Spread Spectrum Signal Detection Method Based on Support Vector Machine

• Published in: 2024 IEEE 2nd International Conference on Control, Electronics and Computer Technology (ICCECT) pp. 786 - 793
• Main Authors: Yang, Peng, Zhang, Huishan, Zhu, Junzhe
• Format: Conference Proceeding
• Language: English
• Published: IEEE 26.04.2024
• Subjects: Modulation; Noise; Pattern classification; secondary power spectrum; signal classification; signal detection; spread spectrum; Spread spectrum communication; support vector machine; Support vector machines; Training; Vectors
• DOI: 10.1109/ICCECT60629.2024.10545686

Direct Sequence Spread Spectrum (DSSS) is more susceptible to noise, and cannot effectively identify the information. In order to effectively identify spread spectrum signals and conventional signals, a method based on quadratic power spectrum is proposed. Firstly, the standard deviation of the normalized secondary power spectrum of the spread spectrum signal and the conventional signal is solved, the signal is identified according to the standard deviation, and then repeated experiments are carried out on a large number of signals. Finally, all the training signals are brought into the support vector machine for training. According to the obtained support vector machine model, the remaining signals are tested, and the accuracy of signal recognition and classification is 99.83 %. The results show that the spread spectrum signal can be detected and identified very effectively.