Computer Engineering Commons^™

Machine Learning For Omics Data Analysis., Ameni Trabelsi

Electronic Theses and Dissertations

In proteomics and metabolomics, to quantify the changes of abundance levels of biomolecules in a biological system, multiple sample analysis steps are involved. The steps include mass spectrum deconvolution and peak list alignment. Each analysis step introduces a certain degree of technical variation in the abundance levels (i.e. peak areas) of those molecules. Some analysis steps introduce technical variations that affect the peak areas of all molecules equally while others affect the peak areas of a subset of molecules with varying degrees. To correct these technical variations, some existing normalization methods simply scale the peak areas of all molecules detected …

End-To-End Learning Framework For Circular Rna Classification From Other Long Non-Coding Rnas Using Multi-Modal Deep Learning., Mohamed Chaabane

Electronic Theses and Dissertations

Over the past two decades, a circular form of RNA (circular RNA) produced from splicing mechanism has become the focus of scientific studies due to its major role as a microRNA (miR) ac tivity modulator and its association with various diseases including cancer. Therefore, the detection of circular RNAs is a vital operation for continued comprehension of their biogenesis and purpose. Prediction of circular RNA can be achieved by first distinguishing non-coding RNAs from protein coding gene transcripts, separating short and long non-coding RNAs (lncRNAs), and finally pre dicting circular RNAs from other lncRNAs. However, available tools to distinguish circular …

Robust Fuzzy Clustering For Multiple Instance Regression., Mohamed Trabelsi

Electronic Theses and Dissertations

Multiple instance regression (MIR) operates on a collection of bags, where each bag contains multiple instances sharing an identical real-valued label. Only few instances, called primary instances, contribute to the bag labels. The remaining instances are noise and outliers observations. The goal in MIR is to identify the primary instances within each bag and learn a regression model that can predict the label of a previously unseen bag. In this thesis, we introduce an algorithm that uses robust fuzzy clustering with an appropriate distance to learn multiple linear models from a noisy feature space simultaneously. We show that fuzzy memberships …

Network Science Algorithms For Mobile Networks., Heba Mohamed Elgazzar

Electronic Theses and Dissertations

Network Science is one of the important and emerging fields in computer science and engineering that focuses on the study and analysis of different types of networks. The goal of this dissertation is to design and develop network science algorithms that can be used to study and analyze mobile networks. This can provide essential information and knowledge that can help mobile networks service providers to enhance the quality of the mobile services. We focus in this dissertation on the design and analysis of different network science techniques that can be used to analyze the dynamics of mobile networks. These techniques …

A Proposed Approach To Hybrid Software-Hardware Application Design For Enhanced Application Performance, Alex Shipman

Graduate Theses and Dissertations

One important aspect of many commercial computer systems is their performance; therefore, system designers seek to improve the performance next-generation systems with respect to previous generations. This could mean improved computational performance, reduced power consumption leading to better battery life in mobile devices, smaller form factors, or improvements in many areas. In terms of increased system speed and computation performance, processor manufacturers have been able to increase the clock frequency of processors up to a point, but now it is more common to seek performance gains through increased parallelism (such as a processor having more processor cores on a single …

Asynchronous Circuit Stacking For Simplified Power Management, Andrew Lloyd Suchanek

Graduate Theses and Dissertations

As digital integrated circuits (ICs) continue to increase in complexity, new challenges arise for designers. Complex ICs are often designed by incorporating multiple power domains therefore requiring multiple voltage converters to produce the corresponding supply voltages. These converters not only take substantial on-chip layout area and/or off-chip space, but also aggregate the power loss during the voltage conversions that must occur fast enough to maintain the necessary power supplies. This dissertation work presents an asynchronous Multi-Threshold NULL Convention Logic (MTNCL) “stacked” circuit architecture that alleviates this problem by reducing the number of voltage converters needed to supply the voltage the …

Real-Time Streaming Video And Image Processing On Inexpensive Hardware With Low Latency, Richard L. Gregg

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

The use of resource constrained inexpensive hardware places restrictions on the design of streaming video and image processing system performance. In order to achieve acceptable frame-per-second (fps) performance with low latency, it is important to understand the response time requirements that the system needs to meet. For humans to be able to process and react to an image there should not be more than a 100ms delay between the time a camera captures an image and subsequently displays that image to the user.

