Matching Items (276)
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
One dimensional (1D) and quasi-one dimensional quantum wires have been a subject of both theoretical and experimental interest since 1990s and before. Phenomena such as the "0.7 structure" in the conductance leave many open questions. In this dissertation, I study the properties and the internal electron states of semiconductor quantum wires with the path integral Monte Carlo (PIMC) method. PIMC is a tool for simulating many-body quantum systems at finite temperature. Its ability to calculate thermodynamic properties and various correlation functions makes it an ideal tool in bridging experiments with theories. A general study of the features interpreted by the Luttinger liquid theory and observed in experiments is first presented, showing the need for new PIMC calculations in this field. I calculate the DC conductance at finite temperature for both noninteracting and interacting electrons. The quantized conductance is identified in PIMC simulations without making the same approximation in the Luttinger model. The low electron density regime is subject to strong interactions, since the kinetic energy decreases faster than the Coulomb interaction at low density. An electron state called the Wigner crystal has been proposed in this regime for quasi-1D wires. By using PIMC, I observe the zig-zag structure of the Wigner crystal. The quantum fluctuations suppress the long range correla- tions, making the order short-ranged. Spin correlations are calculated and used to evaluate the spin coupling strength in a zig-zag state. I also find that as the density increases, electrons undergo a structural phase transition to a dimer state, in which two electrons of opposite spins are coupled across the two rows of the zig-zag. A phase diagram is sketched for a range of densities and transverse confinements. The quantum point contact (QPC) is a typical realization of quantum wires. I study the QPC by explicitly simulating a system of electrons in and around a Timp potential (Timp, 1992). Localization of a single electron in the middle of the channel is observed at 5 K, as the split gate voltage increases. The DC conductance is calculated, which shows the effect of the Coulomb interaction. At 1 K and low electron density, a state similar to the Wigner crystal is found inside the channel.
ContributorsLiu, Jianheng, 1982- (Author) / Shumway, John B (Thesis advisor) / Schmidt, Kevin E (Committee member) / Chen, Tingyong (Committee member) / Yu, Hongbin (Committee member) / Ros, Robert (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
Integrated photonics requires high gain optical materials in the telecom wavelength range for optical amplifiers and coherent light sources. Erbium (Er) containing materials are ideal candidates due to the 1.5 μm emission from Er3+ ions. However, the Er density in typical Er-doped materials is less than 1 x 1020 cm-3, thus limiting the maximum optical gain to a few dB/cm, too small to be useful for integrated photonics applications. Er compounds could potentially solve this problem since they contain much higher Er density. So far the existing Er compounds suffer from short lifetime and strong upconversion effects, mainly due to poor quality of crystals produced by various methods of thin film growth and deposition. This dissertation explores a new Er compound: erbium chloride silicate (ECS, Er3(SiO4)2Cl ) in the nanowire form, which facilitates the growth of high quality single crystals. Growth methods for such single crystal ECS nanowires have been established. Various structural and optical characterizations have been carried out. The high crystal quality of ECS material leads to a long lifetime of the first excited state of Er3+ ions up to 1 ms at Er density higher than 1022 cm-3. This Er lifetime-density product was found to be the largest among all Er containing materials. A unique integrating sphere method was developed to measure the absorption cross section of ECS nanowires from 440 to 1580 nm. Pump-probe experiments demonstrated a 644 dB/cm signal enhancement from a single ECS wire. It was estimated that such large signal enhancement can overcome the absorption to result in a net material gain, but not sufficient to compensate waveguide propagation loss. In order to suppress the upconversion process in ECS, Ytterbium (Yb) and Yttrium (Y) ions are introduced as substituent ions of Er in the ECS crystal structure to reduce Er density. While the addition of Yb ions only partially succeeded, erbium yttrium chloride silicate (EYCS) with controllable Er density was synthesized successfully. EYCS with 30 at. % Er was found to be the best. It shows the strongest PL emission at 1.5 μm, and thus can be potentially used as a high gain material.
