Computer Sciences Commons^™

License Plate Image Quality Enhancement Utilizing Super Resolution Generative Adversarial Networks, Mark Moelter

College of Graduate Studies: Theses & Dissertations

This thesis focuses primarily on enhancing the image quality of blurred license plates through the use of Super-Resolution Generative Adversarial Networks (SRGANs) [1]. We propose a synthetic dataset with SRGAN model to promote blurred image quality enhancement, and allow for model evaluation on a multitude of image input and output size combinations. SRGAN is mainly used for low-resolution image enhancement, but by heavily blurring the input images, the model is tested on its ability to blindly deblur and upsample images to the desired super-resolution (SR) size. The model enhances the image quality to nearly that of the reference images. The …

A Study On Human Face Expressions Using Convolutional Neural Networks And Generative Adversarial Networks, Sriramm Muthyala Sudhakar

Master's Projects

Human beings express themselves via words, signs, gestures, and facial emotions. Previous research using pre-trained convolutional models had been done by freezing the entire network and running the models without the use of any image processing techniques. In this research, we attempt to enhance the accuracy of many deep CNN architectures like ResNet and Senet, using a variety of different image processing techniques like Image Data Generator, Histogram Equalization, and UnSharpMask. We used FER 2013, which is a dataset containing multiple classes of images. While working on these models, we decided to take things to the next level, and we …

Novel Natural Language Processing Models For Medical Terms And Symptoms Detection In Twitter, Farahnaz Golrooy Motlagh

Browse all Theses and Dissertations

This dissertation focuses on disambiguation of language use on Twitter about drug use, consumption types of drugs, drug legalization, ontology-enhanced approaches, and prediction analysis of data-driven by developing novel NLP models. Three technical aims comprise this work: (a) leveraging pattern recognition techniques to improve the quality and quantity of crawled Twitter posts related to drug abuse; (b) using an expert-curated, domain-specific DsOn ontology model that improve knowledge extraction in the form of drug-to-symptom and drug-to-side effect relations; and (c) modeling the prediction of public perception of the drug’s legalization and the sentiment analysis of drug consumption on Twitter. We collected …

Deep Features To Analyze Pulmonary Abnormalities In Chest X-Rays Due To Covid-19, Supriti Ghosh

Dissertations and Theses

Artificial Intelligence (AI) has contributed a lot since the beginning. Healthcare is no exception. Detecting anomaly/abnormality in (bio)medical image is crucial. In this thesis, we aim at detecting/screening pulmonary abnormalities due to Covid-19 in chest X-rays using deep features. We study CheXNet, DenseNet169, ResNet50 and VggNet16 to analyze CXRs to detect the evidence of Covid-19 in this research. CheXNet was primarily designed for radiologist-level pneumonia detection in Chest X-rays (CXRs). We created a benchmark dataset size of 4,716 CXRs (2,358 Covid-19 positive cases and 2,358 non-Covid cases (Healthy and Pneumonia cases)) and with k(=5) fold cross-validation technique, using the DenseNet, …

An Analysis On Adversarial Machine Learning: Methods And Applications, Ali Dabouei

Graduate Theses, Dissertations, and Problem Reports (ETD)

Deep learning has witnessed astonishing advancement in the last decade and revolutionized many fields ranging from computer vision to natural language processing. A prominent field of research that enabled such achievements is adversarial learning, investigating the behavior and functionality of a learning model in presence of an adversary. Adversarial learning consists of two major trends. The first trend analyzes the susceptibility of machine learning models to manipulation in the decision-making process and aims to improve the robustness to such manipulations. The second trend exploits adversarial games between components of the model to enhance the learning process. This dissertation aims to …

Learning Representations For Human Identification, Sinan Sabri

Graduate Theses, Dissertations, and Problem Reports (ETD)

Long-duration visual tracking of people requires the ability to link track snippets (a.k.a. tracklets) based on the identity of people. In lack of the availability of motion priors or hard biometrics (e.g., face, fingerprint, or iris), the common practice is to leverage soft biometrics for matching tracklets corresponding to the same person in different sightings. A common choice is to use the whole-body visual appearance of the person, as determined by the clothing, which is assumed to not change during tracking. The problem is challenging because distinct images of the same person may look very different, since no restrictions are …

