ASU Electronic Theses and Dissertations
This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
Displaying 1 - 10 of 10
Filtering by
- All Subjects: deep learning
- All Subjects: Visual Analytics
- Creators: Davulcu, Hasan
Description
Computer Vision as a eld has gone through signicant changes in the last decade.
The eld has seen tremendous success in designing learning systems with hand-crafted
features and in using representation learning to extract better features. In this dissertation
some novel approaches to representation learning and task learning are studied.
Multiple-instance learning which is generalization of supervised learning, is one
example of task learning that is discussed. In particular, a novel non-parametric k-
NN-based multiple-instance learning is proposed, which is shown to outperform other
existing approaches. This solution is applied to a diabetic retinopathy pathology
detection problem eectively.
In cases of representation learning, generality of neural features are investigated
rst. This investigation leads to some critical understanding and results in feature
generality among datasets. The possibility of learning from a mentor network instead
of from labels is then investigated. Distillation of dark knowledge is used to eciently
mentor a small network from a pre-trained large mentor network. These studies help
in understanding representation learning with smaller and compressed networks.
The eld has seen tremendous success in designing learning systems with hand-crafted
features and in using representation learning to extract better features. In this dissertation
some novel approaches to representation learning and task learning are studied.
Multiple-instance learning which is generalization of supervised learning, is one
example of task learning that is discussed. In particular, a novel non-parametric k-
NN-based multiple-instance learning is proposed, which is shown to outperform other
existing approaches. This solution is applied to a diabetic retinopathy pathology
detection problem eectively.
In cases of representation learning, generality of neural features are investigated
rst. This investigation leads to some critical understanding and results in feature
generality among datasets. The possibility of learning from a mentor network instead
of from labels is then investigated. Distillation of dark knowledge is used to eciently
mentor a small network from a pre-trained large mentor network. These studies help
in understanding representation learning with smaller and compressed networks.
ContributorsVenkatesan, Ragav (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Yang, Yezhou (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2017
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
Machine learning models convert raw data in the form of video, images, audio,
text, etc. into feature representations that are convenient for computational process-
ing. Deep neural networks have proven to be very efficient feature extractors for a
variety of machine learning tasks. Generative models based on deep neural networks
introduce constraints on the feature space to learn transferable and disentangled rep-
resentations. Transferable feature representations help in training machine learning
models that are robust across different distributions of data. For example, with the
application of transferable features in domain adaptation, models trained on a source
distribution can be applied to a data from a target distribution even though the dis-
tributions may be different. In style transfer and image-to-image translation, disen-
tangled representations allow for the separation of style and content when translating
images.
This thesis examines learning transferable data representations in novel deep gen-
erative models. The Semi-Supervised Adversarial Translator (SAT) utilizes adversar-
ial methods and cross-domain weight sharing in a neural network to extract trans-
ferable representations. These transferable interpretations can then be decoded into
the original image or a similar image in another domain. The Explicit Disentangling
Network (EDN) utilizes generative methods to disentangle images into their core at-
tributes and then segments sets of related attributes. The EDN can separate these
attributes by controlling the ow of information using a novel combination of losses
and network architecture. This separation of attributes allows precise modi_cations
to speci_c components of the data representation, boosting the performance of ma-
chine learning tasks. The effectiveness of these models is evaluated across domain
adaptation, style transfer, and image-to-image translation tasks.
text, etc. into feature representations that are convenient for computational process-
ing. Deep neural networks have proven to be very efficient feature extractors for a
variety of machine learning tasks. Generative models based on deep neural networks
introduce constraints on the feature space to learn transferable and disentangled rep-
resentations. Transferable feature representations help in training machine learning
models that are robust across different distributions of data. For example, with the
application of transferable features in domain adaptation, models trained on a source
distribution can be applied to a data from a target distribution even though the dis-
tributions may be different. In style transfer and image-to-image translation, disen-
tangled representations allow for the separation of style and content when translating
images.
