Matching Items (1,136)
Filtering by

Clear all filters

151689-Thumbnail Image.png
Description
Sparsity has become an important modeling tool in areas such as genetics, signal and audio processing, medical image processing, etc. Via the penalization of l-1 norm based regularization, the structured sparse learning algorithms can produce highly accurate models while imposing various predefined structures on the data, such as feature groups

Sparsity has become an important modeling tool in areas such as genetics, signal and audio processing, medical image processing, etc. Via the penalization of l-1 norm based regularization, the structured sparse learning algorithms can produce highly accurate models while imposing various predefined structures on the data, such as feature groups or graphs. In this thesis, I first propose to solve a sparse learning model with a general group structure, where the predefined groups may overlap with each other. Then, I present three real world applications which can benefit from the group structured sparse learning technique. In the first application, I study the Alzheimer's Disease diagnosis problem using multi-modality neuroimaging data. In this dataset, not every subject has all data sources available, exhibiting an unique and challenging block-wise missing pattern. In the second application, I study the automatic annotation and retrieval of fruit-fly gene expression pattern images. Combined with the spatial information, sparse learning techniques can be used to construct effective representation of the expression images. In the third application, I present a new computational approach to annotate developmental stage for Drosophila embryos in the gene expression images. In addition, it provides a stage score that enables one to more finely annotate each embryo so that they are divided into early and late periods of development within standard stage demarcations. Stage scores help us to illuminate global gene activities and changes much better, and more refined stage annotations improve our ability to better interpret results when expression pattern matches are discovered between genes.
ContributorsYuan, Lei (Author) / Ye, Jieping (Thesis advisor) / Wang, Yalin (Committee member) / Xue, Guoliang (Committee member) / Kumar, Sudhir (Committee member) / Arizona State University (Publisher)
Created2013
151716-Thumbnail Image.png
Description
The rapid escalation of technology and the widespread emergence of modern technological equipments have resulted in the generation of humongous amounts of digital data (in the form of images, videos and text). This has expanded the possibility of solving real world problems using computational learning frameworks. However, while gathering a

The rapid escalation of technology and the widespread emergence of modern technological equipments have resulted in the generation of humongous amounts of digital data (in the form of images, videos and text). This has expanded the possibility of solving real world problems using computational learning frameworks. However, while gathering a large amount of data is cheap and easy, annotating them with class labels is an expensive process in terms of time, labor and human expertise. This has paved the way for research in the field of active learning. Such algorithms automatically select the salient and exemplar instances from large quantities of unlabeled data and are effective in reducing human labeling effort in inducing classification models. To utilize the possible presence of multiple labeling agents, there have been attempts towards a batch mode form of active learning, where a batch of data instances is selected simultaneously for manual annotation. This dissertation is aimed at the development of novel batch mode active learning algorithms to reduce manual effort in training classification models in real world multimedia pattern recognition applications. Four major contributions are proposed in this work: $(i)$ a framework for dynamic batch mode active learning, where the batch size and the specific data instances to be queried are selected adaptively through a single formulation, based on the complexity of the data stream in question, $(ii)$ a batch mode active learning strategy for fuzzy label classification problems, where there is an inherent imprecision and vagueness in the class label definitions, $(iii)$ batch mode active learning algorithms based on convex relaxations of an NP-hard integer quadratic programming (IQP) problem, with guaranteed bounds on the solution quality and $(iv)$ an active matrix completion algorithm and its application to solve several variants of the active learning problem (transductive active learning, multi-label active learning, active feature acquisition and active learning for regression). These contributions are validated on the face recognition and facial expression recognition problems (which are commonly encountered in real world applications like robotics, security and assistive technology for the blind and the visually impaired) and also on collaborative filtering applications like movie recommendation.
ContributorsChakraborty, Shayok (Author) / Panchanathan, Sethuraman (Thesis advisor) / Balasubramanian, Vineeth N. (Committee member) / Li, Baoxin (Committee member) / Mittelmann, Hans (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
151718-Thumbnail Image.png
Description
The increasing popularity of Twitter renders improved trustworthiness and relevance assessment of tweets much more important for search. However, given the limitations on the size of tweets, it is hard to extract measures for ranking from the tweet's content alone. I propose a method of ranking tweets by generating a

