Computer Sciences Commons^™

Client Access Feature Engineering For The Homeless Community Of The City Of Portland, Oswaldo Ceballos Jr

altREU Projects

Given the severity of homeless in many cities across the country, the project at hand attempts to assist a service provider organization called Central City Concern (CCC) with their mission of providing services to the community of Portland. These services include housing, recovery, health care, and jobs. With many different types of services available through the works of CCC, there exists an abundance of information and data pertaining to the individuals that interact with the CCC service system. The goal of this project is to perform an exploratory analysis and feature engineer the existing datasets CCC has collected over the …

Teaching Machine Learning For The Physical Sciences: A Summary Of Lessons Learned And Challenges, Viviana Acquaviva

Publications and Research

This paper summarizes some challenges encountered and best practices established in several years of teaching Machine Learning for the Physical Sciences at the undergraduate and graduate level. I discuss motivations for teaching ML to physicists, desirable properties of pedagogical materials, such as accessibility, relevance, and likeness to real-world research problems, and give examples of components of teaching units.

Learning To Interpret Fluid Type Phenomena Via Images, Simron Thapa

LSU Doctoral Dissertations

Learning to interpret fluid-type phenomena via images is a long-standing challenging problem in computer vision. The problem becomes even more challenging when the fluid medium is highly dynamic and refractive due to its transparent nature. Here, we consider imaging through such refractive fluid media like water and air. For water, we design novel supervised learning-based algorithms to recover its 3D surface as well as the highly distorted underground patterns. For air, we design a state-of-the-art unsupervised learning algorithm to predict the distortion-free image given a short sequence of turbulent images. Specifically, we design a deep neural network that estimates the …

Panoramic Learning With A Standardized Machine Learning Formalism, Zhiting Hu, Eric P. Xing

Machine Learning Faculty Publications

Machine Learning (ML) is about computational methods that enable machines to learn concepts from experiences. In handling a wide variety of experiences ranging from data instances, knowledge, constraints, to rewards, adversaries, and lifelong interplay in an ever-growing spectrum of tasks, contemporary ML/AI research has resulted in a multitude of learning paradigms and methodologies. Despite the continual progresses on all different fronts, the disparate narrowly-focused methods also make standardized, composable, and reusable development of learning solutions difficult, and make it costly if possible to build AI agents that panoramically learn from all types of experiences. This paper presents a standardized ML …

Forensic Artifact Finder (Forensicaf): An Approach & Tool For Leveraging Crowd-Sourced Curated Forensic Artifacts, Tyler Balon, Krikor Herlopian, Ibrahim Baggili, Cinthya Grajeda-Mendez

Electrical & Computer Engineering and Computer Science Faculty Publications

Current methods for artifact analysis and understanding depend on investigator expertise. Experienced and technically savvy examiners spend a lot of time reverse engineering applications while attempting to find crumbs they leave behind on systems. This takes away valuable time from the investigative process, and slows down forensic examination. Furthermore, when specific artifact knowledge is gained, it stays within the respective forensic units. To combat these challenges, we present ForensicAF, an approach for leveraging curated, crowd-sourced artifacts from the Artifact Genome Project (AGP). The approach has the overarching goal of uncovering forensically relevant artifacts from storage media. We explain our approach …

Forensicast: A Non-Intrusive Approach & Tool For Logical Forensic Acquisition & Analysis Of The Google Chromecast Tv, Alex Sitterer, Nicholas Dubois, Ibrahim Baggili

Electrical & Computer Engineering and Computer Science Faculty Publications

The era of traditional cable Television (TV) is swiftly coming to an end. People today subscribe to a multitude of streaming services. Smart TVs have enabled a new generation of entertainment, not only limited to constant on-demand streaming as they now offer other features such as web browsing, communication, gaming etc. These functions have recently been embedded into a small IoT device that can connect to any TV with High Definition Multimedia Interface (HDMI) input known as Google Chromecast TV. Its wide adoption makes it a treasure trove for potential digital evidence. Our work is the primary source on forensically …

Space Science And Social Media: Automating Science Communication On Twitter, Maia Williams

