Current Search: Sukthankar, Gita (x)
View All Items
(1 - 20 of 41)
Pages
- Title
- SPARSIFICATION OF SOCIAL NETWORKS USING RANDOM WALKS.
- Creator
-
Wilder, Bryan, Sukthankar, Gita, University of Central Florida
- Abstract / Description
-
Analysis of large network datasets has become increasingly important. Algorithms have been designed to find many kinds of structure, with numerous applications across the social and biological sciences. However, a tradeoff is always present between accuracy and scalability; otherwise promising techniques can be computationally infeasible when applied to networks with huge numbers of nodes and edges. One way of extending the reach of network analysis is to sparsify the graph by retaining only...
Show moreAnalysis of large network datasets has become increasingly important. Algorithms have been designed to find many kinds of structure, with numerous applications across the social and biological sciences. However, a tradeoff is always present between accuracy and scalability; otherwise promising techniques can be computationally infeasible when applied to networks with huge numbers of nodes and edges. One way of extending the reach of network analysis is to sparsify the graph by retaining only a subset of its edges. The reduced network could prove much more tractable. For this thesis, I propose a new sparsification algorithm that preserves the properties of a random walk on the network. Specifically, the algorithm finds a subset of edges that best preserves the stationary distribution of a random walk by minimizing the Kullback-Leibler divergence between a walk on the original and sparsified graphs. A highly efficient greedy search strategy is developed to optimize this objective. Experimental results are presented that test the performance of the algorithm on the influence maximization task. These results demonstrate that sparsification allows near-optimal solutions to be found in a small fraction of the runtime that would required using the full network. Two cases are shown where sparsification allows an influence maximization algorithm to be applied to a dataset that previous work had considered intractable.
Show less - Date Issued
- 2015
- Identifier
- CFH0004732, ucf:45387
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH0004732
- Title
- EXPLOITING OPPONENT MODELING FOR LEARNING IN MULTI-AGENT ADVERSARIAL GAMES.
- Creator
-
Laviers, Kennard, Sukthankar, Gita, University of Central Florida
- Abstract / Description
-
An issue with learning effective policies in multi-agent adversarial games is that the size of the search space can be prohibitively large when the actions of both teammates and opponents are considered simultaneously. Opponent modeling, predicting an opponent's actions in advance of execution, is one approach for selecting actions in adversarial settings, but it is often performed in an ad hoc way. In this dissertation, we introduce several methods for using opponent modeling, in the form of...
Show moreAn issue with learning effective policies in multi-agent adversarial games is that the size of the search space can be prohibitively large when the actions of both teammates and opponents are considered simultaneously. Opponent modeling, predicting an opponent's actions in advance of execution, is one approach for selecting actions in adversarial settings, but it is often performed in an ad hoc way. In this dissertation, we introduce several methods for using opponent modeling, in the form of predictions about the players' physical movements, to learn team policies. To explore the problem of decision-making in multi-agent adversarial scenarios, we use our approach for both offline play generation and real-time team response in the Rush 2008 American football simulator. Simultaneously predicting the movement trajectories, future reward, and play strategies of multiple players in real-time is a daunting task but we illustrate how it is possible to divide and conquer this problem with an assortment of data-driven models. By leveraging spatio-temporal traces of player movements, we learn discriminative models of defensive play for opponent modeling. With the reward information from previous play matchups, we use a modified version of UCT (Upper Conference Bounds applied to Trees) to create new offensive plays and to learn play repairs to counter predicted opponent actions. In team games, players must coordinate effectively to accomplish tasks while foiling their opponents either in a preplanned or emergent manner. An effective team policy must generate the necessary coordination, yet considering all possibilities for creating coordinating subgroups is computationally infeasible. Automatically identifying and preserving the coordination between key subgroups of teammates can make search more productive by pruning policies that disrupt these relationships. We demonstrate that combining opponent modeling with automatic subgroup identification can be used to create team policies with a higher average yardage than either the baseline game or domain-specific heuristics.
Show less - Date Issued
- 2011
- Identifier
- CFE0003914, ucf:48720
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0003914
- Title
- Active Learning with Unreliable Annotations.
- Creator
-
Zhao, Liyue, Sukthankar, Gita, Tappen, Marshall, Georgiopoulos, Michael, Sukthankar, Rahul, University of Central Florida
- Abstract / Description
-
With the proliferation of social media, gathering data has became cheaper and easier than before. However, this data can not be used for supervised machine learning without labels. Asking experts to annotate sufficient data for training is both expensive and time-consuming. Current techniques provide two solutions to reducing the cost and providing sufficient labels: crowdsourcing and active learning. Crowdsourcing, which outsources tasks to a distributed group of people, can be used to...