Smart City Management Using Machine Learning Techniques, Mostafa Zaman

Theses and Dissertations

In response to the growing urban population, "smart cities" are designed to improve people's quality of life by implementing cutting-edge technologies. The concept of a "smart city" refers to an effort to enhance a city's residents' economic and environmental well-being via implementing a centralized management system. With the use of sensors and actuators, smart cities can collect massive amounts of data, which can improve people's quality of life and design cities' services. Although smart cities contain vast amounts of data, only a percentage is used due to the noise and variety of the data sources. Information and communication technology (ICT) …

On The Reproducibility And Replicability Of Deep Learning In Software Engineering, Chao Liu, Cuiyun Gao, Xin Xia, David Lo, John C. Grundy, Xiaohu Yang

Research Collection School Of Computing and Information Systems

Context: Deep learning (DL) techniques have gained significant popularity among software engineering (SE) researchers in recent years. This is because they can often solve many SE challenges without enormous manual feature engineering effort and complex domain knowledge.Objective: Although many DL studies have reported substantial advantages over other state-of-the-art models on effectiveness, they often ignore two factors: (1) reproducibility—whether the reported experimental results can be obtained by other researchers using authors’ artifacts (i.e., source code and datasets) with the same experimental setup; and (2) replicability—whether the reported experimental result can be obtained by other researchers using their re-implemented artifacts with a …

Enhancing Zero-Shot And Few-Shot Text Classification Using Pre-Trained Language Models, Yanan Chen

Theses and Dissertations (Comprehensive)

In recent years, the community of natural language processing (NLP) has seen amazing progress in the development of pre-trained language models (PLMs). The novel paradigm of PLMs does not require labeled data, allowing us to experiment with increased training scale through employing freely available colossal online self-training corpus to push the limits. Language models (LMs), such as GPT, BERT and T5, have achieved high performance on a wide range of NLP tasks. Meanwhile, research on zero-shot and few-shot text classification has received increasing attention. As labelling can be costly and time-consuming, how to perform data augmentation (DA) and enhance the …

Cross-Modal Food Retrieval: Learning A Joint Embedding Of Food Images And Recipes With Semantic Consistency And Attention Mechanism, Hao Wang, Doyen Sahoo, Chenghao Liu, Ke Shu, Palakorn Achananuparp, Ee-Peng Lim, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Food retrieval is an important task to perform analysis of food-related information, where we are interested in retrieving relevant information about the queried food item such as ingredients, cooking instructions, etc. In this paper, we investigate cross-modal retrieval between food images and cooking recipes. The goal is to learn an embedding of images and recipes in a common feature space, such that the corresponding image-recipe embeddings lie close to one another. Two major challenges in addressing this problem are 1) large intra-variance and small inter-variance across cross-modal food data; and 2) difficulties in obtaining discriminative recipe representations. To address these …

Task Classification During Visual Search Using Classic Machine Learning And Deep Learning, Devangi Vilas Chinchankar

Master's Projects

In an average human life, the eyes not only passively scan visual scenes, but most times end up actively performing tasks including, but not limited to, searching, comparing, and counting. As a result of the advances in technology, we are observing a boost in the average screen time. Humans are now looking at an increasing number of screens and in turn images and videos. Understanding what scene a user is looking at and what type of visual task is being performed can be useful in developing intelligent user interfaces, and in virtual reality and augmented reality devices. In this research, …

Analyzing And Detecting Android Malware And Deepfake, Md Shohel Rana

Dissertations

Rapid advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) over the past several decades have produced a variety of technologies and tools that, among numerous cybersecurity issues, have enticed cybercriminals and hackers to design malware for the Android operating systems and/or manipulate multimedia. For example, high-quality and realistic fake videos, images, or audios have been created to spread misinformation and propaganda, foment political discord and hate, or even harass and blackmail people; these manipulated, high-quality and realistic videos became known recently as Deepfake. There has been much work done in recent years on malware analysis and …

