Computer Sciences Commons^™

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 …

Opening Books And The National Corpus Of Graduate Research, William A. Ingram, Edward A. Fox, Jian Wu

Computer Science Faculty Publications

Virginia Tech University Libraries, in collaboration with Virginia Tech Department of Computer Science and Old Dominion University Department of Computer Science, request $505,214 in grant funding for a 3-year project, the goal of which is to bring computational access to book-length documents, demonstrating that with Electronic Theses and Dissertations (ETDs). The project is motivated by the following library and community needs. (1) Despite huge volumes of book-length documents in digital libraries, there is a lack of models offering effective and efficient computational access to these long documents. (2) Nationwide open access services for ETDs generally function at the metadata level. …

Teacher-Student Networks With Multiple Decoders For Solving Math Word Problem, Jipeng Zhang, Roy Ka-Wei Lee, Ee-Peng Lim, Wei Qin, Lei Wang, Jie Shao, Qianru Sun

Research Collection School Of Computing and Information Systems

Math word problem (MWP) is challenging due to the limitation in training data where only one “standard” solution is available. MWP models often simply fit this solution rather than truly understand or solve the problem. The generalization of models (to diverse word scenarios) is thus limited. To address this problem, this paper proposes a novel approach, TSN-MD, by leveraging the teacher network to integrate the knowledge of equivalent solution expressions and then to regularize the learning behavior of the student network. In addition, we introduce the multiple-decoder student network to generate multiple candidate solution expressions by which the final answer …

Deep Learning For Digitized Histology Image Analysis, Sudhir Sornapudi

Doctoral Dissertations

“Cervical cancer is the fourth most frequent cancer that affects women worldwide. Assessment of cervical intraepithelial neoplasia (CIN) through histopathology remains as the standard for absolute determination of cancer. The examination of tissue samples under a microscope requires considerable time and effort from expert pathologists. There is a need to design an automated tool to assist pathologists for digitized histology slide analysis. Pre-cervical cancer is generally determined by examining the CIN which is the growth of atypical cells from the basement membrane (bottom) to the top of the epithelium. It has four grades, including: Normal, CIN1, CIN2, and CIN3. In …

Landing Throttleable Hybrid Rockets With Hierarchical Reinforcement Learning In A Simulated Environment, Francesco Alessandro Stefano Mikulis-Borsoi

Honors Theses and Capstones

In this paper, I develop a hierarchical Markov Decision Process (MDP) structure for completing the task of vertical rocket landing. I start by covering the background of this problem, and formally defining its constraints. In order to reduce mistakes while formulating different MDPs, I define and develop the criteria for a standardized MDP definition format. I then decompose the problem into several sub-problems of vertical landing, namely velocity control and vertical stability control. By exploiting MDP coupling and symmetrical properties, I am able to significantly reduce the size of the state space compared to a unified MDP formulation. This paper …

Computer Vision Based Deep Learning Models For Cyber Physical Systems, Muhammad Monjurul Karim

Masters Theses

“Cyber-Physical Systems (CPSs) are complex systems that integrate physical systems with their counterpart cyber components to form a close loop solution. Due to the ability of deep learning in providing sensor data-based models for analyzing physical systems, it has received increased interest in the CPS community in recent years. However, developing vision data-based deep learning models for CPSs remains critical since the models heavily rely on intensive, tedious efforts of humans to annotate training data. Besides, most of the models have a high tradeoff between quality and computational cost. This research studies deep learning algorithms to achieve affordable and upgradable …

Law, Artificial Intelligence, And Natural Language Processing: A Funny Thing Happened On The Way To My Search Results, Paul D. Callister

Faculty Works

Renowned legal educator Roscoe Pound stated, “Law must be stable and yet it cannot stand still.” Yet, as Susan Nevelow Mart has demonstrated in a seminal article that the different online research services (Westlaw, Lexis Advance, Fastcase, Google Scholar, Ravel and Casetext) produce significantly different results when researching case law. Furthermore, a recent study of 325 federal courts of appeals decisions, revealed that only 16% of the cases cited in appellate briefs make it into the courts’ opinions. This does not exactly inspire confidence in legal research or its tools to maintain stability of the law. As Robert Berring foresaw, …

