a false alarm rate less than 1%.
Breathing Pattern Forecasting using Deep Learning in Smart Factory Environment
Fabliha Bushra Islam,Cosmas Ifeanyi Nwakanma,Esmot Ara Tuli,Jae-Min Lee,Dong-Seong Kim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
This paper provides a Deep Learning (DL) based design framework for forecasting respiratory behaviors of factory floor workers in a smart factory environment (or Industrial Internet of Things (IIoT)). A continuous 30 min breathing responses were collected through Ultra-Wide Band (UWB) sensor and then applying Artificial Neural Network (ANN) models to acquire the highest prediction accuracy. Eight ANN models with different input, hidden, and output nodes were compared with the proposed scheme code-named ANN-5. The result shows that the proposed ANN-5 outperformed other algorithms with 87.43% precision.