Data Science Commons^™

Edge Device Speaker Verification, Thomas P. Duffy

Dissertations and Theses

The continued shrinking of processors and other physical hardware in concert with development of embeddable machine learning frameworks has enabled new use cases placing machine learning directly in the “wild”. The problem of speaker verification, for a long time, has been deployed to perform inference on systems with significant computations resources. More recently, these systems have been built for smaller, cheaper devices which can be placed in people's homes or other edge locations. Here, we aim to demonstrate that a reasonably accurate, generalizable, text-independent speaker verification system can be built, trained, and, ultimately, deployed onto a microcontroller with as a …

Imputation Of Missing Data From Time-Lapse Cameras Used In Recreational Fishing Surveys, Ebenezer Afrifa-Yamoah, Stephen M. Taylor, Aiden Fisher, Ute Mueller

Research outputs 2014 to 2021

While remote camera surveys have the potential to improve the accuracy of recreational fishing estimates, missing data are common and require robust analytical techniques to impute. Time-lapse cameras are being used in Western Australia to monitor recreational boating activities, but outages have occurred. Generalized linear mixed effect models formulated in a fully conditional specification multiple imputation framework were used to reconstruct missing data, with climatic and some temporal classifications as covariates. Using a complete 12-month camera record of hourly counts of recreational powerboat retrievals, data were simulated based on ten observed camera outage patterns, with a missing proportion of between …

How Machine Learning And Probability Concepts Can Improve Nba Player Evaluation, Harrison Miller

CMC Senior Theses

In this paper I will be breaking down a scholarly article, written by Sameer K. Deshpande and Shane T. Jensen, that proposed a new method to evaluate NBA players. The NBA is the highest level professional basketball league in America and stands for the National Basketball Association. They proposed to build a model that would result in how NBA players impact their teams chances of winning a game, using machine learning and probability concepts. I preface that by diving into these concepts and their mathematical backgrounds. These concepts include building a linear model using ordinary least squares method, the bias …

Score Following With Hidden Tempo Using A Switching State-Space Model, Yucong Jiang, Chris Raphael

Department of Math & Statistics Faculty Publications

A score-following program traces the notes in a musical score during a performance. This capability is essential to many meaningful applications that synchronize audio with a score in an on-line fashion. Existing algorithms often stumble on certain difficult cases, one of which is piano music. This paper presents a new method to tackle such cases. The method treats tempo as a variable rather than a constant (with constraints), allowing the program to adapt to live performance variations. This is first expressed by a Kalman filter model at the note level, and then by an almost equivalent switching state-space model at …

Prospects And Challenges Of Population Health With Online And Other Big Data In Africa; Understanding The Link To Improving Healthcare Service Delivery, Rowland Edet, Bolarinwa Afolabi

Department of Sociology: Faculty Publications

Big data analytics offers promises to many health care service challenges and can provide answers to many population health issues. Big data is having a positive impact in almost every sphere of life in more advanced world while developing countries are striving to meet up. Even though healthcare systems in the developed world are recording some breakthroughs due to the application of big data, it is important to research the impact of big data in developing regions of the world, such as Africa and identify its peculiar needs. The purpose of this review was to summarize the challenges faced by …

Image Features For Tuberculosis Classification In Digital Chest Radiographs, Brian Hooper

All Master's Theses

Tuberculosis (TB) is a respiratory disease which affects millions of people each year, accounting for the tenth leading cause of death worldwide, and is especially prevalent in underdeveloped regions where access to adequate medical care may be limited. Analysis of digital chest radiographs (CXRs) is a common and inexpensive method for the diagnosis of TB; however, a trained radiologist is required to interpret the results, and is subject to human error. Computer-Aided Detection (CAD) systems are a promising machine-learning based solution to automate the diagnosis of TB from CXR images. As the dimensionality of a high-resolution CXR image is very …

Mutual Information Decay Curves And Hyper-Parameter Grid Search Design For Recurrent Neural Architectures, Abhijit Mahalunkar, John Kelleher

Conference papers

We present an approach to design the grid searches for hyper-parameter optimization for recurrent neural architectures. The basis for this approach is the use of mutual information to analyze long distance dependencies (LDDs) within a dataset. We also report a set of experiments that demonstrate how using this approach, we obtain state-of-the-art results for DilatedRNNs across a range of benchmark datasets.

