Wireless Interference Identification with Convolutional Neural Networks
This addresses interference mitigation for deterministic medium utilization in wireless networks, representing a domain-specific incremental improvement.
The paper tackles the problem of identifying wireless interference types in license-free frequency bands by proposing the first deep convolutional neural network (CNN) approach, achieving over 95% classification accuracy for signal-to-noise ratios of at least -5 dB.
The steadily growing use of license-free frequency bands requires reliable coexistence management for deterministic medium utilization. For interference mitigation, proper wireless interference identification (WII) is essential. In this work we propose the first WII approach based upon deep convolutional neural networks (CNNs). The CNN naively learns its features through self-optimization during an extensive data-driven GPU-based training process. We propose a CNN example which is based upon sensing snapshots with a limited duration of 12.8 μs and an acquisition bandwidth of 10 MHz. The CNN differs between 15 classes. They represent packet transmissions of IEEE 802.11 b/g, IEEE 802.15.4 and IEEE 802.15.1 with overlapping frequency channels within the 2.4 GHz ISM band. We show that the CNN outperforms state-of-the-art WII approaches and has a classification accuracy greater than 95% for signal-to-noise ratio of at least -5 dB.