A Comparative Analysis Of Reinforcement Learning Applied To Task-Space Reaching With A Robotic Manipulator With And Without Gravity Compensation, Jonathan Fugal

Theses and Dissertations--Electrical and Computer Engineering

Advances in computing power in recent years have facilitated developments in autonomous robotic systems. These robotic systems can be used in prosthetic limbs, wearhouse packaging and sorting, assembly line production, as well as many other applications. Designing these autonomous systems typically requires robotic system and world models (for classical control based strategies) or time consuming and computationally expensive training (for learning based strategies). Often these requirements are difficult to fulfill. There are ways to combine classical control and learning based strategies that can mitigate both requirements. One of these ways is to use a gravity compensated torque control with reinforcement …

Shipbuilding Supply Chain Framework And Digital Transformation: A Project Portfolios Risk Evaluation, Rafael Diaz, Katherine Smith, Rafael Landaeta, Antonio Padovano

VMASC Publications

Program portfolio managers in digital transformation programs have a need for knowledge that can guide decisions related to the alignment of program investments with the sustainability and strategic objectives of the organization. The purpose of this research is to illustrate the utility of a framework capable of clarifying the cost-benefit tradeoffs stemming from assessing digitalization program investment risks in the military shipbuilding sector. Our approach uses Artificial Neural Network to quantify benefits and risks per project while employing scenario analysis to quantify the effects of operational constraints. A Monte Carlo model is used to generate data samples that support the …

Certified Functions For Mesh Generation, Andrey N. Chernikov

Chemistry & Biochemistry Faculty Publications

Formal methods allow for building correct-by-construction software with provable guarantees. The formal development presented here resulted in certified executable functions for mesh generation. The term certified means that their correctness is established via an artifact, or certificate, which is a statement of these functions in a formal language along with the proofs of their correctness. The term is meaningful only when qualified by a specific set of properties that are proven. This manuscript elaborates on the precise statements of the properties being proven and their role in an implementation of a version of the Isosurface Stuffing algorithm by Labelle and …

Unitary And Symmetric Structure In Deep Neural Networks, Kehelwala Dewage Gayan Maduranga

Theses and Dissertations--Mathematics

Recurrent neural networks (RNNs) have been successfully used on a wide range of sequential data problems. A well-known difficulty in using RNNs is the vanishing or exploding gradient problem. Recently, there have been several different RNN architectures that try to mitigate this issue by maintaining an orthogonal or unitary recurrent weight matrix. One such architecture is the scaled Cayley orthogonal recurrent neural network (scoRNN), which parameterizes the orthogonal recurrent weight matrix through a scaled Cayley transform. This parametrization contains a diagonal scaling matrix consisting of positive or negative one entries that can not be optimized by gradient descent. Thus the …

Perceptions, Potholes, And Possibilities Of Using Digital Voice Assistants To Differentiate Instructions, Adrian A. Weir

Walden Dissertations and Doctoral Studies

Access to technologies and understanding the potential uses of technology to differentiate instruction have been a concern for the teachers and students in a local school district located in the southeastern United States. Despite the emergence of digital voice assistants (DVAs) as tools for instructions, teachers lack knowledge and strategies for using DVAs to differentiate instruction in their classrooms. The purpose of this qualitative study was to identify teacher knowledge and strategies employed among special education (SPED) teachers using DVAs to differentiate instruction in their classrooms. The concepts of Carol Tomlinson’s differentiation theory and Mishra and Koehler’s TPACK framework served …

Orthogonal Recurrent Neural Networks And Batch Normalization In Deep Neural Networks, Kyle Eric Helfrich

