Matching Items (333)
Description
This dissertation focuses on seven solo piano works written by contemporary Chinese-American composer Chen Yi. It is presented in the form of a recording project, with a written analysis of each recorded composition. The seven recorded pieces are Variations on "Awariguli", Duo Ye, Guessing, Two Chinese bagatelles: Yu Diao and Small Beijing Gong, Ba Ban, Singing in the Mountain, and Ji-Dong-Nuo. They were written between 1978 and 2005, presenting a wide range of Chen Yi's compositional style. The written portion consists of five chapters. After the introductory chapter, a sketch of Chen Yi's life is presented in Chapter Two. This chapter specifically uncovers Chen Yi's deep roots of Chinese traditional and folk music through her experiences during the Cultural Revolution. Chapter Three analyzes each of the seven pieces. Through formal structure realization, motivic analysis, and folk music implication, the author discovers the blend of Chinese and Western cultures throughout Chen Yi's music. Chapter Four discusses the performance aspect of these compositions through the author's recording experience. In this chapter, the author provides background information as well as suggestions on specific performance practice. The last chapter summarizes the entire dissertation.
ContributorsFeeken, Qing Nadia (Author) / Meir, Baruch (Thesis advisor) / Carpenter, Ellon (Committee member) / Cosand, Walter (Committee member) / Ryan, Russell (Committee member) / Arizona State University (Publisher)
Created2012
Description
Effective modeling of high dimensional data is crucial in information processing and machine learning. Classical subspace methods have been very effective in such applications. However, over the past few decades, there has been considerable research towards the development of new modeling paradigms that go beyond subspace methods. This dissertation focuses on the study of sparse models and their interplay with modern machine learning techniques such as manifold, ensemble and graph-based methods, along with their applications in image analysis and recovery. By considering graph relations between data samples while learning sparse models, graph-embedded codes can be obtained for use in unsupervised, supervised and semi-supervised problems. Using experiments on standard datasets, it is demonstrated that the codes obtained from the proposed methods outperform several baseline algorithms. In order to facilitate sparse learning with large scale data, the paradigm of ensemble sparse coding is proposed, and different strategies for constructing weak base models are developed. Experiments with image recovery and clustering demonstrate that these ensemble models perform better when compared to conventional sparse coding frameworks. When examples from the data manifold are available, manifold constraints can be incorporated with sparse models and two approaches are proposed to combine sparse coding with manifold projection. The improved performance of the proposed techniques in comparison to sparse coding approaches is demonstrated using several image recovery experiments. In addition to these approaches, it might be required in some applications to combine multiple sparse models with different regularizations. In particular, combining an unconstrained sparse model with non-negative sparse coding is important in image analysis, and it poses several algorithmic and theoretical challenges. A convex and an efficient greedy algorithm for recovering combined representations are proposed. Theoretical guarantees on sparsity thresholds for exact recovery using these algorithms are derived and recovery performance is also demonstrated using simulations on synthetic data. Finally, the problem of non-linear compressive sensing, where the measurement process is carried out in feature space obtained using non-linear transformations, is considered. An optimized non-linear measurement system is proposed, and improvements in recovery performance are demonstrated in comparison to using random measurements as well as optimized linear measurements.
ContributorsNatesan Ramamurthy, Karthikeyan (Author) / Spanias, Andreas (Thesis advisor) / Tsakalis, Konstantinos (Committee member) / Karam, Lina (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Image understanding has been playing an increasingly crucial role in vision applications. Sparse models form an important component in image understanding, since the statistics of natural images reveal the presence of sparse structure. Sparse methods lead to parsimonious models, in addition to being efficient for large scale learning. In sparse modeling, data is represented as a sparse linear combination of atoms from a "dictionary" matrix. This dissertation focuses on understanding different aspects of sparse learning, thereby enhancing the use of sparse methods by incorporating tools from machine learning. With the growing need to adapt models for large scale data, it is important to design dictionaries that can model the entire data space and not just the samples considered. By exploiting the relation of dictionary learning to 1-D subspace clustering, a multilevel dictionary learning algorithm is developed, and it is shown to outperform conventional sparse models in compressed recovery, and image denoising. Theoretical aspects of learning such as algorithmic stability and generalization are considered, and ensemble learning is incorporated for effective large scale learning. In addition to building strategies for efficiently implementing 1-D subspace clustering, a discriminative clustering approach is designed to estimate the unknown mixing process in blind source separation. By exploiting the non-linear relation between the image descriptors, and allowing the use of multiple features, sparse methods can be made more effective in recognition problems. The idea of multiple kernel sparse representations is developed, and algorithms for learning dictionaries in the feature space are presented. Using object recognition experiments on standard datasets it is shown that the proposed approaches outperform other sparse coding-based recognition frameworks. Furthermore, a segmentation technique based on multiple kernel sparse representations is developed, and successfully applied for automated brain tumor identification. Using sparse codes to define the relation between data samples can lead to a more robust graph embedding for unsupervised clustering. By performing discriminative embedding using sparse coding-based graphs, an algorithm for measuring the glomerular number in kidney MRI images is developed. Finally, approaches to build dictionaries for local sparse coding of image descriptors are presented, and applied to object recognition and image retrieval.
