Computer Engineering Commons^™

Deep Learning And Polar Transformation To Achieve A Novel Adaptive Automatic Modulation Classification Framework, Pejman Ghasemzadeh

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Automatic modulation classification (AMC) is an approach that can be leveraged to identify an observed signal's most likely employed modulation scheme without any a priori knowledge of the intercepted signal. Of the three primary approaches proposed in literature, which are likelihood-based, distribution test-based, and feature-based (FB), the latter is considered to be the most promising approach for real-world implementations due to its favorable computational complexity and classification accuracy. FB AMC is comprised of two stages: feature extraction and labeling. In this thesis, we enhance the FB approach in both stages. In the feature extraction stage, we propose a new architecture …

Revisiting Elliptic Curve Cryptography With Applications To Post-Quantum Sidh Ciphers, Wesam Nabil Eid

Theses and Dissertations

Elliptic Curve Cryptography (ECC) has positioned itself as one of the most promising candidates for various applications since its introduction by Miller and Kolbitz in 1985 [53, 44]. The core operation for ECC is the scalar multiplication [k]P where many efforts have addressed its computation speed. Here we introduce an efficient approach for calculating elliptic curve operations by a novel regrouping of terms and creating new projective representation operators and increasing parallelism. These operators and the corresponding projective coordinate representations are shown to lead to adjusted versions of scalar multiplication algorithms that are evaluated. These techniques enable more opportunities for …

Improving Wake-Up-Word And General Speech Recognition Systems, Gamal Mohamed Bohouta

Theses and Dissertations

Automatic Speech Recognition (ASR), a technology that allows a machine to recognize the utterances spoken into a microphone by a person and then converts it to text, is commonly used for different types of applications, such as command and control systems, personal assistant systems, medical systems, disabilities systems, dictation systems, telephony systems, and embedded applications. Due to its extensive use, interest in ASR technology has surged among inventors and researchers alike. They have worked diligently to improve the performance of the ASR systems by developing several techniques or approaches in different aspects,such as enhancing features, training an acoustic model, enhancing …

Model Optimization For Edge Devices, Adolf Anthony D’Costa

Theses and Dissertations

Edge devices are undergoing groundbreaking computing transformation, which lets us tap into artificial intelligence, quantum computing, 5th generation network capability, fog networking, and computing complex algorithms. Edge systems have substantial advantages over the conventional system in terms of scalability, optimized resources, reliability, and security. The proliferation of such resource-constrained devices in recent years has resulted in the generation of a large quantity of data; these data-producing devices are attractive targets for applications of machine learning. Machine learning models, especially deep learning neural networks, produced models that have high accuracy and prediction capability, but it comes at the cost of computation …

Coordinated Autonomy Of Unmanned Aerial Vehicles (Uavs), Paribartan Dhakal

Honors Theses

Unmanned Aerial Vehicles (UAVs) are being extensively used in diverse sectors of the society for various tasks ranging from videography to an extremely sensitive situation such as first responders helping during a disaster. It has been seen that if a fleet of UAVs is deployed, they can perform a task quicker and more efficiently than a single UAV. With an increase in the number of UAVs, a problem arises of handling them with proper control structures. It has been studied that the Behavior Trees (BT) can be a better control architecture to handle the autonomous vehicles, as BTs are more …

Enhancing Cellular Communications For Uavs Via Intelligent Reflective Surface, Dong Ma, Ming Ding, Mahbub Hassan

Research Collection School Of Computing and Information Systems

Intelligent reflective surfaces (IRSs) capable of reconfiguring their electromagnetic absorption and reflection properties in real-time are offering unprecedented opportunities to enhance wireless communication experience in challenging environments. In this paper, we analyze the potential of IRS in enhancing cellular communications for UAVs, which currently suffers from poor signal strength due to the down-tilt of base station antennas optimized to serve ground users. We consider deployment of IRS on building walls, which can be remotely configured by cellular base stations to coherently direct the reflected radio waves towards specific UAVs in order to increase their received signal strengths. Using the recently …

Using Online Discussions To Connect Theory And Practice In Core Engineering Undergraduate Courses, Lisa B. Bosman, Somesh Roy, Walter M. Mcdonald, Cristinel Ababei

