Search

Modulation classification is one of the key tasks for communications systems monitoring, management, and control for addressing technical issues, including spectrum awareness, adaptive transmissions, and interference avoidance. Recently, deep learning (DL)-based modulation classification has attracted significant attention due to its superiority in feature extraction and classification accuracy. In DL-based modulation classification, one major challenge is to preprocess a received signal and represent it in a proper format before feeding the signal into deep neural networks. This article provides a comprehensive survey of the state-of-the-art DL-based modulation classification algorithms, especially the techniques of signal representation and data preprocessing utilized in these algorithms. Since a received signal can be represented by either features, images, sequences, or a combination of them, existing algorithms of DL-based modulation classification can be categorized into four groups and are reviewed accordingly in this article. Furthermore, the advantages as well as disadvantages of each signal representation method are summarized and discussed. [ABSTRACT FROM AUTHOR]

Deep learning (DL) is a new machine learning (ML) methodology that has found successful implementations in many application domains. However, its usage in communications systems has not been well explored. This paper investigates the use of the DL in modulation classification, which is a major task in many communications systems. The DL relies on a massive amount of data and, for research and applications, this can be easily available in communications systems. Furthermore, unlike the ML, the DL has the advantage of not requiring manual feature selections, which significantly reduces the task complexity in modulation classification. In this paper, we use two convolutional neural network (CNN)-based DL models, AlexNet and GoogLeNet. Specifically, we develop several methods to represent modulated signals in data formats with gridlike topologies for the CNN. The impacts of representation on classification performance are also analyzed. In addition, comparisons with traditional cumulant and ML-based algorithms are presented. Experimental results demonstrate the significant performance advantage and application feasibility of the DL-based approach for modulation classification. [ABSTRACT FROM AUTHOR]

In this paper, an 8X-parallelism all-digital baseband receiver is proposed to support SC and OFDM modes for both IEEE 802.15.3c and IEEE 802.11ad standards. The all-digital baseband receiver contains a 4-in-1 synchronization (SYNC), a 512-point radix-23 IFFT/FFT, a phase noise cancellation (PNC), a shared memory (MEM) bank and a frequency-domain equalizer (FDE) with an optimized golay-correlator window-based noise cancellation (OGC-WNC) channel estimation (CE) for non-line-of-sight (NLOS) and line-of-sight (LOS) channels. The hardware sharing is 99% between SC and OFDM modes and the shared memory reduces memory usage by 51%. The measurement results show that the fabricated chip can provide PHY data rate of 9.24 Gb/s with power consumption of 497 mW to meet the requirement of OFDM mode for IEEE 802.15.3c and 802.11ad standards. Besides, the PHY data rate of the fabricated chip reaches 14 Gb/s with power consumption of 698 mW for OFDM mode that is beyond the standard requirement to offer higher PHY data rate over 60 GHz transmission environment. [ABSTRACT FROM AUTHOR]

Filter bank multi-carrier (FBMC) is a kind of new waveform that is an important topic in 5th generation wireless systems (5G). In this paper, we propose a novel memory access reordering polyphase network (PPN) for FBMC offset QAM (OQAM) system at 60 GHz band. The novel PPN architecture has lower complexity than the state-of-the-art designs, and it can be used in any FBMC-OQAM baseband design. To evaluate the system performance and hardware complexity of baseband receiver in millimeter wave (mmW) band, the proposed PPN is integrated into our 8X-parallelism 60 GHz band baseband receiver. The out-of-band (OOB) radiation in fixed-point simulation has 25 dB improvement as compared with OFDM. Furthermore, the transmission efficiency of FBMC-OQAM baseband receiver can improve 52% due to using more data subcarriers and removal of cyclic prefix (CP). The proposed PPN is synthesized with 40 nm 1P9M general purposes (GP) process, and can operate at 330/500 MHz clock rate with power consumption of 17/26 mW, providing the maximum PHY data rate up to 21.4 Gb/s. [ABSTRACT FROM PUBLISHER]