Computer Sciences Commons^™

From Invisibility To Readability: Recovering The Ink Of Herculaneum, Clifford Seth Parker, Stephen Parsons, Jack Bandy, Christy Chapman, Frederik Coppens, William Brent Seales

Computer Science Faculty Publications

The noninvasive digital restoration of ancient texts written in carbon black ink and hidden inside artifacts has proven elusive, even with advanced imaging techniques like x-ray-based micro-computed tomography (micro-CT). This paper identifies a crucial mistaken assumption: that micro-CT data fails to capture any information representing the presence of carbon ink. Instead, we show new experiments indicating a subtle but detectable signature from carbon ink in micro-CT. We demonstrate a new computational approach that captures, enhances, and makes visible the characteristic signature created by carbon ink in micro-CT. This previously "unseen" evidence of carbon inks, which can now successfully be made …

Understanding Juuling Trends Among Differing Age And Gender Demographics Through Social Sensing, Thomas Mcfann

Honors Theses

Middle schoolers, high schoolers, and college students have increasingly begun using the Juul, which is a type of e-cigarette. In fact, in 2017 a study showed that “2.1 million high schoolers and middle schoolers used e-cigarettes” (Richtel and Kaplan, 2018). The reason why my research specifically addresses the Juul is that it “is now the largest e-cigarette brand measured by retail sales companies” (Huang et al., 2018b). Studies have been done to show the short time it takes for a child to lose autonomy over tobacco use, ranging from 2 to 30 days of first inhaling a cigarette (DiFranza et …

Differential Estimation Of Audiograms Using Gaussian Process Active Model Selection, Trevor Larsen

McKelvey School of Engineering Graduate Student Theses & Dissertations

Classical methods for psychometric function estimation either require excessive resources to perform, as in the method of constants, or produce only a low resolution approximation of the target psychometric function, as in adaptive staircase or up-down procedures. This thesis makes two primary contributions to the estimation of the audiogram, a clinically relevant psychometric function estimated by querying a patient’s for audibility of a collection of tones. First, it covers the implementation of a Gaussian process model for learning an audiogram using another audiogram as a prior belief to speed up the learning procedure. Second, it implements a use case of …

Low-Energy Acceleration Of Binarized Convolutional Neural Networks Using A Spin Hall Effect Based Logic-In-Memory Architecture, Ashkan Samiee, Payal Borulkar, Ronald F. Demara, Peiyi Zhao, Yu Bai

Engineering Faculty Articles and Research

Deep Learning (DL) offers the advantages of high accuracy performance at tasks such as image recognition, learning of complex intelligent behaviors, and large-scale information retrieval problems such as intelligent web search. To attain the benefits of DL, the high computational and energy-consumption demands imposed by the underlying processing, interconnect, and memory devices on which software-based DL executes can benefit substantially from innovative hardware implementations. Logic-in-Memory (LIM) architectures offer potential approaches to attaining such throughput goals within area and energy constraints starting with the lowest layers of the hardware stack. In this paper, we develop a Spintronic Logic-in-Memory (S-LIM) XNOR neural …

Nitrogenase Iron Protein Detection Using Neural Network, Ishan Shinde

Master's Projects

Nitrogenase Iron Protein (nifH) is the enzyme responsible for nitrogen fixation. Microbes with nifH gene are responsible for injecting reduced nitrogen into the biosphere, which is essential for all living things. Obtaining sequences from GenBank database is problematic due to annotation errors, nomenclature variation and paralogues. One possible solution could be to retrieve sequences from the GenBank database and use a sequence classifier to label the sequences. In this research, we convert sequences to images and build a nifH sequence classifier using image processing and convolutional neural network. We built a nifH classification model which can classify sequences with an …

Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods, Christof Teuscher

Student Research Symposium

In machine learning research, adversarial examples are normal inputs to a classifier that have been specifically perturbed to cause the model to misclassify the input. These perturbations rarely affect the human readability of an input, even though the model’s output is drastically different. Recent work has demonstrated that image-classifying deep neural networks (DNNs) can be reliably fooled with the modification of a single pixel in the input image, without knowledge of a DNN’s internal parameters. This “one-pixel attack” utilizes an iterative evolutionary optimizer known as differential evolution (DE) to find the most effective pixel to perturb, via the evaluation of …