Honors Projects

This project analyzes how social media is used to engage general audiences in astronomy and space science, as well as ways to improve engagement through automation. Tweets from five space science organizations were sampled. The engagement rate for each tweet was calculated from the number of interactions it received. Accounts that tweet more per day had more followers, and accounts with more followers received more interactions. This project also investigated how to build a Twitter bot to automate science communication. Using NASA Application Programming Interfaces, a Twitter bot was written in Python to tweet images taken by the NASA Mars …

An Adaptive Cryptosystem On A Finite Field, Awnon Bhowmik, Unnikrishnan Menon

Publications and Research

Owing to mathematical theory and computational power evolution, modern cryptosystems demand ingenious trapdoor functions as their foundation to extend the gap between an enthusiastic interceptor and sensitive information. This paper introduces an adaptive block encryption scheme. This system is based on product, exponent, and modulo operation on a finite field. At the heart of this algorithm lies an innovative and robust trapdoor function that operates in the Galois Field and is responsible for the superior speed and security offered by it. Prime number theorem plays a fundamental role in this system, to keep unwelcome adversaries at bay. This is a …

Deepsec: A Deep Learning Framework For Secreted Protein Discovery In Human Body Fluids, Dan Shao, Lan Huang, Yan Wang, Kai He, Xueteng Cui, Yao Wang, Qin Ma, Juan Cui

School of Computing: Faculty Publications

Motivation: Human proteins that are secreted into different body fluids from various cells and tissues can be promising disease indicators. Modern proteomics research empowered by both qualitative and quantitative profiling techniques has made great progress in protein discovery in various human fluids. However, due to the large number of proteins and diverse modifications present in the fluids, as well as the existing technical limits of major proteomics platforms (e.g. mass spectrometry), large discrepancies are often generated from different experimental studies. As a result, a comprehensive proteomics landscape across major human fluids are not well determined.

Results: To bridge …

Automated Statistical Structural Testing Techniques And Applications, Yang Shi

Dissertations and Theses

Statistical structural testing(SST) is an effective testing technique that produces random test inputs from probability distributions. SST shows superiority in fault-revealing power over random testing and deterministic approaches since it heritages the merits from both of them. SST ensures testing thoroughness by setting up a probability lower-bound criterion for each structural cover element and test inputs that exercise a structural cover element sampled from the probability distribution, ensuring testing randomness. Despite the advantages, SST is not a widely used approach in practice. There are two major limitations. First, to construct probability distributions, a tester must understand the underlying software's structure, …

Photoacoustic Imaging, Feature Extraction, And Machine Learning Implementation For Ovarian And Colorectal Cancer Diagnosis, Eghbal Amidi

McKelvey School of Engineering Graduate Student Theses & Dissertations

Among all cancers related to women’s reproductive systems, ovarian cancer has the highest mortality rate. Pelvic examination, transvaginal ultrasound (TVUS), and blood testing for cancer antigen 125 (CA-125), are the conventional screening tools for ovarian cancer, but they offer very low specificity. Other tools, such as magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET), also have limitations in detecting small lesions. In the USA, considering men and women separately, colorectal cancer is the third most common cause of death related to cancer; for men and women combined, it is the second leading cause of cancer deaths. …

A Neuromorphic Machine Learning Framework Based On The Growth Transform Dynamical System, Ahana Gangopadhyay

McKelvey School of Engineering Graduate Student Theses & Dissertations

As computation increasingly moves from the cloud to the source of data collection, there is a growing demand for specialized machine learning algorithms that can perform learning and inference at the edge in energy and resource-constrained environments. In this regard, we can take inspiration from small biological systems like insect brains that exhibit high energy-efficiency within a small form-factor, and show superior cognitive performance using fewer, coarser neural operations (action potentials or spikes) than the high-precision floating-point operations used in deep learning platforms. Attempts at bridging this gap using neuromorphic hardware has produced silicon brains that are orders of magnitude …

Preference Elicitation In Constraint-Based Models: Models, Algorithms, And Applications, Atena M. Tabakhi

McKelvey School of Engineering Graduate Student Theses & Dissertations

Constraint-based models offer powerful approaches for describing and resolving many combinatorial optimization problems in a centralized or distributed environment. In such models, the goal is to find a value assignment to a set of variables given a set of preferences expressed by means of cost functions such that the sum over all costs is optimized. The importance of constraint-based models is outlined by the impact of their applications in a wide range of agent-based systems. Many real-life combinatorial problems can be naturally formalized using constraint-based models. Examples of such applications are supply-chain management, roster scheduling, meeting scheduling, combinatorial auctions, bioinformatics, …

Reasoning About Scene And Image Structure For Computer Vision, Zhihao Xia

McKelvey School of Engineering Graduate Student Theses & Dissertations

The wide availability of cheap consumer cameras has democratized photography for novices and experts alike, with more than a trillion photographs taken each year. While many of these cameras---especially those on mobile phones---have inexpensive optics and make imperfect measurements, the use of modern computational techniques can allow the recovery of high-quality photographs as well as of scene attributes.