Parameter Estimation Of A Seasonal Poisson Inar(1) Model With Different Monthly Means, Turaj Vazifedan, Homa Jalaeian Taghadomi, Xixi Wang, Mujde Erten-Unal

Civil & Environmental Engineering Faculty Publications

Analysing seasonality in count time series is an essential application of statistics to predict phenomena in different fields like economics, agriculture, healthcare, environment, and climatic change. However, the information in the existing literature is scarce regarding the performances of relevant statistical models. This study provides the Yule-Walker (Y-W), Conditional Least Squares (CLS), and Maximum Likelihood Estimation (MLE) for First-order Non-negative Integer-valued Autoregressive, INAR(1), process with Poisson innovations with different monthly means. The performance of Y-W, CLS, and MLE are assessed by the Monte Carlo simulation method. The performance of this model is compared with another seasonal INAR(1) model by reproducing …

Digilego For Peripartum Depression: A Novel Patient-Facing Digital Health Instantiation, J Rodin, C Timko, S Harris

Faculty, Staff and Student Publications

Digital health technologies offer unique opportunities to improve health outcomes for mental health conditions such as peripartum depression (PPD), a disorder that affects approximately 10-15% of women in the U.S. every year. In this paper, we present the adaption of a digital technology development framework, Digilego, in the context of PPD. Methods include mapping of the Behavior Intervention Technology (BIT) model and the Patient Engagement Framework (PEF) to translate patient needs captured through focus groups. This informs formative development and implementation of digital health features for optimal patient engagement in PPD screening and management. Results show an array ofPPD-specific Digilego …

Multimodal Fusion Strategies For Outcome Prediction In Stroke, Esra Zihni, John D. Kelleher, Vince I. Madai, Ahmed Khalil, Ivana Galinovic, Jochen Fiebach, Michelle Livne, Dietmar Frey

Conference papers

Data driven methods are increasingly being adopted in the medical domain for clinical predictive modeling. Prediction of stroke outcome using machine learning could provide a decision support system for physicians to assist them in patient-oriented diagnosis and treatment. While patient-specific clinical parameters play an important role in outcome prediction, a multimodal fusion approach that integrates neuroimaging with clinical data has the potential to improve accuracy. This paper addresses two research questions: (a) does multimodal fusion aid in the prediction of stroke outcome, and (b) what fusion strategy is more suitable for the task at hand. The baselines for our experimental …

Modelling Interleaved Activities Using Language Models, Eoin Rogers, Robert J. Ross, John D. Kelleher

Conference papers

We propose a new approach to activity discovery, based on the neural language modelling of streaming sensor events. Our approach proceeds in multiple stages: we build binary links between activities using probability distributions generated by a neural language model trained on the dataset, and combine the binary links to produce complex activities. We then use the activities as sensor events, allowing us to build complex hierarchies of activities. We put an emphasis on dealing with interleaving, which represents a major challenge for many existing activity discovery systems. The system is tested on a realistic dataset, demonstrating it as a promising …

Experiments On The Neural Network Approach To The Handwritten Digit Classification Problem, William Meissner

College of Graduate Studies: Theses & Dissertations

When the MNIST dataset was introduced in 1998, training a network was a multiple week problem in order to receive results far less accurate than an average CPU can produce within a couple of hours today. While this indicates that training a network on such a dataset is not the complicated problem it may have been twenty years ago, the MNIST dataset makes a good tool for study and testing with beginner and medium complexity neural networks. This paper follows along with the work presented in the online textbook “Neural Networks and Deep Learning” by Michael Nielson and an updated …

Three Essays On Health Economics And Policy Evaluation, Shishir Shakya

Graduate Theses, Dissertations, and Problem Reports (ETD)

This dissertation consists of three essays on the U.S. Health care policy. Each paragraph below refers to the three abstracts for the three chapters in this dissertation, respectively. I provide quantitative evidence on how much Prescription Drug Monitoring Programs (PDMPs) affects the retail opioid prescribing behaviors. Using the American Community Survey (ACS), I retrieve county-level high dimensional panel data set from 2010 to 2017. I employ three separate identification strategies: difference-in-difference, double selection post-LASSO, and spatial difference-in-difference. I compare how the retail opioid prescribing behaviors of counties, that are mandatory for prescribers to check the PDMP before prescribing controlled substances …

