Computer Sciences Commons^™

Graph Analysis On Social Networks, Shen Lu

USF Tampa Graduate Theses and Dissertations

With the development of transportation network, social network, and communication network, there are many applications in streaming data. For example, traffic congestion happens between the origin and destination of daily trips. Traffic analysis can help plan the trips so that traffic congestion can be avoided. Social network and communication network represent the behaviors of the entire population. People build connections based on their hobbies, daily activities, photos, videos, simple messages, and even anonymous web surfing. All of these can be turned into commercial use, such as product marketing, business network building, and technology trending. Data science is about how to …

Multimodal Image Retrieval Combining Image And Text, Md Imran Sarker

Theses and Dissertations

Retrieving visual or textual similarities from an image query and vice versa has drawn much interest in computer vision. With the growth of the E-commerce marketplace, image retrieval provides excellent competitive opportunities for vendors and customers through a robust recommendation system. Feature integration has always been an essential task for multimodal-based image retrieval approaches. However, different existing matching techniques have been used separately for visual and text similarity. Still, researchers are looking for new methods when it comes to multimodal Image Retrieval. In this paper, I study the image retrieval task, where the input query is an image plus text …

Towards A Robust And Efficient Deep Neural Network For The Lidar Point Cloud Perception, Zixiang Zhou

Graduate Thesis and Dissertation 2023-2024

In recent years, LiDAR has emerged as a crucial perception tool for robotics and autonomous vehicles. However, most LiDAR perception methods are adapted from 2D image-based deep learning methods, which are not well-suited to the unique geometric structure of LiDAR point cloud data. This domain gap poses challenges for the fast-growing LiDAR perception tasks. This dissertation aims to investigate suitable deep network structures tailored for LiDAR point cloud data, and therefore design a more efficient and robust LiDAR perception framework. Our approach to address this challenge is twofold. First, we recognize that LiDAR point cloud data is characterized by an …

Computer Vision In Adverse Conditions: Small Objects, Low-Resoltuion Images, And Edge Deployment, Raja Sunkara

Masters Theses

"Computer vision based on deep learning is an essential field that plays a significant role in object detection, image classification, semantic segmentation, instance segmentation, and other applications. However, these models face significant challenges in adverse conditions, such as small objects, low-resolution images, and edge deployment. These challenges limit the accuracy and efficiency of computer vision algorithms, making it difficult to obtain reliable results.

The primary objective of this thesis is to assess the performance of deep learning- based computer vision models in challenging conditions and provide viable solutions to overcome the obstacles. The study will specifically address three key challenges, …

Champions For Social Good: How Can We Discover Social Sentiment And Attitude-Driven Patterns In Prosocial Communication?, Raghava Rao Mukkamala, Robert J. Kauffman, Helle Zinner Henriksen

Research Collection School Of Computing and Information Systems

The UN High Commissioner on Refugees (UNHCR) is pursuing a social media strategy to inform people about displaced populations and refugee emergencies. It is actively engaging public figures to increase awareness through its prosocial communications and improve social informedness and support for policy changes in its services. We studied the Twitter communications of UNHCR social media champions and investigated their role as high-profile influencers. In this study, we offer a design science research and data analytics framework and propositions based on the social informedness theory we propose in this paper to assess communication about UNHCR’s mission. Two variables—refugee-emergency and champion …

Rafid: A Lightweight Approach To Radio Frequency Interference Detection In Time Domain Using Lstm And Statistical Analysis, Luke A. Smith, Vishesh Kumar Tanwar, Maciej Jan Zawodniok, Sanjay Kumar Madria

Electrical and Computer Engineering Faculty Research & Creative Works

Recently, the utilization of Radio Frequency (RF) devices has increased exponentially over numerous vertical platforms. This rise has led to an abundance of Radio Frequency Interference (RFI) continues to plague RF systems today. The continued crowding of the RF spectrum makes RFI efficient and lightweight mitigation critical. Detecting and localizing the interfering signals is the foremost step for mitigating RFI concerns. Addressing these challenges, we propose a novel and lightweight approach, namely RaFID, to detect and locate the RFI by incorporating deep neural networks (DNNs) and statistical analysis via batch-wise mean aggregation and standard deviation (SD) calculations. RaFID investigates the …

