Matching Items (19)
Filtering by
- All Subjects: Machine Learning
- Genre: Academic theses
- Genre: Masters Thesis
- Creators: Papandreou-Suppappola, Antonia
- Creators: Runger, George C.
- Member of: Theses and Dissertations
Description
With the increase in computing power and availability of data, there has never been a greater need to understand data and make decisions from it. Traditional statistical techniques may not be adequate to handle the size of today's data or the complexities of the information hidden within the data. Thus knowledge discovery by machine learning techniques is necessary if we want to better understand information from data. In this dissertation, we explore the topics of asymmetric loss and asymmetric data in machine learning and propose new algorithms as solutions to some of the problems in these topics. We also studied variable selection of matched data sets and proposed a solution when there is non-linearity in the matched data. The research is divided into three parts. The first part addresses the problem of asymmetric loss. A proposed asymmetric support vector machine (aSVM) is used to predict specific classes with high accuracy. aSVM was shown to produce higher precision than a regular SVM. The second part addresses asymmetric data sets where variables are only predictive for a subset of the predictor classes. Asymmetric Random Forest (ARF) was proposed to detect these kinds of variables. The third part explores variable selection for matched data sets. Matched Random Forest (MRF) was proposed to find variables that are able to distinguish case and control without the restrictions that exists in linear models. MRF detects variables that are able to distinguish case and control even in the presence of interaction and qualitative variables.
ContributorsKoh, Derek (Author) / Runger, George C. (Thesis advisor) / Wu, Tong (Committee member) / Pan, Rong (Committee member) / Cesta, John (Committee member) / Arizona State University (Publisher)
Created2013
Description
The healthcare system in this country is currently unacceptable. New technologies may contribute to reducing cost and improving outcomes. Early diagnosis and treatment represents the least risky option for addressing this issue. Such a technology needs to be inexpensive, highly sensitive, highly specific, and amenable to adoption in a clinic. This thesis explores an immunodiagnostic technology based on highly scalable, non-natural sequence peptide microarrays designed to profile the humoral immune response and address the healthcare problem. The primary aim of this thesis is to explore the ability of these arrays to map continuous (linear) epitopes. I discovered that using a technique termed subsequence analysis where epitopes could be decisively mapped to an eliciting protein with high success rate. This led to the discovery of novel linear epitopes from Plasmodium falciparum (Malaria) and Treponema palladium (Syphilis), as well as validation of previously discovered epitopes in Dengue and monoclonal antibodies. Next, I developed and tested a classification scheme based on Support Vector Machines for development of a Dengue Fever diagnostic, achieving higher sensitivity and specificity than current FDA approved techniques. The software underlying this method is available for download under the BSD license. Following this, I developed a kinetic model for immunosignatures and tested it against existing data driven by previously unexplained phenomena. This model provides a framework and informs ways to optimize the platform for maximum stability and efficiency. I also explored the role of sequence composition in explaining an immunosignature binding profile, determining a strong role for charged residues that seems to have some predictive ability for disease. Finally, I developed a database, software and indexing strategy based on Apache Lucene for searching motif patterns (regular expressions) in large biological databases. These projects as a whole have advanced knowledge of how to approach high throughput immunodiagnostics and provide an example of how technology can be fused with biology in order to affect scientific and health outcomes.
ContributorsRicher, Joshua Amos (Author) / Johnston, Stephen A. (Thesis advisor) / Woodbury, Neal (Committee member) / Stafford, Phillip (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Arizona State University (Publisher)
Created2014
Description
The rate of progress in improving survival of patients with solid tumors is slow due to late stage diagnosis and poor tumor characterization processes that fail to effectively reflect the nature of tumor before treatment or the subsequent change in its dynamics because of treatment. Further advancement of targeted therapies relies on advancements in biomarker research. In the context of solid tumors, bio-specimen samples such as biopsies serve as the main source of biomarkers used in the treatment and monitoring of cancer, even though biopsy samples are susceptible to sampling error and more importantly, are local and offer a narrow temporal scope.
