ASU Electronic Theses and Dissertations
This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
Displaying 1 - 10 of 178
Filtering by
- Creators: Shen, Wei
- Creators: Kavazanjian, Edward
- Creators: Ye, Jieping
Description
Sparsity has become an important modeling tool in areas such as genetics, signal and audio processing, medical image processing, etc. Via the penalization of l-1 norm based regularization, the structured sparse learning algorithms can produce highly accurate models while imposing various predefined structures on the data, such as feature groups or graphs. In this thesis, I first propose to solve a sparse learning model with a general group structure, where the predefined groups may overlap with each other. Then, I present three real world applications which can benefit from the group structured sparse learning technique. In the first application, I study the Alzheimer's Disease diagnosis problem using multi-modality neuroimaging data. In this dataset, not every subject has all data sources available, exhibiting an unique and challenging block-wise missing pattern. In the second application, I study the automatic annotation and retrieval of fruit-fly gene expression pattern images. Combined with the spatial information, sparse learning techniques can be used to construct effective representation of the expression images. In the third application, I present a new computational approach to annotate developmental stage for Drosophila embryos in the gene expression images. In addition, it provides a stage score that enables one to more finely annotate each embryo so that they are divided into early and late periods of development within standard stage demarcations. Stage scores help us to illuminate global gene activities and changes much better, and more refined stage annotations improve our ability to better interpret results when expression pattern matches are discovered between genes.
ContributorsYuan, Lei (Author) / Ye, Jieping (Thesis advisor) / Wang, Yalin (Committee member) / Xue, Guoliang (Committee member) / Kumar, Sudhir (Committee member) / Arizona State University (Publisher)
Created2013
Description
The rapid escalation of technology and the widespread emergence of modern technological equipments have resulted in the generation of humongous amounts of digital data (in the form of images, videos and text). This has expanded the possibility of solving real world problems using computational learning frameworks. However, while gathering a large amount of data is cheap and easy, annotating them with class labels is an expensive process in terms of time, labor and human expertise. This has paved the way for research in the field of active learning. Such algorithms automatically select the salient and exemplar instances from large quantities of unlabeled data and are effective in reducing human labeling effort in inducing classification models. To utilize the possible presence of multiple labeling agents, there have been attempts towards a batch mode form of active learning, where a batch of data instances is selected simultaneously for manual annotation. This dissertation is aimed at the development of novel batch mode active learning algorithms to reduce manual effort in training classification models in real world multimedia pattern recognition applications. Four major contributions are proposed in this work: $(i)$ a framework for dynamic batch mode active learning, where the batch size and the specific data instances to be queried are selected adaptively through a single formulation, based on the complexity of the data stream in question, $(ii)$ a batch mode active learning strategy for fuzzy label classification problems, where there is an inherent imprecision and vagueness in the class label definitions, $(iii)$ batch mode active learning algorithms based on convex relaxations of an NP-hard integer quadratic programming (IQP) problem, with guaranteed bounds on the solution quality and $(iv)$ an active matrix completion algorithm and its application to solve several variants of the active learning problem (transductive active learning, multi-label active learning, active feature acquisition and active learning for regression). These contributions are validated on the face recognition and facial expression recognition problems (which are commonly encountered in real world applications like robotics, security and assistive technology for the blind and the visually impaired) and also on collaborative filtering applications like movie recommendation.
