TDRA: Transformer-Based Deep Recurrent Architecture for Automatic Modulation Classification Pertinent to Intelligent-Reflecting-Surface-Assisted Internet of Things Networks

In wireless networks, automatic modulation classification (AMC) is crucial for enabling intelligent signal demodulation, thereby enhancing the system’s adaptability across various applications. Concurrently, the rapid expansion of the Internet of Things (IoT) necessitates scalable network solutions with limited power consumption. Moreover, addressing the Nonline-of-Sight (NLoS) effects in IoT networks, intelligent reflecting surface (IRS) emerges as a promising, cost-effective technology. This article introduces a novel transformer-based deep recurrent architecture (TDRA) for AMC, tailored for IRS-assisted IoT networks, which significantly improves IoT Device (IoTD) performance in NLoS scenarios. In TDRA, the existing recurrent models, long-short-term memory (LSTM), and gated-recurrent-unit (GRU) are suitably revamped with a transformer-based approach and termed as transformer-based LSTM (T-LSTM) and transformer-based GRU (T-GRU). Numerical data sets are generated for IoT applications considering the seven widely used modulation types to train and test the proposed models. Comparative analysis with seven state-of-the-art deep learning models and five machine learning models for AMC demonstrates the superior performance of the proposed models across multiple metrics, including accuracy, R-squared-score, mean-square error, mean-absolute error, precision, recall, and F1-score. Further, the proposed models exhibit notable improvements under various conditions, such as optimized and random IRS phase shifts, with and without IRS-assisted IoT networks, different modulation sequence lengths, and fading channels. Additionally, the time complexity and processing time of the proposed models have been studied to test their suitability for IoTD. The simulation results indicate that the TDRA for AMC in IRS-assisted IoT networks achieves up to 87% higher accuracy compared to without IRS-assisted IoT networks. This significant enhancement underscores the potential of TDRA to revolutionize IoT networks by providing robust, efficient, and scalable solutions for real-world applications.

I. Introduction

Automatic modulation classification (AMC) is an essential part of noncooperative wireless communication networks where receivers are unaware of the received signals. AMC is pivotal in military applications, civilian applications, unmanned aerial vehicle (UAV) communications, and Internet of Things (IoT) applications [1], [2]. AMC enhances security, electronic surveillance, spectrum monitoring, and radio signal classification [1], [3], [4]. It also increases spectrum efficiency by reducing the overhead. AMC is a prominent approach for intelligent receiver design [5] in current and future wireless networks. This approach intelligently identifies the modulation scheme in the received signal. AMC is performed at the middle stage of signal detection and demodulation. Efficient deep learning (DL)-based AMC models are designed based on two steps: 1) the data set generation and 2) the suitable classification algorithm [6]. AMC can be split into feature-based [7] and likelihood-based [8]. The feature-based AMC can be accomplished in three steps: 1) data preprocessing; 2) feature extraction; and 3) classificatory decision. Likelihood-based AMC operates by comparing the likelihood ratio of the received signal with a predetermined threshold. Nowadays, DL-based models are an essential part of wireless network environments as they can effectively handle complex problems. DL-based models have been widely adopted for different wireless applications, such as channel estimation [9], AMC [10], secure communication [11], resource allocation [12], wireless standard classification [13], channel state information prediction [14], etc. These models have improved user/devices’ performance and enhanced the Quality of Experience (QoE) in wireless networks [10], [15], [16], [17].