Because of its established role in cancer care and its non-invasive nature imaging offers the potential to complement the findings of cancer biology. Over the past decade, a compelling body of literature has emerged suggesting a more pivotal role for imaging in the diagnosis, prognosis, and monitoring of diseases. These advances have facilitated the rise of an emerging practice known as Radiomics: the extraction and analysis of large numbers of quantitative features from medical images to improve disease characterization and prediction of outcome. It has been suggested that radiomics can contribute to biomarker discovery by detecting imaging traits that are complementary or interchangeable with other markers.
This thesis seeks further advancement of imaging biomarker discovery. This research unfolds over two aims: I) developing a comprehensive methodological pipeline for converting diagnostic imaging data into mineable sources of information, and II) investigating the utility of imaging data in clinical diagnostic applications. Four validation studies were conducted using the radiomics pipeline developed in aim I. These studies had the following goals: (1 distinguishing between benign and malignant head and neck lesions (2) differentiating benign and malignant breast cancers, (3) predicting the status of Human Papillomavirus in head and neck cancers, and (4) predicting neuropsychological performances as they relate to Alzheimer’s disease progression. The long-term objective of this thesis is to improve patient outcome and survival by facilitating incorporation of routine care imaging data into decision making processes.
Because of its established role in cancer care and its non-invasive nature imaging offers the potential to complement the findings of cancer biology. Over the past decade, a compelling body of literature has emerged suggesting a more pivotal role for imaging in the diagnosis, prognosis, and monitoring of diseases. These advances have facilitated the rise of an emerging practice known as Radiomics: the extraction and analysis of large numbers of quantitative features from medical images to improve disease characterization and prediction of outcome. It has been suggested that radiomics can contribute to biomarker discovery by detecting imaging traits that are complementary or interchangeable with other markers.
This thesis seeks further advancement of imaging biomarker discovery. This research unfolds over two aims: I) developing a comprehensive methodological pipeline for converting diagnostic imaging data into mineable sources of information, and II) investigating the utility of imaging data in clinical diagnostic applications. Four validation studies were conducted using the radiomics pipeline developed in aim I. These studies had the following goals: (1 distinguishing between benign and malignant head and neck lesions (2) differentiating benign and malignant breast cancers, (3) predicting the status of Human Papillomavirus in head and neck cancers, and (4) predicting neuropsychological performances as they relate to Alzheimer’s disease progression. The long-term objective of this thesis is to improve patient outcome and survival by facilitating incorporation of routine care imaging data into decision making processes.
ContributorsRanjbar, Sara (Author) / Kaufman, David (Thesis advisor) / Mitchell, Joseph R. (Thesis advisor) / Runger, George C. (Committee member) / Arizona State University (Publisher)
Created2017
Description
The recent technological advances enable the collection of various complex, heterogeneous and high-dimensional data in biomedical domains. The increasing availability of the high-dimensional biomedical data creates the needs of new machine learning models for effective data analysis and knowledge discovery. This dissertation introduces several unsupervised and supervised methods to help understand the data, discover the patterns and improve the decision making. All the proposed methods can generalize to other industrial fields.
The first topic of this dissertation focuses on the data clustering. Data clustering is often the first step for analyzing a dataset without the label information. Clustering high-dimensional data with mixed categorical and numeric attributes remains a challenging, yet important task. A clustering algorithm based on tree ensembles, CRAFTER, is proposed to tackle this task in a scalable manner.
The second part of this dissertation aims to develop data representation methods for genome sequencing data, a special type of high-dimensional data in the biomedical domain. The proposed data representation method, Bag-of-Segments, can summarize the key characteristics of the genome sequence into a small number of features with good interpretability.
The third part of this dissertation introduces an end-to-end deep neural network model, GCRNN, for time series classification with emphasis on both the accuracy and the interpretation. GCRNN contains a convolutional network component to extract high-level features, and a recurrent network component to enhance the modeling of the temporal characteristics. A feed-forward fully connected network with the sparse group lasso regularization is used to generate the final classification and provide good interpretability.
The last topic centers around the dimensionality reduction methods for time series data. A good dimensionality reduction method is important for the storage, decision making and pattern visualization for time series data. The CRNN autoencoder is proposed to not only achieve low reconstruction error, but also generate discriminative features. A variational version of this autoencoder has great potential for applications such as anomaly detection and process control.
