Computer Sciences Commons^™

A Novel Set Of Weight Initialization Techniques For Deep Learning Architectures, Diego Aguirre

Open Access Theses & Dissertations

The importance of weight initialization when building a deep learning model is often underappreciated. Even though it is usually seen as a minor detail in the model creation cycle, this process has shown to have a strong impact on the training time of a network and the quality of the resulting model. In fact, the implications of choosing a poor initialization scheme range from leading to the creation of a poorly performing model to preventing optimization techniques (like stochastic gradient descent) from converging.

In this work, we introduce and evaluate a set of novel weight initialization techniques for deep learning …

Computer-Aided Classification Of Impulse Oscillometric Measures Of Respiratory Small Airways Function In Children, Nancy Selene Avila

Open Access Theses & Dissertations

Computer-aided classification of respiratory small airways dysfunction is not an easy task. There is a need to develop more robust classifiers, specifically for children as the classification studies performed to date have the following limitations: 1) they include features derived from tests that are not suitable for children and 2) they cannot distinguish between mild and severe small airway dysfunction.

This Dissertation describes the classification algorithms with high discriminative capacity to distinguish different levels of respiratory small airways function in children (Asthma, Small Airways Impairment, Possible Small Airways Impairment, and Normal lung function). This ability came from innovative feature selection, …

Dedicated Hardware For Machine/Deep Learning: Domain Specific Architectures, Angel Izael Solis

Open Access Theses & Dissertations

Artificial intelligence has come a very long way from being a mere spectacle on the silver screen in the 1920s [Hml18]. As artificial intelligence continues to evolve, and we begin to develop more sophisticated Artificial Neural Networks, the need for specialized and more efficient machines (less computational strain while maintaining the same performance results) becomes increasingly evident. Though these “new” techniques, such as Multilayer Perceptron’s, Convolutional Neural Networks and Recurrent Neural Networks, may seem as if they are on the cutting edge of technology, many of these ideas are over 60 years old! However, many of these earlier models, at …

The Use Of Cultural Algorithms To Learn The Impact Of Climate On Local Fishing Behavior In Cerro Azul, Peru, Khalid Kattan

Wayne State University Dissertations

Recently it has been found that the earth’s oceans are warming at a pace that is 40% faster than predicted by a United Nations panel a few years ago. As a result, 2019 has become the warmest year on record for the earth’s oceans. That is because the oceans have acted as a buffer by absorbing 93% of the heat produced by the greenhouse gases [40].

The impact of the oceanic warming has already been felt in terms of the periodic warming of the Pacific Ocean as an effect of the ENSO process. The ENSO process is a cycle of …

Capso: A Multi-Objective Cultural Algorithm System To Predict Locations Of Ancient Sites, Samuel Dustin Stanley

Wayne State University Dissertations

ABSTRACT

CAPSO: A MULTI-OBJECTIVE CULTURAL ALGORITHM SYSTEM TO PREDICT LOCATIONS OF ANCIENT SITES

by

SAMUEL DUSTIN STANLEY

August 2019

Advisor: Dr. Robert Reynolds

Major: Computer Science

Degree: Doctor of Philosophy

The recent archaeological discovery by Dr. John O’Shea at University of Michigan of prehistoric caribou remains and Paleo-Indian structures underneath the Great Lakes has opened up an opportunity for Computer Scientists to develop dynamic systems modelling these ancient caribou routes and hunter-gatherer settlement systems as well as the prehistoric environments that they existed in. The Wayne State University Cultural Algorithm team has been interested assisting Dr. O’Shea’s archaeological team by …

Knowledge Graph Reasoning Over Unseen Rdf Data, Bhargavacharan Reddy Kaithi

Browse all Theses and Dissertations

In recent years, the research in deep learning and knowledge engineering has made a wide impact on the data and knowledge representations. The research in knowledge engineering has frequently focused on modeling the high level human cognitive abilities, such as reasoning, making inferences, and validation. Semantic Web Technologies and Deep Learning have an interest in creating intelligent artifacts. Deep learning is a set of machine learning algorithms that attempt to model data representations through many layers of non-linear transformations. Deep learning is in- creasingly employed to analyze various knowledge representations mentioned in Semantic Web and provides better results for Semantic …

