Matching Items (111)
Description
The rapid growth of social media in recent years provides a large amount of user-generated visual objects, e.g., images and videos. Advanced semantic understanding approaches on such visual objects are desired to better serve applications such as human-machine interaction, image retrieval, etc. Semantic visual attributes have been proposed and utilized in multiple visual computing tasks to bridge the so-called "semantic gap" between extractable low-level feature representations and high-level semantic understanding of the visual objects.
Despite years of research, there are still some unsolved problems on semantic attribute learning. First, real-world applications usually involve hundreds of attributes which requires great effort to acquire sufficient amount of labeled data for model learning. Second, existing attribute learning work for visual objects focuses primarily on images, with semantic analysis on videos left largely unexplored.
In this dissertation I conduct innovative research and propose novel approaches to tackling the aforementioned problems. In particular, I propose robust and accurate learning frameworks on both attribute ranking and prediction by exploring the correlation among multiple attributes and utilizing various types of label information. Furthermore, I propose a video-based skill coaching framework by extending attribute learning to the video domain for robust motion skill analysis. Experiments on various types of applications and datasets and comparisons with multiple state-of-the-art baseline approaches confirm that my proposed approaches can achieve significant performance improvements for the general attribute learning problem.
Despite years of research, there are still some unsolved problems on semantic attribute learning. First, real-world applications usually involve hundreds of attributes which requires great effort to acquire sufficient amount of labeled data for model learning. Second, existing attribute learning work for visual objects focuses primarily on images, with semantic analysis on videos left largely unexplored.
In this dissertation I conduct innovative research and propose novel approaches to tackling the aforementioned problems. In particular, I propose robust and accurate learning frameworks on both attribute ranking and prediction by exploring the correlation among multiple attributes and utilizing various types of label information. Furthermore, I propose a video-based skill coaching framework by extending attribute learning to the video domain for robust motion skill analysis. Experiments on various types of applications and datasets and comparisons with multiple state-of-the-art baseline approaches confirm that my proposed approaches can achieve significant performance improvements for the general attribute learning problem.
ContributorsChen, Lin (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Wang, Yalin (Committee member) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2016
Description
This dissertation examines the various factors and processes that have been proposed as explanations for the spread of agriculture in the west Mediterranean. The expansion of the Neolithic in the west Mediterranean (the Impresso-Cardial Neolithic) is characterized by a rapid spread of agricultural subsistence and material culture from the southern portion of the Italian peninsula to the western coast of the Iberian peninsula. To address this unique case, four conceptual models of Neolithic spread have been proposed: the Wave of Advance, the Capillary Spread Model, the Maritime Pioneer Colonization Model and the Dual Model. An agent-based model, the Cardial Spread Model, was built to simulate each conceptual spread model in a spatially explicit environment for comparison with evidence from the archaeological record. Chronological information detailing the arrival of the Neolithic was used to create a map of the initial arrival of the Neolithic (a chronosurface) throughout the study area. The results of each conceptual spread model were then compared to the chronosurface in order to evaluate the relative performance of each conceptual model of spread. These experiments suggest that both the Dual and Maritime Pioneer Colonization models best fit the available chronological and spatial distribution of the Impresso-Cardial Neolithic.
For the purpose of informing agent movement and improving the fit of the conceptual spread models, a variety of paleoenvironmental maps were tested within the Cardial Spread Model. The outcome of these experiments suggests that topographic slope was an important factor in settlement location and that rivers were important vectors of transportation for early Neolithic migration. This research demonstrates the application of techniques rare to archaeological analysis, agent-based modeling and the inclusion of paleoenvironmental information, and provides a valuable tool that future researchers can utilize to further evaluate and fabricate new models of Neolithic expansion.
For the purpose of informing agent movement and improving the fit of the conceptual spread models, a variety of paleoenvironmental maps were tested within the Cardial Spread Model. The outcome of these experiments suggests that topographic slope was an important factor in settlement location and that rivers were important vectors of transportation for early Neolithic migration. This research demonstrates the application of techniques rare to archaeological analysis, agent-based modeling and the inclusion of paleoenvironmental information, and provides a valuable tool that future researchers can utilize to further evaluate and fabricate new models of Neolithic expansion.
