Life Sciences Commons^™

Towards Understanding And Improving Speech Processing, Sonia Yasmin

Electronic Thesis and Dissertation Repository

This dissertation explores mechanisms for understanding and improving speech processing. First, I used EEG to investigate the acoustic and semantic processing of continuous naturalistic speech masked by multi-talker babble. I found that different features of the same speech signal are reflected in different aspects of the neural tracking response, which are themselves differentially affected by noise. These findings point to a complex relationship between speech intelligibility and neural speech encoding.

Next, I systematically reviewed the current advancements in speech enhancement technologies. I find that speech enhancement algorithms are limited in their generalizability to speech-noise (i.e., babble). I demonstrate that, for …

Machine Learning Techniques For Improved Functional Brain Parcellation, Da Zhi

Electronic Thesis and Dissertation Repository

Brain parcellation studies are fundamental for neuroscience as they serve as a bridge between anatomy and function, helping researchers interpret how functions are distributed across different brain regions. However, two substantial challenges exist in current imaging-based brain parcellation studies: large variations in the functional organization across individuals and the intrinsic spatial dependence which causes nearby brain locations to have a similar function. This thesis presents a series of projects aimed to tackle these challenges from different perspectives by using advanced machine learning techniques.

To handle the challenge of individual variability in building precise individual parcellations, Chapter 3 introduces a novel …

Ischemic Stroke Thrombus Characterization Through Quantitative Magnetic Resonance Imaging, Spencer D. Christiansen

Electronic Thesis and Dissertation Repository

Stroke is a pervasive, devastating disease and remains one of the most challenging conditions to treat. In particular, risk of recurrence is dramatically heightened after a primary stroke and requires urgent preventative therapy to effectively mitigate. However, the appropriate preventative therapy depends on the underlying source of the stroke, known as etiology, which is challenging to determine promptly. Current diagnostic tests for determining etiology underwhelm in both sensitivity and specificity, and in as much as 35% of cases etiology is never determined. In ischemic stroke, the composition of the occluding thrombus, specifically its red blood cell (RBC) content, has been …

Machine Learning With Digital Signal Processing For Rapid And Accurate Alignment-Free Genome Analysis: From Methodological Design To A Covid-19 Case Study, Gurjit Singh Randhawa

Electronic Thesis and Dissertation Repository

In the field of bioinformatics, taxonomic classification is the scientific practice of identifying, naming, and grouping of organisms based on their similarities and differences. The problem of taxonomic classification is of immense importance considering that nearly 86% of existing species on Earth and 91% of marine species remain unclassified. Due to the magnitude of the datasets, the need exists for an approach and software tool that is scalable enough to handle large datasets and can be used for rapid sequence comparison and analysis. We propose ML-DSP, a stand-alone alignment-free software tool that uses Machine Learning and Digital Signal Processing to …

Computational Modelling Of Human Transcriptional Regulation By An Information Theory-Based Approach, Ruipeng Lu

Electronic Thesis and Dissertation Repository

ChIP-seq experiments can identify the genome-wide binding site motifs of a transcription factor (TF) and determine its sequence specificity. Multiple algorithms were developed to derive TF binding site (TFBS) motifs from ChIP-seq data, including the entropy minimization-based Bipad that can derive both contiguous and bipartite motifs. Prior studies applying these algorithms to ChIP-seq data only analyzed a small number of top peaks with the highest signal strengths, biasing their resultant position weight matrices (PWMs) towards consensus-like, strong binding sites; nor did they derive bipartite motifs, disabling the accurate modelling of binding behavior of dimeric TFs.

This thesis presents a novel …

Signet: A Neural Network Architecture For Predicting Protein-Protein Interactions, Muhammad S. Ahmed

Electronic Thesis and Dissertation Repository

The study of protein-protein interactions (PPI) is critically important within the field of Molecular Biology, as proteins facilitate key organismal functions including the maintenance of both cellular structure and function. Current experimental methods for elucidating PPIs are greatly hindered by large operating costs, lengthy wait times, as well as low accuracy. The recent development of computational PPI predicting techniques has worked to address many of these issues. Despite this, many of these methods utilize over-engineered features and naive learning algorithms. With the recent advances in Machine Learning and Artificial Intelligence, we attempt to view this problem through a novel, deep …