ContributorsChakraborty, Shayok (Author) / Panchanathan, Sethuraman (Thesis advisor) / Balasubramanian, Vineeth N. (Committee member) / Li, Baoxin (Committee member) / Mittelmann, Hans (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
Description
In a laboratory setting, the soil volume change behavior is best represented by using various testing standards on undisturbed or remolded samples. Whenever possible, it is most precise to use undisturbed samples to assess the volume change behavior but in the absence of undisturbed specimens, remodeled samples can be used. If that is the case, the soil is compacted to in-situ density and water content (or matric suction), which should best represent the expansive profile in question. It is standard practice to subject the specimen to a wetting process at a particular net normal stress. Even though currently accepted laboratory testing standard procedures provide insight on how the profile conditions changes with time, these procedures do not assess the long term effects on the soil due to climatic changes. In this experimental study, an assessment and quantification of the effect of multiple wetting/drying cycles on the volume change behavior of two different naturally occurring soils was performed. The changes in wetting and drying cycles were extreme when comparing the swings in matric suction. During the drying cycle, the expansive soil was subjected to extreme conditions, which decreased the moisture content less than the shrinkage limit. Nevertheless, both soils were remolded at five different compacted conditions and loaded to five different net normal stresses. Each sample was subjected to six wetting and drying cycles. During the assessment, it was evident from the results that the swell/collapse strain is highly non-linear at low stress levels. The strain-net normal stress relationship cannot be defined by one single function without transforming the data. Therefore, the dataset needs to be fitted to a bi-modal logarithmic function or to a logarithmic transformation of net normal stress in order to use a third order polynomial fit. It was also determined that the moisture content changes with time are best fit by non-linear functions. For the drying cycle, the radial strain was determined to have a constant rate of change with respect to the axial strain. However, for the wetting cycle, there was not enough radial strain data to develop correlations and therefore, an assumption was made based on 55 different test measurements/observations, for the wetting cycles. In general, it was observed that after each subsequent cycle, higher swelling was exhibited for lower net normal stress values; while higher collapse potential was observed for higher net normal stress values, once the net normal stress was less than/greater than a threshold net normal stress value. Furthermore, the swelling pressure underwent a reduction in all cases. Particularly, the Anthem soil exhibited a reduction in swelling pressure by at least 20 percent after the first wetting/drying cycle; while Colorado soil exhibited a reduction of 50 percent. After about the fourth cycle, the swelling pressure seemed to stabilized to an equilibrium value at which a reduction of 46 percent was observed for the Anthem soil and 68 percent reduction for the Colorado soil. The impact of the initial compacted conditions on heave characteristics was studied. Results indicated that materials compacted at higher densities exhibited greater swell potential. When comparing specimens compacted at the same density but at different moisture content (matric suction), it was observed that specimens compacted at higher suction would exhibit higher swelling potential, when subjected to the same net normal stress. The least amount of swelling strain was observed on specimens compacted at the lowest dry density and the lowest matric suction (higher water content). The results from the laboratory testing were used to develop ultimate heave profiles for both soils. This analysis showed that even though the swell pressure for each soil decreased with cycles, the amount of heave would increase or decrease depending upon the initial compaction condition. When the specimen was compacted at 110% of optimum moisture content and 90% of maximum dry density, it resulted in an ultimate heave reduction of 92 percent for Anthem and 685 percent for Colorado soil. On the other hand, when the soils were compacted at 90% optimum moisture content and 100% of the maximum dry density, Anthem specimens heave 78% more and Colorado specimens heave was reduced by 69%. Based on the results obtained, it is evident that the current methods to estimate heave and swelling pressure do not consider the effect of wetting/drying cycles; and seem to fail capturing the free swell potential of the soil. Recommendations for improvement current methods of practice are provided.
ContributorsRosenbalm, Daniel Curtis (Author) / Zapata, Claudia E (Thesis advisor) / Houston, Sandra L. (Committee member) / Kavazanjian, Edward (Committee member) / Witczak, Mathew W (Committee member) / Arizona State University (Publisher)
Created2013
Description
Automating aspects of biocuration through biomedical information extraction could significantly impact biomedical research by enabling greater biocuration throughput and improving the feasibility of a wider scope. An important step in biomedical information extraction systems is named entity recognition (NER), where mentions of entities such as proteins and diseases are located within natural-language text and their semantic type is determined. This step is critical for later tasks in an information extraction pipeline, including normalization and relationship extraction. BANNER is a benchmark biomedical NER system using linear-chain conditional random fields and the rich feature set approach. A case study with BANNER locating genes and proteins in biomedical literature is described. The first corpus for disease NER adequate for use as training data is introduced, and employed in a case study of disease NER. The first corpus locating adverse drug reactions (ADRs) in user posts to a health-related social website is also described, and a system to locate and identify ADRs in social media text is created and evaluated. The rich feature set approach to creating NER feature sets is argued to be subject to diminishing returns, implying that additional improvements may require more sophisticated methods for creating the feature set. This motivates the first application of multivariate feature selection with filters and false discovery rate analysis to biomedical NER, resulting in a feature set at least 3 orders of magnitude smaller than the set created by the rich feature set approach. Finally, two novel approaches to NER by modeling the semantics of token sequences are introduced. The first method focuses on the sequence content by using language models to determine whether a sequence resembles entries in a lexicon of entity names or text from an unlabeled corpus more closely. The second method models the distributional semantics of token sequences, determining the similarity between a potential mention and the token sequences from the training data by analyzing the contexts where each sequence appears in a large unlabeled corpus. The second method is shown to improve the performance of BANNER on multiple data sets.