In order to accomplish this goal, several design considerations need to be taken into account that limit …

A Qualitative Research On Marketing And Sales In The Artificial Intelligence Age, Yin Yang, Keng Siau

Research Collection School Of Computing and Information Systems

The age of artificial intelligence is here! Artificial Intelligence, robotics, machine learning, and automation are impacting the field of marketing and sales in an unprecedented way. In this study, the qualitative research methodology will be used to better understand the revolution and evolution of marketing and sales field in the AI age. Multiple case studies will be performed in various marketing and sales units in different organizations. This research is of value to both academics and practitioners as it aims to provide a detailed analysis and documentation of the changes in marketing and sales functionalities and job markets as AI …

Breathing-Based Authentication On Resource-Constrained Iot Devices Using Recurrent Neural Networks, Jagmohan Chauhan, Suranga Seneviratne, Yining Hu, Archan Misra, Aruna Seneviratne, Youngki Lee

Research Collection School Of Computing and Information Systems

Recurrent neural networks (RNNs) have shown promising resultsin audio and speech-processing applications. The increasingpopularity of Internet of Things (IoT) devices makes a strongcase for implementing RNN-based inferences for applicationssuch as acoustics-based authentication and voice commandsfor smart homes. However, the feasibility and performance ofthese inferences on resource-constrained devices remain largelyunexplored. The authors compare traditional machine-learningmodels with deep-learning RNN models for an end-to-endauthentication system based on breathing acoustics.

Wisdom Of Artificial Crowds Feature Selection In Untargeted Metabolomics: An Application To The Development Of A Blood-Based Diagnostic Test For Thrombotic Myocardial Infarction, Patrick J. Trainor, Roman V. Yampolskiy, Andrew P. Defilippis

Faculty and Staff Scholarship

Introduction: Heart disease remains a leading cause of global mortality. While acute myocardial infarction (colloquially: heart attack), has multiple proximate causes, proximate etiology cannot be determined by a blood-based diagnostic test. We enrolled a suitable patient cohort and conducted a non-targeted quantification of plasma metabolites by mass spectrometry for developing a test that can differentiate between thrombotic MI, non-thrombotic MI, and stable disease. A significant challenge in developing such a diagnostic test is solving the NP-hard problem of feature selection for constructing an optimal statistical classifier. Objective: We employed a Wisdom of Artificial Crowds (WoAC) strategy for solving the feature …

Remote Vibration Estimation Using Displaced-Phase-Center Antenna Sar For Strong Clutter Environments, Justin B. Campbell, Francisco Pérez, Qi Wang, Balasubramaniam Santhanam, Ralf Dunkel, Armin W. Doerry, Thomas Atwood, Majeed M. Hayat

Electrical and Computer Engineering Faculty Research and Publications

It has been previously demonstrated that it is possible to perform remote vibrometry using synthetic aperture radar (SAR) in conjunction with the discrete fractional Fourier transform (DFrFT). Specifically, the DFrFT estimates the chirp parameters (related to the instantaneous acceleration of a vibrating object) of a slow-time signal associated with the SAR image. However, ground clutter surrounding a vibrating object introduces uncertainties in the estimate of the chirp parameter retrieved via the DFrFT method. To overcome this shortcoming, various techniques based on subspace decomposition of the SAR slow-time signal have been developed. Nonetheless, the effectiveness of these techniques is limited to …

Service Quality Assessment For Cloud-Based Distributed Data Services, Arun Adiththan

Dissertations, Theses, and Capstone Projects

The issue of less-than-100% reliability and trust-worthiness of third-party controlled cloud components (e.g., IaaS and SaaS components from different vendors) may lead to laxity in the QoS guarantees offered by a service-support system S to various applications. An example of S is a replicated data service to handle customer queries with fault-tolerance and performance goals. QoS laxity (i.e., SLA violations) may be inadvertent: say, due to the inability of system designers to model the impact of sub-system behaviors onto a deliverable QoS. Sometimes, QoS laxity may even be intentional: say, to reap revenue-oriented benefits by cheating on resource allocations and/or …

K-Means: A Revisit, Wan-Lei Zhao, Cheng-Hao Deng, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Due to its simplicity and versatility, k-means remains popular since it was proposed three decades ago. The performance of k-means has been enhanced from different perspectives over the years. Unfortunately, a good trade-off between quality and efficiency is hardly reached. In this paper, a novel k-means variant is presented. Different from most of k-means variants, the clustering procedure is driven by an explicit objective function, which is feasible for the whole l(2)-space. The classic egg-chicken loop in k-means has been simplified to a pure stochastic optimization procedure. The procedure of k-means becomes simpler and converges to a considerably better local …

Building A Smart Nation: Singapore’S Digital Journey, Siu Loon Hoe

Research Collection School Of Computing and Information Systems

The journey towards smart city status is a strong global trend as governments around the world strive to harness technology to improve the quality of life for their citizens (United Nations, 2016). The widespread phenomenon of becoming “smart” is a key topic of discussion and research that continues to change as new digital technologies develop (Ishkineeva et al., 2015). The smart cities theme is important because it explores how governments, as providers of public goods, harness digital technologies to improve the lives of citizens around the world in the present and the future.

