TY - JOUR
T1 - Uncompromised Accuracy
T2 - Fast and Reliable Multivariate Anomaly Detection for Satellite Signals
AU - Sadr, Mohammad Amin Maleki
AU - Qaraqe, Marwa
N1 - Publisher Copyright:
© 1965-2011 IEEE.
PY - 2024
Y1 - 2024
N2 - In the realm of multivariate anomaly detection, Deep Neural Networks (DNNs) have garnered attention. However, relying solely on a single DNN model may not achieve the optimal balance between accuracy and time efficiency. Non-linear variants of Kalman filter models (EKF, UKF) are known for their efficient time complexity but often compromise accuracy. On the other hand, deep learning-based models like Transformers and Recurrent Neural Networks (RNNs) excel in accuracy but introduce complexity challenges. This paper introduces the Selective Points Anomaly Detection (SPAD) method, which strategically merges accurate and time-efficient algorithms by leveraging a selection of multiple models. The optimal model fusion that maximizes the accuracy-to-time ratio is determined by assessing the estimated covariance from both sets of algorithms. The results demonstrate a superior Accuracy-to-Time Ratio (ATR) by at least 30% and 33% compared to the best existing method for SMAP and MSL datasets, respectively.
AB - In the realm of multivariate anomaly detection, Deep Neural Networks (DNNs) have garnered attention. However, relying solely on a single DNN model may not achieve the optimal balance between accuracy and time efficiency. Non-linear variants of Kalman filter models (EKF, UKF) are known for their efficient time complexity but often compromise accuracy. On the other hand, deep learning-based models like Transformers and Recurrent Neural Networks (RNNs) excel in accuracy but introduce complexity challenges. This paper introduces the Selective Points Anomaly Detection (SPAD) method, which strategically merges accurate and time-efficient algorithms by leveraging a selection of multiple models. The optimal model fusion that maximizes the accuracy-to-time ratio is determined by assessing the estimated covariance from both sets of algorithms. The results demonstrate a superior Accuracy-to-Time Ratio (ATR) by at least 30% and 33% compared to the best existing method for SMAP and MSL datasets, respectively.
KW - Anomaly detection
KW - IMM
KW - Kalman filtering
KW - LSTM
UR - http://www.scopus.com/inward/record.url?scp=85204774922&partnerID=8YFLogxK
U2 - 10.1109/TAES.2024.3463629
DO - 10.1109/TAES.2024.3463629
M3 - Article
AN - SCOPUS:85204774922
SN - 0018-9251
JO - IEEE Transactions on Aerospace and Electronic Systems
JF - IEEE Transactions on Aerospace and Electronic Systems
ER -