Show moreWith the proliferation of social media, gathering data has became cheaper and easier than before. However, this data can not be used for supervised machine learning without labels. Asking experts to annotate sufficient data for training is both expensive and time-consuming. Current techniques provide two solutions to reducing the cost and providing sufficient labels: crowdsourcing and active learning. Crowdsourcing, which outsources tasks to a distributed group of people, can be used to provide a large quantity of labels but controlling the quality of labels is hard. Active learning, which requires experts to annotate a subset of the most informative or uncertain data, is very sensitive to the annotation errors. Though these two techniques can be used independently of one another, by using them in combination they can complement each other's weakness. In this thesis, I investigate the development of active learning Support Vector Machines (SVMs) and expand this model to sequential data. Then I discuss the weakness of combining active learning and crowdsourcing, since the active learning is very sensitive to low quality annotations which are unavoidable for labels collected from crowdsourcing. In this thesis, I propose three possible strategies, incremental relabeling, importance-weighted label prediction and active Bayesian Networks. The incremental relabeling strategy requires workers to devote more annotations to uncertain samples, compared to majority voting which allocates different samples the same number of labels. Importance-weighted label prediction employs an ensemble of classifiers to guide the label requests from a pool of unlabeled training data. An active learning version of Bayesian Networks is used to model the difficulty of samples and the expertise of workers simultaneously to evaluate the relative weight of workers' labels during the active learning process. All three strategies apply different techniques with the same expectation -- identifying the optimal solution for applying an active learning model with mixed label quality to crowdsourced data. However, the active Bayesian Networks model, which is the core element of this thesis, provides additional benefits by estimating the expertise of workers during the training phase. As an example application, I also demonstrate the utility of crowdsourcing for human activity recognition problems.
Show less - Date Issued
- 2013
- Identifier
- CFE0004965, ucf:49579
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004965
- Title
- Modeling User Transportation Patterns Using Mobile Devices.
- Creator
-
Davami, Erfan, Sukthankar, Gita, Gonzalez, Avelino, Foroosh, Hassan, Sukthankar, Rahul, University of Central Florida
- Abstract / Description
-
Participatory sensing frameworks use humans and their computing devices as a large mobile sensing network. Dramatic accessibility and affordability have turned mobile devices (smartphone and tablet computers) into the most popular computational machines in the world, exceeding laptops. By the end of 2013, more than 1.5 billion people on earth will have a smartphone. Increased coverage and higher speeds of cellular networks have given these devices the power to constantly stream large amounts...
Show moreParticipatory sensing frameworks use humans and their computing devices as a large mobile sensing network. Dramatic accessibility and affordability have turned mobile devices (smartphone and tablet computers) into the most popular computational machines in the world, exceeding laptops. By the end of 2013, more than 1.5 billion people on earth will have a smartphone. Increased coverage and higher speeds of cellular networks have given these devices the power to constantly stream large amounts of data.Most mobile devices are equipped with advanced sensors such as GPS, cameras, and microphones. This expansion of smartphone numbers and power has created a sensing system capable of achieving tasks practically impossible for conventional sensing platforms. One of the advantages of participatory sensing platforms is their mobility, since human users are often in motion. This dissertation presents a set of techniques for modeling and predicting user transportation patterns from cell-phone and social media check-ins. To study large-scale transportation patterns, I created a mobile phone app, Kpark, for estimating parking lot occupancy on the UCF campus. Kpark aggregates individual user reports on parking space availability to produce a global picture across all the campus lots using crowdsourcing. An issue with crowdsourcing is the possibility of receiving inaccurate information from users, either through error or malicious motivations. One method of combating this problem is to model the trustworthiness of individual participants to use that information to selectively include or discard data.This dissertation presents a comprehensive study of the performance of different worker quality and data fusion models with plausible simulated user populations, as well as an evaluation of their performance on the real data obtained from a full release of the Kpark app on the UCF Orlando campus. To evaluate individual trust prediction methods, an algorithm selection portfolio was introduced to take advantage of the strengths of each method and maximize the overall prediction performance.Like many other crowdsourced applications, user incentivization is an important aspect of creating a successful crowdsourcing workflow. For this project a form of non-monetized incentivization called gamification was used in order to create competition among users with the aim of increasing the quantity and quality of data submitted to the project. This dissertation reports on the performance of Kpark at predicting parking occupancy, increasing user app usage, and predicting worker quality.
Show less - Date Issued
- 2015
- Identifier
- CFE0005597, ucf:50258
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005597
- Title
- Learning Hierarchical Representations for Video Analysis Using Deep Learning.
- Creator
-
Yang, Yang, Shah, Mubarak, Sukthankar, Gita, Da Vitoria Lobo, Niels, Stanley, Kenneth, Sukthankar, Rahul, University of Central Florida
- Abstract / Description
-
With the exponential growth of the digital data, video content analysis (e.g., action, event recognition) has been drawing increasing attention from computer vision researchers. Effective modeling of the objects, scenes, and motions is critical for visual understanding. Recently there has been a growing interest in the bio-inspired deep learning models, which has shown impressive results in speech and object recognition. The deep learning models are formed by the composition of multiple non...
