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 143
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
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
With the rapid growth of power systems and the concomitant technological advancements, the goal of achieving smart grids is no longer a vision but a foreseeable reality. Hence, the existing grids are undergoing infrastructural modifications to achieve the diverse characteristics of a smart grid. While there are many subjects associated with the operation of smart grids, this dissertation addresses two important aspects of smart grids: increased penetration of renewable resources, and increased reliance on sensor systems to improve reliability and performance of critical power system components. Present renewable portfolio standards are changing both structural and performance characteristics of power systems by replacing conventional generation with alternate energy resources such as photovoltaic (PV) systems. The present study investigates the impact of increased penetration of PV systems on steady state performance as well as transient stability of a large power system which is a portion of the Western U.S. interconnection. Utility scale and residential rooftop PVs are added to replace a portion of conventional generation resources. While steady state voltages are observed under various PV penetration levels, the impact of reduced inertia on transient stability performance is also examined. The simulation results obtained effectively identify both detrimental and beneficial impacts of increased PV penetration both for steady state stability and transient stability performance. With increased penetration of the renewable energy resources, and with the current loading scenario, more transmission system components such as transformers and circuit breakers are subject to increased stress and overloading. This research work explores the feasibility of increasing system reliability by applying condition monitoring systems to selected circuit breakers and transformers. A very important feature of smart grid technology is that this philosophy decreases maintenance costs by deploying condition monitoring systems that inform the operator of impending failures; or the approach can ameliorate problematic conditions. A method to identify the most critical transformers and circuit breakers with the aid of contingency ranking methods is presented in this study. The work reported in this dissertation parallels an industry sponsored study in which a considerable level of industry input and industry reported concerns are reflected.
ContributorsEftekharnejad, Sara (Author) / Heydt, Gerald (Thesis advisor) / Vittal, Vijay (Thesis advisor) / Si, Jennie (Committee member) / Tylavsky, Daniel (Committee member) / Arizona State University (Publisher)
Created2012
Description
The combined heat and power (CHP)-based distributed generation (DG) or dis-tributed energy resources (DERs) are mature options available in the present energy mar-ket, considered to be an effective solution to promote energy efficiency. In the urban en-vironment, the electricity, water and natural gas distribution networks are becoming in-creasingly interconnected with the growing penetration of the CHP-based DG. Subse-quently, this emerging interdependence leads to new topics meriting serious consideration: how much of the CHP-based DG can be accommodated and where to locate these DERs, and given preexisting constraints, how to quantify the mutual impacts on operation performances between these urban energy distribution networks and the CHP-based DG. The early research work was conducted to investigate the feasibility and design methods for one residential microgrid system based on existing electricity, water and gas infrastructures of a residential community, mainly focusing on the economic planning. However, this proposed design method cannot determine the optimal DG sizing and sit-ing for a larger test bed with the given information of energy infrastructures. In this con-text, a more systematic as well as generalized approach should be developed to solve these problems. In the later study, the model architecture that integrates urban electricity, water and gas distribution networks, and the CHP-based DG system was developed. The pro-posed approach addressed the challenge of identifying the optimal sizing and siting of the CHP-based DG on these urban energy networks and the mutual impacts on operation per-formances were also quantified. For this study, the overall objective is to maximize the electrical output and recovered thermal output of the CHP-based DG units. The electrici-ty, gas, and water system models were developed individually and coupled by the devel-oped CHP-based DG system model. The resultant integrated system model is used to constrain the DG's electrical output and recovered thermal output, which are affected by multiple factors and thus analyzed in different case studies. The results indicate that the designed typical gas system is capable of supplying sufficient natural gas for the DG normal operation, while the present water system cannot support the complete recovery of the exhaust heat from the DG units.
ContributorsZhang, Xianjun (Author) / Karady, George G. (Thesis advisor) / Ariaratnam, Samuel T. (Committee member) / Holbert, Keith E. (Committee member) / Si, Jennie (Committee member) / Arizona State University (Publisher)
Created2013
Description
This dissertation considers an integrated approach to system design and controller design based on analyzing limits of system performance. Historically, plant design methodologies have not incorporated control relevant considerations. Such an approach could result in a system that might not meet its specifications (or one that requires a complex control architecture to do so). System and controller designers often go through several iterations in order to converge to an acceptable plant and controller design. The focus of this dissertation is on the design and control an air-breathing hypersonic vehicle using such an integrated system-control design framework. The goal is to reduce the number of system-control design iterations (by explicitly incorporate control considerations in the system design process), as well as to influence the guidance/trajectory specifications for the system. Due to the high computational costs associated with obtaining a dynamic model for each plant configuration considered, approximations to the system dynamics are used in the control design process. By formulating the control design problem using bilinear and polynomial matrix inequalities, several common control and system design constraints can be simultaneously incorporated into a vehicle design optimization. Several design problems are examined to illustrate the effectiveness of this approach (and to compare the computational burden of this methodology against more traditional approaches).