Assessing The Quality Of Software Development Tutorials Available On The Web, Manziba A. Nishi

Theses and Dissertations

Both expert and novice software developers frequently access software development resources available on the Web in order to lookup or learn new APIs, tools and techniques. Software quality is affected negatively when developers fail to find high-quality information relevant to their problem. While there is a substantial amount of freely available resources that can be accessed online, some of the available resources contain information that suffers from error proneness, copyright infringement, security concerns, and incompatible versions. Use of such toxic information can have a strong negative effect on developer’s efficacy. This dissertation focuses specifically on software tutorials, aiming to automatically …

Artificial Intelligence, Machine Learning, And Autonomous Technologies In Mining Industry, Zeshan Hyder, Keng Siau, Fiona Nah

Research Collection School Of Computing and Information Systems

The implementation of artificial intelligence (AI), machine learning, and autonomous technologies in the mining industry started about a decade ago with autonomous trucks. Artificial intelligence, machine learning, and autonomous technologies provide many economic benefits for the mining industry through cost reduction, efficiency, and improving productivity, reducing exposure of workers to hazardous conditions, continuous production, and improved safety. However, the implementation of these technologies has faced economic, financial, technological, workforce, and social challenges. This article discusses the current status of AI, machine learning, and autonomous technologies implementation in the mining industry and highlights potential areas of future application. The article presents …

Automated Essay Evaluation Using Natural Language Processing And Machine Learning, Harshanthi Ghanta

Theses and Dissertations

The goal of automated essay evaluation is to assign grades to essays and provide feedback using computers. Automated evaluation is increasingly being used in classrooms and online exams. The aim of this project is to develop machine learning models for performing automated essay scoring and evaluate their performance. In this research, a publicly available essay data set was used to train and test the efficacy of the adopted techniques. Natural language processing techniques were used to extract features from essays in the dataset. Three different existing machine learning algorithms were used on the chosen dataset. The data was divided into …

Towards Improving Accuracy And Interpretability Of Deep Learning Based On Satellite Image Classification, Yamile Patino Vargas

Dissertations and Theses

ABSTRACT

The study of satellite images provides a way to monitor changes in the surface of the Earth and the atmosphere. Convolutional Neural Networks (CNN) have shown accurate results in solving practical problems in multiple fields. Some of the more recognized fields using CNNs are satellite imagery processing, medicine, communication, transportation, and computer vision. Despite the success of CNNs, there remains a need to explain the network predictions further and understand what the network is determining as valuable information.

There are several frameworks and methodologies developed to explain how CNNs predict outputs and what their internal representations are [1, 4, …

Quantifying Human Biological Age: A Machine Learning Approach, Syed Ashiqur Rahman

Graduate Theses, Dissertations, and Problem Reports (ETD)

Quantifying human biological age is an important and difficult challenge. Different biomarkers and numerous approaches have been studied for biological age prediction, each with its advantages and limitations. In this work, we first introduce a new anthropometric measure (called Surface-based Body Shape Index, SBSI) that accounts for both body shape and body size, and evaluate its performance as a predictor of all-cause mortality. We analyzed data from the National Health and Human Nutrition Examination Survey (NHANES). Based on the analysis, we introduce a new body shape index constructed from four important anthropometric determinants of body shape and body size: body …

A Dual State Hierarchical Ensemble Kalman Filter Algorithm, William J. Cook, Jesse Johnson, Marko Maneta, Doug Brinkerhoff

Graduate Student Theses, Dissertations, & Professional Papers

Dynamic models that simulate processes across large geographic locations, such as hydrologic models, are often informed by empirical parameters that are distributed across a geographical area and segmented by geological features such as watersheds. These parameters may be referred to as spatially distributed parameters. Spatially distributed parameters are frequently spatially correlated and any techniques utilized in their calibration ideally incorporate existing spatial hierarchical relationships into their structure. In this paper, a parameter estimation method based on the Dual State Ensemble Kalman Filter called the Dual State Hierarchical Ensemble Kalman Filter (DSHEnKF) is presented. This modified filter is innovative in that …