The first topic of this dissertation focuses on the data clustering. Data clustering is often the first step for analyzing a dataset without the label information. Clustering high-dimensional data with mixed categorical and numeric attributes remains a challenging, yet important task. A clustering algorithm based on tree ensembles, CRAFTER, is proposed to tackle this task in a scalable manner.
The second part of this dissertation aims to develop data representation methods for genome sequencing data, a special type of high-dimensional data in the biomedical domain. The proposed data representation method, Bag-of-Segments, can summarize the key characteristics of the genome sequence into a small number of features with good interpretability.
The third part of this dissertation introduces an end-to-end deep neural network model, GCRNN, for time series classification with emphasis on both the accuracy and the interpretation. GCRNN contains a convolutional network component to extract high-level features, and a recurrent network component to enhance the modeling of the temporal characteristics. A feed-forward fully connected network with the sparse group lasso regularization is used to generate the final classification and provide good interpretability.
The last topic centers around the dimensionality reduction methods for time series data. A good dimensionality reduction method is important for the storage, decision making and pattern visualization for time series data. The CRNN autoencoder is proposed to not only achieve low reconstruction error, but also generate discriminative features. A variational version of this autoencoder has great potential for applications such as anomaly detection and process control.
ContributorsLin, Sangdi (Author) / Runger, George C. (Thesis advisor) / Kocher, Jean-Pierre A (Committee member) / Pan, Rong (Committee member) / Escobedo, Adolfo R. (Committee member) / Arizona State University (Publisher)
Created2018
Description
This dissertation presents the development of structural health monitoring and prognostic health management methodologies for complex structures and systems in the field of mechanical engineering. To overcome various challenges historically associated with complex structures and systems such as complicated sensing mechanisms, noisy information, and large-size datasets, a hybrid monitoring framework comprising of solid mechanics concepts and data mining technologies is developed. In such a framework, the solid mechanics simulations provide additional intuitions to data mining techniques reducing the dependence of accuracy on the training set, while the data mining approaches fuse and interpret information from the targeted system enabling the capability for real-time monitoring with efficient computation.
In the case of structural health monitoring, ultrasonic guided waves are utilized for damage identification and localization in complex composite structures. Signal processing and data mining techniques are integrated into the damage localization framework, and the converted wave modes, which are induced by the thickness variation due to the presence of delamination, are used as damage indicators. This framework has been validated through experiments and has shown sufficient accuracy in locating delamination in X-COR sandwich composites without the need of baseline information. Besides the localization of internal damage, the Gaussian process machine learning technique is integrated with finite element method as an online-offline prediction model to predict crack propagation with overloads under biaxial loading conditions; such a probabilistic prognosis model, with limited number of training examples, has shown increased accuracy over state-of-the-art techniques in predicting crack retardation behaviors induced by overloads. In the case of system level management, a monitoring framework built using a multivariate Gaussian model as basis is developed to evaluate the anomalous condition of commercial aircrafts. This method has been validated using commercial airline data and has shown high sensitivity to variations in aircraft dynamics and pilot operations. Moreover, this framework was also tested on simulated aircraft faults and its feasibility for real-time monitoring was demonstrated with sufficient computation efficiency.
This research is expected to serve as a practical addition to the existing literature while possessing the potential to be adopted in realistic engineering applications.
In the case of structural health monitoring, ultrasonic guided waves are utilized for damage identification and localization in complex composite structures. Signal processing and data mining techniques are integrated into the damage localization framework, and the converted wave modes, which are induced by the thickness variation due to the presence of delamination, are used as damage indicators. This framework has been validated through experiments and has shown sufficient accuracy in locating delamination in X-COR sandwich composites without the need of baseline information. Besides the localization of internal damage, the Gaussian process machine learning technique is integrated with finite element method as an online-offline prediction model to predict crack propagation with overloads under biaxial loading conditions; such a probabilistic prognosis model, with limited number of training examples, has shown increased accuracy over state-of-the-art techniques in predicting crack retardation behaviors induced by overloads. In the case of system level management, a monitoring framework built using a multivariate Gaussian model as basis is developed to evaluate the anomalous condition of commercial aircrafts. This method has been validated using commercial airline data and has shown high sensitivity to variations in aircraft dynamics and pilot operations. Moreover, this framework was also tested on simulated aircraft faults and its feasibility for real-time monitoring was demonstrated with sufficient computation efficiency.
