Graph Regularized Linear Regression

171928-Thumbnail Image.png
Description
Linear-regression estimators have become widely accepted as a reliable statistical tool in predicting outcomes. Because linear regression is a long-established procedure, the properties of linear-regression estimators are well understood and can be trained very quickly. Many estimators exist for modeling

Linear-regression estimators have become widely accepted as a reliable statistical tool in predicting outcomes. Because linear regression is a long-established procedure, the properties of linear-regression estimators are well understood and can be trained very quickly. Many estimators exist for modeling linear relationships, each having ideal conditions for optimal performance. The differences stem from the introduction of a bias into the parameter estimation through the use of various regularization strategies. One of the more popular ones is ridge regression which uses ℓ2-penalization of the parameter vector. In this work, the proposed graph regularized linear estimator is pitted against the popular ridge regression when the parameter vector is known to be dense. When additional knowledge that parameters are smooth with respect to a graph is available, it can be used to improve the parameter estimates. To achieve this goal an additional smoothing penalty is introduced into the traditional loss function of ridge regression. The mean squared error(m.s.e) is used as a performance metric and the analysis is presented for fixed design matrices having a unit covariance matrix. The specific problem setup enables us to study the theoretical conditions where the graph regularized estimator out-performs the ridge estimator. The eigenvectors of the laplacian matrix indicating the graph of connections between the various dimensions of the parameter vector form an integral part of the analysis. Experiments have been conducted on simulated data to compare the performance of the two estimators for laplacian matrices of several types of graphs – complete, star, line and 4-regular. The experimental results indicate that the theory can possibly be extended to more general settings taking smoothness, a concept defined in this work, into consideration.
Date Created
2022
Agent

Addressing the Challenges of Automated Speech and Language Analysis for the Assessment of Mental Health and Functional Competency

171844-Thumbnail Image.png
Description
Severe forms of mental illness, such as schizophrenia and bipolar disorder, are debilitating conditions that negatively impact an individual's quality of life. Additionally, they are often difficult and expensive to diagnose and manage, placing a large burden on society. Mental

Severe forms of mental illness, such as schizophrenia and bipolar disorder, are debilitating conditions that negatively impact an individual's quality of life. Additionally, they are often difficult and expensive to diagnose and manage, placing a large burden on society. Mental illness is typically diagnosed by the use of clinical interviews and a set of neuropsychiatric batteries; a key component of nearly all of these evaluations is some spoken language task. Clinicians have long used speech and language production as a proxy for neurological health, but most of these assessments are subjective in nature. Meanwhile, technological advancements in speech and natural language processing have grown exponentially over the past decade, increasing the capacity of computer models to assess particular aspects of speech and language. For this reason, many have seen an opportunity to leverage signal processing and machine learning applications to objectively assess clinical speech samples in order to automatically compute objective measures of neurological health. This document summarizes several contributions to expand upon this body of research. Mainly, there is still a large gap between the theoretical power of computational language models and their actual use in clinical applications. One of the largest concerns is the limited and inconsistent reliability of speech and language features used in models for assessing specific aspects of mental health; numerous methods may exist to measure the same or similar constructs and lead researchers to different conclusions in different studies. To address this, a novel measurement model based on a theoretical framework of speech production is used to motivate feature selection, while also performing a smoothing operation on features across several domains of interest. Then, these composite features are used to perform a much wider range of analyses than is typical of previous studies, looking at everything from diagnosis to functional competency assessments. Lastly, potential improvements to address practical implementation challenges associated with the use of speech and language technology in a real-world environment are investigated. The goal of this work is to demonstrate the ability of speech and language technology to aid clinical practitioners toward improvements in quality of life outcomes for their patients.
Date Created
2022
Agent

A Tunable Loss Function for Robust, Rigorous, and Reliable Machine Learning

171411-Thumbnail Image.png
Description
In the era of big data, more and more decisions and recommendations are being made by machine learning (ML) systems and algorithms. Despite their many successes, there have been notable deficiencies in the robustness, rigor, and reliability of these ML

