Computer Engineering Commons^™

Leveraging Programmable Switches To Enhance The Performance Of Networks: Active And Passive Deployments, Elie Kfoury

Theses and Dissertations

The performance of networks today is drastically affected by: 1) switches equipped with large buffers, referred to as “bloated buffers”: due to the lack of programmability and traffic visibility in legacy switches, operators nowadays configure large buffers statically without considering the characteristics or dynamics of flows. Such buffers increase the delays on packets, causing the Quality of Service (QoS) of networked applications (e.g., voice over IP, web browsing) to degrade; 2) switches forwarding packets on a best-effort basis: traffic crossing a switch is heterogeneous in many ways. Mixing such traffic in a single queue without any QoS measures can drastically …

Digital Health Design For Improving Treatment Decisions, Akanksha Singh

Theses and Dissertations

In the age of artificial intelligence and large datasets, information retrieval by querying large databases is an impossible task for the common user due to the information overload. Recommender Systems (RS) for commercial applications like YouTube, Amazon and Netflix were designed to support users by finding items of interest based on their user profiles and various filtering techniques. Health Recommender Systems (HRS) is a category of RSs that provides immense opportunities for application across several healthcare domains and contexts including treatment decision support. Unlike RS applications that focus on analyzing consumer choices, a key differentiator for HRS applications is the …

A Semantic Web Approach To Fault Tolerant Autonomous Manufacturing, Fadi El Kalach

Theses and Dissertations

The next phase of manufacturing is centered on making the switch from traditional automated to autonomous systems. Future Factories are required to be agile, allowing for more customized production, and resistant to disturbances. Such production lines would have the capability to reallocate resources as needed and eliminate downtime while keeping up with market demands. These systems must be capable of complex decision making based on different parameters such as machine status, sensory data, and inspection results. Current manufacturing lines lack this complex capability and instead focus on low level decision making on the machine level without utilizing the generated data …

Real-Time Facial Expression Recognition Using Edge Ai Accelerators, Mark Heath Smith

Theses and Dissertations

Facial expression recognition is a popular and challenging area of research in machine learning applications. Facial expressions are critical to human communication and allow us to convey complex thoughts and emotions beyond spoken language. The complexity of facial expressions creates a difficult problem for computer vision systems, especially edge computing systems. Current Deep Learning (DL) methods rely on large-scale Convolutional Neural Networks (CNN) which require millions of floating point operations (FLOPS) to accomplish similar image classification tasks. However, on edge and IoT devices, large-scale convolutional models can cause problems due to memory and power limitations. The intent of this work …

On The Robustness Of Bayesian Network Learning Algorithms Against Malicious Attacks, Noah Joseph Geveke

Theses and Dissertations

Bayesian networks are effective tools for discovering relationships between variables in a data set. Algorithms that learn Bayesian networks from data fall into three categories: constraint-based, score-based, and hybrid. Hybrid algorithms contain a constraint testing sub-procedure as well as a score function to create the network. Malicious changes to the training set can cause invalid networks that do not model the true data. The effects of these changes have been demonstrated using the PC algorithm, a constraint-based algorithm. In this thesis a method was developed to measure the robustness of various algorithms to determine potential malicious changes. The robustness analysis …

An Overlay Architecture For Pattern Matching, Rasha Elham Karakchi

Theses and Dissertations

Deterministic and Non-deterministic Finite Automata (DFA and NFA) comprise the fundamental unit of work for many emerging big data applications, motivating recent efforts to develop Domain-Specific Architectures (DSAs) to exploit fine-grain parallelism available in automata workloads.

This dissertation presents NAPOLY (Non-Deterministic Automata Processor Over- LaY), an overlay architecture and associated software that attempt to maximally exploit on-chip memory parallelism for NFA evaluation. In order to avoid an upper bound in NFA size that commonly affects prior efforts, NAPOLY is optimized for runtime reconfiguration, allowing for full reconfiguration in 10s of microseconds. NAPOLY is also parameterizable, allowing for offline generation of …

Parsimonious Sociology Theory Construction: From A Computational Framework To Semantic-Based Parsimony Analysis, Mingzhe Du

Theses and Dissertations

In the social sciences, theories are used to explain and predict observed phenomena in the natural world. Theory construction is the research process of building testable scientific theories to explain and predict observed phenomena in the natural world. Conceptual new ideas and meanings of theories are conveyed through carefully chosen definitions and terms.

The principle of parsimony, an important criterion for evaluating the quality of theories (e.g., as exemplified by Occam’s Razor), mandates that we minimize the number of definitions (terms) used in a given theory.