This research is expected to serve as a practical addition to the existing literature while possessing the potential to be adopted in realistic engineering applications.
ContributorsLi, Guoyi (Ph.D.) (Author) / Chattopadhyay, Aditi (Thesis advisor) / Mignolet, Marc (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Yekani Fard, Masoud (Committee member) / Jiang, Hanqing (Committee member) / Arizona State University (Publisher)
Created2019
Description
The data explosion in the past decade is in part due to the widespread use of rich sensors that measure various physical phenomenon -- gyroscopes that measure orientation in phones and fitness devices, the Microsoft Kinect which measures depth information, etc. A typical application requires inferring the underlying physical phenomenon from data, which is done using machine learning. A fundamental assumption in training models is that the data is Euclidean, i.e. the metric is the standard Euclidean distance governed by the L-2 norm. However in many cases this assumption is violated, when the data lies on non Euclidean spaces such as Riemannian manifolds. While the underlying geometry accounts for the non-linearity, accurate analysis of human activity also requires temporal information to be taken into account. Human movement has a natural interpretation as a trajectory on the underlying feature manifold, as it evolves smoothly in time. A commonly occurring theme in many emerging problems is the need to \emph{represent, compare, and manipulate} such trajectories in a manner that respects the geometric constraints. This dissertation is a comprehensive treatise on modeling Riemannian trajectories to understand and exploit their statistical and dynamical properties. Such properties allow us to formulate novel representations for Riemannian trajectories. For example, the physical constraints on human movement are rarely considered, which results in an unnecessarily large space of features, making search, classification and other applications more complicated. Exploiting statistical properties can help us understand the \emph{true} space of such trajectories. In applications such as stroke rehabilitation where there is a need to differentiate between very similar kinds of movement, dynamical properties can be much more effective. In this regard, we propose a generalization to the Lyapunov exponent to Riemannian manifolds and show its effectiveness for human activity analysis. The theory developed in this thesis naturally leads to several benefits in areas such as data mining, compression, dimensionality reduction, classification, and regression.
ContributorsAnirudh, Rushil (Author) / Turaga, Pavan (Thesis advisor) / Cochran, Douglas (Committee member) / Runger, George C. (Committee member) / Taylor, Thomas (Committee member) / Arizona State University (Publisher)
Created2016
Description
Feature learning and the discovery of nonlinear variation patterns in high-dimensional data is an important task in many problem domains, such as imaging, streaming data from sensors, and manufacturing. This dissertation presents several methods for learning and visualizing nonlinear variation in high-dimensional data. First, an automated method for discovering nonlinear variation patterns using deep learning autoencoders is proposed. The approach provides a functional mapping from a low-dimensional representation to the original spatially-dense data that is both interpretable and efficient with respect to preserving information. Experimental results indicate that deep learning autoencoders outperform manifold learning and principal component analysis in reproducing the original data from the learned variation sources.
A key issue in using autoencoders for nonlinear variation pattern discovery is to encourage the learning of solutions where each feature represents a unique variation source, which we define as distinct features. This problem of learning distinct features is also referred to as disentangling factors of variation in the representation learning literature. The remainder of this dissertation highlights and provides solutions for this important problem.
An alternating autoencoder training method is presented and a new measure motivated by orthogonal loadings in linear models is proposed to quantify feature distinctness in the nonlinear models. Simulated point cloud data and handwritten digit images illustrate that standard training methods for autoencoders consistently mix the true variation sources in the learned low-dimensional representation, whereas the alternating method produces solutions with more distinct patterns.
Finally, a new regularization method for learning distinct nonlinear features using autoencoders is proposed. Motivated in-part by the properties of linear solutions, a series of learning constraints are implemented via regularization penalties during stochastic gradient descent training. These include the orthogonality of tangent vectors to the manifold, the correlation between learned features, and the distributions of the learned features. This regularized learning approach yields low-dimensional representations which can be better interpreted and used to identify the true sources of variation impacting a high-dimensional feature space. Experimental results demonstrate the effectiveness of this method for nonlinear variation pattern discovery on both simulated and real data sets.