ContributorsJayaraman Thiagarajan, Jayaraman (Author) / Spanias, Andreas (Thesis advisor) / Frakes, David (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
Description
American music of late-nineteenth and early twentieth centuries represents some of the first mature achievements in classical music written by American composers.John Knowles Paine (1839-1906), Arthur Foote (1853-1937), George Whitefield Chadwick (1854-1931), Horatio Parker (1868-1919), and Amy Beach (1867-1944) from the Second New England School were among the most prominent musical figures in America during this time period. These composers shared similar compositional characteristics, perhaps due to the profound influences of German Romantic tradition, either through their direct study with musicians in Germany or with professional German-trained musicians in America.They were active in Boston, affiliated with important music organizations, and had publications through A. P. Schmidt, the most important music publisher of that time. Piano chamber music of the Second New England School is a small but important portion of their diverse repertoire. It is generally considered the first successful body of such repertoire by American composers. Even though most of these works were premiered to great acclaim during the composers' lifetimes, many of them no longer have place in current recital programs and very few are available to the public in published or recorded form. The purpose of this study is to reintroduce this important and worthwhile literature to today's audience. For the purpose of this study the repertoire will be limited to music that involves at least three performers, one of whom must be a pianist. The repertoire must be originally composed for a piano chamber group and must have been published or performed at least once during the composer's lifetime. While Edward MacDowell (1860-1908) is generally considered a member of the Second New England School, he surprisingly did not write any piano chamber music, and therefore has no works in this study. This research project will provide general background information about each composer and their piano chamber music, and a closer examination of one particularly representative work or movement, including performance guidelines from the collaborative pianist's point of view. The author's hope is to awaken greater curiosity about this rich repertoire and to increase its presence on the concert stage.
ContributorsHsu, Juiling (Author) / Campbell, Andrew (Thesis advisor) / Micklich, Albert (Committee member) / Holbrook, Amy (Committee member) / Ryan, Russell (Committee member) / Arizona State University (Publisher)
Created2012
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
About piano students who display disruptive behavior and perform far below reasonable expectations, teachers first conclude that they are lazy, rude, disinterested, and/or lacking intelligence or ability. Most dismiss such students from studios and advise parents to discontinue lessons. In truth, many of these students are both highly gifted and also have a learning disability. Examined literature shows that the incidence of dyslexia and other learning disabilities in the gifted learner population is several times that of the regular learner population. Although large volumes of research have been devoted to dyslexia, and more recently to dyslexia and music (in the classroom and some in individual instrumental instruction), there is no evidence of the same investigation in relation to the specific needs of highly gifted dyslexic students in learning to play the piano. This project examines characteristics of giftedness and dyslexia, gifted learners with learning disabilities, and the difficulties they encounter in learning to read music and play keyboard instruments. It includes historical summaries of author's experience with such students and description of their progress and success. They reveal some of practical strategies that evolved through several decades of teaching regular and gifted dyslexic students that helped them overcome the challenges and learn to play the piano. Informal conversations and experience exchanges with colleagues, as well as a recently completed pilot study also showed that most piano pedagogues had no formal opportunity to learn about this issue and to be empowered to teach these very special students. The author's hope is to offer personal insights, survey of current knowledge, and practical suggestions that will not only assist piano instructors to successfully teach highly gifted learners with dyslexia, but also inspire them to learn more about the topic.
ContributorsVladikovic, Jelena (Author) / Humphreys, Jere T. (Thesis advisor) / Meir, Baruch (Thesis advisor) / Norton, Kay (Committee member) / Hamilton, Robert (Committee member) / Arizona State University (Publisher)
Created2013
Description
In this thesis, quantitative evaluation of quality of movement during stroke rehabilitation will be discussed. Previous research on stroke rehabilitation in hospital has been shown to be effective. In this thesis, we study various issues that arise when creating a home-based system that can be deployed in a patient's home. Limitation of motion capture due to reduced number of sensors leads to problems with design of kinematic features for quantitative evaluation. Also, the hierarchical three-level tasks of rehabilitation requires new design of kinematic features. In this thesis, the design of kinematic features for a home based stroke rehabilitation system will be presented. Results of the most challenging classifier are shown and proves the effectiveness of the design. Comparison between modern classification techniques and low computational cost threshold based classification with same features will also be shown.