This thesis examines learning transferable data representations in novel deep gen-
erative models. The Semi-Supervised Adversarial Translator (SAT) utilizes adversar-
ial methods and cross-domain weight sharing in a neural network to extract trans-
ferable representations. These transferable interpretations can then be decoded into
the original image or a similar image in another domain. The Explicit Disentangling
Network (EDN) utilizes generative methods to disentangle images into their core at-
tributes and then segments sets of related attributes. The EDN can separate these
attributes by controlling the ow of information using a novel combination of losses
and network architecture. This separation of attributes allows precise modi_cations
to speci_c components of the data representation, boosting the performance of ma-
chine learning tasks. The effectiveness of these models is evaluated across domain
adaptation, style transfer, and image-to-image translation tasks.
ContributorsEusebio, Jose Miguel Ang (Author) / Panchanathan, Sethuraman (Thesis advisor) / Davulcu, Hasan (Committee member) / Venkateswara, Hemanth (Committee member) / Arizona State University (Publisher)
Created2018
Description
Fraud is defined as the utilization of deception for illegal gain by hiding the true nature of the activity. While organizations lose around $3.7 trillion in revenue due to financial crimes and fraud worldwide, they can affect all levels of society significantly. In this dissertation, I focus on credit card fraud in online transactions. Every online transaction comes with a fraud risk and it is the merchant's liability to detect and stop fraudulent transactions. Merchants utilize various mechanisms to prevent and manage fraud such as automated fraud detection systems and manual transaction reviews by expert fraud analysts. Many proposed solutions mostly focus on fraud detection accuracy and ignore financial considerations. Also, the highly effective manual review process is overlooked. First, I propose Profit Optimizing Neural Risk Manager (PONRM), a selective classifier that (a) constitutes optimal collaboration between machine learning models and human expertise under industrial constraints, (b) is cost and profit sensitive. I suggest directions on how to characterize fraudulent behavior and assess the risk of a transaction. I show that my framework outperforms cost-sensitive and cost-insensitive baselines on three real-world merchant datasets. While PONRM is able to work with many supervised learners and obtain convincing results, utilizing probability outputs directly from the trained model itself can pose problems, especially in deep learning as softmax output is not a true uncertainty measure. This phenomenon, and the wide and rapid adoption of deep learning by practitioners brought unintended consequences in many situations such as in the infamous case of Google Photos' racist image recognition algorithm; thus, necessitated the utilization of the quantified uncertainty for each prediction. There have been recent efforts towards quantifying uncertainty in conventional deep learning methods (e.g., dropout as Bayesian approximation); however, their optimal use in decision making is often overlooked and understudied. Thus, I present a mixed-integer programming framework for selective classification called MIPSC, that investigates and combines model uncertainty and predictive mean to identify optimal classification and rejection regions. I also extend this framework to cost-sensitive settings (MIPCSC) and focus on the critical real-world problem, online fraud management and show that my approach outperforms industry standard methods significantly for online fraud management in real-world settings.
ContributorsYildirim, Mehmet Yigit (Author) / Davulcu, Hasan (Thesis advisor) / Bakkaloglu, Bertan (Committee member) / Huang, Dijiang (Committee member) / Hsiao, Ihan (Committee member) / Arizona State University (Publisher)
Created2019
Description
Traditionally, visualization is one of the most important and commonly used methods of generating insight into large scale data. Particularly for spatiotemporal data, the translation of such data into a visual form allows users to quickly see patterns, explore summaries and relate domain knowledge about underlying geographical phenomena that would not be apparent in tabular form. However, several critical challenges arise when visualizing and exploring these large spatiotemporal datasets. While, the underlying geographical component of the data lends itself well to univariate visualization in the form of traditional cartographic representations (e.g., choropleth, isopleth, dasymetric maps), as the data becomes multivariate, cartographic representations become more complex. To simplify the visual representations, analytical methods such as clustering and feature extraction are often applied as part of the classification phase. The automatic classification can then be rendered onto a map; however, one common issue in data classification is that items near a classification boundary are often mislabeled.