ContributorsYin, Leijun (Author) / Ning, Cun-Zheng (Thesis advisor) / Chamberlin, Ralph (Committee member) / Yu, Hongbin (Committee member) / Menéndez, Jose (Committee member) / Ponce, Fernando (Committee member) / Arizona State University (Publisher)
Created2013
Description
Nitride semiconductors have wide applications in electronics and optoelectronics technologies. Understanding the nature of the optical recombination process and its effects on luminescence efficiency is important for the development of novel devices. This dissertation deals with the optical properties of nitride semiconductors, including GaN epitaxial layers and more complex heterostructures. The emission characteristics are examined by cathodoluminescence spectroscopy and imaging, and are correlated with the structural and electrical properties studied by transmission electron microscopy and electron holography. Four major areas are covered in this dissertation, which are described next. The effect of strain on the emission characteristics in wurtzite GaN has been studied. The values of the residual strain in GaN epilayers with different dislocation densities are determined by x-ray diffraction, and the relationship between exciton emission energy and the in-plane residual strain is demonstrated. It shows that the emission energy increases withthe magnitude of the in-plane compressive strain. The temperature dependence of the emission characteristics in cubic GaN has been studied. It is observed that the exciton emission and donor-acceptor pair recombination behave differently with temperature. The donor-bound exciton binding energy has been measured to be 13 meV from the temperature dependence of the emission spectrum. It is also found that the ionization energies for both acceptors and donors are smaller in cubic compared with hexagonal structures, which should contribute to higher doping efficiencies. A comprehensive study on the structural and optical properties is presented for InGaN/GaN quantum wells emitting in the blue, green, and yellow regions of the electromagnetic spectrum. Transmission electron microscopy images indicate the presence of indium inhomogeneties which should be responsible for carrier localization. The temperature dependence of emission luminescence shows that the carrier localization effects become more significant with increasing emission wavelength. On the other hand, the effect of non-radiative recombination on luminescence efficiency also varies with the emission wavelength. The fast increase of the non-radiative recombination rate with temperature in the green emitting QWs contributes to the lower efficiency compared with the blue emitting QWs. The possible saturation of non-radiative recombination above 100 K may explain the unexpected high emission efficiency for the yellow emitting QWs Finally, the effects of InGaN underlayers on the electronic and optical properties of InGaN/GaN quantum wells emitting in visible spectral regions have been studied. A significant improvement of the emission efficiency is observed, which is associated with a blue shift in the emission energy, a reduced recombination lifetime, an increased spatial homogeneity in the luminescence, and a weaker internal field across the quantum wells. These are explained by a partial strain relaxation introduced by the InGaN underlayer, which is measured by reciprocal space mapping of the x-ray diffraction intensity.
ContributorsLi, Di (Author) / Ponce, Fernando (Thesis advisor) / Culbertson, Robert (Committee member) / Yu, Hongbin (Committee member) / Shumway, John (Committee member) / Menéndez, Jose (Committee member) / Arizona State University (Publisher)
Created2012
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
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
Description
Video denoising has been an important task in many multimedia and computer vision applications. Recent developments in the matrix completion theory and emergence of new numerical methods which can efficiently solve the matrix completion problem have paved the way for exploration of new techniques for some classical image processing tasks. Recent literature shows that many computer vision and image processing problems can be solved by using the matrix completion theory. This thesis explores the application of matrix completion in video denoising. A state-of-the-art video denoising algorithm in which the denoising task is modeled as a matrix completion problem is chosen for detailed study. The contribution of this thesis lies in both providing extensive analysis to bridge the gap in existing literature on matrix completion frame work for video denoising and also in proposing some novel techniques to improve the performance of the chosen denoising algorithm. The chosen algorithm is implemented for thorough analysis. Experiments and discussions are presented to enable better understanding of the problem. Instability shown by the algorithm at some parameter values in a particular case of low levels of pure Gaussian noise is identified. Artifacts introduced in such cases are analyzed. A novel way of grouping structurally-relevant patches is proposed to improve the algorithm. Experiments show that this technique is useful, especially in videos containing high amounts of motion. Based on the observation that matrix completion is not suitable for denoising patches containing relatively low amount of image details, a framework is designed to separate patches corresponding to low structured regions from a noisy image. Experiments are conducted by not subjecting such patches to matrix completion, instead denoising such patches in a different way. The resulting improvement in performance suggests that denoising low structured patches does not require a complex method like matrix completion and in fact it is counter-productive to subject such patches to matrix completion. These results also indicate the inherent limitation of matrix completion to deal with cases in which noise dominates the structural properties of an image. A novel method for introducing priorities to the ranked patches in matrix completion is also presented. Results showed that this method yields improved performance in general. It is observed that the artifacts in presence of low levels of pure Gaussian noise appear differently after introducing priorities to the patches and the artifacts occur at a wider range of parameter values. Results and discussion suggesting future ways to explore this problem are also presented.
ContributorsMaguluri, Hima Bindu (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Claveau, Claude (Committee member) / Arizona State University (Publisher)
Created2013