Show moreWith the exponential growth of the digital data, video content analysis (e.g., action, event recognition) has been drawing increasing attention from computer vision researchers. Effective modeling of the objects, scenes, and motions is critical for visual understanding. Recently there has been a growing interest in the bio-inspired deep learning models, which has shown impressive results in speech and object recognition. The deep learning models are formed by the composition of multiple non-linear transformations of the data, with the goal of yielding more abstract and ultimately more useful representations. The advantages of the deep models are three fold: 1) They learn the features directly from the raw signal in contrast to the hand-designed features. 2) The learning can be unsupervised, which is suitable for large data where labeling all the data is expensive and unpractical. 3) They learn a hierarchy of features one level at a time and the layerwise stacking of feature extraction, this often yields better representations.However, not many deep learning models have been proposed to solve the problems in video analysis, especially videos ``in a wild''. Most of them are either dealing with simple datasets, or limited to the low-level local spatial-temporal feature descriptors for action recognition. Moreover, as the learning algorithms are unsupervised, the learned features preserve generative properties rather than the discriminative ones which are more favorable in the classification tasks. In this context, the thesis makes two major contributions.First, we propose several formulations and extensions of deep learning methods which learn hierarchical representations for three challenging video analysis tasks, including complex event recognition, object detection in videos and measuring action similarity. The proposed methods are extensively demonstrated for each work on the state-of-the-art challenging datasets. Besides learning the low-level local features, higher level representations are further designed to be learned in the context of applications. The data-driven concept representations and sparse representation of the events are learned for complex event recognition; the representations for object body parts and structures are learned for object detection in videos; and the relational motion features and similarity metrics between video pairs are learned simultaneously for action verification.Second, in order to learn discriminative and compact features, we propose a new feature learning method using a deep neural network based on auto encoders. It differs from the existing unsupervised feature learning methods in two ways: first it optimizes both discriminative and generative properties of the features simultaneously, which gives our features a better discriminative ability. Second, our learned features are more compact, while the unsupervised feature learning methods usually learn a redundant set of over-complete features. Extensive experiments with quantitative and qualitative results on the tasks of human detection and action verification demonstrate the superiority of our proposed models.
Show less - Date Issued
- 2013
- Identifier
- CFE0004964, ucf:49593
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004964
- Title
- Task Focused Robotic Imitation Learning.
- Creator
-
Abolghasemi, Pooya, Boloni, Ladislau, Sukthankar, Gita, Shah, Mubarak, Willenberg, Bradley, University of Central Florida
- Abstract / Description
-
For many years, successful applications of robotics were the domain of controlled environments, such as industrial assembly lines. Such environments are custom designed for the convenience of the robot and separated from human operators. In recent years, advances in artificial intelligence, in particular, deep learning and computer vision, allowed researchers to successfully demonstrate robots that operate in unstructured environments and directly interact with humans. One of the major...
Show moreFor many years, successful applications of robotics were the domain of controlled environments, such as industrial assembly lines. Such environments are custom designed for the convenience of the robot and separated from human operators. In recent years, advances in artificial intelligence, in particular, deep learning and computer vision, allowed researchers to successfully demonstrate robots that operate in unstructured environments and directly interact with humans. One of the major applications of such robots is in assistive robotics. For instance, a wheelchair mounted robotic arm can help disabled users in the performance of activities of daily living (ADLs) such as feeding and personal grooming. Early systems relied entirely on the control of the human operator, something that is difficult to accomplish by a user with motor and/or cognitive disabilities. In this dissertation, we are describing research results that advance the field of assistive robotics. The overall goal is to improve the ability of the wheelchair / robotic arm assembly to help the user with the performance of the ADLs by requiring only high-level commands from the user. Let us consider an ADL involving the manipulation of an object in the user's home. This task can be naturally decomposed into two components: the movement of the wheelchair in such a way that the manipulator can conveniently grasp the object and the movement of the manipulator itself. This dissertation we provide an approach for addressing the challenge of finding the position appropriate for the required manipulation. We introduce the ease-of-reach score (ERS), a metric that quantifies the preferences for the positioning of the base while taking into consideration the shape and position of obstacles and clutter in the environment. As the brute force computation of ERS is computationally expensive, we propose a machine learning approach to estimate the ERS based on features and characteristics of the obstacles. This dissertation addresses the second component as well, the ability of the robotic arm to manipulate objects. Recent work in end-to-end learning of robotic manipulation had demonstrated that a deep learning-based controller of vision-enabled robotic arms can be thought to manipulate objects from a moderate number of demonstrations. However, the current state of the art systems are limited in robustness to physical and visual disturbances and do not generalize well to new objects. We describe new techniques based on task-focused attention that show significant improvement in the robustness of manipulation and performance in clutter.
Show less - Date Issued
- 2019
- Identifier
- CFE0007771, ucf:52392
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007771
- Title
- Effective Task Transfer Through Indirect Encoding.
- Creator
-
Verbancsics, Phillip, Stanley, Kenneth, Sukthankar, Gita, Georgiopoulos, Michael, Garibay, Ivan, University of Central Florida
- Abstract / Description
-
An important goal for machine learning is to transfer knowledge between tasks. For example, learning to play RoboCup Keepaway should contribute to learning the full game of RoboCup soccer. Often approaches to task transfer focus on transforming the original representation to fit the new task. Such representational transformations are necessary because the target task often requires new state information that was not included in the original representation. In RoboCup Keepaway, changing from...
