http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Reducing Faulty Node Detection Delay in Industrial Internet of Things
Alifia Putri Anantha,Sanjay Bhardwaj,Jae-Min Lee,Dong-Seong Kim 한국통신학회 2019 한국통신학회 학술대회논문집 Vol.2019 No.6
In industrial internet of things (IIoT), some data obtained may experience problems during the communication process between nodes that cause high latency and network congestion. Therefore, detection of faulty nodes is necessary. Various methods for detecting faulty nodes in IIoT and overviews of their systems are discussed in this paper. However, the previous solutions experienced long delays in identifying and isolating nodes that produced incorrect data. Artificial intelligence (AI) is a good solution to this problem because of its ability to accelerate time, thereby reducing computing time and delays. The principal purpose of this paper is to serve a framework for researchers about how faulty nodes in IIoT can be detected, point out the weaknesses of each system related to the problem of delay, and propose a mechanism which allows each node to identify whether it produces faulty data rapidly.
Network Intrusion Detection System for IIoT Using GRU and Denoising Autoencoder
Alifia Putri Anantha,Da Hye Kim(김다혜),Jae Min Lee(이재민),Dong-Seong Kim(김동성) 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.2
This work presents a denoising autoencoder-based anomaly detection model using GRU for intelligent network intrusion detection system. The main aim is to secure an IIoT system because its technologies are shadowed by privacy trade-offs and miserable security concerns. The dataset used is NSL-KDD dataset but it suffers from several inefficiencies, one of them is class imbalance issue. This fact made it difficult for classifiers to detect some underrepresented attack types resulting in poor accuracy. By combining denoising autoencoder with GRU and testing the method through a simulation, our proposed system is able to outperforms some methods in the existing literature with the highest accuracy.