ContributorsLeaman, James Robert (Author) / Gonzalez, Graciela (Thesis advisor) / Baral, Chitta (Thesis advisor) / Cohen, Kevin B (Committee member) / Liu, Huan (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
Description
The effect of earthquake-induced liquefaction on the local void ratio distribution of cohesionless soil is evaluated using x-ray computed tomography (CT) and an advanced image processing software package. Intact, relatively undisturbed specimens of cohesionless soil were recovered before and after liquefaction by freezing and coring soil deposits created by pluviation and by sedimentation through water. Pluviated soil deposits were liquefied in the small geotechnical centrifuge at the University of California at Davis shared-use National Science Foundation (NSF)-supported Network for Earthquake Engineering Simulation (NEES) facility. A soil deposit created by sedimentation through water was liquefied on a small shake table in the Arizona State University geotechnical laboratory. Initial centrifuge tests employed Ottawa 20-30 sand but this material proved to be too coarse to liquefy in the centrifuge. Therefore, subsequent centrifuge tests employed Ottawa F60 sand. The shake table test employed Ottawa 20-30 sand. Recovered cores were stabilized by impregnation with optical grade epoxy and sent to the University of Texas at Austin NSF-supported facility at the University of Texas at Austin for high-resolution CT scanning of geologic media. The local void ratio distribution of a CT-scanned core of Ottawa 20-30 sand evaluated using Avizo® Fire, a commercially available advanced program for image analysis, was compared to the local void ratio distribution established on the same core by analysis of optical images to demonstrate that analysis of the CT scans gave similar results to optical methods. CT scans were subsequently conducted on liquefied and not-liquefied specimens of Ottawa 20-30 sand and Ottawa F60 sand. The resolution of F60 specimens was inadequate to establish the local void ratio distribution. Results of the analysis of the Ottawa 20-30 specimens recovered from the model built for the shake table test showed that liquefaction can substantially influence the variability in local void ratio, increasing the degree of non-homogeneity in the specimen.
ContributorsGutierrez, Angel (Author) / Kavazanjian, Edward (Thesis advisor) / Houston, Sandra (Committee member) / Zapata, Claudia (Committee member) / Arizona State University (Publisher)
Created2013
Description
Under the framework of intelligent management of power grids by leveraging advanced information, communication and control technologies, a primary objective of this study is to develop novel data mining and data processing schemes for several critical applications that can enhance the reliability of power systems. Specifically, this study is broadly organized into the following two parts: I) spatio-temporal wind power analysis for wind generation forecast and integration, and II) data mining and information fusion of synchrophasor measurements toward secure power grids. Part I is centered around wind power generation forecast and integration. First, a spatio-temporal analysis approach for short-term wind farm generation forecasting is proposed. Specifically, using extensive measurement data from an actual wind farm, the probability distribution and the level crossing rate of wind farm generation are characterized using tools from graphical learning and time-series analysis. Built on these spatial and temporal characterizations, finite state Markov chain models are developed, and a point forecast of wind farm generation is derived using the Markov chains. Then, multi-timescale scheduling and dispatch with stochastic wind generation and opportunistic demand response is investigated. Part II focuses on incorporating the emerging synchrophasor technology into the security assessment and the post-disturbance fault diagnosis of power systems. First, a data-mining framework is developed for on-line dynamic security assessment by using adaptive ensemble decision tree learning of real-time synchrophasor measurements. Under this framework, novel on-line dynamic security assessment schemes are devised, aiming to handle various factors (including variations of operating conditions, forced system topology change, and loss of critical synchrophasor measurements) that can have significant impact on the performance of conventional data-mining based on-line DSA schemes. Then, in the context of post-disturbance analysis, fault detection and localization of line outage is investigated using a dependency graph approach. It is shown that a dependency graph for voltage phase angles can be built according to the interconnection structure of power system, and line outage events can be detected and localized through networked data fusion of the synchrophasor measurements collected from multiple locations of power grids. Along a more practical avenue, a decentralized networked data fusion scheme is proposed for efficient fault detection and localization.
