Deep Learning-Based Index Modulation for Underground Communications

The world population is rapidly increasing, which in turn increases food needs. On the other hand, production main cause of water withdrawal. Precision agriculture, based on Internet Underground Things (IoUT), has recently been proposed to reduce withdrawals. IoUT comprises sensors and communication devices that are partially or fully submerged beneath ground surface. However, current technology used challenged by inefficient spectral energy efficiency. This paper proposes a deep learning (DL)-based index modulation technique increase efficiency without raising system’s bit error rate. article decreases peak-to-average power ratio (PAPR) enhances employing X-transform time-domain synchronous (TDS-IM) orthogonal frequency division multiplexing (OFDM) underground communication. Unlike radio channel, channel environment-dependent. Therefore, this paper, we propose DL receiver detector eliminate such environmental dependency simplify complexity. proposal can establish new identification parameters, achieving accurate estimation modulated symbols even harsh channels. results simulation indicate superior performance scheme terms both compared benchmarks, as well its ability improve