Digital Commons Network^™

Context In Computer Vision: A Taxonomy, Multi-Stage Integration, And A General Framework, Xuan Wang

Dissertations, Theses, and Capstone Projects

Contextual information has been widely used in many computer vision tasks, such as object detection, video action detection, image classification, etc. Recognizing a single object or action out of context could be sometimes very challenging, and context information may help improve the understanding of a scene or an event greatly. However, existing approaches design specific contextual information mechanisms for different detection tasks.

In this research, we first present a comprehensive survey of context understanding in computer vision, with a taxonomy to describe context in different types and levels. Then we proposed MultiCLU, a new multi-stage context learning and utilization framework, …

Designing Methods For Representation Learning Of Molecular Sequences And Its Application In Analysis Tasks, Taslim Murad

Computer Science Dissertations

Molecular sequence analysis serves as a fundamental process for elucidating the intricate functions, structures, and behaviors inherent in sequences. Its application extends to char- acterizing associated organisms, such as viruses, facilitating the development of preventive measures to mitigate their dissemination and influence. Given the potential of viruses to trigger epidemics with global ramifications, comprehensive sequence analysis is pivotal in understanding and managing their impact effectively. The rapid expansion of bio-sequence data has surpassed the computational capabilities of traditional analytical techniques, such as the phylogenetic approach, due to their high computational costs. Consequently, clustering and classification have emerged as compelling alternatives, …

Crash Detecting System Using Deep Learning, Yogesh Reddy Muddam

Electronic Theses, Projects, and Dissertations

Accidents pose a significant risk to both individual and property safety, requiring effective detection and response systems. This work introduces an accident detection system using a convolutional neural network (CNN), which provides an impressive accuracy of 86.40%. Trained on diverse data sets of images and videos from various online sources, the model exhibits complex accident detection and classification and is known for its prowess in image classification and visualization.

CNN ensures better accident detection in various scenarios and road conditions. This example shows its adaptability to a real-world accident scenario and enhances its effectiveness in detecting early events. A key …

Evaluation Of An End-To-End Radiotherapy Treatment Planning Pipeline For Prostate Cancer, Mohammad Daniel El Basha, Court Laurence, Carlos Eduardo Cardenas, Julianne Pollard-Larkin, Steven Frank, David T. Fuentes, Falk Poenisch, Zhiqian H. Yu

Dissertations & Theses (Open Access)

Radiation treatment planning is a crucial and time-intensive process in radiation therapy. This planning involves carefully designing a treatment regimen tailored to a patient’s specific condition, including the type, location, and size of the tumor with reference to surrounding healthy tissues. For prostate cancer, this tumor may be either local, locally advanced with extracapsular involvement, or extend into the pelvic lymph node chain. Automating essential parts of this process would allow for the rapid development of effective treatment plans and better plan optimization to enhance tumor control for better outcomes.

The first objective of this work, to automate the treatment …

Enhancing Audit Quality Through Artificial Intelligence: An External Auditing Perspective, Jonah Mitan

Accounting Undergraduate Honors Theses

The evolving landscape of the audit profession has been significantly influenced by the integration of artificial intelligence (AI) and automation, marking a pivotal shift in audit methodologies, the auditors' roles, and the overarching quality of audits. This thesis delves into the breadth of AI's impact on the industry through a comprehensive review of academic literature, professional publications, and industry insights, highlighting the transformative effects of AI on audit processes. AI-driven tools, including machine learning, deep learning, and natural language processing can expedite laborious audit tasks, enhancing data analytics capabilities, and enabling more accurate risk assessment and fraud detection. AI technologies …

Pedestrian Pathing Prediction Using Complex Contextual Behavioral Data In High Foot Traffic Settings, Laurel Bingham

All Graduate Theses and Dissertations, Fall 2023 to Present

Ensuring the safe integration of autonomous vehicles into real-world environments requires a comprehensive understanding of pedestrian behavior. This study addresses the challenge of predicting the movement and crossing intentions of pedestrians, a crucial aspect in the development of fully autonomous vehicles.