Practical Ai Value Alignment Using Stories, Md Sultan Al Nahian

Theses and Dissertations--Computer Science

As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally - using only a measure of task performance as feedback--can violate societal norms for acceptable behavior or cause harm. Consequently, it becomes necessary to prioritize task performance and ensure that AI actions do not have detrimental effects. Value alignment is a property of intelligent agents, wherein they solely pursue goals and activities that are non-harmful and beneficial to humans. Current approaches to value alignment largely depend on imitation learning or learning from demonstration methods. However, the dynamic nature …

Novel Architectures And Optimization Algorithms For Training Neural Networks And Applications, Vasily I. Zadorozhnyy

Theses and Dissertations--Mathematics

The two main areas of Deep Learning are Unsupervised and Supervised Learning. Unsupervised Learning studies a class of data processing problems in which only descriptions of objects are known, without label information. Generative Adversarial Networks (GANs) have become among the most widely used unsupervised neural net models. GAN combines two neural nets, generative and discriminative, that work simultaneously. We introduce a new family of discriminator loss functions that adopts a weighted sum of real and fake parts, which we call adaptive weighted loss functions. Using the gradient information, we can adaptively choose weights to train a discriminator in the direction …

Generalizable And Adaptable Data-Driven Methods For Overcoming Barriers To Practical Industrial Condition Monitoring, Matthew B. Russell

Theses and Dissertations--Electrical and Computer Engineering

The future of smart manufacturing relies on predictive maintenance systems that intelligently minimize expensive downtime through timely assessment of machine condition. Deep Learning (DL) has achieved excellent performance in industrial condition monitoring experiments, but the constraints of the manufacturing environment prevent many algorithms from being practically deployed on the factory floor. Ubiquitous sensing from online machines generates high velocity data streams that require new techniques for efficient transmission and storage. Despite these ever-increasing data lakes, many applications still lack the data needed for training DL fault diagnosis and wear tracking models since most data is unlabeled and only from nominal …

Machine Learning Framework For Real-World Electronic Health Records Regarding Missingness, Interpretability, And Fairness, Jing Lucas Liu

Theses and Dissertations--Computer Science

Machine learning (ML) and deep learning (DL) techniques have shown promising results in healthcare applications using Electronic Health Records (EHRs) data. However, their adoption in real-world healthcare settings is hindered by three major challenges. Firstly, real-world EHR data typically contains numerous missing values. Secondly, traditional ML/DL models are typically considered black-boxes, whereas interpretability is required for real-world healthcare applications. Finally, differences in data distributions may lead to unfairness and performance disparities, particularly in subpopulations.

This dissertation proposes methods to address missing data, interpretability, and fairness issues. The first work proposes an ensemble prediction framework for EHR data with large missing …

Dynamic Predictions Of Thermal Heating And Cooling Of Silicon Wafer, Hitesh Kumar

Master's Projects

Neural Networks are now emerging in every industry. All the industries are trying their best to exploit the benefits of neural networks and deep learning to make predictions or simulate their ongoing process with the use of their generated data. The purpose of this report is to study the heating pattern of a silicon wafer and make predictions using various machine learning techniques. The heating of the silicon wafer involves various factors ranging from number of lamps, wafer properties and points taken in consideration to capture the heating temperature. This process involves dynamic inputs which facilitates the heating of the …

Enhancing Facial Emotion Recognition Using Image Processing With Cnn, Sourabh Deokar

Master's Projects

Facial expression recognition (FER) has been a challenging task in computer vision for decades. With recent advancements in deep learning, convolutional neural networks (CNNs) have shown promising results in this field. However, the accuracy of FER using CNNs heavily relies on the quality of the input images and the size of the dataset. Moreover, even in pictures of the same person with the same expression, brightness, backdrop, and stance might change. These variations are emphasized when comparing pictures of individuals with varying ethnic backgrounds and facial features, which makes it challenging for deep-learning models to classify. In this paper, we …

