Matching Items (27)
Filtering by
- All Subjects: Machine Learning
- All Subjects: Aerospace Engineering
- Genre: Academic theses
- Creators: Turaga, Pavan
- Resource Type: Text
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
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
This research focuses on the benefits of using nanocomposites in aerospace structural components to prevent or delay the onset of unique composite failure modes, such as delamination. Analytical, numerical, and experimental analyses were conducted to provide a comprehensive understanding of how carbon nanotubes (CNTs) can provide additional structural integrity when they are used in specific hot spots within a structure. A multiscale approach was implemented to determine the mechanical and thermal properties of the nanocomposites, which were used in detailed finite element models (FEMs) to analyze interlaminar failures in T and Hat section stringers. The delamination that first occurs between the tow filler and the bondline between the stringer and skin was of particular interest. Both locations are considered to be hot spots in such structural components, and failures tend to initiate from these areas. In this research, nanocomposite use was investigated as an alternative to traditional methods of suppressing delamination. The stringer was analyzed under different loading conditions and assuming different structural defects. Initial damage, defined as the first drop in the load displacement curve was considered to be a useful variable to compare the different behaviors in this study and was detected via the virtual crack closure technique (VCCT) implemented in the FE analysis.
Experiments were conducted to test T section skin/stringer specimens under pull-off loading, replicating those used in composite panels as stiffeners. Two types of designs were considered: one using pure epoxy to fill the tow region and another that used nanocomposite with 5 wt. % CNTs. The response variable in the tests was the initial damage. Detailed analyses were conducted using FEMs to correlate with the experimental data. The correlation between both the experiment and model was satisfactory. Finally, the effects of thermal cure and temperature variation on nanocomposite structure behavior were studied, and both variables were determined to influence the nanocomposite structure performance.
Experiments were conducted to test T section skin/stringer specimens under pull-off loading, replicating those used in composite panels as stiffeners. Two types of designs were considered: one using pure epoxy to fill the tow region and another that used nanocomposite with 5 wt. % CNTs. The response variable in the tests was the initial damage. Detailed analyses were conducted using FEMs to correlate with the experimental data. The correlation between both the experiment and model was satisfactory. Finally, the effects of thermal cure and temperature variation on nanocomposite structure behavior were studied, and both variables were determined to influence the nanocomposite structure performance.
ContributorsHasan, Zeaid (Author) / Chattopadhyay, Aditi (Thesis advisor) / Dai, Lenore (Committee member) / Jiang, Hanqing (Committee member) / Rajadas, John (Committee member) / Liu, Yongming (Committee member) / Arizona State University (Publisher)
Created2014
Description
Many learning models have been proposed for various tasks in visual computing. Popular examples include hidden Markov models and support vector machines. Recently, sparse-representation-based learning methods have attracted a lot of attention in the computer vision field, largely because of their impressive performance in many applications. In the literature, many of such sparse learning methods focus on designing or application of some learning techniques for certain feature space without much explicit consideration on possible interaction between the underlying semantics of the visual data and the employed learning technique. Rich semantic information in most visual data, if properly incorporated into algorithm design, should help achieving improved performance while delivering intuitive interpretation of the algorithmic outcomes. My study addresses the problem of how to explicitly consider the semantic information of the visual data in the sparse learning algorithms. In this work, we identify four problems which are of great importance and broad interest to the community. Specifically, a novel approach is proposed to incorporate label information to learn a dictionary which is not only reconstructive but also discriminative; considering the formation process of face images, a novel image decomposition approach for an ensemble of correlated images is proposed, where a subspace is built from the decomposition and applied to face recognition; based on the observation that, the foreground (or salient) objects are sparse in input domain and the background is sparse in frequency domain, a novel and efficient spatio-temporal saliency detection algorithm is proposed to identify the salient regions in video; and a novel hidden Markov model learning approach is proposed by utilizing a sparse set of pairwise comparisons among the data, which is easier to obtain and more meaningful, consistent than tradition labels, in many scenarios, e.g., evaluating motion skills in surgical simulations. In those four problems, different types of semantic information are modeled and incorporated in designing sparse learning algorithms for the corresponding visual computing tasks. Several real world applications are selected to demonstrate the effectiveness of the proposed methods, including, face recognition, spatio-temporal saliency detection, abnormality detection, spatio-temporal interest point detection, motion analysis and emotion recognition. In those applications, data of different modalities are involved, ranging from audio signal, image to video. Experiments on large scale real world data with comparisons to state-of-art methods confirm the proposed approaches deliver salient advantages, showing adding those semantic information dramatically improve the performances of the general sparse learning methods.
