Matching Items (155)
Filtering by
- Genre: Academic theses
- Creators: Li, Baoxin
- Member of: Theses and Dissertations
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
Johann Sebastian Bach's violin Sonata I in G minor, BWV 1001, is a significant and widely performed work that exists in numerous editions and also as transcriptions or arrangements for various other instruments, including the guitar. A pedagogical guitar performance edition of this sonata, however, has yet to be published. Therefore, the core of my project is a transcription and pedagogical edition of this work for guitar. The transcription is supported by an analysis, performance and pedagogical practice guide, and a recording. The analysis and graphing of phrase structures illuminate Bach's use of compositional devices and the architectural function of the work's harmonic gravities. They are intended to guide performers in their assessment of the surface ornamentation and suggest a reduction toward its fundamental purpose. The end result is a clarification of the piece through the organization of phrase structures and the prioritization of harmonic tensions and resolutions. The compiling process is intended to assist the performer in "seeing the forest from the trees." Based on markings from Bach's original autograph score, the transcription considers fingering ease on the guitar that is critical to render the music to a functional and practical level. The goal is to preserve the composer's indications to the highest degree possible while still adhering to the technical confines that allow for actual execution on the guitar. The performance guide provides suggestions for articulation, phrasing, ornamentation, and other interpretive decisions. Considering the limitations of the guitar, the author's suggestions are grounded in various concepts of historically informed performance, and also relate to today's early-music sensibilities. The pedagogical practice guide demonstrates procedures to break down and assimilate the musical material as applied toward the various elements of guitar technique and practice. The CD recording is intended to demonstrate the transcription and the connection to the concepts discussed. It is hoped that this pedagogical edition will provide a rational that serves to support technical decisions within the transcription and generate meaningful interpretive realizations based on principles of historically informed performance.
ContributorsFelice, Joseph Philip (Author) / Koonce, Frank (Thesis advisor) / Feisst, Sabine (Committee member) / Swartz, Jonathan (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
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
The German pianist and composer Johannes Brahms (1883-1897) wrote more than 122 works for a wide variety of ensembles and genres. Despite this remarkable productivity, and his widely heralded talent for innovation and technique as a composer, few of his works have been arranged for solo guitar, and these have focused primarily on his simpler, more melodic works. Conventional wisdom is that his music is "too dense" to be played on the guitar. As a result, there are no arrangements of orchestral works by Brahms in the standard repertoire for the guitar. In arranging Brahms's Serenade in D Major, movt. 1 for the guitar, I provide a counter argument that not all of Brahms's orchestral music is too dense all of the time. In Part I, I provide a brief overview of the history of, and sources for, the Serenade. Part II describes a step-by-step guide through the process of arranging orchestral repertoire for the solo guitar. Part III is an examination of the editing process that utilizes examples from the guitar arrangement of the Serenade in order to illustrate the various techniques and considerations that are part of the editing process. Part IV is a performance edition of the arrangement. In summary, the present arrangement of Brahms's Serenade, op.11 is the beginning of a conversation about why the "guitar world" should be incorporating the music of Brahms into the standard repertoire. The lessons learned, and the technical challenges discovered, should help inform future arrangers and guitar performers for additional compositions by Brahms.
ContributorsLanier, William Hudson (Author) / Koonce, Frank (Thesis advisor) / Micklich, Albie (Committee member) / Rockmaker, Jody (Committee member) / Arizona State University (Publisher)
Created2013
Description
Medical students acquire and enhance their clinical skills using various available techniques and resources. As the health care profession has move towards team-based practice, students and trainees need to practice team-based procedures that involve timely management of clinical tasks and adequate communication with other members of the team. Such team-based procedures include surgical and clinical procedures, some of which are protocol-driven. Cost and time required for individual team-based training sessions, along with other factors, contribute to making the training complex and challenging. A great deal of research has been done on medically-focused collaborative virtual reality (VR)-based training for protocol-driven procedures as a cost-effective as well as time-efficient solution. Most VR-based simulators focus on training of individual personnel. The ones which focus on providing team training provide an interactive simulation for only a few scenarios in a collaborative virtual environment (CVE). These simulators are suited for didactic training for cognitive skills development. The training sessions in the simulators require the physical presence of mentors. The problem with this kind of system is that the mentor must be present at the training location (either physically or virtually) to evaluate the performance of the team (or an individual). Another issue is that there is no efficient methodology that exists to provide feedback to the trainees during the training session itself (formative feedback). Furthermore, they lack the ability to provide training in acquisition or improvement of psychomotor skills for the tasks that require force or touch feedback such as cardiopulmonary resuscitation (CPR). To find a potential solution to overcome some of these concerns, a novel training system was designed and developed that utilizes the integration of sensors into a CVE for time-critical medical procedures. The system allows the participants to simultaneously access the CVE and receive training from geographically diverse locations. The system is also able to provide real-time feedback and is also able to store important data during each training/testing session. Finally, this study also presents a generalizable collaborative team-training system that can be used across various team-based procedures in medical as well as non-medical domains.