In this dissertation, we explore algorithms to infer a wide variety of physical and visual properties of the world, including color, geometry, reflectance etc., from images taken by casual photographers in unconstrained settings. We specifically focus on neural network-based methods, while incorporating …

Bayesian Quadrature With Prior Information: Modeling And Policies, Henry Chai

McKelvey School of Engineering Graduate Student Theses & Dissertations

Quadrature is the problem of estimating intractable integrals. Such integrals regularly arise in engineering and the natural sciences, especially when Bayesian methods are applied; examples include model evidences, normalizing constants and marginal distributions. This dissertation explores Bayesian quadrature, a probabilistic, model-based quadrature method. Specifically, we study different ways in which Bayesian quadrature can be adapted to account for different kinds of prior information one may have about the task. We demonstrate that by taking into account prior knowledge, Bayesian quadrature can outperform commonly used numerical methods that are agnostic to prior knowledge, such as Monte Carlo based integration. We focus …

Continuous-Time And Complex Growth Transforms For Analog Computing And Optimization, Oindrila Chatterjee

McKelvey School of Engineering Graduate Student Theses & Dissertations

Analog computing is a promising and practical candidate for solving complex computational problems involving algebraic and differential equations. At the fundamental level, an analog computing framework can be viewed as a dynamical system that evolves following fundamental physical principles, like energy minimization, to solve a computing task. Additionally, conservation laws, such as conservation of charge, energy, or mass, provide a natural way to couple and constrain spatially separated variables. Taking a cue from these observations, in this dissertation, I have explored a novel dynamical system-based computing framework that exploits naturally occurring analog conservation constraints to solve a variety of optimization …

Machine Learning For Analog/Mixed-Signal Integrated Circuit Design Automation, Weidong Cao

McKelvey School of Engineering Graduate Student Theses & Dissertations

Analog/mixed-signal (AMS) integrated circuits (ICs) play an essential role in electronic systems by processing analog signals and performing data conversion to bridge the analog physical world and our digital information world.Their ubiquitousness powers diverse applications ranging from smart devices and autonomous cars to crucial infrastructures. Despite such critical importance, conventional design strategies of AMS circuits still follow an expensive and time-consuming manual process and are unable to meet the exponentially-growing productivity demands from industry and satisfy the rapidly-changing design specifications from many emerging applications. Design automation of AMS IC is thus the key to tackling these challenges and has been …

Machine Learning In Complex Scientific Domains: Hospitalization Records, Drug Interactions, Predictive Modeling And Fairness For Class Imbalanced Data, Arghya Datta

McKelvey School of Engineering Graduate Student Theses & Dissertations

Machine learning has demonstrated potential in analyzing large, complex datasets and has become ubiquitous across many fields of scientific research. As machine learning is actively deployed in many complex and critical domains, it is essential for machine learning to engage with domain expertise to aid in knowledge discovery as well as address challenges in predictive modeling in complex domains. Domain expertise represents an essential and elaborate collection of knowledge that is often under-utilized when applying machine learning in complex domains. In this dissertation, I have addressed existing challenges regarding knowledge discovery in complex domains via engagement with domain expertise, particularly …

Duck Hunt: Memory Forensics Of Usb Attack Platforms, Tyler Thomas, Mathew Piscitelli, Bhavik Ashok Nahar, Ibrahim Baggili

Electrical & Computer Engineering and Computer Science Faculty Publications

To explore the memory forensic artifacts generated by USB-based attack platforms, we analyzed two of the most popular commercially available devices, Hak5's USB Rubber Ducky and Bash Bunny. We present two open source Volatility plugins, usbhunt and dhcphunt, which extract artifacts generated by these USB attacks from Windows 10 system memory images. Such artifacts include driver-related diagnostic events, unique device identifiers, and DHCP client logs. Our tools are capable of extracting metadata-rich Windows diagnostic events generated by any USB device. The device identifiers presented in this work may also be used to definitively detect device usage. Likewise, the DHCP logs …