Conventional methods for theory construction and parsimony analysis are based on heuristic approaches. However, …

A Machine Learning Based Approach To Accelerate Catalyst Discovery, Asif Jamil Chowdhury

Theses and Dissertations

Computational catalysis, in contrast to experimental catalysis, uses approximations such as density functional theory (DFT) to compute properties of reaction intermediates. But DFT calculations for a large number of surface species on variety of active site models are resource intensive. In this work, we are building a machine learning based predictive framework for adsorption energies of intermediate species, which can reduce the computational overhead significantly. Our work includes the study and development of appropriate machine learning models and effective fingerprints or descriptors to predict energies accurately for different scenarios. Furthermore, Bayesian inverse problem, that integrates experimental catalysis with its computational …

Development Of A National-Scale Big Data Analytics Pipeline To Study The Potential Impacts Of Flooding On Critical Infrastructures And Communities, Nattapon Donratanapat

Theses and Dissertations

With the rapid development of the Internet of Things (IoT) and Big data infrastructure, crowdsourcing techniques have emerged to facilitate data processing and problem solving particularly for flood emergences purposes. A Flood Analytics Information System (FAIS) has been developed as a Python Web application to gather Big data from multiple servers and analyze flooding impacts during historical and real-time events. The application is smartly designed to integrate crowd intelligence, machine learning (ML), and natural language processing of tweets to provide flood warning with the aim to improve situational awareness for flood risk management and decision making. FAIS allows the user …

A Novel And Inexpensive Solution To Build Autonomous Surface Vehicles Capable Of Negotiating Highly Disturbed Environments, Jason Moulton

Theses and Dissertations

This dissertation has four main contributions. The first contribution is the design and build of a fleet of long-range, medium-duration deployable autonomous surface vehicles (ASV). The second is the development, implementation, and testing of inex-pensive sensors to accurately measure wind, current, and depth environmental vari- ables. The third leverages the first two contributions, and is modeling the effects of environmental variables on an ASV, finally leading to the development of a dynamic controller enabling deployment in more uncertain conditions.

The motivation for designing and building a new ASV comes from the lack of availability of a flexible and modular platform …

Exploring Machine Learning Techniques To Improve Peptide Identification, Fawad Kirmani

Theses and Dissertations

The goal of this work is to improve proteotypic peptide prediction with lower pro- cessing time and better efficiency. Proteotypic peptides are the peptides in protein sequence that can be confidently observed by mass-spectrometry based proteomics. One of the widely used method for identifying peptides is tandem mass spectrometry (MS/MS). The peptides that need to be identified are compared with the accurate mass and elution time (AMT) tag database. The AMT tag database helps in reducing the processing time and increases the accuracy of the identified peptides. Prediction of proteotypic peptides has seen a rapid improvement in recent years for …

Inference Framework For Model Update And Development, Xiao Lin

Theses and Dissertations

Computational models play an important role in scientific discovery and engineering design. However, developing computational models is challenging, since the process always follows a path contaminated with errors and uncertainties. The uncertainties and errors inherent in computational models are the result of many factors, including experimental uncertainties, model structure inadequacies, uncertainties in model parameters and initial conditions, as well as errors due to numerical discretizations. To realize the full potential in applications it is critical to systematically and economically reduce the uncertainties inherent in all computational models.

Authenticating Users With 3d Passwords Captured By Motion Sensors, Jing Tian

Theses and Dissertations

Authentication plays a key role in securing various resources including corporate facilities or electronic assets. As the most used authentication scheme, knowledgebased authentication is easy to use but its security is bounded by how much a user can remember. Biometrics-based authentication requires no memorization but ‘resetting’ a biometric password may not always be possible. Thus, we propose study several behavioral biometrics (i.e., mid-air gestures) for authentication which does not have the same privacy or availability concerns as of physiological biometrics.

In this dissertation, we first propose a user-friendly authentication system Kin- Write that allows users to choose arbitrary, short and …

The Design, Development, And Evaluation Of A Usable And Privacy-Enhanced Telepresence Interface For Older Adults, Xian Wu

Theses and Dissertations

Maintaining health and wellness while aging-in-place independently is crucial for older adults. Telepresence technology can be potentially beneficial for this target population to stay socially connected. However, this technology is not specifically designed for older adults. For this target population to adopt such technology successfully, it is important to ensure that they do not experience usability barriers. This research uses HCI/HRI concepts and technology design principles for older adults to design, develop and test telepresence user interfaces (UI). This addresses the following research questions: 1): What are the essential usability and privacy-enhanced features needed to inform the design and development …

Ontology-Guided Pre-Release Inference Disruption, Mark Stephen Daniels

Theses and Dissertations

We investigate privacy violations occurring when non-confidential patient data is combined with medical domain ontologies to disclose a patient’s protected health information (PHI). We propose a framework that detects privacy violations and eliminates undesired inferences. Our inference channel removal process is based on controlling the release of the data items that lead to undesired inferences. These data items are either blocked from release or generalized to eliminate the disclosure of the PHI. We show that our method is sound and complete. Soundness means the only inference paths generated logically follow from released data and corresponding domain knowledge. Completeness means we …