ContributorsSridharan, Srikanth (Author) / Rodriguez, Armando A (Thesis advisor) / Mittelmann, Hans D (Committee member) / Si, Jennie (Committee member) / Tsakalis, Konstantinos S (Committee member) / Arizona State University (Publisher)
Created2014
Description
The basal ganglia are four sub-cortical nuclei associated with motor control and reward learning. They are part of numerous larger mostly segregated loops where the basal ganglia receive inputs from specific regions of cortex. Converging on these inputs are dopaminergic neurons that alter their firing based on received and/or predicted rewarding outcomes of a behavior. The basal ganglia's output feeds through the thalamus back to the areas of the cortex where the loop originated. Understanding the dynamic interactions between the various parts of these loops is critical to understanding the basal ganglia's role in motor control and reward based learning. This work developed several experimental techniques that can be applied to further study basal ganglia function. The first technique used micro-volume injections of low concentration muscimol to decrease the firing rates of recorded neurons in a limited area of cortex in rats. Afterwards, an artificial cerebrospinal fluid flush was injected to rapidly eliminate the muscimol's effects. This technique was able to contain the effects of muscimol to approximately a 1 mm radius volume and limited the duration of the drug effect to less than one hour. This technique could be used to temporarily perturb a small portion of the loops involving the basal ganglia and then observe how these effects propagate in other connected regions. The second part applied self-organizing maps (SOM) to find temporal patterns in neural firing rate that are independent of behavior. The distribution of detected patterns frequency on these maps can then be used to determine if changes in neural activity are occurring over time. The final technique focused on the role of the basal ganglia in reward learning. A new conditioning technique was created to increase the occurrence of selected patterns of neural activity without utilizing any external reward or behavior. A pattern of neural activity in the cortex of rats was selected using an SOM. The pattern was then reinforced by being paired with electrical stimulation of the medial forebrain bundle triggering dopamine release in the basal ganglia. Ultimately, this technique proved unsuccessful possibly due to poor selection of the patterns being reinforced.
ContributorsBaldwin, Nathan Aaron (Author) / Helms Tillery, Stephen I (Thesis advisor) / Castaneda, Edward (Committee member) / Buneo, Christopher A (Committee member) / Muthuswamy, Jitendran (Committee member) / Si, Jennie (Committee member) / Arizona State University (Publisher)
Created2014
Description
This study focuses on state estimation of nonlinear discrete time systems with constraints. Physical processes have inherent in them, constraints on inputs, outputs, states and disturbances. These constraints can provide additional information to the estimator in estimating states from the measured output. Recursive filters such as Kalman Filters or Extended Kalman Filters are commonly used in state estimation; however, they do not allow inclusion of constraints in their formulation. On the other hand, computational complexity of full information estimation (using all measurements) grows with iteration and becomes intractable. One way of formulating the recursive state estimation problem with constraints is the Moving Horizon Estimation (MHE) approximation. Estimates of states are calculated from the solution of a constrained optimization problem of fixed size. Detailed formulation of this strategy is studied and properties of this estimation algorithm are discussed in this work. The problem with the MHE formulation is solving an optimization problem in each iteration which is computationally intensive. State estimation with constraints can be formulated as Extended Kalman Filter (EKF) with a projection applied to estimates. The states are estimated from the measurements using standard Extended Kalman Filter (EKF) algorithm and the estimated states are projected on to a constrained set. Detailed formulation of this estimation strategy is studied and the properties associated with this algorithm are discussed. Both these state estimation strategies (MHE and EKF with projection) are tested with examples from the literature. The average estimation time and the sum of square estimation error are used to compare performance of these estimators. Results of the case studies are analyzed and trade-offs are discussed.
ContributorsJoshi, Rakesh (Author) / Tsakalis, Konstantinos (Thesis advisor) / Rodriguez, Armando (Committee member) / Si, Jennie (Committee member) / Arizona State University (Publisher)
Created2013
Description
This thesis presents approaches to develop micro seismometers and accelerometers based on molecular electronic transducers (MET) technology using MicroElectroMechanical Systems (MEMS) techniques. MET is a technology applied in seismic instrumentation that proves highly beneficial to planetary seismology. It consists of an electrochemical cell that senses the movement of liquid electrolyte between electrodes by converting it to the output current. MET seismometers have advantages of high sensitivity, low noise floor, small size, absence of fragile mechanical moving parts and independence on the direction of sensitivity axis. By using MEMS techniques, a micro MET seismometer is developed with inter-electrode spacing close to 1μm, which improves the sensitivity of fabricated device to above 3000 V/(m/s^2) under operating bias of 600 mV and input acceleration of 400 μG (G=9.81m/s^2) at 0.32 Hz. The lowered hydrodynamic resistance by increasing the number of channels improves the self-noise to -127 dB equivalent to 44 nG/√Hz at 1 Hz. An alternative approach to build the sensing element of MEMS MET seismometer using SOI process is also presented in this thesis. The significantly increased number of channels is expected to improve the noise performance. Inspired by the advantages of combining MET and MEMS technologies on the development of seismometer, a low frequency accelerometer utilizing MET technology with post-CMOS-compatible fabrication processes is developed. In the fabricated accelerometer, the complicated fabrication of mass-spring system in solid-state MEMS accelerometer is replaced with a much simpler post-CMOS-compatible process containing only deposition of a four-electrode MET structure on a planar substrate, and a liquid inertia mass of an electrolyte droplet encapsulated by oil film. The fabrication process does not involve focused ion beam milling which is used in the micro MET seismometer fabrication, thus the cost is lowered. Furthermore, the planar structure and the novel idea of using an oil film as the sealing diaphragm eliminate the complicated three-dimensional packaging of the seismometer. The fabricated device achieves 10.8 V/G sensitivity at 20 Hz with nearly flat response over the frequency range from 1 Hz to 50 Hz, and a low noise floor of 75 μG/√Hz at 20 Hz.
ContributorsHuang, Hai (Author) / Yu, Hongyu (Thesis advisor) / Jiang, Hanqing (Committee member) / Dai, Lenore (Committee member) / Si, Jennie (Committee member) / Arizona State University (Publisher)
Created2014