Electrical and Computer Engineering Faculty Research and Publications

Providing engineering undergraduate students opportunities to connect real-world applications with theory is key to preparing them for the workforce; however, this task often requires a balancing act between meeting course objectives in content-heavy core engineering undergraduate courses and providing experiences that connect real-world applications with theory. This study seeks to address this problem through the integration of online discussion prompts to promote a connection to real-world practical applications. The study included undergraduate students enrolled in three engineering core courses. The hypothesis was that participation in online discussions (using prompts) would lead to 1) an increase in student empowerment towards self-regulated …

Emotional Awareness During Bug Fixes: A Pilot Study, Jada O. Loro, Abigail L. Schneff, Sarah J. Oran, Bonita Sharif

School of Computing: Dissertations, Theses, and Student Research

This study examines the effects of a programmer's emotional awareness on progress while fixing bugs. The goal of the study is to capitalize on emotional awareness to ultimately increase progress made during software development. This process could result in improved software maintenance.

Minet Magnetic Indoor Localization, Michael Drake

Honors Theses

Indoor localization is a modern problem of computer science that has no unified solution, as there are significant trade-offs involved with every technique. Magnetic localization, though less popular than WiFi signal based localization, is a sub-field that is rooted in infrastructure-free design, which can allow universal setup. Magnetic localization is also often paired with probabilistic programming, which provides a powerful method of estimation, given a limited understanding of the environment. This thesis presents Minet, which is a particle filter based localization system using the Earth's geomagnetic field. It explores the novel idea of state space limitation as a method of …

Performance Of Malware Classification On Machine Learning Using Feature Selection, Nusrat Asrafi

Master of Science in Computer Science Theses

The exponential growth of malware has created a significant threat in our daily lives, which heavily rely on computers running all kinds of software. Malware writers create malicious software by creating new variants, new innovations, new infections and more obfuscated malware by using techniques such as packing and encrypting techniques. Malicious software classification and detection play an important role and a big challenge for cyber security research. Due to the increasing rate of false alarm, the accurate classification and detection of malware is a big necessity issue to be solved. In this research, eight malware family have been classifying according …

Ensemble Malware Classification System Using Deep Neural Networks, Barath Narayanan Narayanan, Venkata Salini Priyamvada Davuluru

Electrical and Computer Engineering Faculty Publications

With the advancement of technology, there is a growing need of classifying malware programs that could potentially harm any computer system and/or smaller devices. In this research, an ensemble classification system comprising convolutional and recurrent neural networks is proposed to distinguish malware programs. Microsoft's Malware Classification Challenge (BIG 2015) dataset with nine distinct classes is utilized for this study. This dataset contains an assembly file and a compiled file for each malware program. Compiled files are visualized as images and are classified using Convolutional Neural Networks (CNNs). Assembly files consist of machine language opcodes that are distinguished among classes using …

An Eye Tracking Replication Study Of A Randomized Controlled Trial On The Effects Of Embedded Computer Language Switching, Cole Peterson

School of Computing: Dissertations, Theses, and Student Research

The use of multiple programming languages (polyglot programming) during software development is common practice in modern software development. However, not much is known about how the use of these different languages affects developer productivity. The study presented in this thesis replicates a randomized controlled trial that investigates the use of multiple languages in the context of database programming tasks. Participants in our study were given coding tasks written in Java and one of three SQL-like embedded languages: plain SQL in strings, Java methods only, a hybrid embedded language that was more similar to Java. In addition to recording the online …

Modeling And Experimental Verification Of An Unconventional 9-Phase Asymmetric Winding Pm Motor Dedicated To Electric Traction Applications, Ersin Yolacan, Mustafa K. Guven, Metin Aydin, Ayman M. El-Refaie

Electrical and Computer Engineering Faculty Research and Publications

Multi-phase permanent magnet motors are becoming popular in various applications such as high power traction which require low cogging and torque ripple, and reduced noise and vibration. This paper presents the development process of a full order detailed mathematical model for an unconventional nine-phase permanent magnet (PM) motor with asymmetric AC windings. The phase inductances are calculated based on the individual winding functions. Using these parameters, electrical equations for each phase based on the voltages and flux linkages are generated. These equations are transformed into an arbitrary reference frame and the torque equations are developed for the 9-phase motor. A …

Finding Optimal Input Parameters For Bayeswave, Kelsey M. Rook

Honors Theses

This project involves data analysis for LIGO with the goal of finding optimal input parameters for the BayesWave analysis pipeline, which is an algorithm for the detection of unmodelled gravitational wave transients. To test the BayesWave pipeline, we add binary black hole gravitational waveforms to LIGO noise, and run BayesWave with different combinations of parameters on the resulting signal data to find the best method of separating gravitational waves from noise and glitches. From the results, we calculate various statistical measures for each parameter combination in order to determine which allows for the most accurate classification of gravitational wave transients.