Bytecode-Based Multiple Condition Coverage: An Initial Investigation, Srujana Bollina

Theses and Dissertations

Masking occurs when one condition prevents another condition from influencing the output of a Boolean expression. Logic-based adequacy criteria such as Multiple Condition Coverage (MCC) are designed to overcome masking at the within-expression level, but can offer no guarantees about masking in subsequent expressions. As a result, a Boolean expression written as a single complex statement will yield test cases that are more likely to overcome masking than when the expression is written as series of simple statements. Many approaches to automated analysis and test case generation for Java systems operate not on the source code representation of code, but …

Ms. An (Meeting Students’ Academic Needs): A Socially Adaptive Robot Tutor For Student Engagement In Math Education, Karina Liles

Theses and Dissertations

This research presents a new, socially adaptive robot tutor, Ms. An (Meeting Students’ Academic Needs). The goal of this research was to use a decision tree model to develop a socially adaptive robot tutor that predicted and responded to student emotion and performance to actively engage students in mathematics education. The novelty of this multi-disciplinary project is the combination of the fields of HRI, AI, and education. In this study we 1) implemented a decision tree model to classify student emotion and performance for use in adaptive robot tutoring-an approach not applied to educational robotics; 2) presented an intuitive interface …

Tracking, Detection And Registration In Microscopy Material Images, Hongkai Yu

Theses and Dissertations

Fast and accurate characterization of fiber micro-structures plays a central role for material scientists to analyze physical properties of continuous fiber reinforced composite materials. In materials science, this is usually achieved by continuously crosssectioning a 3D material sample for a sequence of 2D microscopic images, followed by a fiber detection/tracking algorithm through the obtained image sequence.

To speed up this process and be able to handle larger-size material samples, we propose sparse sampling with larger inter-slice distance in cross sectioning and develop a new algorithm that can robustly track large-scale fibers from such a sparsely sampled image sequence. In particular, …

On The Security And Quality Of Wireless Communications In Outdoor Mobile Environment, Sharaf J. Malebary

Theses and Dissertations

The rapid advancement in wireless technology along with their low cost and ease of deployment have been attracting researchers academically and commercially. Researchers from private and public sectors are investing into enhancing the reliability, robustness, and security of radio frequency (RF) communications to accommodate the demand and enhance lifestyle. RF base communications -by nature- are slower and more exposed to attacks than a wired base (LAN). Deploying such networks in various cutting-edge mobile platforms (e.g. VANET, IoT, Autonomous robots) adds new challenges that impact the quality directly. Moreover, adopting such networks in public outdoor areas make them vulnerable to various …

A Machine Learning Approach For Enhancing Security And Quality Of Service Of Optical Burst Switching Networks, Adel Dabash A. Rajab

Theses and Dissertations

The Optical Bust Switching (OBS) network has become one of the most promising switching technologies for building the next-generation of internet backbone infrastructure. However, OBS networks still face a number of security and Quality of Service (QoS) challenges, particularly from Burst Header Packet (BHP) flooding attacks. In OBS, a core switch handles requests, reserving one of the unoccupied channels for incoming data bursts (DB) through BHP. An attacker can exploit this fact and send malicious BHP without the corresponding DB. If unresolved, threats such as BHP flooding attacks can result in low bandwidth utilization, limited network performance, high burst loss …

Blind Change Point Detection And Regime Segmentation Using Gaussian Process Regression, Sourav Das

Theses and Dissertations

Time-series analysis is used heavily in modeling and forecasting weather, economics, medical data as well as in various other fields. Change point detection (CPD) means finding abrupt changes in the time-series when the statistical property of a certain part of it starts to differ. CPD has attracted a lot of attention in the artificial intelligence, machine learning and data mining communities. In this thesis, a novel CPD algorithm is introduced for segmenting multivariate time-series data. The proposed algorithm is a general pipeline to process any high dimensional multivariate time-series data using nonlinear non-parametric dynamic system. It consists of manifold learning …

Improving Facial Action Unit Recognition Using Convolutional Neural Networks, Shizhong Han

Theses and Dissertations

Recognizing facial action units (AUs) from spontaneous facial expression is a challenging problem, because of subtle facial appearance changes, free head movements, occlusions, and limited AU-coded training data. Most recently, convolutional neural networks (CNNs) have shown promise on facial AU recognition. However, CNNs are often overfitted and do not generalize well to unseen subject due to limited AU-coded training images. In order to improve the performance of facial AU recognition, we developed two novel CNN frameworks, by substituting the traditional decision layer and convolutional layer with the incremental boosting layer and adaptive convolutional layer respectively, to recognize the AUs from …

