Matching Items (158)
Filtering by
- All Subjects: Computer Science
- All Subjects: Twitter
- Creators: Davulcu, Hasan
Description
Multi-tenancy architecture (MTA) is often used in Software-as-a-Service (SaaS) and
the central idea is that multiple tenant applications can be developed using compo
nents stored in the SaaS infrastructure. Recently, MTA has been extended where
a tenant application can have its own sub-tenants as the tenant application acts
like a SaaS infrastructure. In other words, MTA is extended to STA (Sub-Tenancy
Architecture ). In STA, each tenant application not only need to develop its own
functionalities, but also need to prepare an infrastructure to allow its sub-tenants to
develop customized applications. This dissertation formulates eight models for STA,
and proposes a Variant Point based customization model to help tenants and sub
tenants customize tenant and sub-tenant applications. In addition, this dissertation
introduces Crowd- sourcing to become the core of STA component development life
cycle. To discover fit tenant developers or components to help building and com
posing new components, dynamic and static ranking models are proposed. Further,
rank computation architecture is presented to deal with the case when the number of
tenants and components becomes huge. At last, an experiment is performed to prove
rank models and the rank computation architecture work as design.
the central idea is that multiple tenant applications can be developed using compo
nents stored in the SaaS infrastructure. Recently, MTA has been extended where
a tenant application can have its own sub-tenants as the tenant application acts
like a SaaS infrastructure. In other words, MTA is extended to STA (Sub-Tenancy
Architecture ). In STA, each tenant application not only need to develop its own
functionalities, but also need to prepare an infrastructure to allow its sub-tenants to
develop customized applications. This dissertation formulates eight models for STA,
and proposes a Variant Point based customization model to help tenants and sub
tenants customize tenant and sub-tenant applications. In addition, this dissertation
introduces Crowd- sourcing to become the core of STA component development life
cycle. To discover fit tenant developers or components to help building and com
posing new components, dynamic and static ranking models are proposed. Further,
rank computation architecture is presented to deal with the case when the number of
tenants and components becomes huge. At last, an experiment is performed to prove
rank models and the rank computation architecture work as design.
ContributorsZhong, Peide (Author) / Davulcu, Hasan (Thesis advisor) / Sarjoughian, Hessam S. (Committee member) / Huang, Dijiang (Committee member) / Tsai, Wei-Tek (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
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
Online learning platforms such as massive online open courses (MOOCs) and
intelligent tutoring systems (ITSs) have made learning more accessible and personalized. These systems generate unprecedented amounts of behavioral data and open the way for predicting students’ future performance based on their behavior, and for assessing their strengths and weaknesses in learning.
This thesis attempts to mine students’ working patterns using a programming problem solving system, and build predictive models to estimate students’ learning. QuizIT, a programming solving system, was used to collect students’ problem-solving activities from a lower-division computer science programming course in 2016 Fall semester. Differential mining techniques were used to extract frequent patterns based on each activity provided details about question’s correctness, complexity, topic, and time to represent students’ behavior. These patterns were further used to build classifiers to predict students’ performances.
Seven main learning behaviors were discovered based on these patterns, which provided insight into students’ metacognitive skills and thought processes. Besides predicting students’ performance group, the classification models also helped in finding important behaviors which were crucial in determining a student’s positive or negative performance throughout the semester.
intelligent tutoring systems (ITSs) have made learning more accessible and personalized. These systems generate unprecedented amounts of behavioral data and open the way for predicting students’ future performance based on their behavior, and for assessing their strengths and weaknesses in learning.
This thesis attempts to mine students’ working patterns using a programming problem solving system, and build predictive models to estimate students’ learning. QuizIT, a programming solving system, was used to collect students’ problem-solving activities from a lower-division computer science programming course in 2016 Fall semester. Differential mining techniques were used to extract frequent patterns based on each activity provided details about question’s correctness, complexity, topic, and time to represent students’ behavior. These patterns were further used to build classifiers to predict students’ performances.
Seven main learning behaviors were discovered based on these patterns, which provided insight into students’ metacognitive skills and thought processes. Besides predicting students’ performance group, the classification models also helped in finding important behaviors which were crucial in determining a student’s positive or negative performance throughout the semester.
ContributorsMandal, Partho Pratim (Author) / Hsiao, I-Han (Thesis advisor) / Davulcu, Hasan (Committee member) / Tong, Hanghang (Committee member) / Arizona State University (Publisher)
Created2017
Description
Online social networks are the hubs of social activity in cyberspace, and using them to exchange knowledge, experiences, and opinions is common. In this work, an advanced topic modeling framework is designed to analyse complex longitudinal health information from social media with minimal human annotation, and Adverse Drug Events and Reaction (ADR) information is extracted and automatically processed by using a biased topic modeling method. This framework improves and extends existing topic modelling algorithms that incorporate background knowledge. Using this approach, background knowledge such as ADR terms and other biomedical knowledge can be incorporated during the text mining process, with scores which indicate the presence of ADR being generated. A case control study has been performed on a data set of twitter timelines of women that announced their pregnancy, the goals of the study is to compare the ADR risk of medication usage from each medication category during the pregnancy.
