Computer Engineering Commons^™

Modeling And Compensating Of Noise In Time-Of-Flight Sensors, Bryan Rodriguez

Electrical Engineering Theses and Dissertations

Three-dimensional (3D) sensors provide the ability to perform contactless measurements of objects and distances that are within their field of view. Unlike traditional two-dimensional (2D) cameras, which only provide RGB data about objects within a scene, 3D sensors are able to directly provide depth information for objects within a scene. Of these 3D sensing technologies, Time-of-Flight (ToF) sensors are becoming more compact which allows them to be more easily integrated with other devices and to find use in more applications. ToF sensors also provide several benefits over other 3D sensing technologies that increase the types of applications where ToF sensors …

Grammatical Triples Extraction For The Distant Reading Of Textual Corpora, Stephanie Buongiorno, Stephanie Buongiorno

Multidisciplinary Studies Theses and Dissertations

Grammatical triples extraction has become increasingly important for the analysis of large, textual corpora. By providing insight into the sentence-level linguistic features of a corpus, extracted triples have supported interpretations of some of the most relevant problems of our time. The growing importance of triples extraction for analyzing large corpora has put the quality of extracted triples under new scrutiny, however. Triples outputs are known to have large amounts of erroneous triples. The extraction of erroneous triples poses a risk for understanding a textual corpus because erroneous triples can be nonfactual and even analogous to misinformation. Disciplines such as the …

Self-Learning Algorithms For Intrusion Detection And Prevention Systems (Idps), Juan E. Nunez, Roger W. Tchegui Donfack, Rohit Rohit, Hayley Horn

SMU Data Science Review

Today, there is an increased risk to data privacy and information security due to cyberattacks that compromise data reliability and accessibility. New machine learning models are needed to detect and prevent these cyberattacks. One application of these models is cybersecurity threat detection and prevention systems that can create a baseline of a network's traffic patterns to detect anomalies without needing pre-labeled data; thus, enabling the identification of abnormal network events as threats. This research explored algorithms that can help automate anomaly detection on an enterprise network using Canadian Institute for Cybersecurity data. This study demonstrates that Neural Networks with Bayesian …

Towards Multipronged On-Chip Memory And Data Protection From Verification To Design And Test, Senwen Kan, Jennifer Dworak

Computer Science and Engineering Theses and Dissertations

Modern System on Chips (SoCs) generally include embedded memories, and these memories may be vulnerable to malicious attacks such as hardware trojan horses (HTHs), test access port exploitation, and malicious software. This dissertation contributes verification as well as design obfuscation solutions aimed at design level detection of memory HTH circuits as well as obfuscation to prevent HTH triggering for embedded memory during functional operation. For malicious attack vectors stemming from test/debug interfaces, this dissertation presents novel solutions that enhance design verification and securitization of an IJTAG based test access interface. Such solutions can enhance SoC protection by preventing memory test …

Energy Dissipation In A Sand Damper Under Cyclic Loading, Ehab Sabi

Civil and Environmental Engineering Theses and Dissertations

Various seismic and wind engineering designs and retrofit strategies have been in development to meet structures' proper and safe operation during earthquake and wind excitation. One such method is the addition of fluid and particle dampers, such as sand dampers, in an effort to reduce excessive and dangerous displacements of structures. The present study implements the discrete element method (DEM) to assess the performance of a pressurized sand damper (PSD) and characterize the dissipated energy under cyclic loading. The idea of a PSD is to exploit the increase in shearing resistance of sand under external pressure and the associated ability …

Performance Analytics Of Cloud Networks, Derek Phanekham

Computer Science and Engineering Theses and Dissertations

As the world becomes more inter-connected and dependent on the Internet, networks become ever more pervasive, and the stresses placed upon them more demanding. Similarly, the expectations of networks to maintain a high level of performance have also increased. Network performance is highly important to any business that operates online, depends on web traffic, runs any part of their infrastructure in a cloud environment, or even hosts their own network infrastructure. Depending upon the exact nature of a network, whether it be local or wide-area, 10 or 100 Gigabit, it will have distinct performance characteristics and it is important for …

Designing Autonomous Drone For Food Delivery In Gazebo/Ros Based Environments, Hrishitva Patel

Computer Science and Engineering Research

There has been a growing global trend towards convenience, speed, and ease in delivery services, and this has been further accelerated by the COVID pandemic. With the everincreasing demand for easily accessible deliveries and expanded delivery service coverage, it has become critical that innovations in this space be developed to further ensure the industry’s smooth operation. With the emergence of the COVID-19 pandemic, the inadequacies became more apparent, emphasizing the need to revolutionize and accelerate the trend in order to meet the increased demand. Drone delivery systems are of particular interest in this context because they can enable faster and …

