Near-Instantaneously Adaptive Learning-Assisted and Compressed Sensing-Aided Joint Multi-Dimensional Index Modulation

Abstract

Index Modulation (IM) is capable of striking an attractive performance, throughput and complexity trade-off. The concept of Multi-dimensional IM (MIM) combines the benefits of IM in multiple dimensions, including the space and frequency dimensions. On the other hand, IM has also been combined with compressed sensing (CS) for attaining an improved throughput. In this paper, we propose Joint MIM (JMIM) that can utilize the time-, space- and frequency-dimensions in order to increase the IM mapping design flexibility. Explicitly, this is the first paper developing a jointly designed MIM architecture combined with CS. Three different JMIM mapping methods are proposed for a space- and frequency-domain aided JMIM system, which can attain different throughput and diversity gains. Then, we extend the proposed JMIM design to three dimensions by combining it with the time domain. Additionally, to circumvent the high detection complexity of the proposed CS-aided JMIM design, we propose Deep Learning (DL) based detection. Both Hard-Decision (HD) as well as Soft-Decision (SD) detection are conceived. Additionally, we investigate the adaptive design of the proposed CS-aided JMIM system, where a learning-based adaptive modulation configuration method is applied. Our simulation results demonstrate that the proposed CS-aided JMIM (CS-JMIM) is capable of outperforming its CS-aided separate-domain MIM counterpart. Furthermore, the learning-aided adaptive scheme is capable of increasing the throughput while maintaining the required error probability target.

Keywords

• Index modulation (IM)
• compressed sensing-aided multi-dimensional index modulation (CS-MIM)
• soft-decision detection
• machine learning
• neural network