Federated Learning For Protecting Medical Data Privacy, Abhishek Reddy Punreddy

Master's Projects

Deep learning is one of the most advanced machine learning techniques, and its prominence has increased in recent years. Language processing, predictions in medical research and pattern recognition are few of the numerous fields in which it is widely utilized. Numerous modern medical applications benefit greatly from the implementation of machine learning (ML) models and the disruptive innovations in the entire modern health care system. It is extensively used for constructing accurate and robust statistical models from large volumes of medical data collected from a variety of sources in contemporary healthcare systems [1]. Due to privacy concerns that restrict access …

Effective Systems For Insider Threat Detection, Muhanned Qasim Jabbar Alslaiman

Browse all Theses and Dissertations

Insider threats to information security have become a burden for organizations. Understanding insider activities leads to an effective improvement in identifying insider attacks and limits their threats. This dissertation presents three systems to detect insider threats effectively. The aim is to reduce the false negative rate (FNR), provide better dataset use, and reduce dimensionality and zero padding effects. The systems developed utilize deep learning techniques and are evaluated using the CERT 4.2 dataset. The dataset is analyzed and reformed so that each row represents a variable length sample of user activities. Two data representations are implemented to model extracted features …

Liquid Tab, Nathan Hulet

Williams Honors College, Honors Research Projects

Guitar transcription is a complex task requiring significant time, skill, and musical knowledge to achieve accurate results. Since most music is recorded and processed digitally, it would seem like many tools to digitally analyze and transcribe the audio would be available. However, the problem of automatic transcription presents many more difficulties than are initially evident. There are multiple ways to play a guitar, many diverse styles of playing, and every guitar sounds different. These problems become even more difficult considering the varying qualities of recordings and levels of background noise.

Machine learning has proven itself to be a flexible tool …

Deep Learning Approaches For Automatic Colorization, Super-Resolution, And Representation Of Volumetric Data, Sudarshan Devkota

Graduate Thesis and Dissertation 2023-2024

This dissertation includes a collection of studies that aim to improve the way we represent and visualize volume data. The advancement of medical imaging has revolutionized healthcare, providing crucial anatomical insights for accurate diagnosis and treatment planning. Our first study introduces an innovative technique to enhance the utility of medical images, transitioning from monochromatic scans to vivid 3D representations. It presents a framework for reference-based automatic color transfer, establishing deep semantic correspondences between a colored reference image and grayscale medical scans. This methodology extends to volumetric rendering, eliminating the need for manual intervention in parameter tuning. Next, it delves into …

Towards A Novel Approach For Smart Agriculture Predictability, Rima Grati, Myriam Aloulou, Khouloud Boukadi

All Works

No abstract provided.

Breast Density Classification Using Deep Learning, Conrad Thomas Testagrose

UNF Graduate Theses and Dissertations

Breast density screenings are an accepted means to determine a patient's predisposed risk of breast cancer development. Although the direct correlation is not fully understood, breast cancer risk increases with higher levels of mammographic breast density. Radiologists visually assess a patient's breast density using mammogram images and assign a density score based on four breast density categories outlined by the Breast Imaging and Reporting Data Systems (BI-RADS). There have been efforts to develop automated tools that assist radiologists with increasing workloads and to help reduce the intra- and inter-rater variability between radiologists. In this thesis, I explored two deep-learning-based approaches …

Bevers: A General, Simple, And Performant Framework For Automatic Fact Verification, Mitchell Dehaven

School of Computing: Dissertations, Theses, and Student Research

Fact verification has become an important process, primarily done manually by humans, to verify the authenticity of claims and statements made online. Increasingly, social media companies have utilized human effort to debunk false claims on their platforms, opting to either tag the content as misleading or false, or removing it entirely to combat misinformation on their sites. In tandem, the field of automatic fact verification has become a subject of focus among the natural language processing (NLP) community, spawning new datasets and research. The most popular dataset is the Fact Extraction and VERification (FEVER) dataset. In this thesis an end-to-end …