In addition, to evaluate the prediction power of this approach, another important aspect of personalized medicine was addressed: the prediction of medication usage through the identification of risk groups. During the prediction process, the health information from Twitter timeline, such as diseases, symptoms, treatments, effects, and etc., is summarized by the topic modelling processes and the summarization results is used for prediction. Dimension reduction and topic similarity measurement are integrated into this framework for timeline classification and prediction. This work could be applied to provide guidelines for FDA drug risk categories. Currently, this process is done based on laboratory results and reported cases.
Finally, a multi-dimensional text data warehouse (MTD) to manage the output from the topic modelling is proposed. Some attempts have been also made to incorporate topic structure (ontology) and the MTD hierarchy. Results demonstrate that proposed methods show promise and this system represents a low-cost approach for drug safety early warning.
In addition, to evaluate the prediction power of this approach, another important aspect of personalized medicine was addressed: the prediction of medication usage through the identification of risk groups. During the prediction process, the health information from Twitter timeline, such as diseases, symptoms, treatments, effects, and etc., is summarized by the topic modelling processes and the summarization results is used for prediction. Dimension reduction and topic similarity measurement are integrated into this framework for timeline classification and prediction. This work could be applied to provide guidelines for FDA drug risk categories. Currently, this process is done based on laboratory results and reported cases.
Finally, a multi-dimensional text data warehouse (MTD) to manage the output from the topic modelling is proposed. Some attempts have been also made to incorporate topic structure (ontology) and the MTD hierarchy. Results demonstrate that proposed methods show promise and this system represents a low-cost approach for drug safety early warning.
ContributorsYang, Jian (Author) / Gonzalez, Graciela (Thesis advisor) / Davulcu, Hasan (Thesis advisor) / Liu, Huan (Committee member) / Papotti, Paolo (Committee member) / Arizona State University (Publisher)
Created2017
Description
In this research, I try to solve multi-class multi-label classication problem, where
the goal is to automatically assign one or more labels(tags) to discussion topics seen
in deepweb. I observed natural hierarchy in our dataset, and I used dierent
techniques to ensure hierarchical integrity constraint on the predicted tag list. To
solve `class imbalance' and `scarcity of labeled data' problems, I developed semisupervised
model based on elastic search(ES) document relevance score. I evaluate
our models using standard K-fold cross-validation method. Ensuring hierarchical
integrity constraints improved F1 score by 11.9% over standard supervised learning,
while our ES based semi-supervised learning model out-performed other models in
terms of precision(78.4%) score while maintaining comparable recall(21%) score.
the goal is to automatically assign one or more labels(tags) to discussion topics seen
in deepweb. I observed natural hierarchy in our dataset, and I used dierent
techniques to ensure hierarchical integrity constraint on the predicted tag list. To
solve `class imbalance' and `scarcity of labeled data' problems, I developed semisupervised
model based on elastic search(ES) document relevance score. I evaluate
our models using standard K-fold cross-validation method. Ensuring hierarchical
integrity constraints improved F1 score by 11.9% over standard supervised learning,
while our ES based semi-supervised learning model out-performed other models in
terms of precision(78.4%) score while maintaining comparable recall(21%) score.
ContributorsPatil, Revanth (Author) / Shakarian, Paulo (Thesis advisor) / Doupe, Adam (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2018
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
This research start utilizing an efficient sparse inverse covariance matrix (precision matrix) estimation technique to identify a set of highly correlated discriminative perspectives between radical and counter-radical groups. A ranking system has been developed that utilizes ranked perspectives to map Islamic organizations on a set of socio-cultural, political and behavioral scales based on their web site corpus. Simultaneously, a gold standard ranking of these organizations was created through domain experts and compute expert-to-expert agreements and present experimental results comparing the performance of the QUIC based scaling system to another baseline method for organizations. The QUIC based algorithm not only outperforms the baseline methods, but it is also the only system that consistently performs at area expert-level accuracies for all scales. Also, a multi-scale ideological model has been developed and it investigates the correlates of Islamic extremism in Indonesia, Nigeria and UK. This analysis demonstrate that violence does not correlate strongly with broad Muslim theological or sectarian orientations; it shows that religious diversity intolerance is the only consistent and statistically significant ideological correlate of Islamic extremism in these countries, alongside desire for political change in UK and Indonesia, and social change in Nigeria. Next, dynamic issues and communities tracking system based on NMF(Non-negative Matrix Factorization) co-clustering algorithm has been built to better understand the dynamics of virtual communities. The system used between Iran and Saudi Arabia to build and apply a multi-party agent-based model that can demonstrate the role of wedges and spoilers in a complex environment where coalitions are dynamic. Lastly, a visual intelligence platform for tracking the diffusion of online social movements has been developed called LookingGlass to track the geographical footprint, shifting positions and flows of individuals, topics and perspectives between groups. The algorithm utilize large amounts of text collected from a wide variety of organizations’ media outlets to discover their hotly debated topics, and their discriminative perspectives voiced by opposing camps organized into multiple scales. Discriminating perspectives is utilized to classify and map individual Tweeter’s message content to social movements based on the perspectives expressed in their tweets.
ContributorsKim, Nyunsu (Author) / Davulcu, Hasan (Thesis advisor) / Sen, Arunabha (Committee member) / Hsiao, Sharon (Committee member) / Corman, Steven (Committee member) / Arizona State University (Publisher)
Created2018
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
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