Development Of A Design Guideline For Pile Foundations Subjected To Liquefaction-Induced Lateral Spreading, Milad Souri, Arash Khosravifar

Student Research Symposium

Past earthquakes confirmed that seismically induced kinematic loads from soil lateral spreading and inertial loads from structure can cause severe damages to pile foundations. The research questions are:

• How to combine inertial and kinematic loads in design of pile foundations in liquefied soil?
• How the combination of inertia and kinematics changes with depth?
• How this combination is affected by long-duration earthquakes?
• How this combination affects inelastic demands in piles?

Cptc - A Security Competition Unlike Any Other, Bill Stackpole, Daryl Johnson

Presentations and other scholarship

Participating in cybersecurity competitions has become increasing popular for students in higher education programs that have a focus on computing or cyber security. The Collegiate Penetration Testing Competition was developed to address the industry skills gap and assist in identifying ethically minded security personnel with experience identifying, exercising, and mitigating vulnerabilities.

Assessing Bias Removal From Word Embeddings, Clare Arrington

Departmental Honors & Graduate Capstone Projects

As machine learning becomes more influential in everyday life, we must begin addressing potential shortcomings. A current problem area is word embeddings, frameworks that transform words into numbers, allowing the algorithmic analysis of language. Without a method for filtering implicit human bias from the documents used to create these embeddings, they contain and propagate stereotypes. Previous work has shown that one commonly used and distributed word embedding model trained on articles from Google News contained prejudice between gender and occupation (Bolukbasi 2016). While unsurprising, the use of biased data in machine learning models only serves to amplify the problem. Although …

Cross-Validating Traffic Speed Measurements From Probe And Stationary Sensors Through State Reconstruction, Jia Li, Kenneth Perrine, Lidong Wu, C. Michael Walton

Computer Science Faculty Publications and Presentations

Traffic speed on freeways can be measured by two types of technologies, i.e. probe sensors and stationary sensors. Cross-validation is critical to ensure the consistency between heterogeneous measurements. A challenge lies in the mismatch of probe and stationary measurements in space and time, especially when one of them is relatively sparse. Towards filling the gap, this paper presents a cross-validation method based on traffic state reconstruction. The proposed method is computationally simple and robust. This makes it ready to be implemented for large data sets without complicated tuning. We present analytical formulation of the proposed method and an analysis of …

Every Data Point Counts: Political Elections In The Age Of Digital Analytics, Julian Kehle, Samir Naimi

Honors Thesis

Synthesizing the investigative research and cautionary messages from experts in the fields of technology, political science, and behavioral science, this project explores the ways in which digital analytics has begun to influence the American political arena. Historically, political parties have constructed systems to target voters and win elections. However, rapid changes in the field of technology (such as big data, artificial intelligence, and the prevalence of social media) threaten to undermine the integrity of elections themselves. Future political campaigns will utilize profiling to micro-target individuals in order to manipulate and persuade them with hyper-personalized political content. Most dangerously, the average …

Optimal Staged Self-Assembly Of Linear Assemblies, Cameron Chalk, Eric M. Martinez, Robert Schweller, Luis Vega, Andrew Winslow, Tim Wylie

Computer Science Faculty Publications

We analyze the complexity of building linear assemblies, sets of linear assemblies, and O(1)-scale general shapes in the staged tile assembly model. For systems with at most b bins and t tile types, we prove that the minimum number of stages to uniquely assemble a 1 n line is (logt n + logb n t + 1). Generalizing to O(1) n lines, we prove the minimum number of stages is O( log n tb t log t b2 + log log b log t ) and

( log n tb t log t b2 ). Next, we consider assembling sets …

A Robust And Automated Deconvolution Algorithm Of Peaks In Spectroscopic Data, William Johan Burke Iv