The research focuses on leveraging Honda's TITAN dataset, comprising 700 unique clips captured by moving vehicles in high-foot-traffic areas of Tokyo, Japan. Each clip provides detailed contextual information, including human-labeled tags for individuals and vehicles, encompassing attributes such as age, motion status, and communicative actions. Long Short-Term Memory (LSTM) networks were employed and trained on various combinations of contextual …

Deep Learning In Indus Valley Script Digitization, Deva Munikanta Reddy Atturu

Theses and Dissertations

This research introduces ASR-net(Ancient Script Recognition), a groundbreaking system that automatically digitizes ancient Indus seals by converting them into coded text, similar to Optical Character Recognition for modern languages. ASR-net, with an 95% success rate in identifying individual symbols, aims to address the crucial need for automated techniques in deciphering the enigmatic Indus script. Initially Yolov3 is utilized to create the bounding boxes around each graphemes present in the Indus Valley Seal. In addition to that we created M-net(Mahadevan) model to encode the graphemes. Beyond digitization, the paper proposes a new research challenge called the Motif Identification Problem (MIP) related …

Automated Brain Tumor Classifier With Deep Learning, Venkata Sai Krishna Chaitanya Kandula

Electronic Theses, Projects, and Dissertations

Brain Tumors are abnormal growth of cells within the brain that can be categorized as benign (non-cancerous) or malignant (cancerous). Accurate and timely classification of brain tumors is crucial for effective treatment planning and patient care. Medical imaging techniques like Magnetic Resonance Imaging (MRI) provide detailed visualizations of brain structures, aiding in diagnosis and tumor classification^[8].

In this project, we propose a brain tumor classifier applying deep learning methodologies to automatically classify brain tumor images without any manual intervention. The classifier uses deep learning architectures to extract and classify brain MRI images. Specifically, a Convolutional Neural Network (CNN) …

Robust And Trustworthy Deep Learning: Attacks, Defenses And Designs, Bingyin Zhao

All Dissertations

Deep neural networks (DNNs) have achieved unprecedented success in many fields. However, robustness and trustworthiness have become emerging concerns since DNNs are vulnerable to various attacks and susceptible to data distributional shifts. Attacks such as data poisoning and out-of-distribution scenarios such as natural corruption significantly undermine the performance and robustness of DNNs in model training and inference and impose uncertainty and insecurity on the deployment in real-world applications. Thus, it is crucial to investigate threats and challenges against deep neural networks, develop corresponding countermeasures, and dig into design tactics to secure their safety and reliability. The works investigated in this …

Deep Learning System Identification, Linearization And Control Of Dynamical Systems Utilizing Koopman Theory With Applications In Orbital Systems, George Mario Nehma

Theses and Dissertations

The computational and complexity burden of current linearization techniques is one that is a hinderance in the application of real world guidance, navigation and control systems. With the advancements in Deep Neural Networks, large data handling and Koopman Theory, the possibility of global linearizations of nonlinear systems is more prominent. This work demonstrates the capability of a Deep Neural Network learned Koopman operator to transform a nonlinear system into a Linear Time-Invariant system. The method presented is applied to both two purely dynamical systems and one controlled system to emphasize the ability for the technique to be applied in all …

Detection And Classification Of Diabetic Retinopathy Using Deep Learning Models, Aishat Olatunji

Electronic Theses and Dissertations

Healthcare analytics leverages extensive patient data for data-driven decision-making, enhancing patient care and results. Diabetic Retinopathy (DR), a complication of diabetes, stems from damage to the retina’s blood vessels. It can affect both type 1 and type 2 diabetes patients. Ophthalmologists employ retinal images for accurate DR diagnosis and severity assessment. Early detection is crucial for preserving vision and minimizing risks. In this context, we utilized a Kaggle dataset containing patient retinal images, employing Python’s versatile tools. Our research focuses on DR detection using deep learning techniques. We used a publicly available dataset to apply our proposed neural network and …

Modeling The Spatiotemporal Variations Of The Magnetic Field In Active Regions On The Sun Using Deep Neural Networks, Godwill Asare Mensah Mensah

Open Access Theses & Dissertations

Solar active regions are areas on the Sun's surface that have especially strong magnetic fields. Active regions are usually linked to a number of phenomena that can have serious detrimental consequences on technology and, in turn, human life. Examples of these phenomena include solar flares and coronal mass ejections, or CMEs. The precise predictionof solar flares and coronal mass ejections is still an open problem since the fundamental processes underpinning the formation and development of active regions are still not well understood. One key area of research at the intersection of solar physics and artificial intelligence is deriving insights from …

