Matching Items (343)
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
Our ability to estimate the position of our body parts in space, a fundamentally proprioceptive process, is crucial for interacting with the environment and movement control. For proprioception to support these actions, the Central Nervous System has to rely on a stored internal representation of the body parts in space. However, relatively little is known about this internal representation of arm position. To this end, I developed a method to map proprioceptive estimates of hand location across a 2-d workspace. In this task, I moved each subject's hand to a target location while the subject's eyes were closed. After returning the hand, subjects opened their eyes to verbally report the location of where their fingertip had been. Then, I reconstructed and analyzed the spatial structure of the pattern of estimation errors. In the first couple of experiments I probed the structure and stability of the pattern of errors by manipulating the hand used and tactile feedback provided when the hand was at each target location. I found that the resulting pattern of errors was systematically stable across conditions for each subject, subject-specific, and not uniform across the workspace. These findings suggest that the observed structure of pattern of errors has been constructed through experience, which has resulted in a systematically stable internal representation of arm location. Moreover, this representation is continuously being calibrated across the workspace. In the next two experiments, I aimed to probe the calibration of this structure. To this end, I used two different perturbation paradigms: 1) a virtual reality visuomotor adaptation to induce a local perturbation, 2) and a standard prism adaptation paradigm to induce a global perturbation. I found that the magnitude of the errors significantly increased to a similar extent after each perturbation. This small effect indicates that proprioception is recalibrated to a similar extent regardless of how the perturbation is introduced, suggesting that sensory and motor changes may be two independent processes arising from the perturbation. Moreover, I propose that the internal representation of arm location might be constructed with a global solution and not capable of local changes.
ContributorsRincon Gonzalez, Liliana (Author) / Helms Tillery, Stephen I (Thesis advisor) / Buneo, Christopher A (Thesis advisor) / Santello, Marco (Committee member) / Santos, Veronica (Committee member) / Kleim, Jeffrey (Committee member) / Arizona State University (Publisher)
Created2012
Description
Achievement of many long-term goals requires sustained practice over long durations. Examples include goals related to areas of high personal and societal benefit, such as physical fitness, which requires a practice of frequent exercise; self-education, which requires a practice of frequent study; or personal productivity, which requires a practice of performing work. Maintaining these practices can be difficult, because even though obvious benefits come with achieving these goals, an individual's willpower may not always be sufficient to sustain the required effort. This dissertation advocates addressing this problem by designing novel interfaces that provide people with new practices that are fun and enjoyable, thereby reducing the need for users to draw upon willpower when pursuing these long-term goals. To draw volitional usage, these practice-oriented interfaces can integrate key characteristics of existing activities, such as music-making and other hobbies, that are already known to draw voluntary participation over long durations. This dissertation makes several key contributions to provide designers with the necessary tools to create practice-oriented interfaces. First, it consolidates and synthesizes key ideas from fields such as activity theory, self-determination theory, HCI design, and serious leisure. It also provides a new conceptual framework consisting of heuristics for designing systems that draw new users, plus heuristics for making systems that will continue drawing usage from existing users over time. These heuristics serve as a collection of useful ideas to consider when analyzing or designing systems, and this dissertation postulates that if designers build these characteristics into their products, the resulting systems will draw more volitional usage. To demonstrate the framework's usefulness as an analytical tool, it is applied as a set of analytical lenses upon three previously-existing experiential media systems. To demonstrate its usefulness as a design tool, the framework is used as a guide in the development of an experiential media system called pdMusic. This system is installed at public events for user studies, and the study results provide qualitative support for many framework heuristics. Lastly, this dissertation makes recommendations to scholars and designers on potential future ways to examine the topic of volitional usage.