Theses and Dissertations

The huge amount of spectroscopic data in use in metabolomic experiments requires an algorithm that can process the data in an autonomous fashion while providing quality of analysis comparable to manual methods. Scientists need an algorithm that effectively deconvolutes spectroscopic peaks automatically and is resilient to the presence of noise in the data. The algorithm must also provide a simple measure of quality of the deconvolution. The deconvolution algorithm presented in this thesis consists of preprocessing steps, noise removal, peak detection, and function fitting. Both a Fourier Transform and Continuous Wavelet Transform (CWT) method of noise removal were investigated. The …

#Whyididntreport: Using Social Media As A Tool To Understand Why Sexual Assault Victims Do Not Report, Abby Garrett

Honors Theses

Sexual assault has gone largely under-reported, and social media movements, like #WhyIDidntReport, have brought great awareness to this issue. In order to take advantage of the large amounts of data the #WhyIDidntReport movement has generated, the study uses tweets to explore reasons why victims do not report their assault. The thesis cites current research on the topic of assault to generate a list of explanations victims use to describe their lack of reporting and compares the distributions with existing studies. We use a supervised learning technique to automatically categorize tweets into one of eight categories. This approach uses social sensing …

Identification And Classification Of Poultry Eggs: A Case Study Utilizing Computer Vision And Machine Learning, Jeremy Lubich, Kyle Thomas, Daniel W. Engels

SMU Data Science Review

We developed a method to identify, count, and classify chickens and eggs inside nesting boxes of a chicken coop. Utilizing an IoT AWS Deep Lens Camera for data capture and inferences, we trained and deployed a custom single-shot multibox (SSD) object detection and classification model. This allows us to monitor a complex environment with multiple chickens and eggs moving and appearing simultaneously within the video frames. The models can label video frames with classifications for 8 breeds of chickens and/or 4 colors of eggs, with 98% accuracy on chickens or eggs alone and 82.5% accuracy while detecting both types of …

A Study Of The Effect Of Memory System Configuration On The Power Consumption Of An Fpga Processor, Adam Blalock

Senior Honors Projects, 2010-2019

With electrical energy being a finite resource, feasible methods of reducing system power consumption continue to be of great importance within the field of computing, especially as computers proliferate. A victim cache is a small fully associative cache that “captures” lines evicted from L1 cache memory, thereby reducing lower memory accesses and compensating for conflict misses. Little experimentation has been done to evaluate its effect on system power behavior and consumption. This project investigates the performance and power consumption of three different processor memory designs for a sample program using a field programmable gate array (FPGA) and the Vivado Integrated …

Using Data Science To Detect Fake News, Eliza Shoemaker

Senior Honors Projects, 2010-2019

The purpose of this thesis is to assist in automating the detection of Fake News by identifying which features are more useful for different classifiers. The effectiveness of different extracted features for Fake News detection are going to be examined. When classifying text with machine learning algorithms features have to be extracted from the articles for the classifiers to be trained on. In this thesis, several different features are extracted: word counts, ngram counts, term frequency-inverse document frequency, sentiment analysis, lemmatization, and named entity recognition to train the classifiers. Two classifiers are used, a Random Forest classifier and a Naïve …

The Effects Of Finite Precision On The Simulation Of The Double Pendulum, Rebecca Wild

Senior Honors Projects, 2010-2019

We use mathematics to study physical problems because abstracting the information allows us to better analyze what could happen given any range and combination of parameters. The problem is that for complicated systems mathematical analysis becomes extremely cumbersome. The only effective and reasonable way to study the behavior of such systems is to simulate the event on a computer. However, the fact that the set of floating-point numbers is finite and the fact that they are unevenly distributed over the real number line raises a number of concerns when trying to simulate systems with chaotic behavior. In this research we …