This thesis explores methods to augment the automated spatial classification by utilizing interactive machine learning as part of the cluster creation step. First, this thesis explores the design space for spatiotemporal analysis through the development of a comprehensive data wrangling and exploratory data analysis platform. Second, this system is augmented with a novel method for evaluating the visual impact of edge cases for multivariate geographic projections. Finally, system features and functionality are demonstrated through a series of case studies, with key features including similarity analysis, multivariate clustering, and novel visual support for cluster comparison.
This thesis explores methods to augment the automated spatial classification by utilizing interactive machine learning as part of the cluster creation step. First, this thesis explores the design space for spatiotemporal analysis through the development of a comprehensive data wrangling and exploratory data analysis platform. Second, this system is augmented with a novel method for evaluating the visual impact of edge cases for multivariate geographic projections. Finally, system features and functionality are demonstrated through a series of case studies, with key features including similarity analysis, multivariate clustering, and novel visual support for cluster comparison.
ContributorsZhang, Yifan (Author) / Maciejewski, Ross (Thesis advisor) / Mack, Elizabeth (Committee member) / Liu, Huan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2016
Description
Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as image retrieval and enhancement, it is more important to rank images based on their aesthetic quality instead of binary-categorizing them. Furthermore, in such applications, it may be possible that all images belong to the same category. Hence determining the aesthetic ranking of the images is more appropriate. To this end, a novel problem of ranking images with respect to their aesthetic quality is formulated in this work. A new data-set of image pairs with relative labels is constructed by carefully selecting images from the popular AVA data-set. Unlike in aesthetics classification, there is no single threshold which would determine the ranking order of the images across the entire data-set.
This problem is attempted using a deep neural network based approach that is trained on image pairs by incorporating principles from relative learning. Results show that such relative training procedure allows the network to rank the images with a higher accuracy than a state-of-art network trained on the same set of images using binary labels. Further analyzing the results show that training a model using the image pairs learnt better aesthetic features than training on same number of individual binary labelled images.
Additionally, an attempt is made at enhancing the performance of the system by incorporating saliency related information. Given an image, humans might fixate their vision on particular parts of the image, which they might be subconsciously intrigued to. I therefore tried to utilize the saliency information both stand-alone as well as in combination with the global and local aesthetic features by performing two separate sets of experiments. In both the cases, a standard saliency model is chosen and the generated saliency maps are convoluted with the images prior to passing them to the network, thus giving higher importance to the salient regions as compared to the remaining. Thus generated saliency-images are either used independently or along with the global and the local features to train the network. Empirical results show that the saliency related aesthetic features might already be learnt by the network as a sub-set of the global features from automatic feature extraction, thus proving the redundancy of the additional saliency module.
This problem is attempted using a deep neural network based approach that is trained on image pairs by incorporating principles from relative learning. Results show that such relative training procedure allows the network to rank the images with a higher accuracy than a state-of-art network trained on the same set of images using binary labels. Further analyzing the results show that training a model using the image pairs learnt better aesthetic features than training on same number of individual binary labelled images.
Additionally, an attempt is made at enhancing the performance of the system by incorporating saliency related information. Given an image, humans might fixate their vision on particular parts of the image, which they might be subconsciously intrigued to. I therefore tried to utilize the saliency information both stand-alone as well as in combination with the global and local aesthetic features by performing two separate sets of experiments. In both the cases, a standard saliency model is chosen and the generated saliency maps are convoluted with the images prior to passing them to the network, thus giving higher importance to the salient regions as compared to the remaining. Thus generated saliency-images are either used independently or along with the global and the local features to train the network. Empirical results show that the saliency related aesthetic features might already be learnt by the network as a sub-set of the global features from automatic feature extraction, thus proving the redundancy of the additional saliency module.