ContributorsBergin, Sean M (Author) / Barton, Michael (Thesis advisor) / Janssen, Marco (Committee member) / Coudart, Anick (Committee member) / Arizona State University (Publisher)
Created2016
Description
The closer integration of the world economy has yielded many positive benefits including the worldwide diffusion of innovative technologies and efficiency gains following the widening of international markets. However, closer integration also has negative consequences. Specifically, I focus on the ecology and economics of the spread of species and pathogens. I approach the problem using theoretical and applied models in ecology and economics. First, I use a multi-species theoretical network model to evaluate the ability of dispersal to maintain system-level biodiversity and productivity. I then extend this analysis to consider the effects of dispersal in a coupled social-ecological system where people derive benefits from species. Finally, I estimate an empirical model of the foot and mouth disease risks of trade. By combining outbreak and trade data I estimate the disease risks associated with the international trade in live animals while controlling for the biosecurity measures in place in importing countries and the presence of wild reservoirs. I find that the risks associated with the spread and dispersal of species may be positive or negative, but that this relationship depends on the ecological and economic components of the system and the interactions between them.
ContributorsShanafelt, David William (Author) / Perrings, Charles (Thesis advisor) / Fenichel, Eli (Committee member) / Richards, Timorthy (Committee member) / Janssen, Marco (Committee member) / Collins, James (Committee member) / Arizona State University (Publisher)
Created2016
Description
In many fields one needs to build predictive models for a set of related machine learning tasks, such as information retrieval, computer vision and biomedical informatics. Traditionally these tasks are treated independently and the inference is done separately for each task, which ignores important connections among the tasks. Multi-task learning aims at simultaneously building models for all tasks in order to improve the generalization performance, leveraging inherent relatedness of these tasks. In this thesis, I firstly propose a clustered multi-task learning (CMTL) formulation, which simultaneously learns task models and performs task clustering. I provide theoretical analysis to establish the equivalence between the CMTL formulation and the alternating structure optimization, which learns a shared low-dimensional hypothesis space for different tasks. Then I present two real-world biomedical informatics applications which can benefit from multi-task learning. In the first application, I study the disease progression problem and present multi-task learning formulations for disease progression. In the formulations, the prediction at each point is a regression task and multiple tasks at different time points are learned simultaneously, leveraging the temporal smoothness among the tasks. The proposed formulations have been tested extensively on predicting the progression of the Alzheimer's disease, and experimental results demonstrate the effectiveness of the proposed models. In the second application, I present a novel data-driven framework for densifying the electronic medical records (EMR) to overcome the sparsity problem in predictive modeling using EMR. The densification of each patient is a learning task, and the proposed algorithm simultaneously densify all patients. As such, the densification of one patient leverages useful information from other patients.
ContributorsZhou, Jiayu (Author) / Ye, Jieping (Thesis advisor) / Mittelmann, Hans (Committee member) / Li, Baoxin (Committee member) / Wang, Yalin (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
In this thesis, the application of pixel-based vertical axes used within parallel coordinate plots is explored in an attempt to improve how existing tools can explain complex multivariate interactions across temporal data. Several promising visualization techniques are combined, such as: visual boosting to allow for quicker consumption of large data sets, the bond energy algorithm to find finer patterns and anomalies through contrast, multi-dimensional scaling, flow lines, user guided clustering, and row-column ordering. User input is applied on precomputed data sets to provide for real time interaction. General applicability of the techniques are tested against industrial trade, social networking, financial, and sparse data sets of varying dimensionality.
ContributorsHayden, Thomas (Author) / Maciejewski, Ross (Thesis advisor) / Wang, Yalin (Committee member) / Runger, George C. (Committee member) / Mack, Elizabeth (Committee member) / Arizona State University (Publisher)
Created2014
Description
The coordination of group behavior in the social insects is representative of a broader phenomenon in nature, emergent biological complexity. In such systems, it is believed that large-scale patterns result from the interaction of relatively simple subunits. This dissertation involved the study of one such system: the social foraging of the ant Temnothorax rugatulus. Physically tiny with small population sizes, these cavity-dwelling ants provide a good model system to explore the mechanisms and ultimate origins of collective behavior in insect societies. My studies showed that colonies robustly exploit sugar water. Given a choice between feeders unequal in quality, colonies allocate more foragers to the better feeder. If the feeders change in quality, colonies are able to reallocate their foragers to the new location of the better feeder. These qualities of flexibility and allocation could be explained by the nature of positive feedback (tandem run recruitment) that these ants use. By observing foraging colonies with paint-marked ants, I was able to determine the `rules' that individuals follow: foragers recruit more and give up less when they find a better food source. By altering the nutritional condition of colonies, I found that these rules are flexible - attuned to the colony state. In starved colonies, individual ants are more likely to explore and recruit to food sources than in well-fed colonies. Similar to honeybees, Temmnothorax foragers appear to modulate their exploitation and recruitment behavior in response to environmental and social cues. Finally, I explored the influence of ecology (resource distribution) on the foraging success of colonies. Larger colonies showed increased consistency and a greater rate of harvest than smaller colonies, but this advantage was mediated by the distribution of resources. While patchy or rare food sources exaggerated the relative success of large colonies, regularly (or easily found) distributions leveled the playing field for smaller colonies. Social foraging in ant societies can best be understood when we view the colony as a single organism and the phenotype - group size, communication, and individual behavior - as integrated components of a homeostatic unit.