Enhancing Mobile App User Experience: A Deep Learning Approach For System Design And Optimization, Deepesh Haryani

Harrisburg University Dissertations and Theses

This paper presents a comprehensive framework for enhancing user experience in mobile applications through the integration of deep learning systems. The proposed system design encompasses various components, including data collection and preprocessing, model development and training, integration with mobile applications, dataset management service, model training service, model serving, hyperparameter optimization, metadata and artifact store, and workflow orchestration. Each component is meticulously designed with a focus on scalability, efficiency, isolation, and critical analysis. Innovative design principles are employed to ensure seamless integration, usability, and automation. Additionally, the paper discusses distributed training service design, advanced optimization techniques, and decision criteria for hyperparameter …

Machine Learning Classifiers For Chronic Obstructive Pulmonary Disease Assessment Using Lung Ct Data., Halimah Alsurayhi

Electronic Thesis and Dissertation Repository

Chronic Obstructive Pulmonary Disease (COPD) is a condition characterized by persistent inflammation and airflow blockages in the lungs, contributing to a significant number of deaths globally each year. To guide tailored treatment strategies and mitigate future risks, the Global Initiative for Chronic Obstructive Lung Disease (GOLD) employs a multifaceted assessment system of COPD severity, considering patient's lung function, symptoms, and exacerbation history. COPD staging systems, such as the high-resolution eight-stage COPD system and the GOLD 2023 three staging systems, have been later developed based on these factors. Lung Computed Tomography (CT) is becoming increasingly crucial in investigating COPD as it …

Extracting Dnn Architectures Via Runtime Profiling On Mobile Gpus, Dong Hyub Kim

Masters Theses

Due to significant investment, research, and development efforts over the past decade, deep neural networks (DNNs) have achieved notable advancements in classification and regression domains. As a result, DNNs are considered valuable intellectual property for artificial intelligence providers. Prior work has demonstrated highly effective model extraction attacks which steal a DNN, dismantling the provider’s business model and paving the way for unethical or malicious activities, such as misuse of personal data, safety risks in critical systems, or spreading misinformation. This thesis explores the feasibility of model extraction attacks on mobile devices using aggregated runtime profiles as a side-channel to leak …

Insights Into Cellular Evolution: Temporal Deep Learning Models And Analysis For Cell Image Classification, Xinran Zhao

Master's Theses

Understanding the temporal evolution of cells poses a significant challenge in developmental biology. This study embarks on a comparative analysis of various machine-learning techniques to classify cell colony images across different timestamps, thereby aiming to capture dynamic transitions of cellular states. By performing Transfer Learning with state-of-the-art classification networks, we achieve high accuracy in categorizing single-timestamp images. Furthermore, this research introduces the integration of temporal models, notably LSTM (Long Short Term Memory Network), R-Transformer (Recurrent Neural Network enhanced Transformer) and ViViT (Video Vision Transformer), to undertake this classification task to verify the effectiveness of incorporating temporal features into the classification …

Active Uncertainty Representation Learning: Toward More Label Efficiency In Deep Learning, Salman Mohamadi

Graduate Theses, Dissertations, and Problem Reports

The primary goal of this dissertation is to investigate and improve the efficiency of deep learning algorithms, especially within computer vision problem domains, from the perspective of label-efficiency. This investigation showed that deep learning algorithms are mostly notorious for the lack of uncertainty representation. Accordingly, we aimed to develop an array of deep learning frameworks rich with uncertainty representation. These frameworks are mainly within two current pillars of machine learning, deep active learning and self-supervised learning. These frameworks include deep active ensemble sampling for efficient sample selection within deep active learning, a two-stage ensemble-based general self-training approach for existing visual …

Deep Learning Applications On Ionospheric Studies, Yang Pan

Physics Dissertations

Machine learning techniques, particularly deep learning techniques, have been vigorously pursued to tackle space physics problems and achieved some impressive results recently. The growth of deep learning technologies in different domains enables innovative solutions to those problems compared to conventional methods. Filling data gaps in instrumental observations is among the demanding issues, which benefits space physicists to study ionospheric phenomena with complete data coverage. Global total electron content (TEC) and regional ionospheric electron density (Ne) are among important physical parameters in ionospheric studies. Due to the limited coverage of global navigation satellite system (GNSS) ground receivers and sporadic …

Enhancing Scanning Tunneling Microscopy With Automation And Machine Learning, Darian Smalley

Graduate Thesis and Dissertation 2023-2024

The scanning tunneling microscope (STM) is one of the most advanced surface science tools capable of atomic resolution imaging and atomic manipulation. Unfortunately, STM has many time-consuming bottlenecks, like probe conditioning, tip instability, and noise artificing, which causes the technique to have low experimental throughput. This dissertation describes my efforts to address these challenges through automation and machine learning. It consists of two main sections each describing four projects for a total of eight studies.

