Deep Learning-Based Spread-Spectrum FGSM for Underwater Communication

The limitation of the available channel bandwidth and availability of a sustainable energy source for battery feed sensor nodes are the main challenges in the underwater acoustic communication. Unlike terrestrial’s communication, using multi-input multi-output (MIMO) technologies to overcome the bandwidth limitation problem is highly restricted in underwater acoustic communication by high inter-channel interference (ICI) and the channel multipath effect. Recently, the spatial modulation techniques (SMTs) have been presented as an alternative solution to overcome these issues by transmitting more data bits using the spatial index of antennas transmission. This paper proposes a new scheme of SMT called spread-spectrum fully generalized spatial modulation (SS-FGSM) carrying the information bits not only using the constellated data symbols and index of active antennas as in conventional SMTs, but also transmitting the information bits by using the index of predefined spreading codes. Consequently, most of the information bits are transmitted in the index of the transmitter antenna, and the index of spreading codes. In the proposed scheme, only a few information bits are transmitted physically. By this way, consumed power transmission can be reduced, and we can save the energy of underwater nodes, as well as enhancing the channel utilization. To relax the receiver computational complexity, a low complexity deep learning (DL) detector is proposed for the SS-FGSM scheme as the first attempt in the underwater SMTs-based communication. The simulation results show that the proposed deep learning detector-based SS-FGSM (DLSS-FGSM), compared to the conventional SMTs, can significantly improve the system data rate, average bit error rate, energy efficiency, and receiver’s computational complexity.

Generation of Spreading Codes with Minimum Correlation using Sorting Genetic Algorithm-II

In a code division multiple access (CDMA) system, multiple access interference (MAI) and Inter-symbol interference (ISI) appears if generated spreading codes are not maintained orthogonally and the communication channel is taken as multi-path communication channel. When generated spreading codes are multi-path spread and then channel delay occurs, it shows that ortho-gonality of the spreading codes is not maintained. The effect of MAI can be mitigated by maintaining low cross-correlation values as much as low between the large numbers of spreading codes. The code division multiple technique spreading codes must maintain absolutely impulsive autocorrelation at origin and very low cross correlation other than origin to avoid false synchronisation. i.e autocorrelation must be maximum at origin and cross correlation must be minimum at non origin point. In this paper, we propose multi-objective Genetic Algorithm approach –Genetic Algorithm-II (NSGA-II) to reduce the out-of-phase average mean-square aperiodic autocorrelation and average mean-square aperiodic cross-correlation value of randomly initialized binary spreading code set.