ContributorsZhang, Qiang (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Wang, Yalin (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2014
Description
As a promising solution to the problem of acquiring and storing large amounts of image and video data, spatial-multiplexing camera architectures have received lot of attention in the recent past. Such architectures have the attractive feature of combining a two-step process of acquisition and compression of pixel measurements in a conventional camera, into a single step. A popular variant is the single-pixel camera that obtains measurements of the scene using a pseudo-random measurement matrix. Advances in compressive sensing (CS) theory in the past decade have supplied the tools that, in theory, allow near-perfect reconstruction of an image from these measurements even for sub-Nyquist sampling rates. However, current state-of-the-art reconstruction algorithms suffer from two drawbacks -- They are (1) computationally very expensive and (2) incapable of yielding high fidelity reconstructions for high compression ratios. In computer vision, the final goal is usually to perform an inference task using the images acquired and not signal recovery. With this motivation, this thesis considers the possibility of inference directly from compressed measurements, thereby obviating the need to use expensive reconstruction algorithms. It is often the case that non-linear features are used for inference tasks in computer vision. However, currently, it is unclear how to extract such features from compressed measurements. Instead, using the theoretical basis provided by the Johnson-Lindenstrauss lemma, discriminative features using smashed correlation filters are derived and it is shown that it is indeed possible to perform reconstruction-free inference at high compression ratios with only a marginal loss in accuracy. As a specific inference problem in computer vision, face recognition is considered, mainly beyond the visible spectrum such as in the short wave infra-red region (SWIR), where sensors are expensive.
ContributorsLohit, Suhas Anand (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2015
Description
Advanced composites are being widely used in aerospace applications due to their high stiffness, strength and energy absorption capabilities. However, the assurance of structural reliability is a critical issue because a damage event will compromise the integrity of composite structures and lead to ultimate failure. In this dissertation a novel homogenization based multiscale modeling framework using semi-analytical micromechanics is presented to simulate the response of textile composites. The novelty of this approach lies in the three scale homogenization/localization framework bridging between the constituent (micro), the fiber tow scale (meso), weave scale (macro), and the global response. The multiscale framework, named Multiscale Generalized Method of Cells (MSGMC), continuously bridges between the micro to the global scale as opposed to approaches that are top-down and bottom-up. This framework is fully generalized and capable of modeling several different weave and braids without reformulation. Particular emphasis in this dissertation is placed on modeling the nonlinearity and failure of both polymer matrix and ceramic matrix composites.
ContributorsLiu, Guang (Author) / Chattopadhyay, Aditi (Thesis advisor) / Mignolet, Marc (Committee member) / Jiang, Hanqing (Committee member) / Li, Jian (Committee member) / Rajadas, John (Committee member) / Arizona State University (Publisher)
Created2011
Description
This thesis focuses on the continued extension, validation, and application of combined thermal-structural reduced order models for nonlinear geometric problems. The first part of the thesis focuses on the determination of the temperature distribution and structural response induced by an oscillating flux on the top surface of a flat panel. This flux is introduced here as a simplified representation of the thermal effects of an oscillating shock on a panel of a supersonic/hypersonic vehicle. Accordingly, a random acoustic excitation is also considered to act on the panel and the level of the thermo-acoustic excitation is assumed to be large enough to induce a nonlinear geometric response of the panel. Both temperature distribution and structural response are determined using recently proposed reduced order models and a complete one way, thermal-structural, coupling is enforced. A steady-state analysis of the thermal problem is first carried out that is then utilized in the structural reduced order model governing equations with and without the acoustic excitation. A detailed validation of the reduced order models is carried out by comparison with a few full finite element (Nastran) computations. The computational expedience of the reduced order models allows a detailed parametric study of the response as a function of the frequency of the oscillating flux. The nature of the corresponding structural ROM equations is seen to be of a Mathieu-type with Duffing nonlinearity (originating from the nonlinear geometric effects) with external harmonic excitation (associated with the thermal moments terms on the panel). A dominant resonance is observed and explained. The second part of the thesis is focused on extending the formulation of the combined thermal-structural reduced order modeling method to include temperature dependent structural properties, more specifically of the elasticity tensor and the coefficient of thermal expansion. These properties were assumed to vary linearly with local temperature and it was found that the linear stiffness coefficients and the "thermal moment" terms then are cubic functions of the temperature generalized coordinates while the quadratic and cubic stiffness coefficients were only linear functions of these coordinates. A first validation of this reduced order modeling strategy was successfully carried out.