ContributorsHe, Miao (Author) / Zhang, Junshan (Thesis advisor) / Vittal, Vijay (Thesis advisor) / Hedman, Kory (Committee member) / Si, Jennie (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
Description
In recent years, machine learning and data mining technologies have received growing attention in several areas such as recommendation systems, natural language processing, speech and handwriting recognition, image processing and biomedical domain. Many of these applications which deal with physiological and biomedical data require person specific or person adaptive systems. The greatest challenge in developing such systems is the subject-dependent data variations or subject-based variability in physiological and biomedical data, which leads to difference in data distributions making the task of modeling these data, using traditional machine learning algorithms, complex and challenging. As a result, despite the wide application of machine learning, efficient deployment of its principles to model real-world data is still a challenge. This dissertation addresses the problem of subject based variability in physiological and biomedical data and proposes person adaptive prediction models based on novel transfer and active learning algorithms, an emerging field in machine learning. One of the significant contributions of this dissertation is a person adaptive method, for early detection of muscle fatigue using Surface Electromyogram signals, based on a new multi-source transfer learning algorithm. This dissertation also proposes a subject-independent algorithm for grading the progression of muscle fatigue from 0 to 1 level in a test subject, during isometric or dynamic contractions, at real-time. Besides subject based variability, biomedical image data also varies due to variations in their imaging techniques, leading to distribution differences between the image databases. Hence a classifier learned on one database may perform poorly on the other database. Another significant contribution of this dissertation has been the design and development of an efficient biomedical image data annotation framework, based on a novel combination of transfer learning and a new batch-mode active learning method, capable of addressing the distribution differences across databases. The methodologies developed in this dissertation are relevant and applicable to a large set of computing problems where there is a high variation of data between subjects or sources, such as face detection, pose detection and speech recognition. From a broader perspective, these frameworks can be viewed as a first step towards design of automated adaptive systems for real world data.
ContributorsChattopadhyay, Rita (Author) / Panchanathan, Sethuraman (Thesis advisor) / Ye, Jieping (Thesis advisor) / Li, Baoxin (Committee member) / Santello, Marco (Committee member) / Arizona State University (Publisher)
Created2013
Description
Currently, to interact with computer based systems one needs to learn the specific interface language of that system. In most cases, interaction would be much easier if it could be done in natural language. For that, we will need a module which understands natural language and automatically translates it to the interface language of the system. NL2KR (Natural language to knowledge representation) v.1 system is a prototype of such a system. It is a learning based system that learns new meanings of words in terms of lambda-calculus formulas given an initial lexicon of some words and their meanings and a training corpus of sentences with their translations. As a part of this thesis, we take the prototype NL2KR v.1 system and enhance various components of it to make it usable for somewhat substantial and useful interface languages. We revamped the lexicon learning components, Inverse-lambda and Generalization modules, and redesigned the lexicon learning algorithm which uses these components to learn new meanings of words. Similarly, we re-developed an inbuilt parser of the system in Answer Set Programming (ASP) and also integrated external parser with the system. Apart from this, we added some new rich features like various system configurations and memory cache in the learning component of the NL2KR system. These enhancements helped in learning more meanings of the words, boosted performance of the system by reducing the computation time by a factor of 8 and improved the usability of the system. We evaluated the NL2KR system on iRODS domain. iRODS is a rule-oriented data system, which helps in managing large set of computer files using policies. This system provides a Rule-Oriented interface langauge whose syntactic structure is like any procedural programming language (eg. C). However, direct translation of natural language (NL) to this interface language is difficult. So, for automatic translation of NL to this language, we define a simple intermediate Policy Declarative Language (IPDL) to represent the knowledge in the policies, which then can be directly translated to iRODS rules. We develop a corpus of 100 policy statements and manually translate them to IPDL langauge. This corpus is then used for the evaluation of NL2KR system. We performed 10 fold cross validation on the system. Furthermore, using this corpus, we illustrate how different components of our NL2KR system work.