ContributorsShaffer, Zachary (Author) / Pratt, Stephen C (Thesis advisor) / Hölldobler, Bert (Committee member) / Janssen, Marco (Committee member) / Fewell, Jennifer (Committee member) / Liebig, Juergen (Committee member) / Arizona State University (Publisher)
Created2014
Description
In Latin America food insecurity is still prevailing in those regions where extreme poverty and political instability are common. Tseltal communities are experiencing changes due to religious conversions and the incursion of external political institutions. These changes have diminished the importance of traditional reciprocal and redistributive institutions that historically have been essential for personal and community survival. This dissertation investigated the impact that variations on governance systems and presence of reciprocal and distributional exchanges have on the food security status of communities. Qualitative data collected in four communities through 117 free lists and 117 semi-structured interviews was used to elaborate six scales that correspond to the traditional and civic authority system and to inter-community and intra-community reciprocity and redistribution. I explore the relationship that the scores of four communities on those scales have on the food security status of their inhabitants based on their results on the National Health and Nutrition Survey 2012. Findings from this study suggest that in marginalized communities that many scientists would described as experiencing market failure, participation in inter-community reciprocal, intra-community reciprocal and intra-community redistribution are better predictors of food security than enrollment in food security programs. Additionally, communities that participated the most in these non-market mechanisms have stronger traditional institutions. In contrast, communities that participated more in inter-community redistribution scored higher on the civic authority scale, are enrolled in more food aid programs, but are less food secure.
ContributorsDe La Torre Pacheco, Sindy Yaneth (Author) / Janssen, Marco (Thesis advisor) / Eakin, Hallie (Committee member) / BurnSilver, Shauna (Committee member) / Arizona State University (Publisher)
Created2015
Description
Sparse learning is a powerful tool to generate models of high-dimensional data with high interpretability, and it has many important applications in areas such as bioinformatics, medical image processing, and computer vision. Recently, the a priori structural information has been shown to be powerful for improving the performance of sparse learning models. A graph is a fundamental way to represent structural information of features. This dissertation focuses on graph-based sparse learning. The first part of this dissertation aims to integrate a graph into sparse learning to improve the performance. Specifically, the problem of feature grouping and selection over a given undirected graph is considered. Three models are proposed along with efficient solvers to achieve simultaneous feature grouping and selection, enhancing estimation accuracy. One major challenge is that it is still computationally challenging to solve large scale graph-based sparse learning problems. An efficient, scalable, and parallel algorithm for one widely used graph-based sparse learning approach, called anisotropic total variation regularization is therefore proposed, by explicitly exploring the structure of a graph. The second part of this dissertation focuses on uncovering the graph structure from the data. Two issues in graphical modeling are considered. One is the joint estimation of multiple graphical models using a fused lasso penalty and the other is the estimation of hierarchical graphical models. The key technical contribution is to establish the necessary and sufficient condition for the graphs to be decomposable. Based on this key property, a simple screening rule is presented, which reduces the size of the optimization problem, dramatically reducing the computational cost.
ContributorsYang, Sen (Author) / Ye, Jieping (Thesis advisor) / Wonka, Peter (Thesis advisor) / Wang, Yalin (Committee member) / Li, Jing (Committee member) / Arizona State University (Publisher)
Created2014
Description
Tessellation and Screen-Space Ambient Occlusion are algorithms which have been widely-used in real-time rendering in the past decade. They aim to enhance the details of the mesh, cast better shadow effects and improve the quality of the rendered images in real time. WebGL is a web-based graphics library derived from OpenGL ES used for rendering in web applications. It is relatively new and has been rapidly evolving, this has resulted in it supporting a subset of rendering features normally supported by desktop applications. In this thesis, the research is focusing on evaluating Curved PN-Triangles tessellation with Screen Space Ambient Occlusion (SSAO), Horizon-Based Ambient Occlusion (HBAO) and Horizon-Based Ambient Occlusion Plus (HBAO+) in WebGL-based real-time application and comparing its performance to desktop based application and to discuss the capabilities, limitations and bottlenecks of WebGL 1.0.
ContributorsLi, Chenyang (Author) / Amresh, Ashish (Thesis advisor) / Wang, Yalin (Thesis advisor) / Kobayashi, Yoshihiro (Committee member) / Arizona State University (Publisher)
Created2017