ContributorsCheng, Long (Author) / Turaga, Pavan (Thesis advisor) / Arizona State University (Publisher)
Created2012
Description
Arnold Schoenberg's 1908-09 song cycle, Das Buch der hängenden Gärten [The Book of the Hanging Gardens], opus 15, represents one of his most decisive early steps into the realm of musical modernism. In the midst of personal and artistic crises, Schoenberg set texts by Stefan George in a style he called "pantonality," and described his composition as radically new. Though stylistically progressive, however, Schoenberg's musical achievement had certain ideologically conservative roots: the composer numbered among turn-of-the-century Viennese artists and thinkers whose opposition to the conventional and the popular--in favor of artistic autonomy and creativity--concealed a reactionary misogyny. A critical reading of Hanging Gardens through the lens of gender reveals that Schoenberg, like many of his contemporaries, incorporated strong frauenfeindlich [anti-women] elements into his work, through his modernist account of artistic creativity, his choice of texts, and his musical settings. Although elements of Hanging Gardens' atonal music suggest that Schoenberg valued gendered-feminine principles in his compositional style, a closer analysis of the work's musical language shows an intact masculinist hegemony. Through his deployment of uncanny tonal reminiscences, underlying tonal gestures, and closed forms in Hanging Gardens, Schoenberg ensures that the feminine-associated "excesses" of atonality remain under masculine control. This study draws upon the critical musicology of Susan McClary while arguing that Schoenberg's music is socially contingent, affected by the gender biases of his social and literary milieux. It addresses likely influences on Schoenberg's worldview including the philosophy of Otto Weininger, Freudian psychoanalysis, and a complex web of personal relationships. Finally, this analysis highlights the relevance of Schoenberg's world and its constructions of gender to modern performance practice, and argues that performers must consider interrelated historical, textual, and musical factors when interpreting Hanging Gardens in new contexts.
ContributorsGinger, Kerry Anne (Author) / FitzPatrick, Carole (Thesis advisor) / Dreyfoos, Dale (Committee member) / Mook, Richard (Committee member) / Norton, Kay (Committee member) / Ryan, Russell (Committee member) / Arizona State University (Publisher)
Created2012
Description
Motion capture using cost-effective sensing technology is challenging and the huge success of Microsoft Kinect has been attracting researchers to uncover the potential of using this technology into computer vision applications. In this thesis, an upper-body motion analysis in a home-based system for stroke rehabilitation using novel RGB-D camera - Kinect is presented. We address this problem by first conducting a systematic analysis of the usability of Kinect for motion analysis in stroke rehabilitation. Then a hybrid upper body tracking approach is proposed which combines off-the-shelf skeleton tracking with a novel depth-fused mean shift tracking method. We proposed several kinematic features reliably extracted from the proposed inexpensive and portable motion capture system and classifiers that correlate torso movement to clinical measures of unimpaired and impaired. Experiment results show that the proposed sensing and analysis works reliably on measuring torso movement quality and is promising for end-point tracking. The system is currently being deployed for large-scale evaluations.
ContributorsDu, Tingfang (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Rikakis, Thanassis (Committee member) / Arizona State University (Publisher)
Created2012
Description
Our research focuses on finding answers through decentralized search, for complex, imprecise queries (such as "Which is the best hair salon nearby?") in situations where there is a spatiotemporal constraint (say answer needs to be found within 15 minutes) associated with the query. In general, human networks are good in answering imprecise queries. We try to use the social network of a person to answer his query. Our research aims at designing a framework that exploits the user's social network in order to maximize the answers for a given query. Exploiting an user's social network has several challenges. The major challenge is that the user's immediate social circle may not possess the answer for the given query, and hence the framework designed needs to carry out the query diffusion process across the network. The next challenge involves in finding the right set of seeds to pass the query to in the user's social circle. One other challenge is to incentivize people in the social network to respond to the query and thereby maximize the quality and quantity of replies. Our proposed framework is a mobile application where an individual can either respond to the query or forward it to his friends. We simulated the query diffusion process in three types of graphs: Small World, Random and Preferential Attachment. Given a type of network and a particular query, we carried out the query diffusion by selecting seeds based on attributes of the seed. The main attributes are Topic relevance, Replying or Forwarding probability and Time to Respond. We found that there is a considerable increase in the number of replies attained, even without saturating the user's network, if we adopt an optimal seed selection process. We found the output of the optimal algorithm to be satisfactory as the number of replies received at the interrogator's end was close to three times the number of neighbors an interrogator has. We addressed the challenge of incentivizing people to respond by associating a particular amount of points for each query asked, and awarding the same to people involved in answering the query. Thus, we aim to design a mobile application based on our proposed framework so that it helps in maximizing the replies for the interrogator's query by diffusing the query across his/her social network.
ContributorsSwaminathan, Neelakantan (Author) / Sundaram, Hari (Thesis advisor) / Davulcu, Hasan (Thesis advisor) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013