A Memory Usage Comparison Between Jitana And Soot, Yuanjiu Hu

School of Computing: Dissertations, Theses, and Student Research

There are several factors that make analyzing Android apps to address dependability and security concerns challenging. These factors include (i) resource efficiency as analysts need to be able to analyze large code-bases to look for issues that can exist in the application code and underlying platform code; (ii) scalability as today’s cybercriminals deploy attacks that may involve many participating apps; and (iii) in many cases, security analysts often rely on dynamic or hybrid analysis techniques to detect and identify the sources of issues.

The underlying principle governing the design of existing program analysis engines is the main cause that prevents …

An Algorithm For Building Language Superfamilies Using Swadesh Lists, Bill Mutabazi

School of Computing: Dissertations, Theses, and Student Research

The main contributions of this thesis are the following: i. Developing an algorithm to generate language families and superfamilies given for each input language a Swadesh list represented using the international phonetic alphabet (IPA) notation. ii. The algorithm is novel in using the Levenshtein distance metric on the IPA representation and in the way it measures overall distance between pairs of Swadesh lists. iii. Building a Swadesh list for the author's native Kinyarwanda language because a Swadesh list could not be found even after an extensive search for it.

Advisor: Peter Z. Revesz

On-Site And External Energy Harvesting In Underground Wireless, Usman Raza, Abdul Salam

Computer Information Technology Faculty Publications

Energy efficiency is vital for uninterrupted long-term operation of wireless underground communication nodes in the field of decision agriculture. In this paper, energy harvesting and wireless power transfer techniques are discussed with applications in underground wireless communications (UWC). Various external wireless power transfer techniques are explored. Moreover, key energy harvesting technologies are presented that utilize available energy sources in the field such as vibration, solar, and wind. In this regard, the Electromagnetic(EM)- and Magnetic Induction(MI)-based approaches are explained. Furthermore, the vibration-based energy harvesting models are reviewed as well. These energy harvesting approaches lead to design of an efficient wireless underground …

Accelerating Reinforcement Learning With Prioritized Experience Replay For Maze Game, Chaoshun Hu, Mehesh Kuklani, Paul Panek

SMU Data Science Review

In this paper we implemented two ways of improving the performance of reinforcement learning algorithms. We proposed a new equation to prioritize transition samples to improve model accuracy, and by deploying a generalized solver of randomly-generated two-dimensional mazes on a distributed computing platform, our dual-network model is available to others for further research and development. Reinforcement Learning is concerned with identifying the optimal sequence of actions for an agent to take in order to reach an objective to achieve the highest score in the future. Complex situations can lead to computational challenges in terms of both finding the best answer …

Qlime-A Quadratic Local Interpretable Model-Agnostic Explanation Approach, Steven Bramhall, Hayley Horn, Michael Tieu, Nibhrat Lohia

SMU Data Science Review

In this paper, we introduce a proof of concept that addresses the assumption and limitation of linear local boundaries by Local Interpretable Model-Agnostic Explanations (LIME), a popular technique used to add interpretability and explainability to black box models. LIME is a versatile explainer capable of handling different types of data and models. At the local level, LIME creates a linear relationship for a given prediction through generated sample points to present feature importance. We redefine the linear relationships presented by LIME as quadratic relationships and expand its flexibility in non-linear cases and improve the accuracy of feature interpretations. We coin …

The Data Market: A Proposal To Control Data About You, David Shaw, Daniel W. Engels

SMU Data Science Review

The current legal and economic infrastructure facilitating data collection practices and data analysis has led to extreme over-collection of data and the overall loss of personal privacy. Data over-collection has led to a secondary market for consumer data that is invisible to the consumer and results in a person's data being distributed far beyond their knowledge or control. In this paper, we propose a Data Market framework and design for personal data management and privacy protection in which the individual controls and profits from the dissemination of their data. Our proposed Data Market uses a market-based approach utilizing blockchain distributed …