The increasing popularity of Twitter renders improved trustworthiness and relevance assessment of tweets much more important for search. However, given the limitations on the size of tweets, it is hard to extract measures for ranking from the tweet's content alone. I propose a method of ranking tweets by generating a reputation score for each tweet that is based not just on content, but also additional information from the Twitter ecosystem that consists of users, tweets, and the web pages that tweets link to. This information is obtained by modeling the Twitter ecosystem as a three-layer graph. The reputation score is used to power two novel methods of ranking tweets by propagating the reputation over an agreement graph based on tweets' content similarity. Additionally, I show how the agreement graph helps counter tweet spam. An evaluation of my method on 16~million tweets from the TREC 2011 Microblog Dataset shows that it doubles the precision over baseline Twitter Search and achieves higher precision than current state of the art method. I present a detailed internal empirical evaluation of RAProp in comparison to several alternative approaches proposed by me, as well as external evaluation in comparison to the current state of the art method.
ContributorsRavikumar, Srijith (Author) / Kambhampati, Subbarao (Thesis advisor) / Davulcu, Hasan (Committee member) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2013
152234-Thumbnail Image.png
Description
One of the main challenges in planetary robotics is to traverse the shortest path through a set of waypoints. The shortest distance between any two waypoints is a direct linear traversal. Often times, there are physical restrictions that prevent a rover form traversing straight to a waypoint. Thus, knowledge of

One of the main challenges in planetary robotics is to traverse the shortest path through a set of waypoints. The shortest distance between any two waypoints is a direct linear traversal. Often times, there are physical restrictions that prevent a rover form traversing straight to a waypoint. Thus, knowledge of the terrain is needed prior to traversal. The Digital Terrain Model (DTM) provides information about the terrain along with waypoints for the rover to traverse. However, traversing a set of waypoints linearly is burdensome, as the rovers would constantly need to modify their orientation as they successively approach waypoints. Although there are various solutions to this problem, this research paper proposes the smooth traversability of the rover using splines as a quick and easy implementation to traverse a set of waypoints. In addition, a rover was used to compare the smoothness of the linear traversal along with the spline interpolations. The data collected illustrated that spline traversals had a less rate of change in the velocity over time, indicating that the rover performed smoother than with linear paths.
ContributorsKamasamudram, Anurag (Author) / Saripalli, Srikanth (Thesis advisor) / Fainekos, Georgios (Thesis advisor) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
152236-Thumbnail Image.png
Description
Continuous Delivery, as one of the youngest and most popular member of agile model family, has become a popular concept and method in software development industry recently. Instead of the traditional software development method, which requirements and solutions must be fixed before starting software developing, it promotes adaptive planning, evolutionary

Continuous Delivery, as one of the youngest and most popular member of agile model family, has become a popular concept and method in software development industry recently. Instead of the traditional software development method, which requirements and solutions must be fixed before starting software developing, it promotes adaptive planning, evolutionary development and delivery, and encourages rapid and flexible response to change. However, several problems prevent Continuous Delivery to be introduced into education world. Taking into the consideration of the barriers, we propose a new Cloud based Continuous Delivery Software Developing System. This system is designed to fully utilize the whole life circle of software developing according to Continuous Delivery concepts in a virtualized environment in Vlab platform.
ContributorsDeng, Yuli (Author) / Huang, Dijiang (Thesis advisor) / Davulcu, Hasan (Committee member) / Chen, Yinong (Committee member) / Arizona State University (Publisher)
Created2013
152196-Thumbnail Image.png
Description
Objectives: Although childhood obesity has received growing attention, parents still fail to recognize overweight and obesity in their children. Accurate identification of overweight or obesity in their child is associated with the parent's responsiveness to interventions aimed at preventing weight-related health issues. Recent research shows that a child's age and

