Engineering Commons^™

Deep-Learning-Based Classification Of Digitally Modulated Signals Using Capsule Networks And Cyclic Cumulants, John A. Snoap, Dimitrie C. Popescu, James A. Latshaw, Chad M. Spooner

Electrical & Computer Engineering Faculty Publications

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper …

Emotion Detection Using An Ensemble Model Trained With Physiological Signals And Inferred Arousal-Valence States, Matthew Nathanael Gray

Electrical & Computer Engineering Theses & Dissertations

Affective computing is an exciting and transformative field that is gaining in popularity among psychologists, statisticians, and computer scientists. The ability of a machine to infer human emotion and mood, i.e. affective states, has the potential to greatly improve human-machine interaction in our increasingly digital world. In this work, an ensemble model methodology for detecting human emotions across multiple subjects is outlined. The Continuously Annotated Signals of Emotion (CASE) dataset, which is a dataset of physiological signals labeled with discrete emotions from video stimuli as well as subject-reported continuous emotions, arousal and valence, from the circumplex model, is used for …

Machine Learning Classification Of Digitally Modulated Signals, James A. Latshaw

Electrical & Computer Engineering Theses & Dissertations

Automatic classification of digitally modulated signals is a challenging problem that has traditionally been approached using signal processing tools such as log-likelihood algorithms for signal classification or cyclostationary signal analysis. These approaches are computationally intensive and cumbersome in general, and in recent years alternative approaches that use machine learning have been presented in the literature for automatic classification of digitally modulated signals. This thesis studies deep learning approaches for classifying digitally modulated signals that use deep artificial neural networks in conjunction with the canonical representation of digitally modulated signals in terms of in-phase and quadrature components. Specifically, capsule networks are …

A Primer On Software Defined Radios, Dimitrie C. Popescu, Rolland Vida

Electrical & Computer Engineering Faculty Publications

The commercial success of cellular phone systems during the late 1980s and early 1990 years heralded the wireless revolution that became apparent at the turn of the 21st century and has led the modern society to a highly interconnected world where ubiquitous connectivity and mobility are enabled by powerful wireless terminals. Software defined radio (SDR) technology has played a major role in accelerating the pace at which wireless capabilities have advanced, in particular over the past 15 years, and SDRs are now at the core of modern wireless communication systems. In this paper we give an overview of SDRs that …

Fast Stochastic Wiener Filter For Super-Resolution Image Restoration With Information Theoretic Visual Quality Assessment, Amr Hussein Yousef, Jiang Li, Mohammad Karim, Mark Allen Neifeld (Ed.), Amit Ashok (Ed.)

Electrical & Computer Engineering Faculty Publications

Super-resolution (SR) refers to reconstructing a single high resolution (HR) image from a set of subsampled, blurred and noisy low resolution (LR) images. The reconstructed image suffers from degradations such as blur, aliasing, photo-detector noise and registration and fusion error. Wiener filter can be used to remove artifacts and enhance the visual quality of the reconstructed images. In this paper, we introduce a new fast stochastic Wiener filter for SR reconstruction and restoration that can be implemented efficiently in the frequency domain. Our derivation depends on the continuous-discrete-continuous (CDC) model that represents most of the degradations encountered during the image-gathering …

Mathematical Model Development Of Super-Resolution Image Wiener Restoration, Amr H. Yousef, Jiang Li, Mohammad A. Karim

Electrical & Computer Engineering Faculty Publications

In super-resolution (SR), a set of degraded low-resolution (LR) images are used to reconstruct a higher-resolution image that suffers from acquisition degradations. One way to boost SR images visual quality is to use restoration filters to remove reconstructed images artifacts. We propose an efficient method to optimally allocate the LR pixels on the high-resolution grid and introduce a mathematical derivation of a stochastic Wiener filter. It relies on the continuous-discrete-continuous model and is constrained by the periodic and nonperiodic interrelationships between the different frequency components of the proposed SR system. We analyze an end-to-end model and formulate the Wiener filter …

Design Of Efficient Algorithms Through Minimization Of Data Transfers, Yong Mo Chong

Electrical & Computer Engineering Theses & Dissertations

This thesis explores the time optimal implementation of computational graphs on a finite register machine. The implementation fully exploits the machine architecture, especially, the number of registers. The derived algorithms allow one to obtain time efficient implementations of a given graph in machines with a known number of registers.

These optimization procedures are applied to digital signal processing graphs. It is shown that the regular structure of these graphs allows one to identify computational kernels which, when used repeatedly, can cover the entire graph. The l- and r-register implementations of Hadamard and Fast Fourier Transforms using various computational kernels are …