Adapting Single-View View Synthesis With Multiplane Images For 3d Video Chat, Anurag Venkata Uppuluri

Master's Theses

Activities like one-on-one video chatting and video conferencing with multiple participants are more prevalent than ever today as we continue to tackle the pandemic. Bringing a 3D feel to video chat has always been a hot topic in Vision and Graphics communities. In this thesis, we have employed novel view synthesis in attempting to turn one-on-one video chatting into 3D. We have tuned the learning pipeline of Tucker and Snavely's single-view view synthesis paper — by retraining it on MannequinChallenge dataset — to better predict a layered representation of the scene viewed by either video chat participant at any given …

Visualizing Features From Deep Neural Networks Trained On Alzheimer’S Disease And Few-Shot Learning Models For Alzheimer’S Disease, John Reeder

All Theses

Alzheimer’s disease is an incurable neural disease, usually affecting the elderly. The afflicted suffer from cognitive impairments that get dramatically worse at each stage. Previous research on Alzheimer’s disease analysis in terms of classification leveraged statistical models such as support vector machines. However, statistical models such as support vector machines train the from numerical data instead of medical images. Today, convolutional neural networks (CNN) are widely considered as the one which can achieve the state-of-the- art image classification performance. However, due to their black box nature, there can be reluctance amongst medical professionals for their use. On the other hand, …

Analysis Of Deep Learning Methods For Wired Ethernet Physical Layer Security Of Operational Technology, Lucas Torlay

All Theses

The cybersecurity of power systems is jeopardized by the threat of spoofing and man-in-the-middle style attacks due to a lack of physical layer device authentication techniques for operational technology (OT) communication networks. OT networks cannot support the active probing cybersecurity methods that are popular in information technology (IT) networks. Furthermore, both active and passive scanning techniques are susceptible to medium access control (MAC) address spoofing when operating at Layer 2 of the Open Systems Interconnection (OSI) model. This thesis aims to analyze the role of deep learning in passively authenticating Ethernet devices by their communication signals. This method operates at …

Information Extraction And Classification On Journal Papers, Lei Yu

School of Computing: Dissertations, Theses, and Student Research

The importance of journals for diffusing the results of scientific research has increased considerably. In the digital era, Portable Document Format (PDF) became the established format of electronic journal articles. This structured form, combined with a regular and wide dissemination, spread scientific advancements easily and quickly. However, the rapidly increasing numbers of published scientific articles requires more time and effort on systematic literature reviews, searches and screens. The comprehension and extraction of useful information from the digital documents is also a challenging task, due to the complex structure of PDF.

To help a soil science team from the United States …

Automating Developer Chat Mining, Shengyi Pan, Lingfeng Bao, Xiaoxue Ren, Xin Xia, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

Online chatrooms are gaining popularity as a communication channel between widely distributed developers of Open Source Software (OSS) projects. Most discussion threads in chatrooms follow a Q&A format, with some developers (askers) raising an initial question and others (respondents) joining in to provide answers. These discussion threads are embedded with rich information that can satisfy the diverse needs of various OSS stakeholders. However, retrieving information from threads is challenging as it requires a thread-level analysis to understand the context. Moreover, the chat data is transient and unstructured, consisting of entangled informal conversations. In this paper, we address this challenge by …

Automating User Notice Generation For Smart Contract Functions, Xing Hu, Zhipeng Gao, Xin Xia, David Lo, Xiaohu Yang

Research Collection School Of Computing and Information Systems

Smart contracts have obtained much attention and are crucial for automatic financial and business transactions. For end-users who have never seen the source code, they can read the user notice shown in end-user client to understand what a transaction does of a smart contract function. However, due to time constraints or lack of motivation, user notice is often missing during the development of smart contracts. For endusers who lack the information of the user notices, there is no easy way for them to check the code semantics of the smart contracts. Thus, in this paper, we propose a new approach …

Automated Identification Of Stages In Gonotrophic Cycle Of Mosquitoes Using Computer Vision Techniques, Sherzod Kariev