Objectives: Although childhood obesity has received growing attention, parents still fail to recognize overweight and obesity in their children. Accurate identification of overweight or obesity in their child is associated with the parent's responsiveness to interventions aimed at preventing weight-related health issues. Recent research shows that a child's age and gender are associated with parental misperception of their child's weight status, but little is known about the interaction of these factors across various age groups. This study examined the association between a wide range of parent, child, and household factors and the accuracy of parental perception of their child's body weight status compared to parent-measured body weight status. Methods: Data were collected from a random-digit-dial telephone survey of 1708 households located in five low-income New Jersey cities with large minority populations. A subset of 548 children whose parents completed the survey and returned a worksheet of parent-measured heights and weights were the focus of the analysis. Bivariate and multivariate analyses were performed to determine the factors significantly associated with parental perception of their child's body weight status. Results: Based on parent-measure heights and weights, 36% of the children were overweight or obese (OWOB). Only 21% of OWOB children were perceived by their parents as OWOB. Child gender, child body mass index (BMI) and parent BMI were significant independent predictors of parents' accuracy at perceiving their child's body weight status. Conclusion: Boys, OWOB children, and children of OWOB parents had significantly greater odds of parental underestimation of their body weight status. Parents had better recognition of OWOB in their daughters, especially older daughters, than in their sons, suggesting parental gender bias in identifying OWOB in children. Further research is needed regarding parental gender bias and its implications in OWOB identification in children.
ContributorsBader, Wendy (Author) / Ohri-Vachaspati, Punam (Thesis advisor) / Lloyd, Kristen (Committee member) / Crespo, Noe (Committee member) / Arizona State University (Publisher)
Created2013
152175-Thumbnail Image.png
Description
Objectives Through a cross-sectional observational study, this thesis evaluates the relationship between food insecurity and weight status, eating behaviors, the home food environment, meal planning and preparation, and perceived stress as it relates to predominantly Hispanic/Latino parents in Phoenix, Arizona. The purpose of this study was to address gaps in

Objectives Through a cross-sectional observational study, this thesis evaluates the relationship between food insecurity and weight status, eating behaviors, the home food environment, meal planning and preparation, and perceived stress as it relates to predominantly Hispanic/Latino parents in Phoenix, Arizona. The purpose of this study was to address gaps in the literature by examining differences in "healthy" and "unhealthy" eating behaviors, foods available in the home, how time and low energy impact meal preparation, and the level of stress between food security groups. Methods Parents, 18 years or older, were recruited during two pre-scheduled health fairs, from English as a second language classes, or from the Women, Infants, and Children's clinic at a local community center, Golden Gate Community Center, in Phoenix, Arizona. An interview, electronic, or paper survey were offered in either Spanish or English to collect data on the variables described above. In addition to the survey, height and weight were collected for all participants to determine BMI and weight status. One hundred and sixty participants were recruited. Multivariate linear and logistic regression models, adjusting for weight status, education, race/ethnicity, income level, and years residing in the U.S., were used to assess the relationship between food security status and weight status, eating behaviors, the home food environment, meal planning and preparation, and perceived stress. Results Results concluded that food insecurity was more prevalent among parents reporting lower income levels compared to higher income levels (p=0.017). In adjusted models, higher perceived cost of fruits (p=0.004) and higher perceived level of stress (p=0.001) were associated with food insecurity. Given that the sample population was predominately women, a post-hoc analysis was completed on women only. In addition to the two significant results noted in the adjusted analyses, the women-only analysis revealed that food insecure mothers reported lower amounts of vegetables served with meals (p=0.019) and higher use of fast-food when tired or running late (p=0.043), compared to food secure mothers. Conclusion Additional studies are needed to further assess differences in stress levels between food insecure parents and food insecure parents, with special consideration for directionality and its relationship to weight status.
ContributorsVillanova, Christina (Author) / Bruening, Meg (Thesis advisor) / Ohri-Vachaspati, Punam (Committee member) / Vega-Lopez, Sonia (Committee member) / Arizona State University (Publisher)
Created2014
152179-Thumbnail Image.png
Description
As the complexity of robotic systems and applications grows rapidly, development of high-performance, easy to use, and fully integrated development environments for those systems is inevitable. Model-Based Design (MBD) of dynamic systems using engineering software such as Simulink® from MathWorks®, SciCos from Metalau team and SystemModeler® from Wolfram® is quite

As the complexity of robotic systems and applications grows rapidly, development of high-performance, easy to use, and fully integrated development environments for those systems is inevitable. Model-Based Design (MBD) of dynamic systems using engineering software such as Simulink® from MathWorks®, SciCos from Metalau team and SystemModeler® from Wolfram® is quite popular nowadays. They provide tools for modeling, simulation, verification and in some cases automatic code generation for desktop applications, embedded systems and robots. For real-world implementation of models on the actual hardware, those models should be converted into compilable machine code either manually or automatically. Due to the complexity of robotic systems, manual code translation from model to code is not a feasible optimal solution so we need to move towards automated code generation for such systems. MathWorks® offers code generation facilities called Coder® products for this purpose. However in order to fully exploit the power of model-based design and code generation tools for robotic applications, we need to enhance those software systems by adding and modifying toolboxes, files and other artifacts as well as developing guidelines and procedures. In this thesis, an effort has been made to propose a guideline as well as a Simulink® library, StateFlow® interface API and a C/C++ interface API to complete this toolchain for NAO humanoid robots. Thus the model of the hierarchical control architecture can be easily and properly converted to code and built for implementation.
ContributorsRaji Kermani, Ramtin (Author) / Fainekos, Georgios (Thesis advisor) / Lee, Yann-Hang (Committee member) / Sarjoughian, Hessam S. (Committee member) / Arizona State University (Publisher)
Created2013
152180-Thumbnail Image.png
Description
Fruit and vegetable (FV) consumption continues to lag far behind US Department of Agriculture (USDA) recommendations. Interventions targeting individuals' dietary behaviors address only a small fraction of dietary influences. Changing the food environment by increasing availability of and excitement for FV through local food production has shown promise as a