Show moreAn important goal for machine learning is to transfer knowledge between tasks. For example, learning to play RoboCup Keepaway should contribute to learning the full game of RoboCup soccer. Often approaches to task transfer focus on transforming the original representation to fit the new task. Such representational transformations are necessary because the target task often requires new state information that was not included in the original representation. In RoboCup Keepaway, changing from the 3 vs. 2 variant of the task to 4 vs. 3 adds state information for each of the new players. In contrast, this dissertation explores the idea that transfer is most effective if the representation is designed to be the same even across different tasks. To this end, (1) the bird's eye view (BEV) representation is introduced, which can represent different tasks on the same two-dimensional map. Because the BEV represents state information associated with positions instead of objects, it can be scaled to more objects without manipulation. In this way, both the 3 vs. 2 and 4 vs. 3 Keepaway tasks can be represented on the same BEV, which is (2) demonstrated in this dissertation.Yet a challenge for such representation is that a raw two-dimensional map is high-dimensional and unstructured. This dissertation demonstrates how this problem is addressed naturally by the Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) approach. HyperNEAT evolves an indirect encoding, which compresses the representation by exploiting its geometry. The dissertation then explores further exploiting the power of such encoding, beginning by (3) enhancing the configuration of the BEV with a focus on modularity. The need for further nonlinearity is then (4) investigated through the addition of hidden nodes. Furthermore, (5) the size of the BEV can be manipulated because it is indirectly encoded. Thus the resolution of the BEV, which is dictated by its size, is increased in precision and culminates in a HyperNEAT extension that is expressed at effectively infinite resolution. Additionally, scaling to higher resolutions through gradually increasing the size of the BEV is explored. Finally, (6) the ambitious problem of scaling from the Keepaway task to the Half-field Offense task is investigated with the BEV. Overall, this dissertation demonstrates that advanced representations in conjunction with indirect encoding can contribute to scaling learning techniques to more challenging tasks, such as the Half-field Offense RoboCup soccer domain.
Show less - Date Issued
- 2011
- Identifier
- CFE0004174, ucf:49071
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004174
- Title
- Life Long Learning in Sparse Learning Environments.
- Creator
-
Reeder, John, Georgiopoulos, Michael, Gonzalez, Avelino, Sukthankar, Gita, Anagnostopoulos, Georgios, University of Central Florida
- Abstract / Description
-
Life long learning is a machine learning technique that deals with learning sequential tasks over time. It seeks to transfer knowledge from previous learning tasks to new learning tasks in order to increase generalization performance and learning speed. Real-time learning environments in which many agents are participating may provide learning opportunities but they are spread out in time and space outside of the geographical scope of a single learning agent. This research seeks to provide an...
Show moreLife long learning is a machine learning technique that deals with learning sequential tasks over time. It seeks to transfer knowledge from previous learning tasks to new learning tasks in order to increase generalization performance and learning speed. Real-time learning environments in which many agents are participating may provide learning opportunities but they are spread out in time and space outside of the geographical scope of a single learning agent. This research seeks to provide an algorithm and framework for life long learning among a network of agents in a sparse real-time learning environment. This work will utilize the robust knowledge representation of neural networks, and make use of both functional and representational knowledge transfer to accomplish this task. A new generative life long learning algorithm utilizing cascade correlation and reverberating pseudo-rehearsal and incorporating a method for merging divergent life long learning paths will be implemented.
Show less - Date Issued
- 2013
- Identifier
- CFE0004917, ucf:49601
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004917
- Title
- Towards Evolving More Brain-Like Artificial Neural Networks.
- Creator
-
Risi, Sebastian, Stanley, Kenneth, Hughes, Charles, Sukthankar, Gita, Wiegand, Rudolf, University of Central Florida
- Abstract / Description
-
An ambitious long-term goal for neuroevolution, which studies how artificial evolutionary processes can be driven to produce brain-like structures, is to evolve neurocontrollers with a high density of neurons and connections that can adapt and learn from past experience. Yet while neuroevolution has produced successful results in a variety of domains, the scale of natural brains remains far beyond reach. In this dissertation two extensions to the recently introduced Hypercube-based...
Show moreAn ambitious long-term goal for neuroevolution, which studies how artificial evolutionary processes can be driven to produce brain-like structures, is to evolve neurocontrollers with a high density of neurons and connections that can adapt and learn from past experience. Yet while neuroevolution has produced successful results in a variety of domains, the scale of natural brains remains far beyond reach. In this dissertation two extensions to the recently introduced Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) approach are presented that are a step towards more brain-like artificial neural networks (ANNs). First, HyperNEAT is extended to evolve plastic ANNs that can learn from past experience. This new approach, called adaptive HyperNEAT, allows not only patterns of weights across the connectivity of an ANN to be generated by a function of its geometry, but also patterns of arbitrary local learning rules. Second, evolvable-substrate HyperNEAT (ES-HyperNEAT) is introduced, which relieves the user from deciding where the hidden nodes should be placed in a geometry that is potentially infinitely dense. This approach not only can evolve the location of every neuron in the network, but also can represent regions of varying density, which means resolution can increase holistically over evolution. The combined approach, adaptive ES-HyperNEAT, unifies for the first time in neuroevolution the abilities to indirectly encode connectivity through geometry, generate patterns of heterogeneous plasticity, and simultaneously encode the density and placement of nodes in space. The dissertation culminates in a major application domain that takes a step towards the general goal of adaptive neurocontrollers for legged locomotion.
Show less - Date Issued
- 2012
- Identifier
- CFE0004287, ucf:49477
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004287
- Title
- Machine Learning from Casual Conversation.
- Creator
-
Mohammed Ali, Awrad, Sukthankar, Gita, Wu, Annie, Boloni, Ladislau, University of Central Florida
- Abstract / Description
-
Human social learning is an effective process that has inspired many existing machine learning techniques, such as learning from observation and learning by demonstration. In this dissertation, we introduce another form of social learning, Learning from a Casual Conversation (LCC). LCC is an open-ended machine learning system in which an artificially intelligent agent learns from an extended dialog with a human. Our system enables the agent to incorporate changes into its knowledge base,...
