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 258
Filtering by
- Creators: Li, Baoxin
- Creators: Shrivastava, Aviral
- Creators: Mobasher, Barzin
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
Manufacture of building materials requires significant energy, and as demand for these materials continues to increase, the energy requirement will as well. Offsetting this energy use will require increased focus on sustainable building materials. Further, the energy used in building, particularly in heating and air conditioning, accounts for 40 percent of a buildings energy use. Increasing the efficiency of building materials will reduce energy usage over the life time of the building. Current methods for maintaining the interior environment can be highly inefficient depending on the building materials selected. Materials such as concrete have low thermal efficiency and have a low heat capacity meaning it provides little insulation. Use of phase change materials (PCM) provides the opportunity to increase environmental efficiency of buildings by using the inherent latent heat storage as well as the increased heat capacity. Incorporating PCM into concrete via lightweight aggregates (LWA) by direct addition is seen as a viable option for increasing the thermal storage capabilities of concrete, thereby increasing building energy efficiency. As PCM change phase from solid to liquid, heat is absorbed from the surroundings, decreasing the demand on the air conditioning systems on a hot day or vice versa on a cold day. Further these materials provide an additional insulating capacity above the value of plain concrete. When the temperature drops outside the PCM turns back into a solid and releases the energy stored from the day. PCM is a hydrophobic material and causes reductions in compressive strength when incorporated directly into concrete, as shown in previous studies. A proposed method for mitigating this detrimental effect, while still incorporating PCM into concrete is to encapsulate the PCM in aggregate. This technique would, in theory, allow for the use of phase change materials directly in concrete, increasing the thermal efficiency of buildings, while negating the negative effect on compressive strength of the material.
ContributorsSharma, Breeann (Author) / Neithalath, Narayanan (Thesis advisor) / Mobasher, Barzin (Committee member) / Rajan, Subramaniam D. (Committee member) / Arizona State University (Publisher)
Created2013
Description
The alkali activation of aluminosilicate materials as binder systems derived from industrial byproducts have been extensively studied due to the advantages they offer in terms enhanced material properties, while increasing sustainability by the reuse of industrial waste and byproducts and reducing the adverse impacts of OPC production. Fly ash and ground granulated blast furnace slag are commonly used for their content of soluble silica and aluminate species that can undergo dissolution, polymerization with the alkali, condensation on particle surfaces and solidification. The following topics are the focus of this thesis: (i) the use of microwave assisted thermal processing, in addition to heat-curing as a means of alkali activation and (ii) the relative effects of alkali cations (K or Na) in the activator (powder activators) on the mechanical properties and chemical structure of these systems. Unsuitable curing conditions instigate carbonation, which in turn lowers the pH of the system causing significant reductions in the rate of fly ash activation and mechanical strength development. This study explores the effects of sealing the samples during the curing process, which effectively traps the free water in the system, and allows for increased aluminosilicate activation. The use of microwave-curing in lieu of thermal-curing is also studied in order to reduce energy consumption and for its ability to provide fast volumetric heating. Potassium-based powder activators dry blended into the slag binder system is shown to be effective in obtaining very high compressive strengths under moist curing conditions (greater than 70 MPa), whereas sodium-based powder activation is much weaker (around 25 MPa). Compressive strength decreases when fly ash is introduced into the system. Isothermal calorimetry is used to evaluate the early hydration process, and to understand the reaction kinetics of the alkali powder activated systems. A qualitative evidence of the alkali-hydroxide concentration of the paste pore solution through the use of electrical conductivity measurements is also presented, with the results indicating the ion concentration of alkali is more prevalent in the pore solution of potassium-based systems. The use of advanced spectroscopic and thermal analysis techniques to distinguish the influence of studied parameters is also discussed.