USF Tampa Graduate Theses and Dissertations

In this paper, we design Computer Vision techniques to determine stages in the Gonotrophic cycle of mosquitoes. The dataset for our problem came from 125 adult female mosquitoes - each of which belonged to one of three species - Aedes aegypti, Culex quinquefasciatus, and Anopheles stephensi. The mosquitoes were raised in a lab and passed through all fourGonotrophic stages (Un-fed, Fully-fed, Semi-gravid, and Gravid). At each stage, their images were captured on a plain background via a Xiaomi smartphone, resulting in a dataset of 1784 images. The images were then augmented using standard techniques to generate a larger dataset of …

A Large-Scale Benchmark For Food Image Segmentation, Xiongwei Wu, Xin Fu, Ying Liu, Ee-Peng Lim, Steven C. H. Hoi, Qianru Sun

Research Collection School Of Computing and Information Systems

Food image segmentation is a critical and indispensible task for developing health-related applications such as estimating food calories and nutrients. Existing food image segmentation models are underperforming due to two reasons: (1) there is a lack of high quality food image datasets with fine-grained ingredient labels and pixel-wise location masks—the existing datasets either carry coarse ingredient labels or are small in size; and (2) the complex appearance of food makes it difficult to localize and recognize ingredients in food images, e.g., the ingredients may overlap one another in the same image, and the identical ingredient may appear distinctly in different …

Reasoning About Scene And Image Structure For Computer Vision, Zhihao Xia

McKelvey School of Engineering Graduate Student Theses & Dissertations

The wide availability of cheap consumer cameras has democratized photography for novices and experts alike, with more than a trillion photographs taken each year. While many of these cameras---especially those on mobile phones---have inexpensive optics and make imperfect measurements, the use of modern computational techniques can allow the recovery of high-quality photographs as well as of scene attributes.

In this dissertation, we explore algorithms to infer a wide variety of physical and visual properties of the world, including color, geometry, reflectance etc., from images taken by casual photographers in unconstrained settings. We specifically focus on neural network-based methods, while incorporating …

Hardware For Quantized Mixed-Precision Deep Neural Networks, Andres Rios

Open Access Theses & Dissertations

Recently, there has been a push to perform deep learning (DL) computations on the edge rather than the cloud due to latency, network connectivity, energy consumption, and privacy issues. However, state-of-the-art deep neural networks (DNNs) require vast amounts of computational power, data, and energyâ??resources that are limited on edge devices. This limitation has brought the need to design domain-specific architectures (DSAs) that implement DL-specific hardware optimizations. Traditionally DNNs have run on 32-bit floating-point numbers; however, a body of research has shown that DNNs are surprisingly robust and do not require all 32 bits. Instead, using quantization, networks can run on …

Forecasting Pedestrian Trajectory Using Deep Learning, Arsal Syed

UNLV Theses, Dissertations, Professional Papers, and Capstones

In this dissertation we develop different methods for forecasting pedestrian trajectories. Complete understanding of pedestrian motion is essential for autonomous agents and social robots to make realistic and safe decisions. Current trajectory prediction methods rely on incorporating historic motion, scene features and social interaction to model pedestrian behaviors. Our focus is to accurately understand scene semantics to better forecast trajectories. In order to do so, we leverage semantic segmentation to encode static scene features such as walkable paths, entry/exits, static obstacles etc. We further evaluate the effectiveness of using semantic maps on different datasets and compare its performance with already …

Code2que: A Tool For Improving Question Titles From Mined Code Snippets In Stack Overflow, Zhipeng Gao, Xin Xia, David Lo, John C. Grundy, Yuan-Fang Li

Research Collection School Of Computing and Information Systems

Stack Overflow is one of the most popular technical Q&A sites used by software developers. Seeking help from Stack Overflow has become an essential part of software developers' daily work for solving programming-related questions. Although the Stack Overflow community has provided quality assurance guidelines to help users write better questions, we observed that a significant number of questions submitted to Stack Overflow are of low quality. In this paper, we introduce a new web-based tool, Code2Que, which can help developers in writing higher quality questions for a given code snippet. Code2Que consists of two main stages: offline learning and online …

