Digital Commons Network^™

Deception Detection Across Domains, Languages And Modalities, Subhadarshi Panda

Dissertations, Theses, and Capstone Projects

With the increase of deception and misinformation especially in social media, it has become crucial to develop machine learning methods to automatically identify deception. In this dissertation, we identify key challenges underlying text-based deception detection in a cross-domain setting, where we do not have training data in the target domain. We analyze the differences between domains and as a result develop methods to improve cross-domain deception detection. We additionally develop approaches that take advantage of cross-lingual properties to support deception detection across languages. This involves the usage of either multilingual NLP models or translation models. Finally, to better understand multi-modal …

From Sesame Street To Beyond: Multi-Domain Discourse Relation Classification With Pretrained Bert, Isaac R. Raff

Dissertations, Theses, and Capstone Projects

Research efforts in transfer learning have gained massive popularity in recent years. Pretrained language models have demonstrated the most successful results in producing high quality neural networks capable of quality inference after training across domains via transfer learning. This study expands on the domain transfer introduced in \cite{ferracane-etal-2019-news} exploring neural methods for transfer learning of discourse parsing between a news source domain and a medical target domain. \cite{ferracane-etal-2019-news} specifically discuss transfer learning from news articles to PubMed medical journal articles. Experiments in transfer learning in the current work expand to include three domains: Wall Street Journal articles previously annotated with …

A Tool-Supported Metamodel For Program Bugfix Analysis In Empirical Software Engineering, Manal Zneit

Theses and Dissertations

This thesis describes a software modeling approach aimed at addressing empirical studies in software engineering. We build a metamodel that provides an overview of the taxonomy of program bugfixes in deep learning programs. For modeling purposes, we present a prototype tool that is an implementation of the model-driven techniques presented.

Challenges In Migrating Imperative Deep Learning Programs To Graph Execution: An Empirical Study, Tatiana Castro Vélez, Raffi T. Khatchadourian, Mehdi Bagherzadeh, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code that supports symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development tends to produce DL code that is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, less error-prone imperative DL frameworks encouraging eager execution have emerged at the expense of run-time performance. While hybrid approaches aim for the "best of both worlds," the challenges in applying them in the real world are largely unknown. We conduct a data-driven analysis of challenges—and resultant bugs—involved …

Diagnosis Of Polypoidal Choroidal Vasculopathy From Fluorescein Angiography Using Deep Learning, Yu-Yeh Tsai, Wei-Yang Ling, Shih-Jen Chen, Paisan Ruamviboonsuk, Cheng-Ho King, Chia-Ling Tsai

Publications and Research

Purpose: To differentiate polypoidal choroidal vasculopathy (PCV) from choroidal neovascularization (CNV) and to determine the extent of PCV from fluorescein angiography (FA) using attention-based deep learning networks.

Methods: We build two deep learning networks for diagnosis of PCV using FA, one for detection and one for segmentation. Attention-gated convolutional neural network (AG-CNN) differentiates PCV from other types of wet age-related macular degeneration. Gradient-weighted class activation map (Grad-CAM) is generated to highlight important regions in the image for making the prediction, which offers explainability of the network. Attention-gated recurrent neural network (AG-PCVNet) for spatiotemporal prediction is applied for segmentation …

Diagnosis Of Polypoidal Choroidal Vasculopathy From Fluorescein Angiography Using Deep Learning, Yu-Yeh Tsai, Wei-Yang Lin, Shih-Jen Chen, Paisan Ruamviboonsuk, Cheng-Ho King, Chia-Ling Tsai

Publications and Research

Purpose: To differentiate polypoidal choroidal vasculopathy (PCV) from choroidal neovascularization (CNV) and to determine the extent of PCV from fluorescein angiography (FA) using attention-based deep learning networks.

Methods: We build two deep learning networks for diagnosis of PCV using FA, one for detection and one for segmentation. Attention-gated convolutional neural network (AG-CNN) differentiates PCV from other types of wet age-related macular degeneration. Gradient-weighted class activation map (Grad-CAM) is generated to highlight important regions in the image for making the prediction, which offers explainability of the network. Attention-gated recurrent neural network (AG-PCVNet) for spatiotemporal prediction is applied for segmentation of PCV. …

Toward A Multimodal Computer-Aided Diagnostic Tool For Alzheimer’S Disease Conversion, Danilo Pena, Jessika Suescun, Mya Schiess, Timothy M. Ellmore, Luca Giancardo, Alzheimer’S Disease Neuroimaging Initiative

Publications and Research

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder. It is one of the leading sources of morbidity and mortality in the aging population AD cardinal symptoms include memory and executive function impairment that profoundly alters a patient’s ability to perform activities of daily living. People with mild cognitive impairment (MCI) exhibit many of the early clinical symptoms of patients with AD and have a high chance of converting to AD in their lifetime. Diagnostic criteria rely on clinical assessment and brain magnetic resonance imaging (MRI). Many groups are working to help automate this process to improve the clinical workflow. Current …

Ai-Driven Automated Medical Imaging Analysis, Jingya Liu

Dissertations and Theses

Medical imaging has been applied widely in many clinical diagnoses to detect and differentiate abnormalities by revealing the internal structure of the human body at normal anatomical and physiological levels. Manual analyzing medical images demands attention and is time-consuming, requiring well-trained expertise. The speed, fatigue, and experience may limit the diagnostic performance, leading to delays and even false diagnoses that significantly impact patient treatment. Therefore, accurate systematic systems based on medical image analysis are crucial for timely clinical diagnosis.

This dissertation focuses on advancing automatic computer-aided diagnosis systems to detect cancer, assisting radiologists with early intervention to improve survival rates. …