Speech Mode Classification Using The Fusion Of Cnns And Lstm Networks, Pratyusha Chowdary Vakkantula

Graduate Theses, Dissertations, and Problem Reports (ETD)

Speech mode classification is an area that has not been as widely explored in the field of sound classification as others such as environmental sounds, music genre, and speaker identification. But what is speech mode? While mode is defined as the way or the manner in which something occurs or is expressed or done, speech mode is defined as the style in which the speech is delivered by a person.

There are some reports on speech mode classification using conventional methods, such as whispering and talking using a normal phonetic sound. However, to the best of our knowledge, deep learning-based …

A Machine Learning Approach To Estimate The Annihilation Photon Interactions Inside The Scintillator Of A Pet Scanner, Sai Akhil Bharthavarapu

Graduate Theses, Dissertations, and Problem Reports (ETD)

Biochemical processes are chemical processes that occur in living organisms. They can be studied with nuclear medicine through the help of radioactive tracers. Based on the radioisotope used, the photons that are emitted from the body tissue are either detected by single-photon emission computed tomography (SPECT) or by positron emission tomography (PET) scanners. SPECT uses gamma rays as tracer but gives a weaker contrast and spatial resolution compared to a PET scanner which uses positrons as tracer. PET scans show the metabolic changes occurring at the cellular level in an organ or a tissue. This detection is important because diseases …

Deconvolution Tools For Extracting Insight From Challenging Two-Flavin Systems, Dallas Michael Bell

Theses and Dissertations--Chemistry

Flavoproteins have long been explored for their ubiquity among a number of metabolic and energetic reactions. The flavin cofactor has the inherent benefit of distinct spectral changes associated with redox transitions; however, the double-edged sword is incurred as these distinct signatures overlap and take up much of the UV-vis spectral range. Therefore, it is crucial to create a method to demarcate the expressed redox transitions for studying these systems. The first portion of these studies discusses the creation of a program that deduces spectra for redox transitions in a single-flavin containing model protein: flavodoxin. The latter portions discuss the application …

A Study On Real-Time Database Technology And Its Applications, Geethmi Nimantha Dissanayake

Masters Theses

No abstract provided.

Causal Discovery In Radiographic Markers Of Knee Osteoarthritis And Prediction For Knee Osteoarthritis Severity With Attention-Long Short-Term Memory, Yanfei Wang, Lei You, Jacqueline Chyr, Lan Lan, Weiling Zhao, Yujia Zhou, Hua Xu, Philip Noble, Xiaobo Zhou

Faculty, Staff and Student Publications

The goal of this study is to build a prognostic model to predict the severity of radiographic knee osteoarthritis (KOA) and to identify long-term disease progression risk factors for early intervention and treatment. We designed a long short-term memory (LSTM) model with an attention mechanism to predict Kellgren/Lawrence (KL) grade for knee osteoarthritis patients. The attention scores reveal a time-associated impact of different variables on KL grades. We also employed a fast causal inference (FCI) algorithm to estimate the causal relation of key variables, which will aid in clinical interpretability. Based on the clinical information of current visits, we accurately …

Interpreting Health Events In Big Data Using Qualitative Traditions, Roschelle L. Fritz, Gordana Dermody

Research outputs 2014 to 2021

© The Author(s) 2020. The training of artificial intelligence requires integrating real-world context and mathematical computations. To achieve efficacious smart health artificial intelligence, contextual clinical knowledge serving as ground truth is required. Qualitative methods are well-suited to lend consistent and valid ground truth. In this methods article, we illustrate the use of qualitative descriptive methods for providing ground truth when training an intelligent agent to detect Restless Leg Syndrome. We show how one interdisciplinary, inter-methodological research team used both sensor-based data and the participant’s description of their experience with an episode of Restless Leg Syndrome for training the intelligent agent. …

