Wireless interference classification with low complexity multi-branch networks

Abstract

In non-cooperative communication systems, wireless interference classification (WIC) is one of the most essential technologies. Recently, deep learning (DL) based WIC methods have been proposed. However, conventional DL-based WIC methods have high computational complexity and unsatisfactory accuracy, especially when the interference-to-noise ratio (INR) is low. To this end, we propose three effective approaches. Firstly, we introduce multi-branch convolutional neural networks (CNNs) for interference recognition. The multi-branch CNN is constructed by repeating a layer that aggregates several transformations with the same topology, and it notably improves the recognition ability for WIC. Our design avoids the carefully crafted selection of each transformation. Unfortunately, multi-branch CNNs are computationally expensive and memory-inefficient. To this end, we further propose Low complexity multi-branch networks (LCMN), which are mathematically equivalent to multi-branch CNNs but maintain low computing costs and efficient inference. Thirdly, we present novel loss function, which encourages networks to have consistent prediction probabilities for samples with high visual similarities, resulting in increasing recognition accuracy of LCMN. Experimental results demonstrate the proposed methods consistently boost the classification performance of WIC without substantially increasing computational overhead compared to traditional DL-based methods.