ContributorsKhanal, Prabal (Author) / Greenes, Robert (Thesis advisor) / Patel, Vimla (Thesis advisor) / Smith, Marshall (Committee member) / Gupta, Ashish (Committee member) / Kaufman, David (Committee member) / Arizona State University (Publisher)
Created2014
Description
Surgery as a profession requires significant training to improve both clinical decision making and psychomotor proficiency. In the medical knowledge domain, tools have been developed, validated, and accepted for evaluation of surgeons' competencies. However, assessment of the psychomotor skills still relies on the Halstedian model of apprenticeship, wherein surgeons are observed during residency for judgment of their skills. Although the value of this method of skills assessment cannot be ignored, novel methodologies of objective skills assessment need to be designed, developed, and evaluated that augment the traditional approach. Several sensor-based systems have been developed to measure a user's skill quantitatively, but use of sensors could interfere with skill execution and thus limit the potential for evaluating real-life surgery. However, having a method to judge skills automatically in real-life conditions should be the ultimate goal, since only with such features that a system would be widely adopted. This research proposes a novel video-based approach for observing surgeons' hand and surgical tool movements in minimally invasive surgical training exercises as well as during laparoscopic surgery. Because our system does not require surgeons to wear special sensors, it has the distinct advantage over alternatives of offering skills assessment in both learning and real-life environments. The system automatically detects major skill-measuring features from surgical task videos using a computing system composed of a series of computer vision algorithms and provides on-screen real-time performance feedback for more efficient skill learning. Finally, the machine-learning approach is used to develop an observer-independent composite scoring model through objective and quantitative measurement of surgical skills. To increase effectiveness and usability of the developed system, it is integrated with a cloud-based tool, which automatically assesses surgical videos upload to the cloud.
ContributorsIslam, Gazi (Author) / Li, Baoxin (Thesis advisor) / Liang, Jianming (Thesis advisor) / Dinu, Valentin (Committee member) / Greenes, Robert (Committee member) / Smith, Marshall (Committee member) / Kahol, Kanav (Committee member) / Patel, Vimla L. (Committee member) / Arizona State University (Publisher)
Created2013
DescriptionThe purpose of this project is to explore the influence of folk music in guitar compositions by Manuel Ponce from 1923 to 1932. It focuses on his Tres canciones populares mexicanas and Tropico and Rumba.
ContributorsGarcia Santos, Arnoldo (Author) / Koonce, Frank (Thesis advisor) / Rogers, Rodney (Committee member) / Rotaru, Catalin (Committee member) / Arizona State University (Publisher)
Created2014
Description
Guitar repertoire from the Baroque period consists primarily of transcriptions, which suggests that modern performers may explore more sources to identify eligible works to transcribe. The Musikalischer Parnassus, a collection of dance suites for harpsichord by Johann Kaspar Ferdinand Fischer (1656-1746), is worthy of such a transcription. This collection has high artistic value and possesses a range and texture that make much of it playable on the guitar. The purpose of this research project is to introduce Fischer and his works to the classical guitar community, and also to explore the artistic qualities of Musikalischer Parnassus that qualify it for transcription for guitar. This document addresses the transcription process of two selected suites: VI, Euterpe and VIII, Polymnia by Fischer. The outcome is an edition for guitar and a performance guide, which includes interpretations and stylistic considerations for each movement.
ContributorsFang, Zhou, D.M.A (Author) / Koonce, Frank (Thesis advisor) / Levy, Benjamin (Committee member) / Rotaru, Catalin (Committee member) / Arizona State University (Publisher)
Created2013