ContributorsChowdhury, Ussala (Author) / Neithalath, Narayanan (Thesis advisor) / Rajan, Subramanium D. (Committee member) / Mobasher, Barzin (Committee member) / Arizona State University (Publisher)
Created2013
Description
Properties of random porous material such as pervious concrete are strongly dependant on its pore structure features. This research deals with the development of an understanding of the relationship between the material structure and the mechanical and functional properties of pervious concretes. The fracture response of pervious concrete specimens proportioned for different porosities, as a function of the pore structure features and fiber volume fraction, is studied. Stereological and morphological methods are used to extract the relevant pore structure features of pervious concretes from planar images. A two-parameter fracture model is used to obtain the fracture toughness (KIC) and critical crack tip opening displacement (CTODc) from load-crack mouth opening displacement (CMOD) data of notched beams under three-point bending. The experimental results show that KIC is primarily dependent on the porosity of pervious concretes. For a similar porosity, an increase in pore size results in a reduction in KIC. At similar pore sizes, the effect of fibers on the post-peak response is more prominent in mixtures with a higher porosity, as shown by the residual load capacity, stress-crack extension relationships, and GR curves. These effects are explained using the mean free spacing of pores and pore-to-pore tortuosity in these systems. A sensitivity analysis is employed to quantify the influence of material design parameters on KIC. This research has also focused on studying the relationship between permeability and tortuosity as it pertains to porosity and pore size of pervious concretes. Various ideal geometric shapes were also constructed that had varying pore sizes and porosities. The pervious concretes also had differing pore sizes and porosities. The permeabilities were determined using three different methods; Stokes solver, Lattice Boltzmann method and the Katz-Thompson equation. These values were then compared to the tortuosity values determined using a Matlab code that uses a pore connectivity algorithm. The tortuosity was also determined from the inverse of the conductivity determined from a numerical analysis that was necessary for using the Katz-Thompson equation. These tortuosity values were then compared to the permeabilities. The pervious concretes and ideal geometric shapes showed consistent similarities betbetween their tortuosities and permeabilities.
ContributorsRehder, Benjamin (Author) / Neithalath, Narayanana (Thesis advisor) / Mobasher, Barzin (Committee member) / Rajan, Subramaniam D. (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
In recent years we have witnessed a shift towards multi-processor system-on-chips (MPSoCs) to address the demands of embedded devices (such as cell phones, GPS devices, luxury car features, etc.). Highly optimized MPSoCs are well-suited to tackle the complex application demands desired by the end user customer. These MPSoCs incorporate a constellation of heterogeneous processing elements (PEs) (general purpose PEs and application-specific integrated circuits (ASICS)). A typical MPSoC will be composed of a application processor, such as an ARM Coretex-A9 with cache coherent memory hierarchy, and several application sub-systems. Each of these sub-systems are composed of highly optimized instruction processors, graphics/DSP processors, and custom hardware accelerators. Typically, these sub-systems utilize scratchpad memories (SPM) rather than support cache coherency. The overall architecture is an integration of the various sub-systems through a high bandwidth system-level interconnect (such as a Network-on-Chip (NoC)). The shift to MPSoCs has been fueled by three major factors: demand for high performance, the use of component libraries, and short design turn around time. As customers continue to desire more and more complex applications on their embedded devices the performance demand for these devices continues to increase. Designers have turned to using MPSoCs to address this demand. By using pre-made IP libraries designers can quickly piece together a MPSoC that will meet the application demands of the end user with minimal time spent designing new hardware. Additionally, the use of MPSoCs allows designers to generate new devices very quickly and thus reducing the time to market. In this work, a complete MPSoC synthesis design flow is presented. We first present a technique \cite{leary1_intro} to address the synthesis of the interconnect architecture (particularly Network-on-Chip (NoC)). We then address the synthesis of the memory architecture of a MPSoC sub-system \cite{leary2_intro}. Lastly, we present a co-synthesis technique to generate the functional and memory architectures simultaneously. The validity and quality of each synthesis technique is demonstrated through extensive experimentation.
ContributorsLeary, Glenn (Author) / Chatha, Karamvir S (Thesis advisor) / Vrudhula, Sarma (Committee member) / Shrivastava, Aviral (Committee member) / Beraha, Rudy (Committee member) / Arizona State University (Publisher)
Created2013
Description
Buildings consume a large portion of the world's energy, but with the integration of phase change materials (PCMs) in building elements this energy cost can be greatly reduced. The addition of PCMs into building elements, however, becomes a challenge to model and analyze how the material actually affects the energy flow and temperatures in the system. This research work presents a comprehensive computer program used to model and analyze PCM embedded wall systems. The use of the finite element method (FEM) provides the tool to analyze the energy flow of these systems. Finite element analysis (FEA) can model the transient analysis of a typical climate cycle along with nonlinear problems, which the addition of PCM causes. The use of phase change materials is also a costly material expense. The initial expense of using PCMs can be compensated by the reduction in energy costs it can provide. Optimization is the tool used to determine the optimal point between adding PCM into a wall and the amount of energy savings that layer will provide. The integration of these two tools into a computer program allows for models to be efficiently created, analyzed and optimized. The program was then used to understand the benefits between two different wall models, a wall with a single layer of PCM or a wall with two different PCM layers. The effect of the PCMs on the inside wall temperature along with the energy flow across the wall are computed. The numerical results show that a multi-layer PCM wall was more energy efficient and cost effective than the single PCM layer wall. A structural analysis was then performed on the optimized designs using ABAQUS v. 6.10 to ensure the structural integrity of the wall was not affected by adding PCM layer(s).