ContributorsKumbhare, Kanchan Ravishankar (Author) / Baral, Chitta (Thesis advisor) / Ye, Jieping (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2013
Description
Unsaturated soil mechanics is becoming a part of geotechnical engineering practice, particularly in applications to moisture sensitive soils such as expansive and collapsible soils and in geoenvironmental applications. The soil water characteristic curve, which describes the amount of water in a soil versus soil suction, is perhaps the most important soil property function for application of unsaturated soil mechanics. The soil water characteristic curve has been used extensively for estimating unsaturated soil properties, and a number of fitting equations for development of soil water characteristic curves from laboratory data have been proposed by researchers. Although not always mentioned, the underlying assumption of soil water characteristic curve fitting equations is that the soil is sufficiently stiff so that there is no change in total volume of the soil while measuring the soil water characteristic curve in the laboratory, and researchers rarely take volume change of soils into account when generating or using the soil water characteristic curve. Further, there has been little attention to the applied net normal stress during laboratory soil water characteristic curve measurement, and often zero to only token net normal stress is applied. The applied net normal stress also affects the volume change of the specimen during soil suction change. When a soil changes volume in response to suction change, failure to consider the volume change of the soil leads to errors in the estimated air-entry value and the slope of the soil water characteristic curve between the air-entry value and the residual moisture state. Inaccuracies in the soil water characteristic curve may lead to inaccuracies in estimated soil property functions such as unsaturated hydraulic conductivity. A number of researchers have recently recognized the importance of considering soil volume change in soil water characteristic curves. The study of correct methods of soil water characteristic curve measurement and determination considering soil volume change, and impacts on the unsaturated hydraulic conductivity function was of the primary focus of this study. Emphasis was placed upon study of the effect of volume change consideration on soil water characteristic curves, for expansive clays and other high volume change soils. The research involved extensive literature review and laboratory soil water characteristic curve testing on expansive soils. The effect of the initial state of the specimen (i.e. slurry versus compacted) on soil water characteristic curves, with regard to volume change effects, and effect of net normal stress on volume change for determination of these curves, was studied for expansive clays. Hysteresis effects were included in laboratory measurements of soil water characteristic curves as both wetting and drying paths were used. Impacts of soil water characteristic curve volume change considerations on fluid flow computations and associated suction-change induced soil deformations were studied through numerical simulations. The study includes both coupled and uncoupled flow and stress-deformation analyses, demonstrating that the impact of volume change consideration on the soil water characteristic curve and the estimated unsaturated hydraulic conductivity function can be quite substantial for high volume change soils.
ContributorsBani Hashem, Elham (Author) / Houston, Sandra L. (Thesis advisor) / Kavazanjian, Edward (Committee member) / Zapata, Claudia (Committee member) / Arizona State University (Publisher)
Created2013
Description
Despite significant advances in digital pathology and automation sciences, current diagnostic practice for cancer detection primarily relies on a qualitative manual inspection of tissue architecture and cell and nuclear morphology in stained biopsies using low-magnification, two-dimensional (2D) brightfield microscopy. The efficacy of this process is limited by inter-operator variations in sample preparation and imaging, and by inter-observer variability in assessment. Over the past few decades, the predictive value quantitative morphology measurements derived from computerized analysis of micrographs has been compromised by the inability of 2D microscopy to capture information in the third dimension, and by the anisotropic spatial resolution inherent to conventional microscopy techniques that generate volumetric images by stacking 2D optical sections to approximate 3D. To gain insight into the analytical 3D nature of cells, this dissertation explores the application of a new technology for single-cell optical computed tomography (optical cell CT) that is a promising 3D tomographic imaging technique which uses visible light absorption to image stained cells individually with sub-micron, isotropic spatial resolution. This dissertation provides a scalable analytical framework to perform fully-automated 3D morphological analysis from transmission-mode optical cell CT images of hematoxylin-stained cells. The developed framework performs rapid and accurate quantification of 3D cell and nuclear morphology, facilitates assessment of morphological heterogeneity, and generates shape- and texture-based biosignatures predictive of the cell state. Custom 3D image segmentation methods were developed to precisely delineate volumes of interest (VOIs) from reconstructed cell images. Comparison with user-defined ground truth assessments yielded an average agreement (DICE coefficient) of 94% for the cell and its nucleus. Seventy nine biologically relevant morphological descriptors (features) were computed from the segmented VOIs, and statistical classification methods were implemented to determine the subset of features that best predicted cell health. The efficacy of our proposed framework was demonstrated on an in vitro model of multistep carcinogenesis in human Barrett's esophagus (BE) and classifier performance using our 3D morphometric analysis was compared against computerized analysis of 2D image slices that reflected conventional cytological observation. Our results enable sensitive and specific nuclear grade classification for early cancer diagnosis and underline the value of the approach as an objective adjunctive tool to better understand morphological changes associated with malignant transformation.
ContributorsNandakumar, Vivek (Author) / Meldrum, Deirdre R (Thesis advisor) / Nelson, Alan C. (Committee member) / Karam, Lina J (Committee member) / Ye, Jieping (Committee member) / Johnson, Roger H (Committee member) / Bussey, Kimberly J (Committee member) / Arizona State University (Publisher)
Created2013