UAV Anomaly Detection with Distributed Artificial Intelligence Based on LSTM-AE and AE

  • Bae, Gimin
  • Joe, Inwhee
Citations

SCOPUS

23

초록

In this paper, we propose a novel method for UAV anomaly detection in the distributed artificial intelligence environment by using deep learning models. In the conventional artificial intelligence environment, a lot of computing power is required for anomaly detection, so it is not suitable to the UAV environment based on embedded systems. For UAV anomaly detection, distributed artificial intelligence with DPS (Distributed Problem Solving) and MAS (Multi-Agent System) is applied using LSTM-AE and AE models. The experimental results show that the proposed method performs well for anomaly detection in the UAV environment.

키워드

Anomaly detectionIntrusion detectionLSTM-AEScoringUAVAircraft detectionDeep learningEmbedded systemsIntelligent agentsIntrusion detectionLong short-term memoryMulti agent systemsProblem solvingUnmanned aerial vehicles (UAV)Computing powerDistributed Artificial IntelligenceDistributed problem solvingLearning modelsLSTM-AEScoringAnomaly detection
제목
UAV Anomaly Detection with Distributed Artificial Intelligence Based on LSTM-AE and AE
저자
Bae, GiminJoe, Inwhee
DOI
10.1007/978-981-32-9244-4_43
발행일
2020-04
유형
Conference Paper
저널명
Lecture Notes in Electrical Engineering
590
페이지
305 ~ 310