ContributorsGattupalli, Jaya Vijetha (Author) / Li, Baoxin (Thesis advisor) / Davulcu, Hasan (Committee member) / Liang, Jianming (Committee member) / Arizona State University (Publisher)
Created2016
Description
The widespread adoption of computer vision models is often constrained by the issue of domain mismatch. Models that are trained with data belonging to one distribution, perform poorly when tested with data from a different distribution. Variations in vision based data can be attributed to the following reasons, viz., differences in image quality (resolution, brightness, occlusion and color), changes in camera perspective, dissimilar backgrounds and an inherent diversity of the samples themselves. Machine learning techniques like transfer learning are employed to adapt computational models across distributions. Domain adaptation is a special case of transfer learning, where knowledge from a source domain is transferred to a target domain in the form of learned models and efficient feature representations.
The dissertation outlines novel domain adaptation approaches across different feature spaces; (i) a linear Support Vector Machine model for domain alignment; (ii) a nonlinear kernel based approach that embeds domain-aligned data for enhanced classification; (iii) a hierarchical model implemented using deep learning, that estimates domain-aligned hash values for the source and target data, and (iv) a proposal for a feature selection technique to reduce cross-domain disparity. These adaptation procedures are tested and validated across a range of computer vision applications like object classification, facial expression recognition, digit recognition, and activity recognition. The dissertation also provides a unique perspective of domain adaptation literature from the point-of-view of linear, nonlinear and hierarchical feature spaces. The dissertation concludes with a discussion on the future directions for research that highlight the role of domain adaptation in an era of rapid advancements in artificial intelligence.
The dissertation outlines novel domain adaptation approaches across different feature spaces; (i) a linear Support Vector Machine model for domain alignment; (ii) a nonlinear kernel based approach that embeds domain-aligned data for enhanced classification; (iii) a hierarchical model implemented using deep learning, that estimates domain-aligned hash values for the source and target data, and (iv) a proposal for a feature selection technique to reduce cross-domain disparity. These adaptation procedures are tested and validated across a range of computer vision applications like object classification, facial expression recognition, digit recognition, and activity recognition. The dissertation also provides a unique perspective of domain adaptation literature from the point-of-view of linear, nonlinear and hierarchical feature spaces. The dissertation concludes with a discussion on the future directions for research that highlight the role of domain adaptation in an era of rapid advancements in artificial intelligence.
ContributorsDemakethepalli Venkateswara, Hemanth (Author) / Panchanathan, Sethuraman (Thesis advisor) / Li, Baoxin (Committee member) / Davulcu, Hasan (Committee member) / Ye, Jieping (Committee member) / Chakraborty, Shayok (Committee member) / Arizona State University (Publisher)
Created2017
Description
The connections between different entities define different kinds of networks, and many such networked phenomena are influenced by their underlying geographical relationships. By integrating network and geospatial analysis, the goal is to extract information about interaction topologies and the relationships to related geographical constructs. In the recent decades, much work has been done analyzing the dynamics of spatial networks; however, many challenges still remain in this field. First, the development of social media and transportation technologies has greatly reshaped the typologies of communications between different geographical regions. Second, the distance metrics used in spatial analysis should also be enriched with the underlying network information to develop accurate models.
Visual analytics provides methods for data exploration, pattern recognition, and knowledge discovery. However, despite the long history of geovisualizations and network visual analytics, little work has been done to develop visual analytics tools that focus specifically on geographically networked phenomena. This thesis develops a variety of visualization methods to present data values and geospatial network relationships, which enables users to interactively explore the data. Users can investigate the connections in both virtual networks and geospatial networks and the underlying geographical context can be used to improve knowledge discovery. The focus of this thesis is on social media analysis and geographical hotspots optimization. A framework is proposed for social network analysis to unveil the links between social media interactions and their underlying networked geospatial phenomena. This will be combined with a novel hotspot approach to improve hotspot identification and boundary detection with the networks extracted from urban infrastructure. Several real world problems have been analyzed using the proposed visual analytics frameworks. The primary studies and experiments show that visual analytics methods can help analysts explore such data from multiple perspectives and help the knowledge discovery process.