Underwater Cave Mapping And Reconstruction Using Stereo Vision, Nicholas Weidner

Theses and Dissertations

This work presents a systematic approach for 3-D mapping and reconstruction of underwater caves. Exploration of underwater caves is very important for furthering our understanding of hydrogeology, managing efficiently water resources, and advancing our knowledge in marine archaeology. Underwater cave exploration by human divers however, is a tedious, labor intensive, extremely dangerous operation, and requires highly skilled people. As such, it is an excellent fit for robotic technology. The proposed solution employs a stereo camera and a video-light. The approach utilizes the intersection of the cone of video-light with the cave boundaries resulting in the construction of a wire frame …

Mobile Application For Shipping Goods For Individuals And Truckers In India, Sendurr Selvaraj

Theses and Dissertations

India is a vast country with majority of its cities and towns connected through roads. Road transportation contributes to 86% share of the freight transport of the country with trucking companies dominating the entire space. With growing economy and demands raising, the quality of service of the trucking company remains poor. The major reasons are unorganized practice and lack of transparency. Moreover, limited access for customers to reach out to truckers to transport their goods.

This thesis aims to create a platform for customers and truckers to realize their needs with a help of a mobile application. Customers can search …

Improving Peptide Identification By Considering Ordered Amino Acid Usage, Ahmed Al-Qurri

Theses and Dissertations

Proteomics has made major progress in recent years after the sequencing of the genomes of a substantial number of organisms. A typical method for identifying peptides uses a database of peptides identified using tandem mass spectrometry (MS/MS). The profile of accurate mass and elution time (AMT) for peptides that need to be identified will be compared with this database. Restricting the search to those peptides detectable by MS will reduce processing time and more importantly increase accuracy. In addition, there are significant impacts for clinical studies. Proteotypic peptides are those peptides in a protein sequence that are most likely to …

Investigate Genomic 3d Structure Using Deep Neural Network, Yan Zhang

Theses and Dissertations

The 3D structures of the chromosomes play fundamental roles in essential cellular functions, e.g., gene regulation, gene expression, evolution and Hi-C technique provides the interaction density between loci on chromosomes. In this dissertation, we developed multiple algorithms, focusing the deep learning approach, to study the Hi-C datasets and the genomic 3D structures.

Building 3D structure of the genome one of the most critical purpose of the Hi-C technique. Recently, several approaches have been developed to reconstruct the 3D model of the chromosomes from HiC data. However, all of the methods are based on a particular mathematical model and lack of …

Visibility-Based Pursuit-Evasion In The Plane, Nicholas Michael Stiffler

Theses and Dissertations

As technological advances further increase the amount of memory and computing power available to mobile robots, we are seeing an unprecedented explosion in the utilization of deployable robots for various tasks. The speed at which robots begin to enter various domains is largely dependent on the availability of robust and efficient algorithms that are capable of solving the complex planning problems inherent to the given domain. One such domain which is experiencing unprecedented growth in recent years requires a robot to detect and/or track a mobile agent or group of agents.

In these scenarios, there are typically two players with …

A Hierarchical Framework For Phylogenetic And Ancestral Genome Reconstruction On Whole Genome Data, Lingxi Zhou

Theses and Dissertations

Gene order gets evolved under events such as rearrangements, duplications, and losses, which can change both the order and content along the genome, through the long history of genome evolution. Recently, the accumulation of genomic sequences provides researchers with the chance to handle long-standing problems about the phylogenies, or evolutionary histories, of sets of species, and ancestral genomic content and orders. Over the past few years, such problems have been proven so interesting that a large number of algorithms have been proposed in the attempt to resolve them, following different standards. The work presented in this dissertation focuses on algorithms …

Hydro-Geological Flow Analysis Using Hidden Markov Models, Chandrahas Raj Venkat Gurram

Theses and Dissertations

Hidden Markov Models a class of statistical models used in various disciplines for understanding speech, finding different types of genes responsible for cancer and much more. In this thesis, Hidden Markov Models are used to obtain hidden states that can correlate the flow changes in the Wakulla Spring Cave. Sensors installed in the tunnels of Wakulla Spring Cave have recorded huge correlated changes in the water flows at numerous tunnels. Assuming the correlated flow changes are a consequence of system being in a set of discrete states, a Hidden Markov Model is calculated. This model comprising all the sensors installed …

Revealing Malicious Contents Hidden In The Internet, Muhammad Nazmus Sakib

Theses and Dissertations

In this age of ubiquitous communication in which we can stay constantly connected with the rest of the world, for most of the part, we have to be grateful for one particular invention - the Internet. But as the popularity of Internet connectivity grows, it has become a very dangerous place where objects of malicious content and intent can be hidden in plain sight. In this dissertation, we investigate different ways to detect and capture these malicious contents hidden in the Internet. First, we propose an automated system that mimics high-risk browsing activities such as clicking on suspicious online ads, …