Physical Sciences and Mathematics Commons^™

Cover Song Identification - A Novel Stem-Based Approach To Improve Song-To-Song Similarity Measurements, Lavonnia Newman, Dhyan Shah, Chandler Vaughn, Faizan Javed

SMU Data Science Review

Music is incorporated into our daily lives whether intentional or unintentional. It evokes responses and behavior so much so there is an entire study dedicated to the psychology of music. Music creates the mood for dancing, exercising, creative thought or even relaxation. It is a powerful tool that can be used in various venues and through advertisements to influence and guide human reactions. Music is also often "borrowed" in the industry today. The practices of sampling and remixing music in the digital age have made cover song identification an active area of research. While most of this research is focused …

Reducing Age Bias In Machine Learning: An Algorithmic Approach, Adriana Solange Garcia De Alford, Steven K. Hayden, Nicole Wittlin, Amy Atwood

SMU Data Science Review

In this paper, we study the prevalence of bias in machine learning; we explore the life cycle phases where bias is potentially introduced into a machine learning model; and lastly, we present how adversarial learning can be leveraged to measure unwanted bias and unfair behavior from a machine learning algorithm. This study focuses particularly on the topics of age bias in predicting employee attrition and presents a practical approach for how adversarial learning can be successful in mitigating age bias. To measure bias, we calculate group fairness metrics across five-year age groups and evaluate fairness between a baseline predictive model …

Forecasting Spare Parts Sporadic Demand Using Traditional Methods And Machine Learning - A Comparative Study, Bhuvana Adur Kannan, Ganesh Kodi, Oscar Padilla, Dough Gray, Barry C. Smith

SMU Data Science Review

Sporadic demand presents a particular challenge to traditional time forecasting methods. In the past 50 years, there has been developments, such as, the Croston Model [3], which has improved forecast performance. With the rise of Machine Learning (ML) there is abundant research in the field of applying ML algorithms to predict sporadic demand [8][12][9]. However, most existing research has analyzed this problem from the demand side [17]. In this paper, we tackle this predictive analytics challenge from the supply side. We perform a comparative analysis utilizing a spare parts demand dataset from an Original Equipment Manufacturer (OEM). Since traditional measurements …

Tag: Automated Image Captioning, Nathan Funckes

McNair Scholars Manuscripts

Many websites remain non-ADA compliant, containing images which lack accompanying textual descriptions. This leaves sight-impaired individuals unable to fully enjoy the rich wonders of the web. To address this inequity, our research aims to create an autonomous system capable of generating semantically accurate descriptions of images. This problem involves two tasks: recognizing an image and linguistically describing it. Our solution uses state-of-the-art deep learning: employing a convolutional neural network that "learns" to understand images and extracts their salient features, and a recurrent neural network that learns to generate structured, coherent sentences. These two networks are merged to create a single …

Machine Learning Applications For Drug Repurposing, Hansaim Lim

Dissertations, Theses, and Capstone Projects

The cost of bringing a drug to market is astounding and the failure rate is intimidating. Drug discovery has been of limited success under the conventional reductionist model of one-drug-one-gene-one-disease paradigm, where a single disease-associated gene is identified and a molecular binder to the specific target is subsequently designed. Under the simplistic paradigm of drug discovery, a drug molecule is assumed to interact only with the intended on-target. However, small molecular drugs often interact with multiple targets, and those off-target interactions are not considered under the conventional paradigm. As a result, drug-induced side effects and adverse reactions are often neglected …

Creating A Culture Of Data-Driven Decision-Making, Kevin Bryan Rogers

Doctoral Dissertations and Projects

Researchers have consistently shown that a supportive culture is one of the most crucial success factors in the implementation of any big data solution. Creating a culture that supports data-driven decision-making is a difficult but ultimately required step in transforming an organization into one that can readily and successfully adopt business intelligence technologies. The purpose of this qualitative case study was to understand the ways in which organizations can foster a culture of smarter decision-making and accountability so that businesses can improve operational metrics and ultimately profitability. Participants identified three major themes that drive the adoption of a data-driven culture. …

Compressed Dna Representation For Efficient Amr Classification, John Partee, Robert Hazell, Anjli Solsi, John Santerre

SMU Data Science Review

In this paper, we explore a representation methodology for the compression of DNA isolates. Using lossless string compression via tokenization of frequently repeated segments of DNA, we reduce the length of the isolates to be counted as k-mers for classification. With this new representation, we apply a previously established feature sampling method to dramatically reduce the feature space. In understanding the genetic diversity, we also look at conserving biological function across these spaces. Using a random forest model we were able to predict the resistance or susceptibility of bacteria with 85-90\% accuracy, with a 30-50\% reduction in overall isolate length, …

Evaluation Of Standard And Semantically-Augmented Distance Metrics For Neurology Patients, Daniel B. Hier, Jonathan Kopel, Steven U. Brint, Donald C. Wunsch, Gayla R. Olbricht, Sima Azizi, Blaine Allen

Electrical and Computer Engineering Faculty Research & Creative Works

Background: Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks.

