GNSS/GPS Spoofing and Jamming Detection and Classification Using Machine Learning, Deep Learning, and Computer Vision
I have provided a Google Colaboratory link for each Jupyter Notebook (.ipynb) file. Feel free to open the code files and run them effortlessly.
All the code for this project has been developed in Python, utilizing Google Colaboratory for execution. The original dataset, known as the Raw IQ dataset for GNSS GPS jamming signal classification, can be accessed here.
A relevant research paper titled Jammer Classification in GNSS Bands Via Machine Learning Algorithms provides foundational insights into this task and can be found here.
By leveraging advanced image classification techniques, optimized preprocessing steps, and improved dataset partitioning, I have achieved a remarkable increase in accuracy—exceeding the results presented in the aforementioned paper by over 5%(~ 99% accuracy). The initial draft of our research paper can be found here titled GNSS/GPS Spoofing and Jamming Identification Using Machine Learning and Deep Learning.
I am currently focused on enhancing the machine learning components of this project. Please stay tuned for future commits and updates.
If you require any additional information, please don't hesitate to reach out to me via email.