ContributorsMatney, Andrew (Author) / Mignolet, Marc (Thesis advisor) / Jiang, Hanqing (Committee member) / Spottswood, Stephen (Committee member) / Arizona State University (Publisher)
Created2011
Description
The performance of most of the visual computing tasks depends on the quality of the features extracted from the raw data. Insightful feature representation increases the performance of many learning algorithms by exposing the underlying explanatory factors of the output for the unobserved input. A good representation should also handle anomalies in the data such as missing samples and noisy input caused by the undesired, external factors of variation. It should also reduce the data redundancy. Over the years, many feature extraction processes have been invented to produce good representations of raw images and videos.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
ContributorsChandakkar, Parag Shridhar (Author) / Li, Baoxin (Thesis advisor) / Yang, Yezhou (Committee member) / Turaga, Pavan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2017
Description
With the maturity of advanced composites as feasible structural materials for various applications there is a critical need to solve the challenge of designing these material systems for optimal performance. However, determining superior design methods requires a deep understanding of the material-structure properties at various length scales. Due to the length-scale dependent behavior of advanced composites, multiscale modeling techniques may be used to describe the dominant mechanisms of damage and failure in these material systems. With polymer matrix fiber composites and nanocomposites it becomes essential to include even the atomic length scale, where the resin-hardener-nanofiller molecules interact, in the multiscale modeling framework. Additionally, sources of variability are also critical to be included in these models due to the important role of uncertainty in advance composite behavior. Such a methodology should be able to describe length scale dependent mechanisms in a computationally efficient manner for the analysis of practical composite structures.
In the research presented in this dissertation, a comprehensive nano to macro multiscale framework is developed for the mechanical and multifunctional analysis of advanced composite materials and structures. An atomistically informed statistical multiscale model is developed for linear problems, to estimate and scale elastic properties of carbon fiber reinforced polymer composites (CFRPs) and carbon nanotube (CNT) enhanced CFRPs using information from molecular dynamics simulation of the resin-hardener-nanofiller nanoscale system. For modeling inelastic processes, an atomistically informed coupled damage-plasticity model is developed using the framework of continuum damage mechanics, where fundamental nanoscale covalent bond disassociation information is scaled up as a continuum scale damage identifying parameter. This damage model is coupled with a nanocomposite microstructure generation algorithm to study the sub-microscale damage mechanisms in CNT/CFRP microstructures. It is further integrated in a generalized method of cells (GMC) micromechanics model to create a low-fidelity computationally efficient nonlinear multiscale method with imperfect interfaces between the fiber and matrix, where the interface behavior is adopted from nanoscale MD simulations. This algorithm is used to understand damage mechanisms in adhesively bonded composite joints as a case study for the comprehensive nano to macroscale structural analysis of practical composites structures. At each length scale sources of variability are identified, characterized, and included in the multiscale modeling framework.
In the research presented in this dissertation, a comprehensive nano to macro multiscale framework is developed for the mechanical and multifunctional analysis of advanced composite materials and structures. An atomistically informed statistical multiscale model is developed for linear problems, to estimate and scale elastic properties of carbon fiber reinforced polymer composites (CFRPs) and carbon nanotube (CNT) enhanced CFRPs using information from molecular dynamics simulation of the resin-hardener-nanofiller nanoscale system. For modeling inelastic processes, an atomistically informed coupled damage-plasticity model is developed using the framework of continuum damage mechanics, where fundamental nanoscale covalent bond disassociation information is scaled up as a continuum scale damage identifying parameter. This damage model is coupled with a nanocomposite microstructure generation algorithm to study the sub-microscale damage mechanisms in CNT/CFRP microstructures. It is further integrated in a generalized method of cells (GMC) micromechanics model to create a low-fidelity computationally efficient nonlinear multiscale method with imperfect interfaces between the fiber and matrix, where the interface behavior is adopted from nanoscale MD simulations. This algorithm is used to understand damage mechanisms in adhesively bonded composite joints as a case study for the comprehensive nano to macroscale structural analysis of practical composites structures. At each length scale sources of variability are identified, characterized, and included in the multiscale modeling framework.