Classification Of Stars From Redshifted Stellar Spectra Utilizing Machine Learning, Michael J. Brice

All Master's Theses

The classification of stellar spectra is a fundamental task in stellar astrophysics. There have been many explorations into the automated classification of stellar spectra but few that involve the Sloan Digital Sky Survey (SDSS). Stellar spectra from the SDSS are applied to standard classification methods such as K-Nearest Neighbors, Random Forest, and Support Vector Machine to automatically classify the spectra. Stellar spectra are high dimensional data and the dimensionality is reduced using standard Feature Selection methods such as Chi-Squared and Fisher score and with domain-specific astronomical knowledge because classifiers work in low dimensional space. These methods are utilized to classify …

Exploring Cyber-Physical Systems, Misbah Uddin Mohammed

Graduate Research Theses & Dissertations

The advances in IOT, Computer Vision, AI and Machine Learning have made these technologies ubiquitous to our daily lives. From Smart Phones to Connected Vehicles, Cyber Physical systems have been interspersed into everything we interact in today’s world. The aim or this thesis was to explore these advances in Cyber Physical Systems and analyze the different sectors they were affecting. We then hand-picked certain domains and explored further by carrying out practical projects using some of the latest software and hardware resources available. Technologies like Amazon Alexa services, NVIDIA Jetson boards, TensorFlow, OpenCV, NodeJS were heavily employed in our various …

Intelligent Malware Detection Using File-To-File Relations And Enhancing Its Security Against Adversarial Attacks, Lingwei Chen

Graduate Theses, Dissertations, and Problem Reports (ETD)

With computing devices and the Internet being indispensable in people's everyday life, malware has posed serious threats to their security, making its detection of utmost concern. To protect legitimate users from the evolving malware attacks, machine learning-based systems have been successfully deployed and offer unparalleled flexibility in automatic malware detection. In most of these systems, resting on the analysis of different content-based features either statically or dynamically extracted from the file samples, various kinds of classifiers are constructed to detect malware. However, besides content-based features, file-to-file relations, such as file co-existence, can provide valuable information in malware detection and make …

Automatic Identification Of Animals In The Wild: A Comparative Study Between C-Capsule Networks And Deep Convolutional Neural Networks., Joel Kamdem Teto, Ying Xie

Master of Science in Computer Science Theses

The evolution of machine learning and computer vision in technology has driven a lot of

improvements and innovation into several domains. We see it being applied for credit decisions, insurance quotes, malware detection, fraud detection, email composition, and any other area having enough information to allow the machine to learn patterns. Over the years the number of sensors, cameras, and cognitive pieces of equipment placed in the wilderness has been growing exponentially. However, the resources (human) to leverage these data into something meaningful are not improving at the same rate. For instance, a team of scientist volunteers took 8.4 years, …

On The Feasibility Of Profiling, Forecasting And Authenticating Internet Usage Based On Privacy Preserving Netflow Logs, Soheil Sarmadi

USF Tampa Graduate Theses and Dissertations

Understanding Internet user behavior and Internet usage patterns is fundamental in developing future access networks and services that meet technical as well as Internet user needs. User behavior is routinely studied and measured, but with different methods depending on the research discipline of the investigator, and these disciplines rarely cross. We tackle this challenge by developing frameworks that the Internet usage statistics used as the main features in understanding Internet user behaviors, with the purpose of finding a complete picture of the user behavior and working towards a unified analysis methodology. In this dissertation we collected Internet usage statistics via …

A Comprehensive Framework To Replicate Process-Level Concurrency Faults, Supat Rattanasuksun

School of Computing: Dissertations, Theses, and Student Research

Concurrency faults are one of the most damaging types of faults that can affect the dependability of today’s computer systems. Currently, concurrency faults such as process-level races, order violations, and atomicity violations represent the largest class of faults that has been reported to various Linux bug repositories. Clearly, existing approaches for testing such faults during software development processes are not adequate as these faults escape in-house testing efforts and are discovered during deployment and must be debugged.