The first section details two studies on nanoscale sample fabrication and two studies on STM tip preparation. The first two studies describe the fabrication of …

Applications Of Predictive And Generative Ai Algorithms: Regression Modeling, Customized Large Language Models, And Text-To-Image Generative Diffusion Models, Suhaima Jamal

Electronic Theses and Dissertations

The integration of Machine Learning (ML) and Artificial Intelligence (AI) algorithms has radically changed predictive modeling and classification tasks, enhancing a multitude of domains with unprecedented analytical capabilities. Predictive modeling leverages ML and AI to forecast future trends or behaviors based on historical data, while classification tasks categorize data into distinct classes, from email filtering to medical diagnosis. Concurrently, text-to-image generation has emerged as a transformative potential, allowing visual content creation directly from textual descriptions. These advancements are pivotal in design, art, entertainment, and visual communication, as well as enhancing creativity and productivity. This work explores three significant studies in …

Statistically Principled Deep Learning For Sar Image Segmentation, Cassandra Goldberg

Honors Projects

This project explores novel approaches for Synthetic Aperture Radar (SAR) image segmentation that integrate established statistical properties of SAR into deep learning models. First, Perlin Noise and Generalized Gamma distribution sampling methods were utilized to generate a synthetic dataset that effectively captures the statistical attributes of SAR data. Subsequently, deep learning segmentation architectures were developed that utilize average pooling and 1x1 convolutions to perform statistical moment computations. Finally, supervised and unsupervised disparity-based losses were incorporated into model training. The experimental outcomes yielded promising results: the synthetic dataset effectively trained deep learning models for real SAR data segmentation, the statistically-informed architectures …

Prediction Of Anomalous Events With Data Augmentation And Hybrid Deep Learning Approach, Ahmed Shoyeb Raihan

Graduate Theses, Dissertations, and Problem Reports

In this study, we propose a novel anomaly detection framework designed specifically for Multivariate Time Series (MTS) data, addressing the prevalent challenges in analyzing such complex datasets. The detection of anomalies within MTS data is notably difficult due to the complex interplay of numerous variables, temporal dependencies, and the common issue of class imbalance, where one category significantly outnumbers another. Traditional deep learning (DL) approaches often fall short in simultaneously tackling these issues. Our framework is designed to address these challenges through a two-phased approach. Phase I employs Conditional Tabular Generative Adversarial Networks (CTGAN) to create strategic synthetic data, setting …

Towards Patient Specific Mitral Valve Modelling Via Dynamic 3d Transesophageal Echocardiography, Patrick Carnahan

Electronic Thesis and Dissertation Repository

Mitral valve disease is a common pathologic problem occurring increasingly in an aging population, and many patients suffering from mitral valve disease require surgical intervention. Planning an interventional approach from diagnostic imaging alone remains a significant clinical challenge. Transesophageal echocardiography (TEE) is the primary imaging modality used diagnostically, it has limitations in image quality and field-of-view. Recently, developments have been made towards modelling patient-specific deformable mitral valves from TEE imaging, however, a major barrier to producing accurate valve models is the need to derive the leaflet geometry through segmentation of diagnostic TEE imaging. This work explores the development of volume …

Smart Applications And Resource Management In Internet Of Things, Zeinab Akhavan

Computer Science ETDs

Internet of Things (IoT) technologies are currently the principal solutions driving smart cities. These new technologies such as Cyber Physical Systems, 5G and data analytic have emerged to address various cities' infrastructure issues ranging from transportation and energy management to healthcare systems. An IoT setting primarily consists of a wide range of users and devices as a massive network interacting with different layers of the city infrastructure resulting in generating sheer volume of data to enable smart city services. The goal of smart city services is to create value for the entire ecosystem, whether this is health, education, transportation, energy, …

Utilizing Multitask Transfer Learning For Sonographic Rheumatoid Arthritis Synovitis Grading, Jordan Marie Claire Sanders

Doctoral Dissertations and Master's Theses

Classifying the four sonographic Rheumatoid Arthritis (RA) synovitis grades (Grade 0, Grade 1, Grade 2, and Grade 3) is a difficult problem due to the complexity of the relevant markers. Therefore, the current research proposes a Multitask Transfer Learning (MTL) framework for sonographic RA synovitis grading of Ultrasound (US) images in Brightness mode (B-Mode) and Power Doppler mode.

