Digital Commons Network^™

A Comparison Of Classical Versus Deep Learning Techniques For Abusive Content Detection On Social Media Sites, Hao Che, Susan Mckeever, Sarah Jane Delany

Conference papers

The automated detection of abusive content on social media websites faces a variety of challenges including imbalanced training sets, the identification of an appropriate feature representation and the selection of optimal classifiers. Classifiers such as support vector machines (SVM), combined with bag of words or ngram feature representation, have traditionally dominated in text classification for decades. With the recent emergence of deep learning and word embeddings, an increasing number of researchers have started to focus on deep neural networks. In this paper, our aim is to explore cutting-edge techniques in automated abusive content detection. We use two deep learning approaches: …

Validation Of Tagging Suggestion Models For A Hotel Ticketing Corpus, Bojan Bozic, Andre Rios, Sarah Jane Delany

Conference papers

This paper investigates methods for the prediction of tags on a textual corpus that describes hotel staff inputs in a ticketing system. The aim is to improve the tagging process and find the most suitable method for suggesting tags for a new text entry. The paper consists of two parts: (i) exploration of existing sample data, which includes statistical analysis and visualisation of the data to provide an overview, and (ii) evaluation of tag prediction approaches. We have included different approaches from different research fields in order to cover a broad spectrum of possible solutions. As a result, we have …

Non-Linear Machine Learning With Active Sampling For Mox Drift Compensation, Tamara Matthews, Muhammad Iqbal, Horacio Gonzalez-Velez

Conference papers

Abstract—Metal oxide (MOX) gas detectors based on SnO2 provide low-cost solutions for real-time sensing of complex gas mixtures for indoor ambient monitoring. With high sensitivity under ideal conditions, MOX detectors may have poor longterm response accuracy due to environmental factors (humidity and temperature) along with sensor aging, leading to calibration drifts. Finding a simple and efficient solution to correct such calibration drifts has been the subject of numerous studies but remains an open problem. In this work, we present an efficient approach to MOX calibration using active and transfer sampling techniques coupled with non-linear machine learning algorithms, namely neural networks, …

Sensory Seduction And Narrative Pull, Nina Lyons, Matt Smith, Hugh Mccabe

Conference papers

User experience design is a process that has been defined, developed and refined over the last few decades. It is a process of shaping a user's movements through a website or mobile application. It is user-focussed, prioritising utility, ease-of-use and efficiency. It is widely used and has helped advance the way in which users interact with websites and mobile applications, making it far less frustrating. User experience design is a key element in how the internet and mobile technology have become ubiquitous in our daily lives. Given this success, it would seem that continuing to use this process for new …

Use Of Hyperspectral Images (Hsi) And Convolutional Neural Network (Cnn) To Identify Normal, Precancerous And Cancerous Tissues, Pallavi Jain

Dissertations

Cancer detection has been a great topic of research for a long time, as early detection of cancer can help in increasing the survival rate of patients by providing on time better treatment. A robust system is required in order to detect early-stage cancer as its difficult to identify early-stage cancer from the normal clinical process. The computer vision techniques provide a new way to understand the challenges related to the medical image analysis. This thesis presents the medical image analysis using a combination of Convolutional Neural Network and Hyperspectral Images of cancer patient's tissues. The idea behind choosing the …

Predicting Happiness - Comparison Of Supervised Machine Learning Techniques Performance On A Multiclass Classification Problem, Dorota Nieciecka

Dissertations

In the modern world, especially in contemporary economies and politics, a population's subjective well-being is a frequent subject of the public debate. As comparisons of happiness levels in different countries are published, different circumstances and their effect on the value of the subjective well-being reported by people are also analysed. However, a significant amount of the research related to subjective well-being and its determinants is still based upon survey answers and employing conventional statistical methods providing details regarding correlations and causality between different factors and subjective well-being. Application of Supervised Machine Learning techniques for prediction of subjective well-being may provide …

A Demographic Analysis To Determine User Vulnerability Among Several Categories Of Phishing Attacks., Robert Griffin

Dissertations

Phishing attacks have been on a meteoric rise in the last number of years, with 2016 seeing a 65% increase. The attacks range from targeting individuals with personalised messages to spam attacks from bot accounts. With the chances of being targeted by a phishing attack increasing, it is important to identify who is most at risk in order to help alleviate this threat. The aim of this study is to examine members from several demographics and their vulnerability to three types of phishing using data collected from a survey (n = 198). The survey tested the participant’s ability to recognise …

An Investigation Into Factors Which Explain The Scores And Voting Patterns Of The Eurovision Song Contest., Oisín Leonard