The main reason concurrency faults are hard to test is because the conditions that allow these to occur can be difficult to replicate, …

Improvement Of Decision On Coding Unit Split Mode And Intra-Picture Prediction By Machine Learning, Wenchan Jiang

Master of Science in Computer Science Theses

High efficiency Video Coding (HEVC) has been deemed as the newest video coding standard of the ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group. The reference software (i.e., HM) have included the implementations of the guidelines in appliance with the new standard. The software includes both encoder and decoder functionality.

Machine learning (ML) works with data and processes it to discover patterns that can be later used to analyze new trends. ML can play a key role in a wide range of critical applications, such as data mining, natural language processing, image recognition, and expert systems. …

Deep Machine Learning For Mechanical Performance And Failure Prediction, Elijah Reber, Nickolas D. Winovich, Guang Lin

The Summer Undergraduate Research Fellowship (SURF) Symposium

Deep learning has provided opportunities for advancement in many fields. One such opportunity is being able to accurately predict real world events. Ensuring proper motor function and being able to predict energy output is a valuable asset for owners of wind turbines. In this paper, we look at how effective a deep neural network is at predicting the failure or energy output of a wind turbine. A data set was obtained that contained sensor data from 17 wind turbines over 13 months, measuring numerous variables, such as spindle speed and blade position and whether or not the wind turbine experienced …

Predict The Failure Of Hydraulic Pumps By Different Machine Learning Algorithms, Yifei Zhou, Monika Ivantysynova, Nathan Keller

The Summer Undergraduate Research Fellowship (SURF) Symposium

Pump failure is a general concerned problem in the hydraulic field. Once happening, it will cause a huge property loss and even the life loss. The common methods to prevent the occurrence of pump failure is by preventative maintenance and breakdown maintenance, however, both of them have significant drawbacks. This research focuses on the axial piston pump and provides a new solution by the prognostic of pump failure using the classification of machine learning. Different kinds of sensors (temperature, acceleration and etc.) were installed into a good condition pump and three different kinds of damaged pumps to measure 10 of …

Deep Neural Network Architectures For Modulation Classification Using Principal Component Analysis, Sharan Ramjee, Shengtai Ju, Diyu Yang, Aly El Gamal

The Summer Undergraduate Research Fellowship (SURF) Symposium

In this work, we investigate the application of Principal Component Analysis to the task of wireless signal modulation recognition using deep neural network architectures. Sampling signals at the Nyquist rate, which is often very high, requires a large amount of energy and space to collect and store the samples. Moreover, the time taken to train neural networks for the task of modulation classification is large due to the large number of samples. These problems can be drastically reduced using Principal Component Analysis, which is a technique that allows us to reduce the dimensionality or number of features of the samples …

Application Of Machine Learning In Cancer Research, Mandana Bozorgi

UNLV Theses, Dissertations, Professional Papers, and Capstones

This dissertation revisits the problem of five-year survivability predictions for breast cancer using machine learning tools. This work is distinguishable from the past experiments based on the size of the training data, the unbalanced distribution of data in minority and majority classes, and modified data cleaning procedures. These experiments are also based on the principles of TIDY data and reproducible research. In order to fine-tune the predictions, a set of experiments were run using naive Bayes, decision trees, and logistic regression.

Of particular interest were strategies to improve the recall level for the minority class, as the cost of misclassification …

Machine Learning To Predict College Course Success, Anthony R.Y. Dalton, Justin Beer, Sriharshasai Kommanapalli, James S. Lanich Ph.D.