Another Brick In The Wall: An Exploratory Analysis Of Digital Forensics Programs In The United States, Syria Mccullough, Stella Abudu, Ebere Onwubuariri, Ibrahim Baggili

Electrical & Computer Engineering and Computer Science Faculty Publications

We present a comprehensive review of digital forensics programs offered by universities across the United States (U.S.). While numerous studies on digital forensics standards and curriculum exist, few, if any, have examined digital forensics courses offered across the nation. Since digital forensics courses vary from university to university, online course catalogs for academic institutions were evaluated to curate a dataset. Universities were selected based on online searches, similar to those that would be made by prospective students. Ninety-seven (n = 97) degree programs in the U.S. were evaluated. Overall, results showed that advanced technical courses are missing from curricula. We …

Who Creates Strong Passwords When Nudging Fails, Shelia M. Kennison, Ian T. Jones, Victoria H. Spooner, D. Eric Chan-Tin

Computer Science: Faculty Publications and Other Works

The use of strong passwords is viewed as a recommended cybersecurity practice, as the hacking of weak passwords led to major cybersecurity breaches. The present research investigated whether nudging with messages based on participants’ self-schemas could lead them to create stronger passwords. We modeled our study on prior health-related research demonstrating positive results using messages based on self-schema categories (i.e., True Colors categories -compassionate, loyal, intellectual, and adventurous). We carried out an online study, one with 256 (185 women, 66 men, 5 other) undergraduates and one with 424 (240 men, 179 women, 5 other) Amazon Mechanical Turk (MTurk) workers, in …

Electronic Voting Implementation Through Bitcoin Blockchain Technology, Cassie Schultz

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

Even with all the advances we have seen in secure digital technology, the most secure way to currently cast a vote on election day consist of a hand-marked paper ballot. When extenuating circumstances arise, offering a voting environment that is accessible and safe for everyone, but also secure can be a difficult task under the current voting system. This paper discusses one proposed electronic voting system which uses blockchain technology. Based on a review of literature on blockchain technology and specific implementations of voting systems, a summary of relevant background information as well as implementation protocol are provided. Even though …

Browser Fingerprinting And The Importance Of Digital Privacy, Aaron M. Corpstein

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

Browser fingerprinting is a type of internet tracking where the attributes of a user’s computer and browser accessing a web page are remotely recorded and then used for profiling, tracking, and advertising purposes. This paper focuses on defining browser fingerprinting and enumerating ways in which the user can combat fingerprinting. Browser fingerprinting can be thwarted by changing attributes within the user’s browser or machine, using a browser designed to combat fingerprinting, or with security and anti-fingerprinting focused browser extensions. All of these methods are capable of increasing the security of the user.

A Look Into User's Privacy Perceptions And Data Practices Of Iot Devices, Mahdi Nasrullah Al-Ameen, Apoorva Chauhan, M.A. Manazir Ahsan, Huzeyfe Kocabas

Computer Science Student Research

Purpose: With the rapid deployment of Internet of Things (IoT) technologies, it has been essential to address the security and privacy issues through maintaining transparency in data practices. The prior research focused on identifying people’s privacy preferences in different contexts of IoT usage, and their mental models of security threats. However, there is a dearth in existing literature to understand the mismatch between user’s perceptions and the actual data practices of IoT devices. Such mismatches could lead users unknowingly sharing their private information, exposing themselves to unanticipated privacy risks. We aim to identify these mismatched privacy perceptions in our work. …

An Automated Method To Enrich Consumer Health Vocabularies Using Glove Word Embeddings And An Auxiliary Lexical Resource, Mohammed Ibrahim, Susan Gauch, Omar Salman, Mohammed Alqahtani

Computer Science and Computer Engineering Faculty Publications and Presentations

Background

Clear language makes communication easier between any two parties. A layman may have difficulty communicating with a professional due to not understanding the specialized terms common to the domain. In healthcare, it is rare to find a layman knowledgeable in medical terminology which can lead to poor understanding of their condition and/or treatment. To bridge this gap, several professional vocabularies and ontologies have been created to map laymen medical terms to professional medical terms and vice versa.