Dissertations

The Eurovision Song Contest (ESC) is an annual international television song competition. Participating countries send a group or individual artist to perform an original song at the competition. The winner is decided by all participating countries using a voting system that incorporates both a public televote and an expert jury vote. Countries are excluded from voting for their entry and the country with the highest score wins. A high scoring performance and the voting patterns of the ESC can be explained by a complex set of factors. These factors can be divided into three groups; performance factors, competition factors and …

Image Classification Using Bag-Of-Visual-Words Model, Kaiqiang Huang

Dissertations

Recently, with the explosive growth of digital technologies, there has been a rapid proliferation of the size of image collection. The technique of supervised image clas sification has been widely applied in many domains in order to organize, search, and retrieve images. However, the traditional feature extraction approaches yield the poor classification accuracy. Therefore, the Bag-of-visual-words model, inspired by Bag-of Words model in document classification, was used to present images with the local descriptors for image classification, and also it performs well in some fields. This research provides the empirical evidence to prove that the BoVW model outperforms the traditional …

A Javascript Framework Comparison Based On Benchmarking Software Metrics And Environment Configuration, Jefferson Ferreira

Dissertations

JavaScript is a client-side programming language that can be used in multi-platform applications. It controls HTML and CSS to manipulate page behaviours and is widely used in most websites over the internet. JavaScript frameworks are structures made to help web developers build web applications faster by offering features that enhance the user interaction with the web page. An increasing number of JavaScript frameworks have been released in recent years in the market to help front-end developers build applications in a shorter space of time. Decision makers in software companies have been struggling to determine which frameworks are best suited for …

That Seems Made Up: Deep Learning Classifiers For Fiction & Non Fiction Book Reviews, Clement Manger

Dissertations

The thesis aims to take the first step towards automated extraction of the information found in book reviews, by using machine learning tools to assign a label of fiction or non fiction to the text. The thesis makes use of neural networks and performs experiments around architecture, hyper-parameters and text processing from which an optimized model is produced. The thesis enjoys certain successes; it was possible to match the state of the art achieved by (Kim, 2014) and computation was sped up considerably from the default to the optimized model by 13.8 seconds per 50 steps. Further it is confirmed …

Identifying Expert Investors On Financial Microblog Via Artificial Neural Networks, Pierluca Del Buono

Dissertations

In the recent years, thanks to social media platform, a plethora of information has been available to financial investors, that were traditionally dependent from financial institutions advisors. Strategies are now shared among web users, performances of stocks are commented in web communities and hints and suggestions are travelling on the internet with a fast pace, in a way that was unthinkable few years before. Several attempts have been made in the recent past, to predict Market movements and trends from activity of Financial Social Networks participants, and to evaluate if contributions from individuals with high level of expertise distinguish themselves …

A Systems Approach To Research And Innovation For Food System Transformation, M. Gill, A.C.L. Den Boer, K.P. Kok, Jean Cahill, C. Callenius, P. Caron, Z. Damianova, M.A. Gurinovic, L. Lahteenmaki, T. Lang, A. Lappiere, C. Mango, J. Ryder, R. Sonnino, H. Westhoek, B.J. Regeer, J.E.W. Broerse

Research and Innovation - Other

This policy brief of the European Union (EU) Think Tank – part of the FIT4FOOD2030 Coordination and Support Action (CSA) of the FOOD 2030 initiative – is a response and contribution to growing pleas for a ‘systems approach’ to transform food systems for Food and Nutrition Security (FNS) for present and future generations. This policy brief specifically focusses on the necessity of the adoption of a systems approach to Research and Innovation (R&I) in order to foster the transformation of food systems.

The Oral Writing-Revision Space: Identifying A New And Common Discourse Feature Of Writing Center Consultations, Melody Denny

The Writing Center Journal

No abstract provided.

Addressing The Proton Radius Puzzle Using Qed-Nrqed Effective Field Theory, Steven Patrick Dye

Wayne State University Dissertations

In 2010 the first extraction of the proton charge radius from muonic hydrogen was found to be five standard deviations away from the regular hydrogen value. Seven years later, this proton radius puzzle still persists, and challenges our understanding of the structure of the proton. An effective field theory analysis using Non-Relativistic Quantum Electrody- namics (NRQED) indicates that the muonic hydrogen result can be interpreted as a large, compared to some model estimates, muon-proton spin-independent contact interaction. The muonic hydrogen result can be tested by a muon-proton scattering experiment, MUSE, that is planned at the Paul Scherrer Institute in Switzerland. …

Surfactants, Thermal And Surface Energy Effects On Emulsions’ Transport Properties: A Study Using Lattice Boltzmann Method, Wessam Falih Hasan

Wayne State University Dissertations

This work aims to provide an efficient Gunstensen LBM based CFD model, capable of solving complex problems related to droplets behavior in shear and parabolic flows.

