Deep Learning Approach for GNSS Jamming Detection-Based PCA and Bayesian Optimization Feature Selection Algorithm
- 16 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (6) , 8349-8363
Abstract
In Global Navigation Satellite Systems (GNSS), receivers are susceptible to various types of jammers. Detecting these jammers is crucial for developing effective anti-jamming techniques due to the increasing complexity of the communication environment and the proliferation of jamming technologies. Different kinds of jammers exhibit distinct behaviors in both the time and frequency domains, leading to various forms of degradation in GNSS receiver performance. This study investigates the detection of two specific kinds of jammers; Continuous Wave (CW) jammers and chirp jammers. Consequently, extracting the original signal or accurately determining the features of the jamming signal using conventional techniques can pose significant challenges. This paper introduces a signal jamming detection Deep Learning (DL) model with a feature selection algorithm. After pre-processing the dataset and analyzing the GNSS data, a feature selection algorithm using the Principal Component Analysis (PCA) combined with the Bayesian Optimization (BO) algorithm is proposed, which processes the data sequentially in the following leads in a systematic manner and distinguishes between two unique signal categories: normal signals and jamming signals. Then, Bidirectional Long Short-term Memory with Attention Mechanism (BiLSTM-A) is applied to detect the jamming signals. Numerical results and a confusion matrix validate the correctness and efficiency of the proposed PCABO feature selection algorithm. The results of the BiLSTM-A model demonstrate 98.95% accuracy. Moreover, PCA-BO results in a 33% dimensionality reduction and the learning time is reduced by 23%, with nearly the same accuracy.Keywords
This publication has 30 references indexed in Scilit:
- Research on GNSS interference recognition based on ROI of correlation peaksInternational Journal of Satellite Communications and Networking, 2022
- GPS Interference Signal Recognition Based on Machine LearningMobile Networks and Applications, 2020
- Daily Activity Feature Selection in Smart Homes Based on Pearson Correlation CoefficientNeural Processing Letters, 2020
- Adaptive Interference Mitigation in GNSS2018
- GNSS Signal Authentication Via Power and Distortion MonitoringIEEE Transactions on Aerospace and Electronic Systems, 2017
- Detection of Spoofing Attack using Machine Learning based on Multi-Layer Neural Network in Single-Frequency GPS ReceiversJournal of Navigation, 2017
- Improved particle swarm optimization algorithm and its application in text feature selectionApplied Soft Computing, 2015
- Bayesian optimization for learning gaits under uncertaintyAnnals of Mathematics and Artificial Intelligence, 2015
- Methods of goodness of fit for GNSS interference detectionIEEE Transactions on Aerospace and Electronic Systems, 2014
- An analysis of four missing data treatment methods for supervised learningApplied Artificial Intelligence, 2003