Theses and Dissertations--Mathematics

Despite the recent success of various machine learning techniques, there are still numerous obstacles that must be overcome. One obstacle is known as the vanishing/exploding gradient problem. This problem refers to gradients that either become zero or unbounded. This is a well known problem that commonly occurs in Recurrent Neural Networks (RNNs). In this work we describe how this problem can be mitigated, establish three different architectures that are designed to avoid this issue, and derive update schemes for each architecture. Another portion of this work focuses on the often used technique of batch normalization. Although found to be successful …

Attack Detection And Mitigation In Mobile Robot Formations, Arnold Fernandes

Masters Theses

"A formation of cheap and agile robots can be deployed for space, mining, patrolling, search and rescue applications due to reduced system and mission cost, redundancy, improved system accuracy, reconfigurability, and structural flexibility. However, the performance of the formation can be altered by an adversary. Therefore, this thesis investigates the effect of adversarial inputs or attacks on a nonholonomic leader-follower-based robot formation and introduces novel detection and mitigation schemes.

First, an observer is designed for each robot in the formation in order to estimate its state vector and to compute the control law. Based on the healthy operation of the …

Coverage Guided Differential Adversarial Testing Of Deep Learning Systems, Jianmin Guo, Houbing Song, Yue Zhao, Yu Jiang

Publications

Deep learning is increasingly applied to safety-critical application domains such as autonomous cars and medical devices. It is of significant importance to ensure their reliability and robustness. In this paper, we propose DLFuzz, the coverage guided differential adversarial testing framework to guide deep learing systems exposing incorrect behaviors. DLFuzz keeps minutely mutating the input to maximize the neuron coverage and the prediction difference between the original input and the mutated input, without manual labeling effort or cross-referencing oracles from other systems with the same functionality. We also design multiple novel strategies for neuron selection to improve the neuron coverage. The …

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. …

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 …

Language Model Co-Occurrence Linking For Interleaved Activity Discovery, Eoin Rogers, Robert J. Ross, John D. Kelleher

Conference papers

As ubiquitous computer and sensor systems become abundant, the potential for automatic identification and tracking of human behaviours becomes all the more evident. Annotating complex human behaviour datasets to achieve ground truth for supervised training can however be extremely labour-intensive, and error prone. One possible solution to this problem is activity discovery: the identification of activities in an unlabelled dataset by means of an unsupervised algorithm. This paper presents a novel approach to activity discovery that utilises deep learning based language production models to construct a hierarchical, tree-like structure over a sequential vector of sensor events. Our approach differs from …

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 …

Estimating Free-Flow Speed With Lidar And Overhead Imagery, Armin Hadzic

Theses and Dissertations--Computer Science

Understanding free-flow speed is fundamental to transportation engineering in order to improve traffic flow, control, and planning. The free-flow speed of a road segment is the average speed of automobiles unaffected by traffic congestion or delay. Collecting speed data across a state is both expensive and time consuming. Some approaches have been presented to estimate speed using geometric road features for certain types of roads in limited environments. However, estimating speed at state scale for varying landscapes, environments, and road qualities has been relegated to manual engineering and expensive sensor networks. This thesis proposes an automated approach for estimating free-flow …

Deep Neural Architectures For End-To-End Relation Extraction, Tung Tran

Theses and Dissertations--Computer Science

The rapid pace of scientific and technological advancements has led to a meteoric growth in knowledge, as evidenced by a sharp increase in the number of scholarly publications in recent years. PubMed, for example, archives more than 30 million biomedical articles across various domains and covers a wide range of topics including medicine, pharmacy, biology, and healthcare. Social media and digital journalism have similarly experienced their own accelerated growth in the age of big data. Hence, there is a compelling need for ways to organize and distill the vast, fragmented body of information (often unstructured in the form of natural …

Temporal Data Extraction And Query System For Epilepsy Signal Analysis, Yan Huang

Theses and Dissertations--Computer Science

The 2016 Epilepsy Innovation Institute (Ei2) community survey reported that unpredictability is the most challenging aspect of seizure management. Effective and precise detection, prediction, and localization of epileptic seizures is a fundamental computational challenge. Utilizing epilepsy data from multiple epilepsy monitoring units can enhance the quantity and diversity of datasets, which can lead to more robust epilepsy data analysis tools. The contributions of this dissertation are two-fold. One is the implementation of a temporal query for epilepsy data; the other is the machine learning approach for seizure detection, seizure prediction, and seizure localization. The three key components of our temporal …

Special Section Guest Editorial: Machine Learning In Optics, Jonathan Howe, Travis Axtell, Khan Iftekharuddin

Electrical & Computer Engineering Faculty Publications

This guest editorial summarizes the Special Section on Machine Learning in Optics.

