Design of deep learning based pulse repetition interval modulation classification and recognition

In radar signal processing area, pulse repetition interval (PRI) is a significant parameter, representing the time interval between consecutive radar pulse emissions. This is an important temporal property in identifying emitters and their modes of operation in electronic warfare. The emergence of d...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Zhuang, Yiran
مؤلفون آخرون: Teh Kah Chan
التنسيق: Thesis-Master by Coursework
اللغة:English
منشور في: Nanyang Technological University 2024
الموضوعات:
الوصول للمادة أونلاين:https://hdl.handle.net/10356/172920
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
المؤسسة: Nanyang Technological University
اللغة: English
الوصف
الملخص:In radar signal processing area, pulse repetition interval (PRI) is a significant parameter, representing the time interval between consecutive radar pulse emissions. This is an important temporal property in identifying emitters and their modes of operation in electronic warfare. The emergence of deep learning has emerged the improvement of radar signal classification. This dissertation project focuses on the development and evaluation of an innovative deep learning-based model for automatic identification of multiple PRI modulation modes. This research is implemented using MATLAB and Python. The overall goal of this work is to advance PRI modulation identification techniques and contribute to the growth of knowledge on radar signal processing, with potential applications spanning all areas of radar technology. This project successfully developed a deep learning-based model for automatically identifying multiple PRI modulation modes in radar signals using MATLAB and Python. The model showed promise in improving PRI modulation recognition accuracy and efficiency. While the findings contribute to radar signal processing, it is important to acknowledge that further research and real-world validation may be needed to fully assess its practical impact. Keywords: Pulse repetition interval, deep learning, convolutional neural network.