Methods: We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by …

A Smart Soil Loss Estimator, Brandon W. Sims

Student Theses and Dissertations

Machine learning was combined with RUSLE2 erosion prediction technology to quickly estimate soil erosion by water over large areas. The new modeling framework combines efficient geoprocessing and machine learning techniques to allow the application of the RUSLE2 model to entire watersheds while maintaining high spatial resolution that consider actual overland flow paths, drainage networks, soil properties, and land use. The methodology uses topographic information from LiDAR digital elevation models, soil maps from SSURGO, spatial crop data from USDA NASS, and RUSLE2 databases describing climate and agricultural operations. New geoprocessing algorithms define hillslopes and extract topographic, soil, and crop properties. A …

Routing Optimization In Heterogeneous Wireless Networks For Space And Mission-Driven Internet Of Things (Iot) Environments, Sara El Alaoui

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

As technological advances have made it possible to build cheap devices with more processing power and storage, and that are capable of continuously generating large amounts of data, the network has to undergo significant changes as well. The rising number of vendors and variety in platforms and wireless communication technologies have introduced heterogeneity to networks compromising the efficiency of existing routing algorithms. Furthermore, most of the existing solutions assume and require connection to the backbone network and involve changes to the infrastructures, which are not always possible -- a 2018 report by the Federal Communications Commission shows that over 31% …

A Study Of Information Bots And Knowledge Bots, Amartya Hatua

Dissertations

In this dissertation, a study of different aspects of information bots and knowledge bots is done. The research contributes to a better understanding of the various characteristics of information bots as well as the different patterns and factors responsible for the information diffusion in a social network. This research also shows how these factors can be used to predict information diffusion for a particular topic in a social network. The second part of the research is focused on strategies for improving the knowledge base of knowledge bots, where two different approaches are studied. In the first approach, knowledge is transferred …

An Investigation Into Multi-View Error Correcting Output Code Classifiers Applied To Organ Tissue Classification, Daniel Alvarez

UNLV Theses, Dissertations, Professional Papers, and Capstones

Large amounts of data is being generated constantly each day, so much data that it is difficult to find patterns in order to predict outcomes and make decisions for both humans and machines alike. It would be useful if this data could be simplified using machine learning techniques. For example, biological cell identity is dependent on many factors tied to genetic processes. Such factors include proteins, gene transcription, and gene methylation. Each of these factors are highly complex mechanism with immense amounts of data. Simplifying these can then be helpful in finding patterns in them. Error-Correcting Output Codes (ECOC) does …

Data Mining And Image Classification Using Genetic Programming, Mahsa Shokri Varniab

Master of Science in Computer Science Theses

Genetic programming (GP), a capable machine learning and search method, motivated by Darwinian-evolution, is an evolutionary learning algorithm which automatically evolves computer programs in the form of trees to solve problems. This thesis studies the application of GP for data mining and image processing. Knowledge discovery and data mining have been widely used in business, healthcare, and scientific fields. In data mining, classification is supervised learning that identifies new patterns and maps the data to predefined targets. A GP based classifier is developed in order to perform these mappings. GP has been investigated in a series of studies to classify …

Variability In The Effectiveness Of Psychological Interventions Based On Machine Learning In Stem Education, Mohammad Hasan, Bilal Khan

School of Computing: Faculty Publications

This manuscript presents a framework to investigate the variability in the effectiveness of psychological interventions supported by Machine Learning (ML) based early-warning systems (EWS) in science, technology, engineering, and mathematics education. It emphasizes the importance of investigating the resulting variability and suggests that effective EWS cannot be designed without a deeper understanding of the variability. The framework uses an ML-based model to predict students’ academic performance early in the semester for a Sophomore-level Computer Science course at a public university in the United States. The students were given psychological interventions by sending their end-of-term performance forecast thrice during the semester. …

Deep Learning Predictive Modeling With Data Challenges (Small, Big, Or Imbalanced), Renhao Liu

USF Tampa Graduate Theses and Dissertations

In the real world, data used to build machine learning models always has different sizes and characteristics. These size and characteristic features, including small datasets, big datasets, imbalanced datasets, often lead to different challenges when training machine learning models. Models trained on a small number of observations tend to overfit the training data and produce inaccurate results. When it comes to big data, efficiently learning from "huge" size data in a short time becomes important. With an imbalanced dataset, learning is usually biased towards the majority class in the data and appropriate measurements are needed to check model performance.

