Objective: Cervical cancer causes 311,000 deaths annually. However, routine pap smears can facilitate early detection and improve patient outcomes. Liquid Pap smears are conducted in …
Volcanic hazards monitoring relies heavily on constraints offered by geophysical inversions to decipher the structure of subvolcanic magmatic systems. Over the past decades a multidisciplinary …
The proliferation of Artificial Intelligence (AI) in edge computing environments, which are characterized by limited computational resources, memory, and energy, necessitates capitalizing on efficient deep …
Anterior cruciate ligament (ACL) disruption is a common injury, particularly in the young and active patient. ACL reconstruction surgery is the current standard of care, …
Sleep apnea is a common, yet underdiagnosed, sleep-related breathing disorder associated with increased risk of cardiovascular issues. This work uses a multifaceted approach integrating artificial …
Biological brains are dynamic. Recent advances in electrophysiology and neuroimaging have helped uncover various mechanisms through which brains construct and utilize rich variations in neural …
In this thesis, we studied the dynamic toughening mechanisms of a hierarchically nanostructured copolymer, polyurea. We first quantitively measured the dynamic fracture toughness as well …
This study introduces Biologically Annotated Neural Networks (BANNs) for identifying causal Single Nucleotide Polymorphisms (SNPs) linked to complex traits. BANNs combine neural network flexibility with …
Deep learning shifts the way to build signal processing systems from coding or model-centric to data-centric. This paper presents a system to support data-centric deep …
The structures of molecules in solution are essential to their reactivities in solution. The solution structures can be characterized by estimating the molecular weight of …
How to effectively extract important information and conduct meaningful analyses from large collections of data is an essential problem we need to tackle in order …
This dissertation studies the canonical tasks of database compression and similarity search, and demonstrates how advanced deep learning models can be used to develop effective …
The unprecedented success of deep learning technology has elevated the state-of-the-art accuracy performance in many application domains such as computer vision and voice recognition. At …
Progress in deep feedforward neural networks has spawned great successes in many practical applications, but these models struggle to reproduce human-level generalization in tasks that …
Development and implementation of machine and deep learning models has grown massively with increased availability of large datasets and improved computing capabilities. Despite this huge …
To help healthcare professionals be better prepared for spikes in cases, it would be beneficial for public health officials to develop intervention plans based on …
Optical coherence tomography (OCT) is becoming increasingly popular for neuroscientific study, but it remains challenging to objectively quantify tissue and vascular properties from 3D or …
Brain cancer remains a pervasive public health issue. The use of CNN’s to segment brain tumor images has gained significant traction since 2012; however, most …
How the performance of black box machine learning algorithms (e.g., deep learning models) is affected by different factors can be hard to evaluate. Thus, in …