Show moreHuman social learning is an effective process that has inspired many existing machine learning techniques, such as learning from observation and learning by demonstration. In this dissertation, we introduce another form of social learning, Learning from a Casual Conversation (LCC). LCC is an open-ended machine learning system in which an artificially intelligent agent learns from an extended dialog with a human. Our system enables the agent to incorporate changes into its knowledge base, based on the human's conversational text input. This system emulates how humans learn from each other through a dialog. LCC closes the gap in the current research that is focused on teaching specific tasks to computer agents. Furthermore, LCC aims to provide an easy way to enhance the knowledge of the system without requiring the involvement of a programmer. This system does not require the user to enter specific information; instead, the user can chat naturally with the agent. LCC identifies the inputs that contain information relevant to its knowledge base in the learning process. LCC's architecture consists of multiple sub-systems combined to perform the task. Its learning component can add new knowledge to existing information in the knowledge base, confirm existing information, and/or update existing information found to be related to the user input. %The test results indicate that the prototype was successful in learning from a conversation. The LCC system functionality was assessed using different evaluation methods. This includes tests performed by the developer, as well as by 130 human test subjects. Thirty of those test subjects interacted directly with the system and completed a survey of 13 questions/statements that asked the user about his/her experience using LCC. A second group of 100 human test subjects evaluated the dialogue logs of a subset of the first group of human testers. The collected results were all found to be acceptable and within the range of our expectations.
Show less - Date Issued
- 2019
- Identifier
- CFE0007503, ucf:52634
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007503
- Title
- Quality Diversity: Harnessing Evolution to Generate a Diversity of High-Performing Solutions.
- Creator
-
Pugh, Justin, Stanley, Kenneth, Wu, Annie, Sukthankar, Gita, Garibay, Ivan, University of Central Florida
- Abstract / Description
-
Evolution in nature has designed countless solutions to innumerable interconnected problems, giving birth to the impressive array of complex modern life observed today. Inspired by this success, the practice of evolutionary computation (EC) abstracts evolution artificially as a search operator to find solutions to problems of interest primarily through the adaptive mechanism of survival of the fittest, where stronger candidates are pursued at the expense of weaker ones until a solution of...
Show moreEvolution in nature has designed countless solutions to innumerable interconnected problems, giving birth to the impressive array of complex modern life observed today. Inspired by this success, the practice of evolutionary computation (EC) abstracts evolution artificially as a search operator to find solutions to problems of interest primarily through the adaptive mechanism of survival of the fittest, where stronger candidates are pursued at the expense of weaker ones until a solution of satisfying quality emerges. At the same time, research in open-ended evolution (OEE) draws different lessons from nature, seeking to identify and recreate processes that lead to the type of perpetual innovation and indefinitely increasing complexity observed in natural evolution. New algorithms in EC such as MAP-Elites and Novelty Search with Local Competition harness the toolkit of evolution for a related purpose: finding as many types of good solutions as possible (rather than merely the single best solution). With the field in its infancy, no empirical studies previously existed comparing these so-called quality diversity (QD) algorithms. This dissertation (1) contains the first extensive and methodical effort to compare different approaches to QD (including both existing published approaches as well as some new methods presented for the first time here) and to understand how they operate to help inform better approaches in the future.It also (2) introduces a new technique for encoding neural networks for evolution with indirect encoding that contain multiple sensory or output modalities.Further, it (3) explores the idea that QD can act as an engine of open-ended discovery by introducing an expressive platform called Voxelbuild where QD algorithms continually evolve robots that stack blocks in new ways. A culminating experiment (4) is presented that investigates evolution in Voxelbuild over a very long timescale. This research thus stands to advance the OEE community's desire to create and understand open-ended systems while also laying the groundwork for QD to realize its potential within EC as a means to automatically generate an endless progression of new content in real-world applications.
Show less - Date Issued
- 2019
- Identifier
- CFE0007513, ucf:52638
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007513
- Title
- Describing Images by Semantic Modeling using Attributes and Tags.
- Creator
-
Mahmoudkalayeh, Mahdi, Shah, Mubarak, Sukthankar, Gita, Rahnavard, Nazanin, Zhang, Teng, University of Central Florida
- Abstract / Description
-
This dissertation addresses the problem of describing images using visual attributes and textual tags, a fundamental task that narrows down the semantic gap between the visual reasoning of humans and machines. Automatic image annotation assigns relevant textual tags to the images. In this dissertation, we propose a query-specific formulation based on Weighted Multi-view Non-negative Matrix Factorization to perform automatic image annotation. Our proposed technique seamlessly adapt to the...
Show moreThis dissertation addresses the problem of describing images using visual attributes and textual tags, a fundamental task that narrows down the semantic gap between the visual reasoning of humans and machines. Automatic image annotation assigns relevant textual tags to the images. In this dissertation, we propose a query-specific formulation based on Weighted Multi-view Non-negative Matrix Factorization to perform automatic image annotation. Our proposed technique seamlessly adapt to the changes in training data, naturally solves the problem of feature fusion and handles the challenge of the rare tags. Unlike tags, attributes are category-agnostic, hence their combination models an exponential number of semantic labels. Motivated by the fact that most attributes describe local properties, we propose exploiting localization cues, through semantic parsing of human face and body to improve person-related attribute prediction. We also demonstrate that image-level attribute labels can be effectively used as weak supervision for the task of semantic segmentation. Next, we analyze the Selfie images by utilizing tags and attributes. We collect the first large-scale Selfie dataset and annotate it with different attributes covering characteristics such as gender, age, race, facial gestures, and hairstyle. We then study the popularity and sentiments of the selfies given an estimated appearance of various semantic concepts. In brief, we automatically infer what makes a good selfie. Despite its extensive usage, the deep learning literature falls short in understanding the characteristics and behavior of the Batch Normalization. We conclude this dissertation by providing a fresh view, in light of information geometry and Fisher kernels to why the batch normalization works. We propose Mixture Normalization that disentangles modes of variation in the underlying distribution of the layer outputs and confirm that it effectively accelerates training of different batch-normalized architectures including Inception-V3, Densely Connected Networks, and Deep Convolutional Generative Adversarial Networks while achieving better generalization error.