As …

An Improved Method For Spectroscopic Quality Classification, Elizabeth G. Mayer

Mathematics & Statistics ETDs

Spectral quality classification is a vital step in data cleaning before the

analysis of magnetic resonance spectroscopy (MRS) data can be done. This

analysis compares five methods of quality classification; three of these are

legacy methods, Maudsley et al. (2006), Zhang et al. (2018), and

Bustillo et al. (2020), and two newly created methods that used a random forests

classifier (RFC) to inform their classifications. We found that the random forest

classifier was the most accurate at predicting spectra quality (balanced

accuracy for RF of 88% vs legacy of 70%, 72%, or 72%). A

Random-Forests-Informed Filtering method (RFIFM) for quality …

A Study Of The Efficacy Of Machine Learning For Diagnosing Obstructive Coronary Artery Disease In Non-Diabetic Patients, Demond Larae Handley

Theses and Dissertations

According to the Centers for Disease Control and Prevention, about 18.2 million adults age 20 and older have Coronary Artery Disease in the United States. Early diagnosis is therefore of crucial importance to help prevent debilitating consequences, and principally death for many patients. In this study we use data containing gene expression values from peripheral blood samples in 198 non-diabetic patients, with the goal of developing an age and sex gene expression model for diagnosis of Coronary Artery Disease. We employ machine learning methods to obtain a classification based on genetic information, age and sex. Our implementation uses feed forward …

Machine Learning For The Internet Of Things: Applications, Implementation, And Security, Vishalini Laguduva Ramnath

USF Tampa Graduate Theses and Dissertations

Artificial intelligence and ubiquitous sensor systems have seen tremendous advances in recent times, resulting in groundbreaking impact across domains such as healthcare, entertainment, and transportation through a collective ecosystem called the Internet of Things. The advent of 5G and improved wireless networks will further accelerate the research and development of tools in deep learning, sensor systems, and computing platforms by providing improved network latency and bandwidth. While tremendous progress has been made in the Internet of Things, current work has largely focused on building robust applications that leverage the data collected through ubiquitous sensor nodes to provide actionable rules and …

Groundwater Storage Loss Associated With Land Subsidence In Western United States Mapped Using Machine Learning, Ryan G. Smith, Sayantan Majumdar

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

Land subsidence caused by groundwater extraction has numerous negative consequences, such as loss of groundwater storage and damage to infrastructure. Understanding the magnitude, timing, and locations of land subsidence, as well as the mechanisms driving it, is crucial to implementing mitigation strategies, yet the complex, nonlinear processes causing subsidence are difficult to quantify. Physical models relating groundwater flux to aquifer compaction exist but require substantial hydrological data sets and are time consuming to calibrate. Land deformation can be measured using interferometric synthetic aperture radar (InSAR) and GPS, but the former is computationally expensive to estimate at scale and is subject …

Algorithmic Robot Design: Label Maps, Procrustean Graphs, And The Boundary Of Non-Destructiveness, Shervin Ghasemlou

Theses and Dissertations

This dissertation is focused on the problem of algorithmic robot design. The process of designing a robot or a team of robots that can reliably accomplish a task in an environment requires several key elements. How the problem is formulated can play a big role in the design process. The ability of the model to correctly reflect the environment, the events, and different pieces of the problem is crucial. Another key element is the ability of the model to show the relationship between different designs of a single system. These two elements can enable design algorithms to navigate through the …

Analysis On Suicidal Ideation Among Adolescents (12-17 Years) In The Usa, Himani Raturi

Electronic Theses, Projects, and Dissertations

Suicide is one of the leading health concerns in United States among adolescents and the presence of suicidal ideation (SI) is quite high, with ~20-30% of adolescents reporting it at some point. Though we have seen growth and development in the prevention of suicide, there is limited research on the ability to identify the adolescents which might be at risk for SI. The objective behind the project is to identify adolescents with SI using machine learning.

The project shows statistics from different articles on adolescents in the U.S. For this study, adolescent data was taken from NSDUH 2018. Moreover, detailed …

Combining Machine Learning And Empirical Engineering Methods Towards Improving Oil Production Forecasting, Andrew J. Allen

Master's Theses

Current methods of production forecasting such as decline curve analysis (DCA) or numerical simulation require years of historical production data, and their accuracy is limited by the choice of model parameters. Unconventional resources have proven challenging to apply traditional methods of production forecasting because they lack long production histories and have extremely variable model parameters. This research proposes a data-driven alternative to reservoir simulation and production forecasting techniques. We create a proxy-well model for predicting cumulative oil production by selecting statistically significant well completion parameters and reservoir information as independent predictor variables in regression-based models. Then, principal component analysis (PCA) …

What Was Written Vs. Who Read It: News Media Profiling Using Text Analysis And Social Media Context, Ramy Baly, Georgi Karadzhov, Jisun An, Haewoon Kwak, Yoan Dinkov, Ahmed Ali, James Glass, Preslav. Nakov