Wildfire Spread Prediction Using Attention Mechanisms In U-Net, Kamen Haresh Shah, Kamen Haresh Shah

Master's Theses

An investigation into using attention mechanisms for better feature extraction in wildfire spread prediction models. This research examines the U-net architecture to achieve image segmentation, a process that partitions images by classifying pixels into one of two classes. The deep learning models explored in this research integrate modern deep learning architectures, and techniques used to optimize them. The models are trained on 12 distinct observational variables derived from the Google Earth Engine catalog. Evaluation is conducted with accuracy, Dice coefficient score, ROC-AUC, and F1-score. This research concludes that when augmenting U-net with attention mechanisms, the attention component improves feature suppression …

Attention In The Faithful Self-Explanatory Nlp Models, Mostafa Rafaiejokandan

School of Computing: Dissertations, Theses, and Student Research

Deep neural networks (DNNs) can perform impressively in many natural language processing (NLP) tasks, but their black-box nature makes them inherently challenging to explain or interpret. Self-Explanatory models are a new approach to overcoming this challenge, generating explanations in human-readable languages besides task objectives like answering questions. The main focus of this thesis is the explainability of NLP tasks, as well as how attention methods can help enhance performance. Three different attention modules are proposed, SimpleAttention, CrossSelfAttention, and CrossModality. It also includes a new dataset transformation method called Two-Documents that converts every dataset into two separate documents required by the …

Glacier Segmentation From Remote Sensing Imagery Using Deep Learning, Bibek Aryal

Open Access Theses & Dissertations

Large-scale study of glaciers improves our understanding of global glacier change and is imperative for monitoring the ecological environment, preventing disasters, and studying the effects of global climate change. In recent years, remote sensing imagery has been preferred over riskier and resource-intensive field visits for tracking landscape level changes like glaciers. However, periodic manual labeling of glaciers over a large area is not feasible due to the considerable amount of time it requires while automatic segmentation of glaciers has its own set of challenges. Our work aims to study the challenges associated with segmentation of glaciers from remote sensing imagery …

Classroom Audio Classification Using Deep Learning Frameworks, Afsana Rahman Mou

Theses and Dissertations

For both teachers and students studying science, technology, engineering, and mathematics (STEM), active learning is more likely to be productive because learners engage in a variety of classroom activities. As instructors are trying different pedagogies in classroom, it is also important to check the effectiveness of those methods. The aim of our work is to identify the classroom activities with more accuracy which will help to measure the student involvement in the class. Using automatic audio classification, we can help to improve active learning strategies in the classroom, and it will be cost effective too. Various deep learning techniques, such …

Generative Spatio-Temporal And Multimodal Analysis Of Neonatal Pain, Md Sirajus Salekin

USF Tampa Graduate Theses and Dissertations

Neonates can not express their pain like an adult person. Due to the lacking of proper muscle growth and inability to express non-verbally, it is difficult to understand their emotional status. In addition, if the neonates are under any treatment or left monitored after any major surgeries (post-operative), it is more difficult to understand their pain due to the side effect of medications and the caring system (i.e. intubated, masked face, covered body with blanket, etc.). In a clinical environment, usually, bedside nurses routinely observe the neonate and measure the pain status following any standard clinical pain scale. But current …

Computer Vision Based Analysis Of Crowd Behavior For Efficient Video Surveillance In Public Places, Abhilash K. Pai

Technical Collection

Automated crowd behavior analysis and monitoring is a challenging task due to the unpredictable nature of the crowd, making it an open problem. Within this domain, we are focusing on two research problems which deal with low to mid-level analysis of crowd videos. The first problem focuses on how to effectively utilize the readily available compressed motion vector information in an input crowd video to model the motion of the crowd and perform crowd behavior analysis in varying densities of crowds. For this purpose, we consider a mid-level crowd scene analysis task called as motion pattern segmentation. The second research …