Objective

Many of the presented vocabularies are built manually or semi-automatically requiring large investments of time and human effort and consequently the …

Telomere Roles In Fungal Genome Evolution And Adaptation, Mostafa Rahnama, Baohua Wang, Jane Dostart, Olga Novikova, Daniel Yackzan, Andrew T. Yackzan, Haley Bruss, Maray Baker, Haven Jacob, Xiaofei Zhang, April Lamb, Alex Stewart, Melanie Heist, Joey Hoover, Patrick Calie, Li Chen, Jinze Liu, Mark L. Farman

Plant Pathology Faculty Publications

Telomeres form the ends of linear chromosomes and usually comprise protein complexes that bind to simple repeated sequence motifs that are added to the 3′ ends of DNA by the telomerase reverse transcriptase (TERT). One of the primary functions attributed to telomeres is to solve the “end-replication problem” which, if left unaddressed, would cause gradual, inexorable attrition of sequences from the chromosome ends and, eventually, loss of viability. Telomere-binding proteins also protect the chromosome from 5′ to 3′ exonuclease action, and disguise the chromosome ends from the double-strand break repair machinery whose illegitimate action potentially generates catastrophic chromosome aberrations. Telomeres …

Quantum Grover's Oracles With Symmetry Boolean Functions, Peng Gao

Dissertations and Theses

Quantum computing has become an important research field of computer science and engineering. Among many quantum algorithms, Grover's algorithm is one of the most famous ones. Designing an effective quantum oracle poses a challenging conundrum in circuit and system-level design for practical application realization of Grover's algorithm.

In this dissertation, we present a new method to build quantum oracles for Grover's algorithm to solve graph theory problems. We explore generalized Boolean symmetric functions with lattice diagrams to develop a low quantum cost and area efficient quantum oracle. We study two graph theory problems: cycle detection of undirected graphs and generalized …

High-Throughput Discovery Of Novel Cubic Crystal Materials Using Deep Generative Neural Networks, Yong Zhao, Mohammed Al-Fahdi, Ming Hu, Edirisuriya M.D. Siriwardane, Yuqi Song, Alireza Nasiri, Jianjun Hu

Faculty Publications

High-throughput screening has become one of the major strategies for the discovery of novel functional materials. However, its effectiveness is severely limited by the lack of sufficient and diverse materials in current materials repositories such as the open quantum materials database (OQMD). Recent progress in deep learning have enabled generative strategies that learn implicit chemical rules for creating hypothetical materials with new compositions and structures. However, current materials generative models have difficulty in generating structurally diverse, chemically valid, and stable materials. Here we propose CubicGAN, a generative adversarial network (GAN) based deep neural network model for large scale generative design …

Fast Multipole Methods For Wave And Charge Source Interactions In Layered Media And Deep Neural Network Algorithms For High-Dimensional Pdes, Wenzhong Zhang

Mathematics Theses and Dissertations

In this dissertation, we develop fast algorithms for large scale numerical computations, including the fast multipole method (FMM) in layered media, and the forward-backward stochastic differential equation (FBSDE) based deep neural network (DNN) algorithms for high-dimensional parabolic partial differential equations (PDEs), addressing the issues of real-world challenging computational problems in various computation scenarios.

We develop the FMM in layered media, by first studying analytical and numerical properties of the Green's functions in layered media for the 2-D and 3-D Helmholtz equation, the linearized Poisson--Boltzmann equation, the Laplace's equation, and the tensor Green's functions for the time-harmonic Maxwell's equations and the …

Classification Of Explainable Artificial Intelligence Methods Through Their Output Formats, Giulia Vilone, Luca Longo

Articles

Machine and deep learning have proven their utility to generate data-driven models with high accuracy and precision. However, their non-linear, complex structures are often difficult to interpret. Consequently, many scholars have developed a plethora of methods to explain their functioning and the logic of their inferences. This systematic review aimed to organise these methods into a hierarchical classification system that builds upon and extends existing taxonomies by adding a significant dimension—the output formats. The reviewed scientific papers were retrieved by conducting an initial search on Google Scholar with the keywords “explainable artificial intelligence”; “explainable machine learning”; and “interpretable machine learning”. …