Thermal conditions determine the outcome of the physical and transport properties of emulsions during their various processing phases. A better understanding of the intricate relationship between thermal, surfactants and hydrodynamics can help in the optimization of these processes during the production of emulsions. To investigate the outcome of coupling thermal, surfactants and hydrodynamics on emulsions behavior, a robust quasi-steady thermal-surfactants numerical scheme is presented and used here. To validate the model, the rheological behavior …

On-Road Remote Sensing Of Automobile Emissions In The Denver Area: Winter 2017, Gary A. Bishop, Molly J. Haugen

Fuel Efficiency Automobile Test Publications

No abstract provided.

On-Road Remote Sensing Of Automobile Emissions In The Tulsa Area: Fall 2017, Gary A. Bishop

Fuel Efficiency Automobile Test Publications

No abstract provided.

Study Of Gas Production From Shale Reservoirs With Multi-Stage Hydraulic Fracturing Horizontal Well Considering Multiple Transport Mechanisms, Chaohua Guo, Mingzhen Wei, Hong Liu

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

Development of unconventional shale gas reservoirs (SGRs) has been boosted by the advancements in two key technologies: horizontal drilling and multi-stage hydraulic fracturing. A large number of multi-stage fractured horizontal wells (MsFHW) have been drilled to enhance reservoir production performance. Gas flow in SGRs is a multi-mechanism process, including: desorption, diffusion, and non-Darcy flow. The productivity of the SGRs with MsFHW is influenced by both reservoir conditions and hydraulic fracture properties. However, rare simulation work has been conducted for multi-stage hydraulic fractured SGRs. Most of them use well testing methods, which have too many unrealistic simplifications and assumptions. Also, no …

Varied Length Stokes Shift Bodipy-Based Fluorophores For Multicolor Microscopy, Amy M. Bittel, Ashley M. Davis, Lei Wang, Michel A. Nederlof, Jorge O. Escobedo, Robert Strongin, Summer L. Gibbs

Chemistry Faculty Publications and Presentations

Multicolor microscopy tools necessary to localize and visualize the complexity of subcellular systems are limited by current fluorophore technology. While commercial fluorophores cover spectral space from the ultraviolet to the near infrared region and are optimized for conventional bandpass based fluorescence microscopy, they are not ideal for highly multiplexed fluorescence microscopy as they tend to have short Stokes shifts, restricting the number of fluorophores that can be detected in a single sample to four to five. Herein, we synthesized a library of 95 novel boron-dipyrromethene (BODIPY)- based fluorophores and screened their photophysical, optical and spectral properties for their utility in …

Exploring The Effectiveness Of Academic Coaching For Academically At-Risk College Students, Madeline Kyle Capstick

Electronic Theses and Dissertations Archive

The purpose of this study was to determine the effectiveness of the Academic Coaching for Excellence (ACE) program for academically at-risk students over the course of five academic semesters from Spring 2015 to Spring 2017. The study utilized archival data from 1,440 undergraduate students using a cohort-based, nonequivalent groups post-tests design. The students were on academic warning, meaning they had fallen below a 2.00 GPA in the previous academic semester and were within their first 59 credit hours of college. Results from the study found that full- and part-time students who participated in academic coaching had significant GPA increases, were …

An Analysis Of The Relationship Between Teacher Perception Of Community Support And Involvement At Their School And Student Rates Of Attendance, Graduation And Academic Proficiency, Sandra Hamer Smith

Electronic Theses and Dissertations Archive

The purpose of this study was to explore the relationships between educators perceptions of the quality of community support and involvement at their high schools and five longitudinally measured indices of school effectiveness. Given a sample of 248 Tennessee high schools, secondary data derived from the Community Support and Involvement subsection of the Teaching, Empowering, Leading, and Learning (TELL) Questionnaire Survey administered in 2013 were merged with concurrent student attendance, student graduation, and student achievement outcomes archived and made publically available on the Tennessee Department of Education website.After controlling for the impact of student and faculty demographic variables, hierarchical multiple …

Optimal Delivery Of Remedial Mathematics Programs In U.S. Higher Education, Lisa Renee Loden

Electronic Theses and Dissertations Archive

Remedial mathematics has been considered the roadblock to obtaining a college degree by students and educators for years. The purpose of this research is to determine the optimal time and delivery method of the three presented (fully module, module with a traditional lecture component, and fully on-line) for teaching remedial mathematics. This is accomplished by comparing pass rates. First, pass rates are compared to determine if there is a statistically significant difference between pass rates in the two models for teaching remedial mathematics (pre-requisite and co-requisite). Next, pass rates are compared to determine if there is a statistically significant difference …

Education On The Inside: Incarcerated Students' Perceptions Of Correctional Education Programs, Stephanie Cage