Show less - Date Issued
- 2019
- Identifier
- CFE0007493, ucf:52640
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007493
- Title
- Learning Dynamic Network Models for Complex Social Systems.
- Creator
-
Hajibagheri, Alireza, Sukthankar, Gita, Turgut, Damla, Chatterjee, Mainak, Lakkaraju, Kiran, University of Central Florida
- Abstract / Description
-
Human societies are inherently complex and highly dynamic, resulting in rapidly changing social networks, containing multiple types of dyadic interactions. Analyzing these time-varying multiplex networks with approaches developed for static, single layer networks often produces poor results. To address this problem, our approach is to explicitly learn the dynamics of these complex networks. This dissertation focuses on five problems: 1) learning link formation rates; 2) predicting changes in...
Show moreHuman societies are inherently complex and highly dynamic, resulting in rapidly changing social networks, containing multiple types of dyadic interactions. Analyzing these time-varying multiplex networks with approaches developed for static, single layer networks often produces poor results. To address this problem, our approach is to explicitly learn the dynamics of these complex networks. This dissertation focuses on five problems: 1) learning link formation rates; 2) predicting changes in community membership; 3) using time series to predict changes in network structure; 4) modeling coevolution patterns across network layers and 5) extracting information from negative layers of a multiplex network.To study these problems, we created a rich dataset extracted from observing social interactions in the massively multiplayer online game Travian. Most online social media platforms are optimized to support a limited range of social interactions, primarily focusing on communication and information sharing. In contrast, relations in massively-multiplayer online games (MMOGs) are often formed during the course of gameplay and evolve as the game progresses. To analyze the players' behavior, we constructed multiplex networks with link types for raid, communication, and trading.The contributions of this dissertation include 1) extensive experiments on the dynamics of networks formed from diverse social processes; 2) new game theoretic models for community detection in dynamic networks; 3) supervised and unsupervised methods for link prediction in multiplex coevolving networks for both positive and negative links. We demonstrate that our holistic approach for modeling network dynamics in coevolving, multiplex networks outperforms factored methods that separately consider temporal and cross-layer patterns.
Show less - Date Issued
- 2017
- Identifier
- CFE0006598, ucf:51306
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006598
- Title
- Quantitative Framework For Social Cultural Interactions.
- Creator
-
Bhatia, Taranjeet, Boloni, Ladislau, Turgut, Damla, Sukthankar, Gita, Fiore, Stephen, University of Central Florida
- Abstract / Description
-
For an autonomous robot or software agent to participate in the social life of humans, it must have a way to perform a calculus of social behavior. Such a calculus must have explanatory power (it must provide a coherent theory for why the humans act the way they do), and predictive power (it must provide some plausible events from the predicted future actions of the humans).This dissertation describes a series of contributions that would allow agents observing or interacting with humans to...
Show moreFor an autonomous robot or software agent to participate in the social life of humans, it must have a way to perform a calculus of social behavior. Such a calculus must have explanatory power (it must provide a coherent theory for why the humans act the way they do), and predictive power (it must provide some plausible events from the predicted future actions of the humans).This dissertation describes a series of contributions that would allow agents observing or interacting with humans to perform a calculus of social behavior taking into account cultural conventions and socially acceptable behavior models. We discuss the formal components of the model: culture-sanctioned social metrics (CSSMs), concrete beliefs (CBs) and action impact functions. Through a detailed case study of a crooked seller who relies on the manipulation of public perception, we show that the model explains how the exploitation of social conventions allows the seller to finalize transactions, despite the fact that the clients know that they are being cheated. In a separate study, we show that how the crooked seller can find an optimal strategy with the use of reinforcement learning.We extend the CSSM model for modeling the propagation of public perception across multiple social interactions. We model the evolution of the public perception both over a single interaction and during a series of interactions over an extended period of time. An important aspect for modeling the public perception is its propagation - how the propagation is affected by the spatio-temporal context of the interaction and how does the short-term and long-term memory of humans affect the overall public perception.We validated the CSSM model through a user study in which participants cognizant with the modeled culture had to evaluate the impact on the social values. The scenarios used in the experiments modeled emotionally charged social situations in a cross-cultural setting and with the presence of a robot. The scenarios model conflicts of cross-cultural communication as well as ethical, social and financial choices. This study allowed us to study whether people sharing the same culture evaluate CSSMs at the same way (the inter-cultural uniformity conjecture). By presenting a wide range of possible metrics, the study also allowed us to determine whether any given metric can be considered a CSSM in a given culture or not.
Show less - Date Issued
- 2016
- Identifier
- CFE0006262, ucf:51047
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006262
- Title
- Gesture Assessment of Teachers in an Immersive Rehearsal Environment.