In the medical community, the lack of reliability of scoring these images has been an issue and reason for concern for doctors and other medical practitioners. The human/machine variability across the acquisition procedure of these US images creates an additional challenge that …

Deep-Learning Based Multiple-Model Bayesian Architecture For Spacecraft Fault Estimation, Rocio Jado Puente

Doctoral Dissertations and Master's Theses

This thesis presents recent findings regarding the performance of an intelligent architecture designed for spacecraft fault estimation. The approach incorporates a collection of systematically organized autoencoders within a Bayesian framework, enabling early detection and classification of various spacecraft faults such as reaction-wheel damage, sensor faults, and power system degradation.

To assess the effectiveness of this architecture, a range of performance metrics is employed. Through extensive numerical simulations and in-lab experimental testing utilizing a dedicated spacecraft testbed, the capabilities and accuracy of the proposed intelligent architecture are analyzed. These evaluations provide valuable insights into the architecture's ability to detect and classify …

Hyper-Learning With Deep Artificial Neurons, Brendan Blake Camp

Computer Science Dissertations

Two problems have plagued artificial neural networks since their birth in the mid-20th century. The first is a tendency to lose previously acquired knowledge when there is a large shift in the underlying data-distribution, a phenomenon provocatively known as catastrophic forgetting. The second is an inability to know-what-they-don’t-know, resulting in excessively confident behavior, even in uncertain or novel conditions. This text provides an in-depth history of these obstacles, complete with formal problem definitions and literature reviews. Most importantly, the proposed solutions herein demonstrate that these challenges can be overcome with the right architectures and training objectives. As this text will …

Privacy-Preserving Deep Learning Mechanisms For Multimedia Data-Oriented Applications, Honghui Xu Ph.D.

Computer Science Dissertations

Nowadays, with the proliferation of multimedia and the coming of deep learning era, many multimedia data-oriented applications have been proposed to achieve face recognition, automatic retailing, automatic driving, intelligent medical healthcare, visual-audio speech recognition, and so on. However, these deep learning models may face a serious risk of data privacy leakage in the utilization process of these multimedia data. For example, malicious attackers can exploit deep learning techniques to deduce sensitive information from eavesdropped multimedia data, and these attackers can pilfer historical training data through a membership inference attack. Although some privacy-preserving deep learning approaches have been investigated, there are …

Neural Networks For Improved Signal Source Enumeration And Localization With Unsteered Antenna Arrays, John T. Rogers Ii

Theses and Dissertations

Direction of Arrival estimation using unsteered antenna arrays, unlike mechanically scanned or phased arrays, requires complex algorithms which perform poorly with small aperture arrays or without a large number of observations, or snapshots. In general, these algorithms compute a sample covriance matrix to obtain the direction of arrival and some require a prior estimate of the number of signal sources. Herein, artificial neural network architectures are proposed which demonstrate improved estimation of the number of signal sources, the true signal covariance matrix, and the direction of arrival. The proposed number of source estimation network demonstrates robust performance in the case …

Generalized Differentiable Neural Architecture Search With Performance And Stability Improvements, Emily J. Herron

Doctoral Dissertations

This work introduces improvements to the stability and generalizability of Cyclic DARTS (CDARTS). CDARTS is a Differentiable Architecture Search (DARTS)-based approach to neural architecture search (NAS) that uses a cyclic feedback mechanism to train search and evaluation networks concurrently, thereby optimizing the search process by enforcing that the networks produce similar outputs. However, the dissimilarity between the loss functions used by the evaluation networks during the search and retraining phases results in a search-phase evaluation network, a sub-optimal proxy for the final evaluation network utilized during retraining. ICDARTS, a revised algorithm that reformulates the search phase loss functions to ensure …