In the era of big data, more and more decisions and recommendations are being made by machine learning (ML) systems and algorithms. Despite their many successes, there have been notable deficiencies in the robustness, rigor, and reliability of these ML systems, which have had detrimental societal impacts. In the next generation of ML, these significant challenges must be addressed through careful algorithmic design, and it is crucial that practitioners and meta-algorithms have the necessary tools to construct ML models that align with human values and interests. In an effort to help address these problems, this dissertation studies a tunable loss function called α-loss for the ML setting of classification. The alpha-loss is a hyperparameterized loss function originating from information theory that continuously interpolates between the exponential (alpha = 1/2), log (alpha = 1), and 0-1 (alpha = infinity) losses, hence providing a holistic perspective of several classical loss functions in ML. Furthermore, the alpha-loss exhibits unique operating characteristics depending on the value (and different regimes) of alpha; notably, for alpha > 1, alpha-loss robustly trains models when noisy training data is present. Thus, the alpha-loss can provide robustness to ML systems for classification tasks, and this has bearing in many applications, e.g., social media, finance, academia, and medicine; indeed, results are presented where alpha-loss produces more robust logistic regression models for COVID-19 survey data with gains over state of the art algorithmic approaches.
Date Created
2022
Agent

Correlational Analysis Between Speech and Gait in Parkinson's Disease

171401-Thumbnail Image.png
Description
Parkinson’s Disease is one of the most complicated and abundantneurodegenerative diseases in the world. Previous analysis of Parkinson’s disease has identified both speech and gait deficits throughout progression of the disease. There has been minimal research looking into the correlation between both

Parkinson’s Disease is one of the most complicated and abundantneurodegenerative diseases in the world. Previous analysis of Parkinson’s disease has identified both speech and gait deficits throughout progression of the disease. There has been minimal research looking into the correlation between both the speech and gait deficits in those diagnosed with Parkinson’s. There is high indication that there is a correlation between the two given the similar pathology and origins of both deficits. This exploratory study aims to establish correlation between both the gait and speech deficits in those diagnosed with Parkinson’s disease. Using previously identified motor and speech measurements and tasks, I conducted a correlational study of individuals with Parkinson’s disease at baseline. There were correlations between multiple speech and gait variability outcomes. The expected correlations ranged from average harmonics-to-noise ratio values against anticipatory postural adjustments-lateral peak distance to average shimmer values against anticipatory postural adjustments-lateral peak distance. There were also unexpected outcomes that ranged from F2 variability against the average number of steps in a turn to intensity variability against step duration variability. I also analyzed the speech changes over 1 year as a secondary outcome of the study. Finally, I found that averages and variabilities increased over 1 year regarding speech primary outcomes. This study serves as a basis for further treatment that may be able to simultaneously treat both speech and gait deficits in those diagnosed with Parkinson’s. The exploratory study also indicates multiple targets for further investigation to better understand cohesive and compensatory mechanisms.
Date Created
2022
Agent

Does Human Speech Follow Benford's Law

168796-Thumbnail Image.png
Description
Researchers have observed that the frequencies of leading digits in many man-made and naturally occurring datasets follow a logarithmic curve, with digits that start with the number 1 accounting for 30% of all numbers in the dataset and digits that

Researchers have observed that the frequencies of leading digits in many man-made and naturally occurring datasets follow a logarithmic curve, with digits that start with the number 1 accounting for 30% of all numbers in the dataset and digits that start with the number 9 accounting for 5% of all numbers in the dataset. This phenomenon, known as Benford's Law, is highly repeatable and appears in lists of numbers from electricity bills, stock prices, tax returns, house prices, death rates, lengths of rivers, and naturally occurring images. This paper will demonstrate that human speech spectra also follow Benford's Law. This observation is used to motivate a new set of features that can be efficiently extracted from speech and demonstrate that these features can be used to classify between human speech and synthetic speech.
Date Created
2022
Agent

Representation Learning for Graph Structured Data using Deep Neural Networks

168287-Thumbnail Image.png
Description
Dealing with relational data structures is central to a wide-range of applications including social networks, epidemic modeling, molecular chemistry, medicine, energy distribution, and transportation. Machine learning models that can exploit the inherent structural/relational bias in the graph structured data have

Dealing with relational data structures is central to a wide-range of applications including social networks, epidemic modeling, molecular chemistry, medicine, energy distribution, and transportation. Machine learning models that can exploit the inherent structural/relational bias in the graph structured data have gained prominence in recent times. A recurring idea that appears in all approaches is to encode the nodes in the graph (or the entire graph) as low-dimensional vectors also known as embeddings, prior to carrying out downstream task-specific learning. It is crucial to eliminate hand-crafted features and instead directly incorporate the structural inductive bias into the deep learning architectures. In this dissertation, deep learning models that directly operate on graph structured data are proposed for effective representation learning. A literature review on existing graph representation learning is provided in the beginning of the dissertation. The primary focus of dissertation is on building novel graph neural network architectures that are robust against adversarial attacks. The proposed graph neural network models are extended to multiplex graphs (heterogeneous graphs). Finally, a relational neural network model is proposed to operate on a human structural connectome. For every research contribution of this dissertation, several empirical studies are conducted on benchmark datasets. The proposed graph neural network models, approaches, and architectures demonstrate significant performance improvements in comparison to the existing state-of-the-art graph embedding strategies.
Date Created
2021
Agent