A key issue in using autoencoders for nonlinear variation pattern discovery is to encourage the learning of solutions where each feature represents a unique variation source, which we define as distinct features. This problem of learning distinct features is also referred to as disentangling factors of variation in the representation learning literature. The remainder of this dissertation highlights and provides solutions for this important problem.
An alternating autoencoder training method is presented and a new measure motivated by orthogonal loadings in linear models is proposed to quantify feature distinctness in the nonlinear models. Simulated point cloud data and handwritten digit images illustrate that standard training methods for autoencoders consistently mix the true variation sources in the learned low-dimensional representation, whereas the alternating method produces solutions with more distinct patterns.
Finally, a new regularization method for learning distinct nonlinear features using autoencoders is proposed. Motivated in-part by the properties of linear solutions, a series of learning constraints are implemented via regularization penalties during stochastic gradient descent training. These include the orthogonality of tangent vectors to the manifold, the correlation between learned features, and the distributions of the learned features. This regularized learning approach yields low-dimensional representations which can be better interpreted and used to identify the true sources of variation impacting a high-dimensional feature space. Experimental results demonstrate the effectiveness of this method for nonlinear variation pattern discovery on both simulated and real data sets.
ContributorsHoward, Phillip (Author) / Runger, George C. (Thesis advisor) / Montgomery, Douglas C. (Committee member) / Mirchandani, Pitu (Committee member) / Apley, Daniel (Committee member) / Arizona State University (Publisher)
Created2016
Description
Biological and biomedical measurements, when adequately analyzed and processed, can be used to impart quantitative diagnosis during primary health care consultation to improve patient adherence to recommended treatments. For example, analyzing neural recordings from neurostimulators implanted in patients with neurological disorders can be used by a physician to adjust detrimental stimulation parameters to improve treatment. As another example, biosequences, such as sequences from peptide microarrays obtained from a biological sample, can potentially provide pre-symptomatic diagnosis for infectious diseases when processed to associate antibodies to specific pathogens or infectious agents. This work proposes advanced statistical signal processing and machine learning methodologies to assess neurostimulation from neural recordings and to extract diagnostic information from biosequences.
For locating specific cognitive and behavioral information in different regions of the brain, neural recordings are processed using sequential Bayesian filtering methods to detect and estimate both the number of neural sources and their corresponding parameters. Time-frequency based feature selection algorithms are combined with adaptive machine learning approaches to suppress physiological and non-physiological artifacts present in neural recordings. Adaptive processing and unsupervised clustering methods applied to neural recordings are also used to suppress neurostimulation artifacts and classify between various behavior tasks to assess the level of neurostimulation in patients.
For pathogen detection and identification, random peptide sequences and their properties are first uniquely mapped to highly-localized signals and their corresponding parameters in the time-frequency plane. Time-frequency signal processing methods are then applied to estimate antigenic determinants or epitope candidates for detecting and identifying potential pathogens.
For locating specific cognitive and behavioral information in different regions of the brain, neural recordings are processed using sequential Bayesian filtering methods to detect and estimate both the number of neural sources and their corresponding parameters. Time-frequency based feature selection algorithms are combined with adaptive machine learning approaches to suppress physiological and non-physiological artifacts present in neural recordings. Adaptive processing and unsupervised clustering methods applied to neural recordings are also used to suppress neurostimulation artifacts and classify between various behavior tasks to assess the level of neurostimulation in patients.
For pathogen detection and identification, random peptide sequences and their properties are first uniquely mapped to highly-localized signals and their corresponding parameters in the time-frequency plane. Time-frequency signal processing methods are then applied to estimate antigenic determinants or epitope candidates for detecting and identifying potential pathogens.
ContributorsMaurer, Alexander Joseph (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Bliss, Daniel (Committee member) / Chakrabarti, Chaitali (Committee member) / Kovvali, Narayan (Committee member) / Arizona State University (Publisher)
Created2016
Description
This dissertation proposes a new set of analytical methods for high dimensional physiological sensors. The methodologies developed in this work were motivated by problems in learning science, but also apply to numerous disciplines where high dimensional signals are present. In the education field, more data is now available from traditional sources and there is an important need for analytical methods to translate this data into improved learning. Affecting Computing which is the study of new techniques that develop systems to recognize and model human emotions is integrating different physiological signals such as electroencephalogram (EEG) and electromyogram (EMG) to detect and model emotions which later can be used to improve these learning systems.