ContributorsWallis, Isaac (Author) / Ingalls, Todd (Thesis advisor) / Coleman, Grisha (Committee member) / Sundaram, Hari (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
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
Humans' ability to perform fine object and tool manipulation is a defining feature of their sensorimotor repertoire. How the central nervous system builds and maintains internal representations of such skilled hand-object interactions has attracted significant attention over the past three decades. Nevertheless, two major gaps exist: a) how digit positions and forces are coordinated during natural manipulation tasks, and b) what mechanisms underlie the formation and retention of internal representations of dexterous manipulation. This dissertation addresses these two questions through five experiments that are based on novel grip devices and experimental protocols. It was found that high-level representation of manipulation tasks can be learned in an effector-independent fashion. Specifically, when challenged by trial-to-trial variability in finger positions or using digits that were not previously engaged in learning the task, subjects could adjust finger forces to compensate for this variability, thus leading to consistent task performance. The results from a follow-up experiment conducted in a virtual reality environment indicate that haptic feedback is sufficient to implement the above coordination between digit position and forces. However, it was also found that the generalizability of a learned manipulation is limited across tasks. Specifically, when subjects learned to manipulate the same object across different contexts that require different motor output, interference was found at the time of switching contexts. Data from additional studies provide evidence for parallel learning processes, which are characterized by different rates of decay and learning. These experiments have provided important insight into the neural mechanisms underlying learning and control of object manipulation. The present findings have potential biomedical applications including brain-machine interfaces, rehabilitation of hand function, and prosthetics.
ContributorsFu, Qiushi (Author) / Santello, Marco (Thesis advisor) / Helms Tillery, Stephen (Committee member) / Buneo, Christopher (Committee member) / Santos, Veronica (Committee member) / Artemiadis, Panagiotis (Committee member) / Arizona State University (Publisher)
Created2013
Description
Reaching movements are subject to noise in both the planning and execution phases of movement production. Although the effects of these noise sources in estimating and/or controlling endpoint position have been examined in many studies, the independent effects of limb configuration on endpoint variability have been largely ignored. The present study investigated the effects of arm configuration on the interaction between planning noise and execution noise. Subjects performed reaching movements to three targets located in a frontal plane. At the starting position, subjects matched one of two desired arm configuration 'templates' namely "adducted" and "abducted". These arm configurations were obtained by rotations along the shoulder-hand axis, thereby maintaining endpoint position. Visual feedback of the hand was varied from trial to trial, thereby increasing uncertainty in movement planning and execution. It was hypothesized that 1) pattern of endpoint variability would be dependent on arm configuration and 2) that these differences would be most apparent in conditions without visual feedback. It was found that there were differences in endpoint variability between arm configurations in both visual conditions, but these differences were much larger when visual feedback was withheld. The overall results suggest that patterns of endpoint variability are highly dependent on arm configuration, particularly in the absence of visual feedback. This suggests that in the presence of vision, movement planning in 3D space is performed using coordinates that are largely arm configuration independent (i.e. extrinsic coordinates). In contrast, in the absence of vision, movement planning in 3D space reflects a substantial contribution of intrinsic coordinates.
ContributorsLakshmi Narayanan, Kishor (Author) / Buneo, Christopher (Thesis advisor) / Santello, Marco (Committee member) / Helms Tillery, Stephen (Committee member) / Arizona State University (Publisher)
Created2013
Description
Stroke remains the leading cause of adult disability in developed countries. Most survivors live with residual motor impairments that severely diminish independence and quality of life. After stroke, the only accepted treatment for these patients is motor rehabilitation. However, the amount and kind of rehabilitation required to induce clinically significant improvements in motor function is rarely given due to the constraints of our current health care system. Research reported in this dissertation contributes towards developing adjuvant therapies that may augment the impact of motor rehabilitation and improve functional outcome. These studies have demonstrated reorganization of maps within motor cortex as a function of experience in both healthy and brain-injured animals by using intracortical microstimulation technique. Furthermore, synaptic plasticity has been identified as a key neural mechanism in directing motor map plasticity, evidenced by restoration of movement representations within the spared cortical tissue accompanied by increase in synapse number translating into motor improvement after stroke. There is increasing evidence that brain-derived neurotrophic factor (BDNF) modulates synaptic and morphological plasticity in the developing and mature nervous system. Unfortunately, BDNF itself is a poor candidate because of its short half-life, low penetration through the blood brain barrier, and activating multiple receptor units, p75 and TrkB on the neuronal membrane. In order to circumvent this problem efficacy of two recently developed novel TrkB agonists, LM22A-4 and 7,8-dihydroxyflavone, that actively penetrate the blood brain barrier and enhance functional recovery. Findings from these dissertation studies indicate that administration of these pharmacological compounds, accompanied by motor rehabilitation provide a powerful therapeutic tool for stroke recovery.
ContributorsWarraich, Zuha (Author) / Kleim, Jeffrey A (Thesis advisor) / Stabenfeldt, Sarah (Committee member) / Tillery, Stephen-Helms (Committee member) / Santello, Marco (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
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