- Creator
-
Barmaki, Roghayeh, Hughes, Charles, Foroosh, Hassan, Sukthankar, Gita, Dieker, Lisa, University of Central Florida
- Abstract / Description
-
Interactive training environments typically include feedback mechanisms designed to help trainees improve their performance through either guided- or self-reflection. When the training system deals with human-to-human communications, as one would find in a teacher, counselor, enterprise culture or cross-cultural trainer, such feedback needs to focus on all aspects of human communication. This means that, in addition to verbal communication, nonverbal messages must be captured and analyzed for...
Show moreInteractive training environments typically include feedback mechanisms designed to help trainees improve their performance through either guided- or self-reflection. When the training system deals with human-to-human communications, as one would find in a teacher, counselor, enterprise culture or cross-cultural trainer, such feedback needs to focus on all aspects of human communication. This means that, in addition to verbal communication, nonverbal messages must be captured and analyzed for semantic meaning.?The goal of this dissertation is to employ machine-learning algorithms that semi-automate and, where supported, automate event tagging in training systems developed to improve human-to-human interaction. The specific context in which we prototype and validate these models is the TeachLivE teacher rehearsal environment developed at the University of Central Florida. The choice of this environment was governed by its availability, large user population, ?extensibility and existing reflection tools found within the AMITIES ??framework underlying the TeachLivE system.?Our contribution includes accuracy improvement of the existing data-driven gesture recognition utility from Microsoft; called Visual Gesture Builder. Using this proposed methodology and tracking sensors, we created a gesture database and used it for the implementation of our proposed online gesture recognition and feedback application. We also investigated multiple methods of feedback provision, including visual and haptics. The results from the conducted user studies indicate the positive impact of the proposed feedback applications and informed body language in teaching competency.In this dissertation, we describe the context in which the algorithms have been developed, the importance of recognizing nonverbal communication in this context, the means of providing semi- and fully-automated feedback associated with nonverbal messaging, and a series of preliminary studies developed to inform the research. Furthermore, we outline future research directions on new case studies, and multimodal annotation and analysis, in order to understand the synchrony of acoustic features and gestures in teaching context.
Show less - Date Issued
- 2016
- Identifier
- CFE0006260, ucf:51053
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006260
- Title
- An Exploration of Unmanned Aerial Vehicle Direct Manipulation Through 3D Spatial Interaction.
- Creator
-
Pfeil, Kevin, Laviola II, Joseph, Hughes, Charles, Sukthankar, Gita, University of Central Florida
- Abstract / Description
-
We present an exploration that surveys the strengths and weaknesses of various 3D spatial interaction techniques, in the context of directly manipulating an Unmanned Aerial Vehicle (UAV). Particularly, a study of touch- and device- free interfaces in this domain is provided. 3D spatial interaction can be achieved using hand-held motion control devices such as the NintendoWiimote, but computer vision systems offer a different and perhaps more natural method. In general, 3D user interfaces ...
Show moreWe present an exploration that surveys the strengths and weaknesses of various 3D spatial interaction techniques, in the context of directly manipulating an Unmanned Aerial Vehicle (UAV). Particularly, a study of touch- and device- free interfaces in this domain is provided. 3D spatial interaction can be achieved using hand-held motion control devices such as the NintendoWiimote, but computer vision systems offer a different and perhaps more natural method. In general, 3D user interfaces (3DUI) enable a user to interact with a system on a more robust and potentially more meaningful scale. We discuss the design and development of various 3D interaction techniques using commercially available computer vision systems, and provide an exploration of the effects that these techniques have on an overall user experience in the UAV domain. Specific qualities of the user experience are targeted, including the perceived intuition, ease of use, comfort, and others. We present a complete user study for upper-body gesture, and preliminary reactions towards 3DUI using hand-and-finger gestures are also discussed. The results provide evidence that supports the use of 3DUI in this domain, as well as the use of certain styles of techniques over others.
Show less - Date Issued
- 2013
- Identifier
- CFE0004910, ucf:49612
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004910
- Title
- Modeling social norms in real-world agent-based simulations.
- Creator
-
Beheshti, Rahmatollah, Sukthankar, Gita, Boloni, Ladislau, Wu, Annie, Swarup, Samarth, University of Central Florida
- Abstract / Description
-
Studying and simulating social systems including human groups and societies can be a complex problem. In order to build a model that simulates humans' actions, it is necessary to consider the major factors that affect human behavior. Norms are one of these factors: social norms are the customary rules that govern behavior in groups and societies. Norms are everywhere around us, from the way people handshake or bow to the clothes they wear. They play a large role in determining our behaviors....
Show moreStudying and simulating social systems including human groups and societies can be a complex problem. In order to build a model that simulates humans' actions, it is necessary to consider the major factors that affect human behavior. Norms are one of these factors: social norms are the customary rules that govern behavior in groups and societies. Norms are everywhere around us, from the way people handshake or bow to the clothes they wear. They play a large role in determining our behaviors. Studies on norms are much older than the age of computer science, since normative studies have been a classic topic in sociology, psychology, philosophy and law. Various theories have been put forth about the functioning of social norms. Although an extensive amount of research on norms has been performed during the recent years, there remains a significant gap between current models and models that can explain real-world normative behaviors. Most of the existing work on norms focuses on abstract applications, and very few realistic normative simulations of human societies can be found. The contributions of this dissertation include the following: 1) a new hybrid technique based on agent-based modeling and Markov Chain Monte Carlo is introduced. This method is used to prepare a smoking case study for applying normative models. 2) This hybrid technique is described using category theory, which is a mathematical theory focusing on relations rather than objects. 3) The relationship between norm emergence in social networks and the theory of tipping points is studied. 4) A new lightweight normative architecture for studying smoking cessation trends is introduced. This architecture is then extended to a more general normative framework that can be used to model real-world normative behaviors. The final normative architecture considers cognitive and social aspects of norm formation in human societies. Normative architectures based on only one of these two aspects exist in the literature, but a normative architecture that effectively includes both of these two is missing.