Cooperative Co-Evolution For Feature Selection In Big Data With Random Feature Grouping, A.N.M. Bazlur Rashid, Mohiuddin Ahmed, Leslie F. Sikos, Paul Haskell-Dowland

Research outputs 2014 to 2021

© 2020, The Author(s). A massive amount of data is generated with the evolution of modern technologies. This high-throughput data generation results in Big Data, which consist of many features (attributes). However, irrelevant features may degrade the classification performance of machine learning (ML) algorithms. Feature selection (FS) is a technique used to select a subset of relevant features that represent the dataset. Evolutionary algorithms (EAs) are widely used search strategies in this domain. A variant of EAs, called cooperative co-evolution (CC), which uses a divide-and-conquer approach, is a good choice for optimization problems. The existing solutions have poor performance because …

Correction To: Cooperative Co‑Evolution For Feature Selection In Big Data With Random Feature Grouping (Journal Of Big Data, (2020), 7, 1, (107), 10.1186/S40537-020-00381-Y), A. N.M.Bazlur Rashid, Mohiuddin Ahmed, Leslie F. Sikos, Paul Haskell‑Dowland

Research outputs 2014 to 2021

© 2020, The Author(s). Following publication of the original article [1], the author reported that the 2nd author affiliation was incorrect. It should only be “School of Science, Edith Cowan University, Joondalup, WA, Australia”. The affiliation is presented correctly in this correction article. The original article [1] has been corrected.

Invariance And Invertibility In Deep Neural Networks, Han Zhang

Theses and Dissertations

Machine learning is concerned with computer systems that learn from data instead of being explicitly programmed to solve a particular task. One of the main approaches behind recent advances in machine learning involves neural networks with a large number of layers, often referred to as deep learning. In this dissertation, we study how to equip deep neural networks with two useful properties: invariance and invertibility. The first part of our work is focused on constructing neural networks that are invariant to certain transformations in the input, that is, some outputs of the network stay the same even if the input …

The Trust Principles For Digital Repositories, Dawei Lin, Jonathan Crabtree, Ingrid Dillo, Robert R. Downs, Rorie Edmunds, David Giaretta, Marisa De Giusti, Hervé L'Hours, Wim Hugo, Reyna Jenkyns, Varsha Khodiyar, Maryann E. Martone, Mustapha Mokrane, Vivek Navale, Jonathan Petters, Barbara Sierman, Dina V. Sokolova, Martina Stockhause, John Westbrook

Copyright, Fair Use, Scholarly Communication, etc.

As information and communication technology has become pervasive in our society, we are increasingly dependent on both digital data and repositories that provide access to and enable the use of such resources. Repositories must earn the trust of the communities they intend to serve and demonstrate that they are reliable and capable of appropriately managing the data they hold.

Following a year-long public discussion and building on existing community consensus , several stakeholders, representing various segments of the digital repository community, have collaboratively developed and endorsed a set of guiding principles to demonstrate digital repository trustworthiness. Transparency, Responsibility, User focus, …

Synthesizing Aspect-Driven Recommendation Explanations From Reviews, Trung-Hoang Le, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Explanations help to make sense of recommendations, increasing the likelihood of adoption. However, existing approaches to explainable recommendations tend to rely on rigid, standardized templates, customized only via fill-in-the-blank aspect sentiments. For more flexible, literate, and varied explanations covering various aspects of interest, we synthesize an explanation by selecting snippets from reviews, while optimizing for representativeness and coherence. To fit target users' aspect preferences, we contextualize the opinions based on a compatible explainable recommendation model. Experiments on datasets of several product categories showcase the efficacies of our method as compared to baselines based on templates, review summarization, selection, and text …

Health-Aware Food Planner: A Personalized Recipe Generation Approach Based On Gpt-2, Bushra Aljbawi

Theses and Dissertations (Comprehensive)

"What to eat today?" With the flourish of Internet, more and more people nowadays are inclined to find an answer to this most problematic question online. The recent explosion of food networks; however, produces large volumes of recipes, making it even harder to make an informed decision. This yields the need for advanced decision-making algorithms and efficient recommendation systems. Conventional recommender systems are not feasible anymore as food is a complicated feature that presents unique challenges and is less studied. For example, it can be one of the main reasons for obesity and many other chronic diseases. Food recommender system …