Generative Adversarial Networks For Visible To Infrared Video Conversion, Mohammad Shahab Uddin, Jiang Li, Chiman Kwan (Ed.)

Electrical & Computer Engineering Faculty Publications

Deep learning models are data driven. For example, the most popular convolutional neural network (CNN) model used for image classification or object detection requires large labeled databases for training to achieve competitive performances. This requirement is not difficult to be satisfied in the visible domain since there are lots of labeled video and image databases available nowadays. However, given the less popularity of infrared (IR) camera, the availability of labeled infrared videos or image databases is limited. Therefore, training deep learning models in infrared domain is still challenging. In this chapter, we applied the pix2pix generative adversarial network (Pix2Pix GAN) …

Local Binary Pattern Based Algorithms For The Discrimination And Detection Of Crops And Weeds With Similar Morphologies, Vi Nguyen Thanh Le

Theses: Doctorates and Masters

In cultivated agricultural fields, weeds are unwanted species that compete with the crop plants for nutrients, water, sunlight and soil, thus constraining their growth. Applying new real-time weed detection and spraying technologies to agriculture would enhance current farming practices, leading to higher crop yields and lower production costs. Various weed detection methods have been developed for Site-Specific Weed Management (SSWM) aimed at maximising the crop yield through efficient control of weeds. Blanket application of herbicide chemicals is currently the most popular weed eradication practice in weed management and weed invasion. However, the excessive use of herbicides has a detrimental impact …

Toward Efficient Automation Of Interpretable Machine Learning Boosting, Nathan Neuhaus

All Master's Theses

Developing efficient automated methods for Interpretable Machine Learning (IML) is an important and long-term goal in the field of Artificial Intelligence. Currently the Machine Learning landscape is dominated by Neural Networks (NNs) and Support Vector Machines (SVMs), models which are often highly accurate. Despite high accuracy, such models are essentially “black boxes” and therefore are too risky for situations like healthcare where real lives are at stake. In such situations, so called “glass-box” models, such as Decision Trees (DTs), Bayesian Networks (BNs), and Logic Relational (LR) models are often preferred, however can succumb to accuracy limitations. Unfortunately, having to choose …

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 …

Confusion Detection From Facial Expression Using Deep Neural Network, Nun Vanichkul

Chulalongkorn University Theses and Dissertations (Chula ETD)

Confusion is the most frequently observed emotion in daily life and can greatly affect the effectiveness and efficiency of communication. Detecting the confusion from learners and resolving timely is critical for achieving successful teaching in education. Most Facial Expression Recognition (FER) research works focus only on detecting six basic emotions: happiness, sadness, anger, fear, disgust, and surprise. Even though the confusion detection problem gains more attention from researchers recently, analysis of both spatial and temporal information with sufficient data is still short. In this study, we present a spatial-temporal network for confusion detection on video level which was trained on …

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.

Image And Video-Based Autism Spectrum Disorder Detection Via Deep Learning, Mindi Ruan

Graduate Theses, Dissertations, and Problem Reports (ETD)

People with Autism Spectrum Disorder (ASD) show atypical attention to social stimuli and aberrant gaze when viewing images of the physical world. However, it is unknown how they perceive the world from a first-person perspective. In this study, we used machine learning to classify photos taken in three different categories (people, indoors, and outdoors) as either having been taken by individuals with ASD or by peers without ASD. Our classifier effectively discriminated photos from all three categories but was particularly successful at classifying photos of people with >80% accuracy. Importantly, the visualization of our model revealed critical features that led …