Marmoset Calls Labeling

Description
Callithrix jacchus, also known as a common marmoset, is native to the new world. These marmosets possess a wide range of vocal repertoire that is interesting to observe for the purpose of understanding their group communication and their fight or

Callithrix jacchus, also known as a common marmoset, is native to the new world. These marmosets possess a wide range of vocal repertoire that is interesting to observe for the purpose of understanding their group communication and their fight or flight responses to the environment around them. In this project, I am continuing with the project that a previous student, Jasmin, had done to find more data for her study. For the most part, my project entailed recording and labeling the marmoset’s calls into different types.
Date Created
2021-05
Agent

Characterizing EEG Data for Epileptic Seizures Using a Variety of Data Analysis Methods to Understand the Data and Enable Future Research

164885-Thumbnail Image.png
Description

In this research, I surveyed existing methods of characterizing Epilepsy from Electroencephalogram (EEG) data, including the Random Forest algorithm, which was claimed by many researchers to be the most effective at detecting epileptic seizures [7]. I observed that although many

In this research, I surveyed existing methods of characterizing Epilepsy from Electroencephalogram (EEG) data, including the Random Forest algorithm, which was claimed by many researchers to be the most effective at detecting epileptic seizures [7]. I observed that although many papers claimed a detection of >99% using Random Forest, it was not specified “when” the detection was declared within the 23.6 second interval of the seizure event. In this research, I created a time-series procedure to detect the seizure as early as possible within the 23.6 second epileptic seizure window and found that the detection is effective (> 92%) as early as the first few seconds of the epileptic episode. I intend to use this research as a stepping stone towards my upcoming Masters thesis research where I plan to expand the time-series detection mechanism to the pre-ictal stage, which will require a different dataset.

Date Created
2022-05
Agent

Song Demo Accuracy User Study (Spring 2022)

164826-Thumbnail Image.jpg
Description

Spatial audio can be especially useful for directing human attention. However, delivering spatial audio through speakers, rather than headphones that deliver audio directly to the ears, produces the issue of crosstalk, where sounds from each of the two speakers reach

Spatial audio can be especially useful for directing human attention. However, delivering spatial audio through speakers, rather than headphones that deliver audio directly to the ears, produces the issue of crosstalk, where sounds from each of the two speakers reach the opposite ear, inhibiting the spatialized effect. A research team at Meteor Studio has developed an algorithm called Xblock that solves this issue using a crosstalk cancellation technique. This thesis project expands upon the existing Xblock IoT system by providing a way to test the accuracy of the directionality of sounds generated with spatial audio. More specifically, the objective is to determine whether the usage of Xblock with smart speakers can provide generalized audio localization, which refers to the ability to detect a general direction of where a sound might be coming from. This project also expands upon the existing Xblock technique to integrate voice commands, where users can verbalize the name of a lost item using the phrase, “Find [item]”, and the IoT system will use spatial audio to guide them to it.

Date Created
2022-05
Agent

Song Final Project (Spring 2022)

164825-Thumbnail Image.png
Description

Spatial audio can be especially useful for directing human attention. However, delivering spatial audio through speakers, rather than headphones that deliver audio directly to the ears, produces the issue of crosstalk, where sounds from each of the two speakers reach

Spatial audio can be especially useful for directing human attention. However, delivering spatial audio through speakers, rather than headphones that deliver audio directly to the ears, produces the issue of crosstalk, where sounds from each of the two speakers reach the opposite ear, inhibiting the spatialized effect. A research team at Meteor Studio has developed an algorithm called Xblock that solves this issue using a crosstalk cancellation technique. This thesis project expands upon the existing Xblock IoT system by providing a way to test the accuracy of the directionality of sounds generated with spatial audio. More specifically, the objective is to determine whether the usage of Xblock with smart speakers can provide generalized audio localization, which refers to the ability to detect a general direction of where a sound might be coming from. This project also expands upon the existing Xblock technique to integrate voice commands, where users can verbalize the name of a lost item using the phrase, “Find [item]”, and the IoT system will use spatial audio to guide them to it.

Date Created
2022-05
Agent