PhD Dissertations - DO NOT EDIT
Browse by
Recent Submissions
-
Towards Nuclei Segmentation with Limited Annotations
(2023-09-01)Nuclei segmentation is a fundamental but challenging task in histopathology image analysis. For semantic segmentation of nuclei, Convolutional Neural Network (CNN), and Vision Transformer (VT) models give very promising ... -
Generative and Implicit Methods for 3D Point Cloud Processing
(2023-08-15)3D point clouds are a popular form of data representation with many applications in computer vision, computer graphics, and robotics. As the output of range sensing devices, point clouds have gained popularity with the ... -
DEEP LEARNING FOR MOLECULAR PROPERTY PREDICTION
(2023-08-14)Drug discovery has always been a crucial task for society, and molecular property prediction is one of the fundamental problem. It is responsible for identifying the target properties or severe side-effects, so that certain ... -
On-Line Environment Adaptation for User Performance Optimization
(2023-08-14)In today’s fast-paced and globally connected world, businesses are creating products with more significance to user personalization and customization. This has amplified the importance of capturing and learning user ... -
COMPACT REPRESENTATIVES OF DATABASES AND RESPONSIBLE DATA MANAGEMENT
(2023-08-08)With the advent of advanced computational models, we are being constantly judged by AI systems, complex algorithmic systems based on data that has been collected about us. These analysis are critical as they span many wide ... -
INVESTIGATING THE EFFECT OF PEEPHOLE OPTIMIZATIONS ON BINARY CODE DIFFERENCES
(2023-09-01)**Please note that the full text is embargoed until 8/1/2025** ABSTRACT: Binary diffing is a technique used to compare and identify differences or similarities in executable files without access to source code. The potential ... -
RESOURCE PROVISIONING FOR DATA-INTENSIVE USER-FACING APPLICATIONS
(2023-07-27)**Please note that the full text is embargoed until 08/01/2024** Data-intensive, User-facing Services (DUSes) such as web searching, digital marketing, online social networking, and online retailing are critical workloads ... -
Fuzz Testing of Zigbee Protocol Implementations
(2023-07-12)In recent years, we have witnessed the increasing of the Internet of Things (IoT) devices deployed by many areas, such as home automation, healthcare, manufacture, and smart vehicle. Among the numerous IoT wireless standards ... -
Video-based Face Recognition using Deep Learning for Single Sample Per Person (SSPP) Surveillance Applications
Face Recognition (FR) is the task of identifying a person based on images of the face of the identity. Systems for video-based face recognition in video surveillance seek to recognize individuals of interest in real-time ... -
A Real-time Activity Recognition in a Congested Wireless Environment
(2022-08-16)**Please note that the full text is embargoed until 8/16/2024** ABSTRACT: This dissertation reports on how to achieve real-time activity recognition in a congested wireless environment. Recently, human activity recognition ... -
Graph Representation Learning for Heterogeneous Multimodal Biomedical Data
(2022-12-20)The emergence of high-throughput sequencing technology has generated a wealth of “multi-omics” data, capturing information about different types of biomolecules at multiple levels. Since large-scale genomics, transcriptomics, ... -
Human Behavior Modeling in Long Videos: Drowsiness Detection and Action Segmentation
(2022-05-09)"In this thesis we focus on two instances of human behavior modeling in long untrimmed videos: drowsiness detection, and action segmentation. In the first section, we focus on drowsiness detection. Specifically, we introduce ... -
LEARNING CAUSAL BOUNDS USING MARGINAL INDEPENDENCE INFORMATION WITH APPLICATIONS TO GENE EXPRESSION ANALYSIS
(2022-03-14)Discovering causal relations is a fundamental goal of science. Randomized controlled experiments were often considered to be the only reliable method for tackling this task. However, in recent years, various causal discovery ... -
REPRESENTATION AND STRATEGY LEARNING FOR VARIABLE-SIZE TREE TRANSFORMATION USING REINFORCEMENT LEARNING
(2021-08-12)Trees as acyclic graphs are ubiquitous in representing different context where they encode connectivity patterns at all scales of organization, from biological systems to social networks. Trees are powerful resources which ... -
MACHINE LEARNING WITH GRAPHS
(2021-05-09)In recent years, graph-based machine learning methods have attracted great attention because of their effectiveness and efficiency. Inspired by this trend, this thesis summarizes my research topics on machine learning ... -
EXTEND THE SENSING BOUNDARY OF MOBILE SYSTEMS: SECURITY AND NEW APPLICATIONS
(2021-04-28)The exploding growth of mobile devices like smartphones and wearables has envisioned various applications, which are developed to collect a wide spectrum of data using on-board device sensors and process them to serve ... -
Neural Network Architecture Optimization Using Reinforcement Learning
(2023-05-19)Deep learning has emerged as an increasingly valuable tool, employed across a myriad of applications. However, the intricacies of deep learning systems, stemming from their sensitivity to specific network architectures, ... -
Toward a deeper integration of low-fidelity sketches into mobile application development
(2023-05-18)Mobile application development often starts with creating low-fidelity sketches of user interfaces. Integrating these sketches into the software development process can reduce repetition, narrow the gap between user ... -
Practical Indirect Control Flow Analysis for Binary Executables
(2023-04-27)Resolving indirect control flow is one of the fundamental challenges in binary analysis. Improving the accuracy of the indirect control flow analysis is vital to the binary analysis domain. Many analysis algorithms and ... -
Optimizing Resource Utilization, Efficiency and Scalability in Deep Learning Systems
(2023-05-01)This thesis addresses the challenges of utilization, efficiency, and scalability faced by deep learning systems, which are essential for high-performance training and serving of deep learning models. Deep learning systems ...