A Comparative Analysis Of Clone Detection Techniques On Semanticclonebench, Sohaib Masood Rabbani, Nabeel Ahmad Gulzar, Saad Arshad, Shamsa Abid, Shafay Shamail

Research Collection School Of Computing and Information Systems

Semantic code clone detection involves the detection of functionally similar code fragments which may otherwise be lexically, syntactically, or structurally dissimilar. The detection of semantic code clones has important applications in aspect mining and product line analysis. The accurate detection of semantic code clones is a challenging task and various techniques have been proposed. However, the evaluation of these techniques is performed using various datasets and we do not have a clear picture of the performance of these techniques relative to each other. Recently, SemanticCloneBench has been introduced as a benchmark for semantic clones. Now, we can use the SemanticCloneBench …

Overview Of The Clpsych 2022 Shared Task: Capturing Moments Of Change In Longitudinal User Posts, Adam Tsakalidis, Jenny Chim, Iman Munire Bilal, Ayah Zirikly, Dana Atzil-Slonim, Federico Nanni, Philip Resnik, Manas Gaur, Kaushik Roy, Becky Inkster, Jeff Leintz, Maria Liakata

Publications

We provide an overview of the CLPsych 2022 Shared Task, which focusses on the automatic identification of Moments of Change in longitudinal posts by individuals on social media and its connection with information regarding mental health . This year's task introduced the notion of longitudinal modelling of the text generated by an individual online over time, along with appropriate temporally sensitive evaluation metrics. The Shared Task consisted of two subtasks: (a) the main task of capturing changes in an individual's mood (drastic changes-`Switches'- and gradual changes -`Escalations'- on the basis of textual content shared online; and subsequently (b) the sub-task …

Towards Understanding The Faults Of Javascript-Based Deep Learning Systems, Lili Quan, Qianyu Guo, Xiaofei Xie, Sen Chen, Xiaohong Li, Yang Liu

Research Collection School Of Computing and Information Systems

Quality assurance is of great importance for deep learning (DL) systems, especially when they are applied in safety-critical applications. While quality issues of native DL applications have been extensively analyzed, the issues of JavaScript-based DL applications have never been systematically studied. Compared with native DL applications, JavaScript-based DL applications can run on major browsers, making the platform- and device-independent. Specifically, the quality of JavaScript-based DL applications depends on the 3 parts: the application, the third-party DL library used and the underlying DL framework (e.g., TensorFlow.js), called JavaScript-based DL system. In this paper, we conduct the first empirical study on the …

Cov-Inception: Covid-19 Detection Tool Using Chest X-Ray, Aswini Thota, Ololade Awodipe, Rashmi Patel

SMU Data Science Review

Since the pandemic started, researchers have been trying to find a way to detect COVID-19 which is a cost-effective, fast, and reliable way to keep the economy viable and running. This research details how chest X-ray radiography can be utilized to detect the infection. This can be for implementation in Airports, Schools, and places of business. Currently, Chest imaging is not a first-line test for COVID-19 due to low diagnostic accuracy and confounding with other viral pneumonia. Different pre-trained algorithms were fine-tuned and applied to the images to train the model and the best model obtained was fine-tuned InceptionV3 model …

Deep Learning For Coverage-Guided Fuzzing: How Far Are We?, Siqi Li, Xiaofei Xie, Yun Lin, Yuekang Li, Ruitao Feng, Xiaohong Li, Weimin Ge, Jin Song Dong

Research Collection School Of Computing and Information Systems

Fuzzing is a widely-used software vulnerability discovery technology, many of which are optimized using coverage-feedback. Recently, some techniques propose to train deep learning (DL) models to predict the branch coverage of an arbitrary input owing to its always-available gradients etc. as a guide. Those techniques have proved their success in improving coverage and discovering bugs under different experimental settings. However, DL models, usually as a magic black-box, are notoriously lack of explanation. Moreover, their performance can be sensitive to the collected runtime coverage information for training, indicating potentially unstable performance. In this work, we conduct a systematic empirical study on …