Группа авторов

Handbook of Intelligent Computing and Optimization for Sustainable Development


Скачать книгу

the abrasive quantization instituted by the ADC [22]. In molecular communication systems, the fundamental channel models are indefinite [40]. Therefore, both systems offer themselves to NN-based detectors. Jeon et al. [40] draw a contrast in speech recognition and found that this a domain in which DL algorithms have done extremely good. Speech recognition and digital communication both begin with a signal which is generally sent over a channel to some receiver. This channel can be a wireless, acoustic, or chemical and a receiver can be a microphone, cell phone, or chemical sensor. The receiver tends to detect the original transmitted signal. This evaluation emphasizes the ability of DL algorithms in signal detection over undetermined channels.

      In wireless detection, we initially estimate the parameters of a channel over which the signal is being transmitted. These estimates of the CSI are needed for detection at the receiver. Conventional algorithms to estimate CSI, such as minimum mean square error (MMSE) or maximum a posteriori probability (MAP) estimation, necessitate an analytical model of the channel, but the blend of channel distortion and hardware imperfections can be challenging to model systematically. Authors in [41] employed a DL-based method to estimate the carrier frequency offset (CFO) and timing estimates to empower detection of single carrier phase-shift keyed signals.

      5.2.4 Millimeter Wave

      Here, we discuss two case studies based on our present work. In first case, AMC using time-frequency (TF) image channelized deep convolution network. Second one discusses the CSI feedback for FDD massive MIMO systems using modified deep network called InceptNet.

      5.3.1 Case Study-1: Automatic Modulation Classification

      AMC acts as one of important entity in cognitive radio for spectrum monitoring and interferes mitigation of 5G wireless systems [27]. Hence, in daily life, we encounter wide variety of radio access technology (RAT) with different modulation techniques. Hence, by using DL-enabled classification would achieve high accuracy and indirectly help in increasing spectrum efficiency. Recent highly cited work by O’Shea et al. [19] has used in-phase and quadrature-phase (IQ) data as radio time series as input to the CNN and shown good classification accuracy of 10 modulation techniques. Generally real-time radio signals are non-stationary in nature. Only time domain radio image may drop some of the characteristics possessed by acquired real radio signals. There are some recent works on modulation classification that use TF feature as input to NNs for classifying wireless signal mode identification and radar signal classification [29].

      Case study proposes TF channelized input to CNN, with an objective to the enhance feature dimension for CNN input. The lost information like phase or frequency variation are easily captured in energy variation of TF map. Thus, our proposed technique enhances the classification capability. In addition, work proposes a simple architecture modification called extended output classes (EOC) which is quite different from previously proposed method in [19]. The extended data set labeling on various modulation based on signal-to-noise ratio (SNR) is created, so that the trained network can approximately understand even the relative SNR of modulation.

       5.3.1.1 System Model

Schematic illustration of the block diagram for the proposed blind identification method.

      Next stage is deep NN block that takes 2D TF image as the input. In this block, we have employed widely used CNN, and it has ability to extract features from image autonomously. Exciting feature of CNN is it avoids the tedious task of manual feeding of features to classify object in hand. Thus, CNN works as feature extractor and classifier of modulated signals by taking the input as TF image of baseband IQ time samples. Since system model presented uses the TF analysis block that captures phase information, energy density information and hardware and channel impairments during trans-reception.

      In this work, CNN learns modulation features and channel models from TF spectral images and intuitively able to design the matched filter (MF) for each modulation scheme and provide some filter gain at lower SNR. Thus, without the expert understanding or estimation of the underlying modulated waveform, CNN can blindly classify modulation encountered.

      The last block is a baseband processing unit within the cognitive radio. This block processes the identified modulation signal to classify whether it is the primary user or secondary interfere without demodulation of the received signal. Then, it can optimize the bandwidth as per modulation types or identified radio access techniques for dynamic spectrum allocation in a next-generation wireless system.

       5.3.1.2 CNN Architectures for Modulation Classification