ContributorsRai, Ashwin (Author) / Chattopadhyay, Aditi (Thesis advisor) / Dai, Lenore (Committee member) / Jiang, Hanqing (Committee member) / Rajadas, John (Committee member) / Fard, Masoud Yekani (Committee member) / Arizona State University (Publisher)
Created2018
Description
This dissertation presents the development of structural health monitoring and prognostic health management methodologies for complex structures and systems in the field of mechanical engineering. To overcome various challenges historically associated with complex structures and systems such as complicated sensing mechanisms, noisy information, and large-size datasets, a hybrid monitoring framework comprising of solid mechanics concepts and data mining technologies is developed. In such a framework, the solid mechanics simulations provide additional intuitions to data mining techniques reducing the dependence of accuracy on the training set, while the data mining approaches fuse and interpret information from the targeted system enabling the capability for real-time monitoring with efficient computation.
In the case of structural health monitoring, ultrasonic guided waves are utilized for damage identification and localization in complex composite structures. Signal processing and data mining techniques are integrated into the damage localization framework, and the converted wave modes, which are induced by the thickness variation due to the presence of delamination, are used as damage indicators. This framework has been validated through experiments and has shown sufficient accuracy in locating delamination in X-COR sandwich composites without the need of baseline information. Besides the localization of internal damage, the Gaussian process machine learning technique is integrated with finite element method as an online-offline prediction model to predict crack propagation with overloads under biaxial loading conditions; such a probabilistic prognosis model, with limited number of training examples, has shown increased accuracy over state-of-the-art techniques in predicting crack retardation behaviors induced by overloads. In the case of system level management, a monitoring framework built using a multivariate Gaussian model as basis is developed to evaluate the anomalous condition of commercial aircrafts. This method has been validated using commercial airline data and has shown high sensitivity to variations in aircraft dynamics and pilot operations. Moreover, this framework was also tested on simulated aircraft faults and its feasibility for real-time monitoring was demonstrated with sufficient computation efficiency.
This research is expected to serve as a practical addition to the existing literature while possessing the potential to be adopted in realistic engineering applications.
In the case of structural health monitoring, ultrasonic guided waves are utilized for damage identification and localization in complex composite structures. Signal processing and data mining techniques are integrated into the damage localization framework, and the converted wave modes, which are induced by the thickness variation due to the presence of delamination, are used as damage indicators. This framework has been validated through experiments and has shown sufficient accuracy in locating delamination in X-COR sandwich composites without the need of baseline information. Besides the localization of internal damage, the Gaussian process machine learning technique is integrated with finite element method as an online-offline prediction model to predict crack propagation with overloads under biaxial loading conditions; such a probabilistic prognosis model, with limited number of training examples, has shown increased accuracy over state-of-the-art techniques in predicting crack retardation behaviors induced by overloads. In the case of system level management, a monitoring framework built using a multivariate Gaussian model as basis is developed to evaluate the anomalous condition of commercial aircrafts. This method has been validated using commercial airline data and has shown high sensitivity to variations in aircraft dynamics and pilot operations. Moreover, this framework was also tested on simulated aircraft faults and its feasibility for real-time monitoring was demonstrated with sufficient computation efficiency.
This research is expected to serve as a practical addition to the existing literature while possessing the potential to be adopted in realistic engineering applications.
ContributorsLi, Guoyi (Ph.D.) (Author) / Chattopadhyay, Aditi (Thesis advisor) / Mignolet, Marc (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Yekani Fard, Masoud (Committee member) / Jiang, Hanqing (Committee member) / Arizona State University (Publisher)
Created2019