ContributorsStockwell, Amie (Author) / Rajan, Subramaniam D. (Thesis advisor) / Neithalath, Narayanan (Thesis advisor) / Mobasher, Barzin (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
We solve the problem of activity verification in the context of sustainability. Activity verification is the process of proving the user assertions pertaining to a certain activity performed by the user. Our motivation lies in incentivizing the user for engaging in sustainable activities like taking public transport or recycling. Such incentivization schemes require the system to verify the claim made by the user. The system verifies these claims by analyzing the supporting evidence captured by the user while performing the activity. The proliferation of portable smart-phones in the past few years has provided us with a ubiquitous and relatively cheap platform, having multiple sensors like accelerometer, gyroscope, microphone etc. to capture this evidence data in-situ. In this research, we investigate the supervised and semi-supervised learning techniques for activity verification. Both these techniques make use the data set constructed using the evidence submitted by the user. Supervised learning makes use of annotated evidence data to build a function to predict the class labels of the unlabeled data points. The evidence data captured can be either unimodal or multimodal in nature. We use the accelerometer data as evidence for transportation mode verification and image data as evidence for recycling verification. After training the system, we achieve maximum accuracy of 94% when classifying the transport mode and 81% when detecting recycle activity. In the case of recycle verification, we could improve the classification accuracy by asking the user for more evidence. We present some techniques to ask the user for the next best piece of evidence that maximizes the probability of classification. Using these techniques for detecting recycle activity, the accuracy increases to 93%. The major disadvantage of using supervised models is that it requires extensive annotated training data, which expensive to collect. Due to the limited training data, we look at the graph based inductive semi-supervised learning methods to propagate the labels among the unlabeled samples. In the semi-supervised approach, we represent each instance in the data set as a node in the graph. Since it is a complete graph, edges interconnect these nodes, with each edge having some weight representing the similarity between the points. We propagate the labels in this graph, based on the proximity of the data points to the labeled nodes. We estimate the performance of these algorithms by measuring how close the probability distribution of the data after label propagation is to the probability distribution of the ground truth data. Since labeling has a cost associated with it, in this thesis we propose two algorithms that help us in selecting minimum number of labeled points to propagate the labels accurately. Our proposed algorithm achieves a maximum of 73% increase in performance when compared to the baseline algorithm.
ContributorsDesai, Vaishnav (Author) / Sundaram, Hari (Thesis advisor) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Woven fabric composite materials are widely used in the construction of aircraft engine fan containment systems, mostly due to their high strength to weight ratios and ease of implementation. The development of a predictive model for fan blade containment would provide great benefit to engine manufactures in shortened development cycle time, less risk in certification and fewer dollars lost to redesign/recertification cycles. A mechanistic user-defined material model subroutine has been developed at Arizona State University (ASU) that captures the behavioral response of these fabrics, namely Kevlar® 49, under ballistic loading. Previously developed finite element models used to validate the consistency of this material model neglected the effects of the physical constraints imposed on the test setup during ballistic testing performed at NASA Glenn Research Center (NASA GRC). Part of this research was to explore the effects of these boundary conditions on the results of the numerical simulations. These effects were found to be negligible in most instances. Other material models for woven fabrics are available in the LS-DYNA finite element code. One of these models, MAT234: MAT_VISCOELASTIC_LOOSE_FABRIC (Ivanov & Tabiei, 2004) was studied and implemented in the finite element simulations of ballistic testing associated with the FAA ASU research. The results from these models are compared to results obtained from the ASU UMAT as part of this research. The results indicate an underestimation in the energy absorption characteristics of the Kevlar 49 fabric containment systems. More investigation needs to be performed in the implementation of MAT234 for Kevlar 49 fabric. Static penetrator testing of Kevlar® 49 fabric was performed at ASU in conjunction with this research. These experiments are designed to mimic the type of loading experienced during fan blade out events. The resulting experimental strains were measured using a non-contact optical strain measurement system (ARAMIS).
ContributorsFein, Jonathan (Author) / Rajan, Subramaniam D. (Thesis advisor) / Mobasher, Barzin (Committee member) / Jiang, Hanqing (Committee member) / Arizona State University (Publisher)
Created2012