Modeling A Chaotic Billiard: The Bunimovich Stadium, Randal Shoemaker

Senior Honors Projects, 2010-2019

The Bunimovich stadium is a chaotic dynamical system in which a single particle, known as a billiard, moves indefinitely within a barrier without loss of momentum. Mathematicians and physicists have been interested in its properties since it was discovered to be chaotic in the 1970’s [5] [3] [4]. The Bunimovich stadium is actively researched [9]. This thesis and its accompanying software, the Bunimovich Stadia Evolution Viewer (BSEV), present a novel visual representation of the the chaotic dynamical system. The goal for the software is to provide insights into the stadium’s properties to aid researchers. This tool allows one to visualize …

Nurse-Led Design And Development Of An Expert System For Pressure Ulcer Management, Débora Abranches, Dympna O'Sullivan, Jon Bird

Conference papers

The use of Clinical Practice Guidelines (CPGs) is known to enable better care outcomes by promoting a consistent way of treating patients. This paper describes a user-centered design approach involving nurses, to develop a prototype expert system for modelling CPGs for Pressure Ulcer management. The system was developed using Visirule, a software tool that uses a graphical approach to modeling knowledge. The system was evaluated by 5 staff nurses and compared nurses’ time and accuracy to assess a wound using CPGs accessed via the Intranet of an NHS Trust and the expert system. A post task qualitative evaluation revealed that …

Analysis Of Computer Audit Data To Create Indicators Of Compromise For Intrusion Detection, Steven Millett, Michael Toolin, Justin Bates

SMU Data Science Review

Network security systems are designed to identify and, if possible, prevent unauthorized access to computer and network resources. Today most network security systems consist of hardware and software components that work in conjunction with one another to present a layered line of defense against unauthorized intrusions. Software provides user interactive layers such as password authentication, and system level layers for monitoring network activity. This paper examines an application monitoring network traffic that attempts to identify Indicators of Compromise (IOC) by extracting patterns in the network traffic which likely corresponds to unauthorized access. Typical network log data and construct indicators are …

Visualization And Machine Learning Techniques For Nasa’S Em-1 Big Data Problem, Antonio P. Garza Iii, Jose Quinonez, Misael Santana, Nibhrat Lohia

SMU Data Science Review

In this paper, we help NASA solve three Exploration Mission-1 (EM-1) challenges: data storage, computation time, and visualization of complex data. NASA is studying one year of trajectory data to determine available launch opportunities (about 90TBs of data). We improve data storage by introducing a cloud-based solution that provides elasticity and server upgrades. This migration will save $120k in infrastructure costs every four years, and potentially avoid schedule slips. Additionally, it increases computational efficiency by 125%. We further enhance computation via machine learning techniques that use the classic orbital elements to predict valid trajectories. Our machine learning model decreases trajectory …

Machine Learning Pipeline For Exoplanet Classification, George Clayton Sturrock, Brychan Manry, Sohail Rafiqi

SMU Data Science Review

Planet identification has typically been a tasked performed exclusively by teams of astronomers and astrophysicists using methods and tools accessible only to those with years of academic education and training. NASA’s Exoplanet Exploration program has introduced modern satellites capable of capturing a vast array of data regarding celestial objects of interest to assist with researching these objects. The availability of satellite data has opened up the task of planet identification to individuals capable of writing and interpreting machine learning models. In this study, several classification models and datasets are utilized to assign a probability of an observation being an exoplanet. …

Automate Nuclei Detection Using Neural Networks, Jonathan Flores, Thejas Prasad, Jordan Kassof, Robert Slater

SMU Data Science Review

Nuclei identification is a pivotal first step in many areas of biomedical research. Pathologists often observe images containing microscopic nuclei as part of their day to day jobs. During research, pathologists must identify nuclei characteristics from microscopic images such as: volume of nuclei, size, density and individual position within image. The pathology field can benefit from image detection enhancements done through the use of computer image segmentation techniques. This research presents methods that can be used to identify all the cell nuclei contained in images. Multiple techniques were experimented with such as edge detection and Convolutional Neural Networks with U-Net …

Leveraging Natural Language Processing Applications And Microblogging Platform For Increased Transparency In Crisis Areas, Ernesto Carrera-Ruvalcaba, Johnson Ekedum, Austin Hancock, Ben Brock