Visual analytics provides methods for data exploration, pattern recognition, and knowledge discovery. However, despite the long history of geovisualizations and network visual analytics, little work has been done to develop visual analytics tools that focus specifically on geographically networked phenomena. This thesis develops a variety of visualization methods to present data values and geospatial network relationships, which enables users to interactively explore the data. Users can investigate the connections in both virtual networks and geospatial networks and the underlying geographical context can be used to improve knowledge discovery. The focus of this thesis is on social media analysis and geographical hotspots optimization. A framework is proposed for social network analysis to unveil the links between social media interactions and their underlying networked geospatial phenomena. This will be combined with a novel hotspot approach to improve hotspot identification and boundary detection with the networks extracted from urban infrastructure. Several real world problems have been analyzed using the proposed visual analytics frameworks. The primary studies and experiments show that visual analytics methods can help analysts explore such data from multiple perspectives and help the knowledge discovery process.
ContributorsWang, Feng (Author) / Maciejewski, Ross (Thesis advisor) / Davulcu, Hasan (Committee member) / Grubesic, Anthony (Committee member) / Shakarian, Paulo (Committee member) / Arizona State University (Publisher)
Created2017
Description
Causality analysis is the process of identifying cause-effect relationships among variables. This process is challenging because causal relationships cannot be tested solely based on statistical indicators as additional information is always needed to reduce the ambiguity caused by factors beyond those covered by the statistical test. Traditionally, controlled experiments are carried out to identify causal relationships, but recently there is a growing interest in causality analysis with observational data due to the increasing availability of data and tools. This type of analysis will often involve automatic algorithms that extract causal relations from large amounts of data and rely on expert judgment to scrutinize and verify the relations. Over-reliance on these automatic algorithms is dangerous because models trained on observational data are susceptible to bias that can be difficult to spot even with expert oversight. Visualization has proven to be effective at bridging the gap between human experts and statistical models by enabling an interactive exploration and manipulation of the data and models. This thesis develops a visual analytics framework to support the interaction between human experts and automatic models in causality analysis. Three case studies were conducted to demonstrate the application of the visual analytics framework in which feature engineering, insight generation, correlation analysis, and causality inspections were showcased.
ContributorsWang, Hong, Ph.D (Author) / Maciejewski, Ross (Thesis advisor) / He, Jingrui (Committee member) / Davulcu, Hasan (Committee member) / Thies, Cameron (Committee member) / Arizona State University (Publisher)
Created2019
Description
Animal pose estimation (APE) is utilized in preclinical research settings for various neurological disorders such as Parkinson's disease (PD), Huntington's disease (HD) and multiple sclerosis. The technique includes real-time scoring of impairment in the animals during testing or video recording. This is a time-consuming operation prone to errors due to visual fatigue. To overcome these shortcomings, APE automation by deep learning has been studied. The field of APE has gone through significant development backed by improvements in deep learning techniques. These developments have improved 2D and 3D pose estimation, 3D mesh reconstruction and behavior prediction capabilities. As a result, there are numerous sophisticated tools and datasets available today. Despite these developments, APE still lags behind human observer scoring with respect to accuracy and flexibility under complex scenarios. In this project, two critical challenges are being addressed within the context of neurological research focusing on PD. The first challenge is about the lack of comprehensive diverse datasets necessary for accurate training as well as for fine-tuning deep learning models. This is compounded by the inherent difficulty in working with uncooperative rodent subjects, whose unpredictable behaviors often impede reliable data collection. The second challenge focuses on reduction in variation of scores that result from being scored by different evaluators. This will also involve tackling bias and reducing human error for the purpose of reliable and accurate assessments. In order to address these issues, systematic data collection and deep learning in APE have been utilized to automate manual scoring procedures. This project will contribute to neurological research, particularly in understanding and treating disorders like PD. The goal is to improve methods used in assessing rodent behavior which could aid in developing effective therapeutics. The successful implementation of an automated scoring mechanism could set a new standard in neurological research, offering insights and methodologies that are more accurate and reliable.
ContributorsJanapareddi, Ajay Kumar (Author) / Davulcu, Hasan (Thesis advisor) / Poste, George (Thesis advisor) / Kelley, Christy (Committee member) / Arizona State University (Publisher)
Created2024