SMU Data Science Review

In this paper, we present an analysis of the predictive ability of machine learning on the success of students in college courses in a California Community College. The California Legislature passed assembly bill 705 in order to place students in non-remedial coursework, based on high school transcripts, to increase college completion. We utilize machine learning methods on de-identified student high school transcript data to create predictive algorithms on whether or not the student will be successful in college-level English and Mathematics coursework. To satisfy the bill’s requirements, we first use exploratory data analysis on applicable transcript variables. Then we use …

Automatic Multimodal Assessment Of Neonatal Pain, Ghada Zamzmi

USF Tampa Graduate Theses and Dissertations

For several decades, pediatricians used to believe that neonates do not feel pain. The American Academy of Pediatrics (AAP) recognized neonates' sense of pain in 1987. Since then, there have been many studies reporting a strong association between repeated pain exposure (under-treatment) and alterations in brain structure and function. This association has led to the increased use of anesthetic medications. However, recent studies found that the excessive use of analgesic medications (over-treatment) can cause many side effects. The current standard for assessing neonatal pain is discontinuous and suffers from inter-observer variations, which can lead to over- or under-treatment. Therefore, it …

Machine Learning Methods For Network Intrusion Detection And Intrusion Prevention Systems, Zheni Svetoslavova Stefanova

USF Tampa Graduate Theses and Dissertations

Given the continuing advancement of networking applications and our increased dependence upon software-based systems, there is a pressing need to develop improved security techniques for defending modern information technology (IT) systems from malicious cyber-attacks. Indeed, anyone can be impacted by such activities, including individuals, corporations, and governments. Furthermore, the sustained expansion of the network user base and its associated set of applications is also introducing additional vulnerabilities which can lead to criminal breaches and loss of critical data. As a result, the broader cybersecurity problem area has emerged as a significant concern, with many solution strategies being proposed for both …

A Bayesian Latent Variable Model Of User Preferences With Item Context, Aghiles Salah, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Personalized recommendation has proven to be very promising in modeling the preference of users over items. However, most existing work in this context focuses primarily on modeling user-item interactions, which tend to be very sparse. We propose to further leverage the item-item relationships that may reflect various aspects of items that guide users’ choices. Intuitively, items that occur within the same “context” (e.g., browsed in the same session, purchased in the same basket) are likely related in some latent aspect. Therefore, accounting for the item’s context would complement the sparse user-item interactions by extending a user’s preference to other items …

Machine Learning For Inspired, Structured, Lyrical Music Composition, Paul Mark Bodily

Theses and Dissertations

Computational creativity has been called the "final frontier" of artificial intelligence due to the difficulty inherent in defining and implementing creativity in computational systems. Despite this difficulty computer creativity is becoming a more significant part of our everyday lives, in particular music. This is observed in the prevalence of music recommendation systems, co-creational music software packages, smart playlists, and procedurally-generated video games. Significant progress can be seen in the advances in industrial applications such as Spotify, Pandora, Apple Music, etc., but several problems persist. Of more general interest, however, is the question of whether or not computers can exhibit autonomous …

Modeling Contemporaneous Basket Sequences With Twin Networks For Next-Item Recommendation, Duc Trong Le, Hady W. Lauw, Yuan Fang

Research Collection School Of Computing and Information Systems

Our interactions with an application frequently leave a heterogeneous and contemporaneous trail of actions and adoptions (e.g., clicks, bookmarks, purchases). Given a sequence of a particular type (e.g., purchases)-- referred to as the target sequence, we seek to predict the next item expected to appear beyond this sequence. This task is known as next-item recommendation. We hypothesize two means for improvement. First, within each time step, a user may interact with multiple items (a basket), with potential latent associations among them. Second, predicting the next item in the target sequence may be helped by also learning from another supporting sequence …

Online Deep Learning: Learning Deep Neural Networks On The Fly, Doyen Sahoo, Hong Quang Pham, Jing Lu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch setting, requiring the entire training data to be made available prior to the learning task. This is not scalable for many real-world scenarios where new data arrives sequentially in a stream. We aim to address an open challenge of “Online Deep Learning” (ODL) for learning DNNs on the fly in an online setting. Unlike traditional online learning that often optimizes some convex objective function with respect to a shallow model (e.g., a linear/kernel-based hypothesis), ODL is more challenging as the optimization objective is non-convex, and regular DNN with …