Enhanced Security Utilizing Side Channel Data Analysis, Michael Taylor

Computer Science and Engineering Theses and Dissertations

The physical state of a system is affected by the activities and processes in which it is tasked with carrying out. In the past there have been many instances where such physical changes have been exploited by bad actors in order to gain insight into the operational state and even the data being held on a system. This method of side channel exploitation is very often effective due to the relative difficulty of obfuscating activity on a physical level. However, in order to take advantage of side channel data streams one must have a detailed working knowledge of how a …

Exploring Neural Networks For Predicting Sentinel-C Backscatter Between Image Acquisitions, Zhongdi Wu

Computer Science and Engineering Theses and Dissertations

Measuring moisture dynamics in soil and overlying vegetation is key to understanding ecosystem and agricultural dynamics in many contexts. For many applications, moisture information is demanded at high temporal frequency over large areas. Sentinel-1 C-band radar backscatter satellite images provide a repeating sequence of fine-resolution (10-m) observations that can be used to infer soil and vegetation moisture, but the 12-day interval between satellite observations is infrequent relative to the sensed moisture dynamics. Machine learning approaches have been used to predict soil moisture at higher spatial resolutions than the original satellite images, but little effort has been made to increase the …

Using A Light-Based Power Source To Defeat Power Analysis Attacks, Remus Valentin Tumac

Computer Science and Engineering Theses and Dissertations

Power analysis attacks exploit the correlation between the information processed by an electronic system and the power consumption of the system. By powering an electronic system with an optical power source, we can prevent meaningful information from being leaked to the power pins and captured in power traces. The relatively constant current draw of the optical power source hides any variability in the power consumption of the target system caused by the logic gates' switching activity of the system as observed at the power pins. This thesis will provide evidence to show that using an optical power source should make …

Reducing Power During Manufacturing Test Using Different Architectures, Yi Sun

Computer Science and Engineering Theses and Dissertations

Power during manufacturing test can be several times higher than power consumption in functional mode. Excessive power during test can cause IR drop, over-heating, and early aging of the chips. In this dissertation, three different architectures have been introduced to reduce test power in general cases as well as in certain scenarios, including field test.

In the first architecture, scan chains are divided into several segments. Every segment needs a control bit to enable capture in a segment when new faults are detectable on that segment for that pattern. Otherwise, the segment should be disabled to reduce capture power. We …

Bert For Question Answering On Bioasq, Eric R. Fu, Rikel Djoko, Maysam Mansor, Robert Slater

SMU Data Science Review

Machine reading comprehension and question answering are topics of considerable focus in the field of Natural Language Processing (NLP). In recent years, language models like Bidirectional Encoder Representations from Transformers (BERT) [3] have been very successful in language related tasks like question answering. The difficulty of the question answering task lies in developing accurate representations of language and being able to produce answers for questions. In this study, the focus is to investigate how to train and fine tune a BERT model to improve its performance on BioASQ, a challenge on large scale biomedical question answering. Our most accurate BERT …

Blockchain And Its Transformational Impact To Global Business, Mohammed Qaudeer

Operations Research and Engineering Management Theses and Dissertations

The advent of internet to the public back in 1994 resulted in the 4th industrial revolution disrupting and transforming business and communication models. As much as the transformation changed our lives and experiences, it has resulted in centralized models like Amazon and Facebook. It also resulted in exponential growth of Fraud, Identity theft, and lack of trust. Blockchain is considered an emerging technology of this era, which will trigger the 5th industrial revolution enabling another massive storm of disruptive transformation completely changing the current business models based on trust, security, collaboration and crypto currency. As the evolution of blockchain technology …

A 2.56 Gbps Serial Wireline Transceiver That Supports An Auxiliary Channel And A Hybrid Line Driver To Compensate Large Channel Loss, Xiaoran Wang

Electrical Engineering Theses and Dissertations

Serial transceiver links are widely used for high-speed point-to-point communications. This dissertation describes two transceiver link designs for two different applications.