Optimizing The Use Of A Liquid Handling Robot To Conduct A High Throughput Forward Chemical Genetics Screen Of Arabidopsis Thaliana, B. Kirtley Amos, Victoria G. Pook, Seth Debolt

Horticulture Faculty Publications

Chemical genetics is increasingly being employed to decode traits in plants that may be recalcitrant to traditional genetics due to gene redundancy or lethality. However, the probability of a synthetic small molecule being bioactive is low; therefore, thousands of molecules must be tested in order to find those of interest. Liquid handling robotics systems are designed to handle large numbers of samples, increasing the speed with which a chemical library can be screened in addition to minimizing/standardizing error. To achieve a high-throughput forward chemical genetics screen of a library of 50,000 small molecules on Arabidopsis thaliana (Arabidopsis), protocols using a …

A Strategic Audit Of Chegg, Jacob Melcher

Honors Program: Senior Projects (Public)

The paper researches and discusses the strategy of Chegg in the past and future with regards to what was taught in UNL’s MNGT 495H course. The data was compiled from online resources including the company’s website and financials along with insights learned during an internship and interviews done in the Summer of 2016 and Spring of 2018. The insights of how Chegg went from a textbook rental company to the student learning hub it is today include experienced leaders, acquisitions and mergers, and being ahead of the curve in the industry. The final recommendation for Chegg’s strategy is to widen …

Comparative Study Of Deep Learning Models For Network Intrusion Detection, Brian Lee, Sandhya Amaresh, Clifford Green, Daniel Engels

SMU Data Science Review

In this paper, we present a comparative evaluation of deep learning approaches to network intrusion detection. A Network Intrusion Detection System (NIDS) is a critical component of every Internet connected system due to likely attacks from both external and internal sources. A NIDS is used to detect network born attacks such as Denial of Service (DoS) attacks, malware replication, and intruders that are operating within the system. Multiple deep learning approaches have been proposed for intrusion detection systems. We evaluate three models, a vanilla deep neural net (DNN), self-taught learning (STL) approach, and Recurrent Neural Network (RNN) based Long Short …

Comparative Study: Reducing Cost To Manage Accessibility With Existing Data, Claire Chu, Bill Kerneckel, Eric C. Larson, Nathan Mowat, Christopher Woodard

SMU Data Science Review

“Project Sidewalk” is an existing research effort that focuses on mapping accessibility issues for handicapped persons to efficiently plan wheelchair and mobile scooter friendly routes around Washington D.C. As supporters of this project, we utilized the data “Project Sidewalk” collected and used it to confirm predictions about where problem sidewalks exist based on real estate and crime data. We present a study that identifies correlations found between accessibility data and crime and housing statistics in the Washington D.C. metropolitan area. We identify the key reasons for increased accessibility and the issues with the current infrastructure management system. After a thorough …

Distributed Iterative Graph Processing Using Nosql With Data Locality, Ayam Pokhrel

LSU Master's Theses

A tremendous amount of data is generated every day from a wide range of sources such as social networks, sensors, and application logs. Among them, graph data is one type that represents valuable relationships between various entities. Analytics of large graphs has become an essential part of business processes and scientific studies because it leads to deep and meaningful insights into the related domain based on the connections between various entities. However, the optimal processing of large-scale iterative graph computations is very challenging due to the issues like fault tolerance, high memory requirement, parallelization, and scalability. Most of the contemporary …

Library Awesome Sauce Undergraduate Research, Jeremy Evert, Phillip Joe Fitzsimmons, Hector Lucas

Faculty Articles & Research

Library Awesome Sauce Undergraduate Research was a presentation at the 2018 CADRE Conference in Stillwater, OK. The presenters discussed their collaboration on a video project to film interviews of students giving progress reports about their software engineering projects. The videos were posted on the institutional repository.

The speakers discussed Student-Led research and the role that academic libraries play in facilitating student and faculty research and publishing for all disciplines on campus.