Electronic Theses and Dissertations Archive

The United States has alarmingly high incarceration and recidivism rates. Many of those incarcerated have less education than their general population counterparts. Correctional education programs have a proven ability to reduce incarceration and recidivism rates by helping rehabilitate people. Current research on incarcerated students primarily focuses on the external benefits of correctional education programs such as recidivism. A limited amount of research is represented in the literature on incarcerated students’ perceptions about their academic experiences. The purpose of this study was to explore incarcerated students’ perceptions regarding their correctional education experiences. The study particularly investigated students at a Louisiana correctional …

Multiple Stimuli Responsive Drug Delivery System Based On Magnetic Nanoparticle Embedded Chitosan Microbeads, Ankita Mohapatra

Electronic Theses and Dissertations Archive

Direct drug administration has several shortcomings such as low circulation concentration due to rapid flushing by the immune system, non-specificity to target tissue and inefficient delivery to avascular sites. A widely adopted solution to these limitations is to sterically shield the drug from a harsh in vivo environment by encapsulation in a biocompatible, bio-degradable substrate. These Drug Delivery System (DDS) can be localized at the site and release drug gradually until the drug reserve is exhausted. However, the efficiency of this DDS can be further enhanced by designing them to elute drug in response to an external stimulus. This enhancement …

Problems In Extremal Graph Theory, Kamil Popielarz

Electronic Theses and Dissertations Archive

This dissertation consists of six chapters concerning a variety of topics in extremal graph theory.Chapter 1 is dedicated to the results in the papers with Antnio Giro, Gbor Mszros, and Richard Snyder. We say that a graph is path-pairable if for any pairing of its vertices there exist edge disjoint paths joining the vertices in eachpair. We study the extremal behavior of maximum degree and diameter in some classes of path-pairable graphs. In particular we show that a path-pairable planar graph must have a vertex of linear degree.In Chapter 2 we present a joint work with Antnio Giro and Teeradej …

Simulation Of Strong Ground Motions Using The Stochastic Summation Of Small To Moderate Earthquakes As Green's Functions, Farhad Sedaghati

Electronic Theses and Dissertations Archive

Central and eastern North America (CENA) is considered to be a moderately active region, but it suffers from a lack of recorded earthquakes in the magnitude-distance range of engineering interest. In this dissertation, region-specific synthetic strong ground motion time histories are generated using a new and improved stochastic summation of Green's functions method (SSGFM) for CENA. In addition, the synthetics are used to develop ground motion prediction equations (GMPEs) for this region. For simulating large earthquakes, considering the effects of finite-fault rupture such as rupture propagation, asperities, and fault-site geometry (saturation effect) are significant and influential. The SSGFM is a …

Teachers Perceptions Of Implementing M-Learning Using Pedagogical Approaches, James Albert Barnes

Electronic Theses and Dissertations Archive

Mobile learning (m-learning) has begun its transition from focusing on technology devices to pedagogical approaches that guide the design, development, and implementation of teaching and learning. The trends in the literature have identified pedagogical approaches, professional development and instructional practices that have improved academic achievement with teachers abilities and perceptions as a contributing factor. However, a gap remains about the degree to which teachers effectively integrate and implement m-learning to make a significant impact on teaching and learning. To address this gap, this research was a causal comparative study examining two schools perceptions of implementing m-learning after receiving differing types …

The Relationship Between The Perceived Implementation Of Green's Four-Dimensional Model Of Educational Leadership And Students' Proficiency In Basic Skills, Josie Currie

Electronic Theses and Dissertations Archive

The purpose of this study is to investigate relationships between elementary-level educators perceptions of their schools implementation of Greens four-dimensional model of educational leadership and the percentage of students proficient in Language Arts and in Mathematics, averaged over three years. Represented by responses to twenty items selected from the 2013 state-wide administration of the Teaching, Empowering, Leading, and Learning survey in Tennessee (TELL Tennessee), school-level means at 1,187 elementary schools were obtained for each of four five-item scales that were intended to measure each dimension of Greens model. Along with a grand mean computed across all twenty items and denoting …

Three Voices, One Goal: A Narrative Study Of High School Facilitators' Experience In A Community Of Practice, Ebony Briggs

Electronic Theses and Dissertations Archive

Special education and general education teachers must work collaboratively in a single classroom that serves the diverse needs of all children due to federal regulations such as the No Child Left Behind Act of 2001 and the Individuals with Disabilities Education Act of 2004. Evidence-based practices that foster collaboration are scarce. The purpose of this narrative inquiry research was to explore the perceptions of a team of educators which consists of a general education teacher, special education teacher, and an administrator on how their experience of participating in a community of practice is beneficial to addressing collaboration needs of team …