In serial wireline communications, security is an increasingly important factor to concern. Securing an information processing system at the application and system software layers is regarded as a necessary but incomplete defense against the cyber security threats. In this dissertation, an asynchronous serial transceiver that is capable of transmitting and receiving an auxiliary data stream concurrently with the primary data stream is described. The transceiver instantiates the auxiliary data stream by modulating the phase of the primary data without …

Learning Deep Architectures For Power Systems Operation And Analysis, Mahdi Khodayar

Electrical Engineering Theses and Dissertations

With the rapid increase in size and computational complexities of power systems, the need for powerful computational models to capture strong patterns from energy datasets is emerged. In this thesis, we provide a comprehensive review on recent advances in deep neural architectures that lead to significant improvements in classification and regression problems in the area of power engineering. Furthermore, we introduce our novel deep learning methodologies proposed for a large variety of applications in this area. First, we present the interval deep probabilistic modeling for wind speed forecasting. Incorporating the Rough Set Theory into deep neural networks, we create an …

Machine Learning Applications In Power Systems, Xinan Wang

Electrical Engineering Theses and Dissertations

Machine learning (ML) applications have seen tremendous adoption in power system research and applications. For instance, supervised/unsupervised learning-based load forecasting and fault detection are classic ML topics that have been well studied. Recently, reinforcement learning-based voltage control, distribution analysis, etc., are also gaining popularity. Compared to conventional mathematical methods, ML methods have the following advantages: (i). better robustness against different system configurations due to its data-driven nature; (ii). better adaption to system uncertainties; (iii). less dependent on the modeling accuracy and validity of assumptions. However, due to the unique physics of the power grid, many problems cannot be directly solved …

Design Of A Drone-Flight-Enabled Wireless Isolation Chamber, John Wensowitch

Electrical Engineering Theses and Dissertations

The next wave of drone applications is moving from repeatable, single-drone activities such as evaluating propagation environments to team-based, multi-drone objectives such as drone-based emergency services. In parallel, testbeds have sought to evaluate emerging concepts such as highly-directional and distributed wireless communications. However, there is a lack of intersection between the two works to characterize the impact of the drone body, antenna placement, swarm topologies, and multi-dimensional connectivity needs that require in-flight experimentation with a surrounding testbed infrastructure. In this work, we design a drone-flight-enabled isolation chamber to capture complex spatial wireless channel relationships that drone links experience as applications …

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 …

Heuristic-Based Threat Analysis Of Register-Transfer-Level Hardware Designs, Wesley Layton Ellington

Electrical Engineering Theses and Dissertations

The development of globalized semiconductor manufacturing processes and supply chains has lead to an increased interest in hardware security as new types of hardware based attacks, called hardware Trojans, are being observed in industrial and military electronics. To combat this, a technique was developed to help analyze hardware designs at the register-transfer-level (RTL) and locate points of interest within a design that might be vulnerable to attack. This method aims to eventually enable the creation of an end-to-end design hardening solution that analyzes existing designs and suggests countermeasures for potential Trojan attacks. The method presented in this work uses a …

Identifying Customer Churn In After-Market Operations Using Machine Learning Algorithms, Vitaly Briker, Richard Farrow, William Trevino, Brent Allen

SMU Data Science Review

This paper presents a comparative study on machine learning methods as they are applied to product associations, future purchase predictions, and predictions of customer churn in aftermarket operations. Association rules are used help to identify patterns across products and find correlations in customer purchase behaviour. Studying customer behaviour as it pertains to Recency, Frequency, and Monetary Value (RFM) helps inform customer segmentation and identifies customers with propensity to churn. Lastly, Flowserve’s customer purchase history enables the establishment of churn thresholds for each customer group and assists in constructing a model to predict future churners. The aim of this model is …

Resource Allocation And Task Scheduling Optimization In Cloud-Based Content Delivery Networks With Edge Computing, Yang Peng

Operations Research and Engineering Management Theses and Dissertations

The extensive growth in adoption of mobile devices pushes global Internet protocol (IP) traffic to grow and content delivery network (CDN) will carry 72 percent of total Internet traffic by 2022, up from 56 percent in 2017. In this praxis, Interconnected Cache Edge (ICE) based on different public cloud infrastructures with multiple edge computing sites is considered to help CDN service providers (SPs) to maximize their operational profit. The problem of resource allocation and performance optimization is studied in order to maximize the cache hit ratio with available CDN capacity.