SMU Data Science Review

Through microblogging applications, such as Twitter, people actively document their lives even in times of natural disasters such as hurricanes and earthquakes. While first responders and crisis-teams are able to help people who call 911, or arrive at a designated shelter, there are vast amounts of information being exchanged online via Twitter that provide real-time, location-based alerts that are going unnoticed. To effectively use this information, the Tweets must be verified for authenticity and categorized to ensure that the proper authorities can be alerted. In this paper, we create a Crisis Message Corpus from geotagged Tweets occurring during 7 hurricanes …

Autonomous Watercraft Simulation And Programming, Nicholas J. Savino

Undergraduate Theses and Capstone Projects

Automation of various modes of transportation is thought to make travel more safe and efficient. Over the past several decades advances to semi-autonomous and autonomous vehicles have led to advanced autopilot systems on planes and boats and an increasing popularity of self-driving cars. We simulated the motion of an autonomous vehicle using computational models. The simulation models the motion of a small-scale watercraft, which can then be built and programmed using an Arduino Microcontroller. We examined different control methods for a simulated rescue craft to reach a target. We also examined the effects of different factors, such as various biases …

Sensor System And Method For Cognitive Health Assessment, Debraj De, Sajal K. Das, Mignon Makos

Computer Science Faculty Research & Creative Works

Sensors arranged on a chair on which a subject is seated detect a physical characteristic of the subject during administration of a cognitive health assessment. An assessment processor coupled to the sensors executes computer-executable instructions causing the processor to determine a contemporaneous reaction corresponding to each of the questions as a function of the detected physical characteristic. And the subject is assigned a cognitive health assessment score based on the subject's answers and determined reactions.

Intrusion-Tolerant Order-Preserving Encryption, John Huson

Masters Theses, 2010-2019

Traditional encryption schemes such as AES and RSA aim to achieve the highest level of security, often indistinguishable security under the adaptive chosen-ciphertext attack. Ciphertexts generated by such encryption schemes do not leak useful information. As a result, such ciphertexts do not support efficient searchability nor range queries.

Order-preserving encryption is a relatively new encryption paradigm that allows for efficient queries on ciphertexts. In order-preserving encryption, the data-encrypting key is a long-term symmetric key that needs to stay online for insertion, query and deletion operations, making it an attractive target for attacks.

In this thesis, an intrusion-tolerant order-preserving encryption system …

Sensitive Research, Practice And Design In Hci, Stevie Chancellor, Nazanin Andalibi, Lindsay Blackwell, David Nemer, Wendy Moncur

Information Science Faculty Publications

New research areas in HCI examine complex and sensitive research areas, such as crisis, life transitions, and mental health. Further, research in complex topics such as harassment and graphic content can leave researchers vulnerable to emotional and physical harm. There is a need to bring researchers together to discuss challenges across sensitive research spaces and environments. We propose a workshop to explore the methodological, ethical, and emotional challenges of sensitive research in HCI. We will actively recruit from diverse research environments (industry, academia, government, etc.) and methods areas (qualitative, quantitative, design practices, etc.) and identify commonalities in and encourage relationship-building …

Draft Genome Sequences Of Three Monokaryotic Isolates Of The White-Rot Basidiomycete Fungus Dichomitus Squalens, Sara Casado López, Mao Peng, Paul Daly, Bill Andreopoulos, Jasmyn Pangilinan, Anna Lipzen, Robert Riley, Steven Ahrendt, Vivian Ng, Kerrie Barry, Chris Daum, Igor Grigoriev, Kristiina Hildén, Miia Mäkelä, Ronald De Vries

Faculty Publications, Computer Science

Here, we report the draft genome sequences of three isolates of the wood-decaying white-rot basidiomycete fungus Dichomitus squalens. The genomes of these monokaryons were sequenced to provide more information on the intraspecies genomic diversity of this fungus and were compared to the previously sequenced genome of D. squalens LYAD-421 SS1.