Accuracy Analysis of Feature-Based Automatic Modulation Classification via Deep Neural Network

A feature-based automatic modulation classification (FB-AMC) algorithm has been widely investigated because of its better performance and lower complexity. In this study, a deep learning model was designed to analyze the classification performance of FB-AMC among the most commonly used features, including higher-order cumulants (HOC), features-based fuzzy c-means clustering (FCM), grid-like constellation diagram (GCD), cumulative distribution function (CDF), and raw IQ data. A novel end-to-end modulation classifier based on deep learning, named CCT classifier, which can automatically identify unknown modulation schemes from extracted features using a general architecture, was proposed. Features except GCD are first converted into two-dimensional representations. Then, each feature is fed into the CCT classifier for modulation classification. In addition, Gaussian channel, phase offset, frequency offset, non-Gaussian channel, and flat-fading channel are also introduced to compare the performance of different features. Additionally, transfer learning is introduced to reduce training time. Experimental results showed that the features HOC, raw IQ data, and GCD obtained better classification performance than CDF and FCM under Gaussian channel, while CDF and FCM were less sensitive to the given phase offset and frequency offset. Moreover, CDF was an effective feature for AMC under non-Gaussian and flat-fading channels, and the raw IQ data can be applied to different channels’ conditions. Finally, it showed that compared with the existing CNN and K-S classifiers, the proposed CCT classifier significantly improved the classification performance for MQAM at N = 512, reaching about 3.2% and 2.1% under Gaussian channel, respectively.

A Very Low Reference Spur Phase Offset Technique in Fractional-N Charge pump PLLs

Fractional-N charge pump phase locked loops (PLLs) suffer from the problem of increased in-band phase noise due to charge pump non-linearity caused by UP/DN chargepump current mismatch. Existing techniques that resolve this problem by introducing phase offset between reference and divide signals cause large reference spurs or increase jitter at PLL output. A very low reference spur phase offset technique is proposed in this work. It produces the lowest reference spurs compared to previously published works. A detailed comparison of the reference spurs caused by the different techniques to introduce phase offset is presented. Simulation results show that the reference spur level generated at the PLL output after applying the proposed technique is 26 dB lower than the existing techniques in the presence of 5% chargepump current mismatch.<br>

A Very Low Reference Spur Phase Offset Technique in Fractional-N Charge pump PLLs

Fractional-N charge pump phase locked loops (PLLs) suffer from the problem of increased in-band phase noise due to charge pump non-linearity caused by UP/DN chargepump current mismatch. Existing techniques that resolve this problem by introducing phase offset between reference and divide signals cause large reference spurs or increase jitter at PLL output. A very low reference spur phase offset technique is proposed in this work. It produces the lowest reference spurs compared to previously published works. A detailed comparison of the reference spurs caused by the different techniques to introduce phase offset is presented. Simulation results show that the reference spur level generated at the PLL output after applying the proposed technique is 26 dB lower than the existing techniques in the presence of 5% chargepump current mismatch.<br>

Nonlinear Dynamics of Two-State Quantum Dot Lasers under Optical Feedback

A modified rate equation model was presented to theoretically investigate the nonlinear dynamics of solitary two-state quantum dot lasers (TSQDLs) under optical feedback. The simulated results showed that, for a TSQDL biased at a relatively high current, the ground-state (GS) and excited-state (ES) lasing of the TSQDL can be stimulated simultaneously. After introducing optical feedback, both GS lasing and ES lasing can exhibit rich nonlinear dynamic states including steady state (S), period one (P1), period two (P2), multi-period (MP), and chaotic (C) state under different feedback strength and phase offset, respectively, and the dynamic states for the two lasing types are always identical. Furthermore, the influences of the linewidth enhancement factor (LEF) on the nonlinear dynamical state distribution of TSQDLs in the parameter space of feedback strength and phase offset were also analyzed. For a TSQDL with a larger LEF, much more dynamical states can be observed, and the parameter regions for two lasing types operating at chaotic state are widened after introducing optical feedback.

Magnetic Resonance Spectroscopy Frequency and Phase Correction Using Convolutional Neural Networks

We introduce DeepSPEC, a novel convolutional neural network (CNN) -based approach for frequency-and-phase correction (FPC) of MRS spectra to achieve fast and accurate FPC of single-voxel PRESS MRS and MEGA-PRESS data. In DeepSPEC, two neural networks, including one for frequency correction and one for phase correction were trained and validated using published simulated and in vivo PRESS and MEGA-PRESS MRS dataset with wide-range artificial frequency and phase offsets applied. DeepSPEC was subsequently tested and compared to the current deep learning solution - a ″vanilla″ neural network approach using multilayer perceptrons (MLP). Furthermore, random noise was added to the original simulated dataset to further investigate the model performance with noise at varied signal-to-noise (SNR) levels (i.e., 6 dB, 3 dB, and 1.5 dB). The testing showed that DeepSPEC is more robust to noise compared to the MLP-based approach due to having a smaller absolute error in both frequency and phase offset prediction. The DeepSPEC framework was capable of correcting frequency offset with 0.01±0.01 Hz and phase offset with 0.12±0.09° absolute errors on average for unseen simulated data at a high SNR (12 dB) and correcting frequency offset with 0.01±0.02 Hz and phase offset within -0.07±0.44° absolute errors on average at very low SNR (1.5 dB). Furthermore, additional frequency and phase offsets (i.e., small, moderate, large) were applied to the in vivo dataset, and DeepSPEC demonstrated better performance for FPC when compared to the MLP-based approach. Results also show DeepSPEC has superior performance than the model-based SR implementation (mSR) in FPC by having higher accuracy in a wider range of additional offsets. These results represent a proof of concept for the use of CNNs for preprocessing MRS data and demonstrate that DeepSPEC accurately predicts frequency and phase offsets at varying noise levels with state-of-the-art performance.