The considered problem is formulated as a multi-stage stochastic linear …

Machine Learning To Predict The Likelihood Of A Personal Computer To Be Infected With Malware, Maryam Shahini, Ramin Farhanian, Marcus Ellis

SMU Data Science Review

In this paper, we present a new model to predict the prob- ability that a personal computer will become infected with malware. The dataset is selected from a Kaggle competition supported by Mi- crosoft. The data includes computer configuration, owner information, installed software, and configuration information. In our research, sev- eral classification models are utilized to assign a probability of a machine being infected with malware. The LightGBM classifier is the optimum machine learning model by performing faster with higher efficiency and lower memory usage in this research. The LightGBM algorithm obtained a cross-validation ROC-AUC score of 74%. Leading factors …

Aws Ec2 Instance Spot Price Forecasting Using Lstm Networks, Jeffrey Lancon, Yejur Kunwar, David Stroud, Monnie Mcgee, Robert Slater

SMU Data Science Review

Cloud computing is a network of remote computing resources hosted on the Internet that allow users to utilize cloud resources on demand. As such, it represents a paradigm shift in the way businesses and industries think about digital infrastructure. With the shift from IT resources being a capital expenditure to a managed service, companies must rethink how they approach utilizing and optimizing these resources in order to maximize productivity and minimize costs. With proper resource management, cloud resources can be instrumental in reducing computing expenses.

Cloud resources are perishable commodities; therefore, cloud service providers have developed strategies to maximize utilization …

Long Term Software Quality And Reliability Assurance In A Small Company, Eric Abuta

Computer Science and Engineering Theses and Dissertations

Demonstrating software reliability across multiple software releases has become essential in making informed decisions of upgrading software releases without impacting significantly end users' characterized processes and software quality standards. Standard defect and workload data normally collected in a typical small software development organization can be used for this purpose. Objective of this study was to demonstrate how to measure software reliability in multiple releases and whether continuous defect fixes and code upgrades increased software reliability. This study looked at techniques such as trend test that evaluated software system's overall trend and stability, input domain reliability models (IDRM) that assessed system's …

Self-Driving Cars: Evaluation Of Deep Learning Techniques For Object Detection In Different Driving Conditions, Ramesh Simhambhatla, Kevin Okiah, Shravan Kuchkula, Robert Slater

SMU Data Science Review

Deep Learning has revolutionized Computer Vision, and it is the core technology behind capabilities of a self-driving car. Convolutional Neural Networks (CNNs) are at the heart of this deep learning revolution for improving the task of object detection. A number of successful object detection systems have been proposed in recent years that are based on CNNs. In this paper, an empirical evaluation of three recent meta-architectures: SSD (Single Shot multi-box Detector), R-CNN (Region-based CNN) and R-FCN (Region-based Fully Convolutional Networks) was conducted to measure how fast and accurate they are in identifying objects on the road, such as vehicles, pedestrians, …

A Grammar Based Approach To Distributed Systems Fault Diagnosis Using Log Files, Stephen Hanka

Computer Science and Engineering Theses and Dissertations

Diagnosing and correcting failures in complex, distributed systems is difficult. In a network of perhaps dozens of nodes, each of which is executing dozens of interacting applications, sometimes from different suppliers or vendors, finding the source of a system failure is a confusing, tedious piece of detective work. The person assigned this task must trace the failing command, event, or operation through the network components and find a deviation from the correct, desired interaction sequence. After a deviation is identified, the failing applications must be found, and the fault or faults traced to the incorrect source code.

Often the primary …

Finding Truth In Fake News: Reverse Plagiarism And Other Models Of Classification, Matthew Przybyla, David Tran, Amber Whelpley, Daniel W. Engels

SMU Data Science Review

As the digital age creates new ways of spreading news, fake stories are propagated to widen audiences. A majority of people obtain both fake and truthful news without knowing which is which. There is not currently a reliable and efficient method to identify “fake news”. Several ways of detecting fake news have been produced, but the various algorithms have low accuracy of detection and the definition of what makes a news item ‘fake’ remains unclear. In this paper, we propose a new method of detecting on of fake news through comparison to other news items on the same topic, as …

Comparative Study Of Sentiment Analysis With Product Reviews Using Machine Learning And Lexicon-Based Approaches, Heidi Nguyen, Aravind Veluchamy, Mamadou Diop, Rashed Iqbal

SMU Data Science Review

In this paper, we present a comparative study of text sentiment classification models using term frequency inverse document frequency vectorization in both supervised machine learning and lexicon-based techniques. There have been multiple promising machine learning and lexicon-based techniques, but the relative goodness of each approach on specific types of problems is not well understood. In order to offer researchers comprehensive insights, we compare a total of six algorithms to each other. The three machine learning algorithms are: Logistic Regression (LR), Support Vector Machine (SVM), and Gradient Boosting. The three lexicon-based algorithms are: Valence Aware Dictionary and Sentiment Reasoner (VADER), Pattern, …