The first contribution proposes an event-crossover (ECO) methodology to analyze performance in learning environments. The methodology is relevant to studies where it is desired to evaluate the relationships between sentinel events in a learning environment and a physiological measurement which is provided in real time.
The second contribution introduces analytical methods to study relationships between multi-dimensional physiological signals and sentinel events in a learning environment. The methodology proposed learns physiological patterns in the form of node activations near time of events using different statistical techniques.
The third contribution addresses the challenge of performance prediction from physiological signals. Features from the sensors which could be computed early in the learning activity were developed for input to a machine learning model. The objective is to predict success or failure of the student in the learning environment early in the activity. EEG was used as the physiological signal to train a pattern recognition algorithm in order to derive meta affective states.
The last contribution introduced a methodology to predict a learner's performance using Bayes Belief Networks (BBNs). Posterior probabilities of latent nodes were used as inputs to a predictive model in real-time as evidence was accumulated in the BBN.
The methodology was applied to data streams from a video game and from a Damage Control Simulator which were used to predict and quantify performance. The proposed methods provide cognitive scientists with new tools to analyze subjects in learning environments.
The first contribution proposes an event-crossover (ECO) methodology to analyze performance in learning environments. The methodology is relevant to studies where it is desired to evaluate the relationships between sentinel events in a learning environment and a physiological measurement which is provided in real time.
The second contribution introduces analytical methods to study relationships between multi-dimensional physiological signals and sentinel events in a learning environment. The methodology proposed learns physiological patterns in the form of node activations near time of events using different statistical techniques.
The third contribution addresses the challenge of performance prediction from physiological signals. Features from the sensors which could be computed early in the learning activity were developed for input to a machine learning model. The objective is to predict success or failure of the student in the learning environment early in the activity. EEG was used as the physiological signal to train a pattern recognition algorithm in order to derive meta affective states.
The last contribution introduced a methodology to predict a learner's performance using Bayes Belief Networks (BBNs). Posterior probabilities of latent nodes were used as inputs to a predictive model in real-time as evidence was accumulated in the BBN.
The methodology was applied to data streams from a video game and from a Damage Control Simulator which were used to predict and quantify performance. The proposed methods provide cognitive scientists with new tools to analyze subjects in learning environments.
ContributorsLujan Moreno, Gustavo A. (Author) / Runger, George C. (Thesis advisor) / Atkinson, Robert K (Thesis advisor) / Montgomery, Douglas C. (Committee member) / Villalobos, Rene (Committee member) / Arizona State University (Publisher)
Created2017
Description
In the last 15 years, there has been a significant increase in the number of motor neural prostheses used for restoring limb function lost due to neurological disorders or accidents. The aim of this technology is to enable patients to control a motor prosthesis using their residual neural pathways (central or peripheral). Recent studies in non-human primates and humans have shown the possibility of controlling a prosthesis for accomplishing varied tasks such as self-feeding, typing, reaching, grasping, and performing fine dexterous movements. A neural decoding system comprises mainly of three components: (i) sensors to record neural signals, (ii) an algorithm to map neural recordings to upper limb kinematics and (iii) a prosthetic arm actuated by control signals generated by the algorithm. Machine learning algorithms that map input neural activity to the output kinematics (like finger trajectory) form the core of the neural decoding system. The choice of the algorithm is thus, mainly imposed by the neural signal of interest and the output parameter being decoded. The various parts of a neural decoding system are neural data, feature extraction, feature selection, and machine learning algorithm. There have been significant advances in the field of neural prosthetic applications. But there are challenges for translating a neural prosthesis from a laboratory setting to a clinical environment. To achieve a fully functional prosthetic device with maximum user compliance and acceptance, these factors need to be addressed and taken into consideration. Three challenges in developing robust neural decoding systems were addressed by exploring neural variability in the peripheral nervous system for dexterous finger movements, feature selection methods based on clinically relevant metrics and a novel method for decoding dexterous finger movements based on ensemble methods.
ContributorsPadmanaban, Subash (Author) / Greger, Bradley (Thesis advisor) / Santello, Marco (Committee member) / Helms Tillery, Stephen (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Crook, Sharon (Committee member) / Arizona State University (Publisher)
Created2017