Recently, jamming signal causes a serious damage to wireless communication. Jamming signal can be a threat not only to the industries and the commercials, but also to the military. There are two steps to reduce the damage caused by the jamming signal. The first step is detection and identifying the jamming signal. To properly cope with the wireless communication environment, identify the jamming signals such as types, cycle time and frequency are necessary. The second step is effectively avoidance the jamming signal with the identified information.
In this thesis, we identify and classify the jamming signal using artificial neural networks (ANN). Then we propose the jamming signal avoiding algorithm by changing the transmission frequency band. We consider jamming signals as Chirp and OFDM signal that changes the radiation time and frequency step size.
Using this proposed jamming avoidance algorithm, it can classify the jamming signal according to set of radiation time and frequency step size. Also we change the transmission frequency band according to classification of jamming signal. As a result, BER performance decreased sharply when using proposed jamming avoidance algorithm. In the environment where jamming signals exist, the proposed algorithm can be very effective to detect and avoid jamming signal.