Research Collection School Of Computing and Information Systems

Predicting the political bias and the factuality of reporting of entire news outlets are critical elements of media profiling, which is an understudied but an increasingly important research direction. The present level of proliferation of fake, biased, and propagandistic content online has made it impossible to fact-check every single suspicious claim, either manually or automatically. Thus, it has been proposed to profile entire news outlets and to look for those that are likely to publish fake or biased content. This makes it possible to detect likely “fake news” the moment they are published, by simply checking the reliability of their …

Using Group Affinity To Predict Community Formation In Social Networks, Joseph Leung

Undergraduate Honors Theses

A well-studied topic in network theory is detecting the communities found in real-world networks. Community detection is a technique to better understand the way in which small dense substructures appear in these networks. Such substructures can often tell important information about groups that form in such systems. A prominent feature of many networks is that they evolve over time, forming and dissolving new edges between different nodes that appear. In this thesis, we consider how we can use the community structure of a network at a certain point in time to predict the state of a network’s communities at some …

Evidence-Based Detection Of Pancreatic Canc, Rajeshwari Deepak Chandratre

Master's Projects

This study is an effort to develop a tool for early detection of pancreatic cancer using evidential reasoning. An evidential reasoning model predicts the likelihood of an individual developing pancreatic cancer by processing the outputs of a Support Vector Classifier, and other input factors such as smoking history, drinking history, sequencing reads, biopsy location, family and personal health history. Certain features of the genomic data along with the mutated gene sequence of pancreatic cancer patients was obtained from the National Cancer Institute (NIH) Genomic Data Commons (GDC). This data was used to train the SVC. A prediction accuracy of ~85% …

Computational Astronomy: Classification Of Celestial Spectra Using Machine Learning Techniques, Gayatri Milind Hungund

Master's Projects

Lightyears beyond the Planet Earth there exist plenty of unknown and unexplored stars and Galaxies that need to be studied in order to support the Big Bang Theory and also make important astronomical discoveries in quest of knowing the unknown. Sophisticated devices and high-power computational resources are now deployed to make a positive effort towards data gathering and analysis. These devices produce massive amount of data from the astronomical surveys and the data is usually in terabytes or petabytes. It is exhaustive to process this data and determine the findings in short period of time. Many details can be missed …

Network Traffic Based Botnet Detection Using Machine Learning, Anand Ravindra Vishwakarma

Master's Projects

The field of information and computer security is rapidly developing in today’s world as the number of security risks is continuously being explored every day. The moment a new software or a product is launched in the market, a new exploit or vulnerability is exposed and exploited by the attackers or malicious users for different motives. Many attacks are distributed in nature and carried out by botnets that cause widespread disruption of network activity by carrying out DDoS (Distributed Denial of Service) attacks, email spamming, click fraud, information and identity theft, virtual deceit and distributed resource usage for cryptocurrency mining. …

Sensor Data Analysis In Smart Buildings, Manuel A. Mane Penton

Publications and Research

Data analysis and Machine Learning are destined to evolve the current technology infrastructure by solving technology and economy demands present mainly in developed cities like New York. This research proposes a machine learning (ML) based solution to alleviate one of the main issues that big buildings such as CUNY campuses have, that is the waste of energy resources. The analysis of data coming from the readings of different deployed sensors such as CO2, humidity and temperature can be used to estimate occupancy in a specific room and building in general. The outcome of this research established a relationship between the …

Integrated Machine Learning And Bioinformatics Approaches For Prediction Of Cancer-Driving Gene Mutations, Oluyemi Odeyemi

Computational and Data Sciences (PhD) Dissertations

Cancer arises from the accumulation of somatic mutations and genetic alterations in cell division checkpoints and apoptosis, this often leads to abnormal tumor proliferation. Proper classification of cancer-linked driver mutations will considerably help our understanding of the molecular dynamics of cancer. In this study, we compared several cancer-specific predictive models for prediction of driver mutations in cancer-linked genes that were validated on canonical data sets of functionally validated mutations and applied to a raw cancer genomics data. By analyzing pathogenicity prediction and conservation scores, we have shown that evolutionary conservation scores play a pivotal role in the classification of cancer …

Toward The Automatic Classification Of Self-Affirmed Refactoring, Mohamed Wiem Mkaouer, Eman Abdullah Alomar, Ali Ouni

Articles

The concept of Self-Affirmed Refactoring (SAR) was introduced to explore how developers document their refactoring activities in commit messages, i.e., developers explicit documentation of refactoring operations intentionally introduced during a code change. In our previous study, we have manually identified refactoring patterns and defined three main common quality improvement categories including internal quality attributes, external quality attributes, and code smells, by only considering refactoring-related commits. However, this approach heavily depends on the manual inspection of commit messages. In this paper, we propose a two-step approach to first identify whether a commit describes developer-related refactoring events, then to classify it according …