An Empirical Study Of Gui Widget Detection For Industrial Mobile Games, Jiaming Ye, Ke Chen, Xiaofei Xie, Lei Ma, Ruochen Huang, Yingfeng Chen, Yinxing Xue, Jianjun Zhao

Research Collection School Of Computing and Information Systems

With the widespread adoption of smartphones in our daily life, mobile games experienced increasing demand over the past years. Meanwhile, the quality of mobile games has been continuously drawing more and more attention, which can greatly affect the player experience. For better quality assurance, general-purpose testing has been extensively studied for mobile apps. However, due to the unique characteristic of mobile games, existing mobile testing techniques may not be directly suitable and applicable. To better understand the challenges in mobile game testing, in this paper, we first initiate an early step to conduct an empirical study towards understanding the challenges …

Toward Deep Supervised Anomaly Detection: Reinforcement Learning From Partially Labeled Anomaly Data, Guansong Pang, Anton Van Den Hengel, Chunhua Shen, Longbing Cao

Research Collection School Of Computing and Information Systems

We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively fit the limited anomaly examples that typically do not span the entire set of anomalies, or proceed with unsupervised learning from the unlabeled data. We propose here instead a deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies. This approach learns the known abnormality by automatically interacting with an anomalybiased simulation environment, while continuously extending the …

Computational Techniques For Elucidating Plant-Pathogen Interactions: A Case Study On Citrus-Hlb Interactome, Cristian D. Loaiza

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

The Citrus fruit industry in the United States has been affected during the last two decades because of the outbreak of the citrus greening disease, also known as Huanglongbing (HLB). Many people and organizations are working in therapeutics to help mitigate the impact of this disease, unfortunately there is not a cure yet. There are many mechanisms that needs to be understood about this disease, especially at the molecular level. Not only HLB, but many other infectious diseases are controlled by the interaction of proteins from the host (Citrus in this case) and from the pathogen that causes the disease. …

Multi-Modal Self-Supervised Representation Learning For Earth Observation, Pallavi Jain, Bianca Schoen Phelan, Robert J. Ross

Conference papers

Self-Supervised learning (SSL) has reduced the performance gap between supervised and unsupervised learning, due to its ability to learn invariant representations. This is a boon to the domains like Earth Observation (EO), where labelled data availability is scarce but unlabelled data is freely available. While Transfer Learning from generic RGB pre-trained models is still common-place in EO, we argue that, it is essential to have good EO domain specific pre-trained model in order to use with downstream tasks with limited labelled data. Hence, we explored the applicability of SSL with multi-modal satellite imagery for downstream tasks. For this we utilised …

Design, Deployment, And Validation Of Computer Vision Techniques For Societal Scale Applications, Arup Kanti Dey

USF Tampa Graduate Theses and Dissertations

Artificial Intelligence techniques have ensued a significant impact on our daily lives. Numerous applications in so many diverse fields have been made possible by AI algorithms today, and there are many more yet to come. In this dissertation, we design, deploy and validate computer vision algorithms for innovative and high-impact societal scale applications.We specifically focus on two applications in this dissertation: Detection of distracted driving and Detection of breeding habitats of mosquito vectors.

Distracted driving on roads is a major problem around the world. Distracted driving is the case where a driver diverts his/her focus from the road and engages …

Knowledge Extraction And Inference Based On Visual Understanding Of Cooking Contents, Ahmad Babaeian Babaeian Jelodar

USF Tampa Graduate Theses and Dissertations

In this dissertation, we discuss our work on analyzing cooking content for the ultimate goal ofautomatic robotic manipulation. For a robot to perform a cooking task, it will need to both have an understanding of the scene and utilize prior knowledge. We will explore two main sub-problems: knowledge extraction and inference, and visual understanding of the scene in this dissertation. Visual understanding of a scene, requires algorithms that can visually infer information from a single image or video. Many algorithms in the area of image classification, object detection, or activity recognition can be used in this area. Although great advances …