Fruit and vegetable (FV) consumption continues to lag far behind US Department of Agriculture (USDA) recommendations. Interventions targeting individuals' dietary behaviors address only a small fraction of dietary influences. Changing the food environment by increasing availability of and excitement for FV through local food production has shown promise as a method for enhancing intake. However, the extent to which local production is sufficient to meet recommended FV intakes, or actual intakes, of specific populations remains largely unconsidered. This study was the first of its kind to evaluate the capacity to support FV intake of Arizona's population with statewide production of FV. We created a model to evaluate what percentage of Dietary Guidelines for Americans (DGA) recommendations, as well as actual consumption, state-level FV production could meet in a given year. Intake and production figures were amended to include estimates of only fresh, non-tropical FV. Production was then estimated by month and season to illustrate fluctuations in availability of FV. Based on our algorithm, Arizona production met 184.5% of aggregate fresh vegetable recommendations, as well as 351.9% of estimated intakes of Arizonans, but met only 29.7% of recommended and 47.8% of estimated intake of fresh, non-tropical fruit. Much of the excess vegetable production can be attributed to the dark-green vegetable sub-group category, which could meet 3204.6% and 3160% of Arizonans' aggregated recommendations and estimated intakes, respectively. Only minimal seasonal variations in the total fruit and total vegetable categories were found, but production of the five vegetable sub-groups varied between the warm and cool seasons by 19-98%. For example, in the starchy vegetable group, cool season (October to March) production met only 3.6% of recommendations, but warm season (April to November) production supplied 196.5% of recommendations. Results indicate that Arizona agricultural production has the capacity to meet a large proportion of the population's FV needs throughout much of the year, while at the same time remaining a major producer of dark-green vegetables for out-of-state markets.
ContributorsVaudrin, Nicole (Author) / Wharton, Christopher (Christopher Mack), 1977- (Thesis advisor) / Bruening, Meg (Thesis advisor) / Ohri-Vachaspati, Punam (Committee member) / Villalobos, J. Rene (Committee member) / Arizona State University (Publisher)
Created2013
152092-Thumbnail Image.png
Description
In recent years, overall consumption of meat products has been decreasing, and at the same time vegetarianism is on the rise. A variety of factors are likely driving changes in consumers' attitudes towards, and consumption of, meat products. Although concern regarding animal welfare may contribute to these trends, growing consumer

In recent years, overall consumption of meat products has been decreasing, and at the same time vegetarianism is on the rise. A variety of factors are likely driving changes in consumers' attitudes towards, and consumption of, meat products. Although concern regarding animal welfare may contribute to these trends, growing consumer interest in the roles that production and processing of meat play in terms of environmental degradation could also impact individuals' decisions about the inclusion of meat in their diets. Because these factors could be related to moral attitudes as well, the purpose of this study was to explore the relations among meat consumption, general environmental attitudes, and moral `foundations' of decision-making, including concern about minimizing `harm' and maximizing `care,' as well as issues of `purity' and `sanctity.' A survey was conducted among current college students using the New Ecological Paradigm scale and the Moral Foundations Questionnaire to assess environmental and moral attitudes. A food frequency questionnaire was used to assess meat consumption. Multiple linear regression analyses explored the relations of environmental and moral attitudes with meat consumption, controlling for potential confounding variables. The results showed no significant correlations among meat consumption, environmental attitudes or moral foundations of harm/care and purity/sanctity.
ContributorsSpringer, LeeAnn (Author) / Wharton, Christopher (Christopher Mack), 1977- (Thesis advisor) / Hekler, Eric (Thesis advisor) / Ohri-Vachaspati, Punam (Committee member) / Hall, Rick (Committee member) / Arizona State University (Publisher)
Created2013