Show less - Date Issued
- 2015
- Identifier
- CFE0005577, ucf:50244
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005577
- Title
- Autonomous Quadcopter Videographer.
- Creator
-
Coaguila Quiquia, Rey, Sukthankar, Gita, Wu, Annie, Hughes, Charles, University of Central Florida
- Abstract / Description
-
In recent years, the interest in quadcopters as a robotics platform for autonomous photography has increased. This is due to their small size and mobility, which allow them to reach places that are difficult or even impossible for humans. This thesis focuses on the design of an autonomous quadcopter videographer, i.e. a quadcopter capable of capturing good footage of a specific subject. In order to obtain this footage, the system needs to choose appropriate vantage points and control the...
Show moreIn recent years, the interest in quadcopters as a robotics platform for autonomous photography has increased. This is due to their small size and mobility, which allow them to reach places that are difficult or even impossible for humans. This thesis focuses on the design of an autonomous quadcopter videographer, i.e. a quadcopter capable of capturing good footage of a specific subject. In order to obtain this footage, the system needs to choose appropriate vantage points and control the quadcopter. Skilled human videographers can easily spot good filming locations where the subject and its actions can be seen clearly in the resulting video footage, but translating this knowledge to a robot can be complex. We present an autonomous system implemented on a commercially available quadcopter that achieves this using only the monocular information and an accelerometer. Our system has two vantage point selection strategies: 1) a reactive approach, which moves the robot to a fixed location with respect to the human and 2) the combination of the reactive approach and a POMDP planner that considers the target's movement intentions. We compare the behavior of these two approaches under different target movement scenarios. The results show that the POMDP planner obtains more stable footage with less quadcopter motion.
Show less - Date Issued
- 2015
- Identifier
- CFE0005592, ucf:50246
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005592
- Title
- Synthetic generators for simulating social networks.
- Creator
-
Mohammed Ali, Awrad, Sukthankar, Gita, Wu, Annie, Boloni, Ladislau, University of Central Florida
- Abstract / Description
-
An application area of increasing importance is creating agent-based simulations to model human societies. One component of developing these simulations is the ability to generate realistic human social networks. Online social networking websites, such as Facebook, Google+, and Twitter, have increased in popularity in the last decade. Despite the increase in online social networking tools and the importance of studying human behavior in these networks, collecting data directly from these...
Show moreAn application area of increasing importance is creating agent-based simulations to model human societies. One component of developing these simulations is the ability to generate realistic human social networks. Online social networking websites, such as Facebook, Google+, and Twitter, have increased in popularity in the last decade. Despite the increase in online social networking tools and the importance of studying human behavior in these networks, collecting data directly from these networks is not always feasible due to privacy concerns. Previous work in this area has primarily been limited to 1) network generators that aim to duplicate a small subset of the original network's properties and 2) problem-specific generators for applications such as the evaluation of community detection algorithms.In this thesis, we extended two synthetic network generators to enable them to duplicate the properties of a specific dataset. In the first generator, we consider feature similarity and label homophily among individuals when forming links. The second generator is designed to handle multiplex networks that contain different link types. We evaluate the performance of both generators on existing real-world social network datasets, as well as comparing our methods with a related synthetic network generator. In this thesis, we demonstrate that the proposed synthetic network generators are both time efficient and require only limited parameter optimization.
Show less - Date Issued
- 2014
- Identifier
- CFE0005532, ucf:50300
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005532
- Title
- ACTION RECOGNITION USING PARTICLE FLOW FIELDS.
- Creator
-
Reddy, Kishore, Shah, Mubarak, Sukthankar, Gita, Wei, Lei, Moore, Brian, University of Central Florida
- Abstract / Description
-
In recent years, research in human action recognition has advanced on multiple fronts to address various types of actions including simple, isolated actions in staged data (e.g., KTH dataset), complex actions (e.g., Hollywood dataset), and naturally occurring actions in surveillance videos (e.g, VIRAT dataset). Several techniques including those based on gradient, flow, and interest-points, have been developed for their recognition. Most perform very well in standard action recognition...
Show moreIn recent years, research in human action recognition has advanced on multiple fronts to address various types of actions including simple, isolated actions in staged data (e.g., KTH dataset), complex actions (e.g., Hollywood dataset), and naturally occurring actions in surveillance videos (e.g, VIRAT dataset). Several techniques including those based on gradient, flow, and interest-points, have been developed for their recognition. Most perform very well in standard action recognition datasets, but fail to produce similar results in more complex, large-scale datasets. Action recognition on large categories of unconstrained videos taken from the web is a very challenging problem compared to datasets like KTH (six actions), IXMAS (thirteen actions), and Weizmann (ten actions). Challenges such as camera motion, different viewpoints, huge interclass variations, cluttered background, occlusions, bad illumination conditions, and poor quality of web videos cause the majority of the state-of-the-art action recognition approaches to fail. An increasing number of categories and the inclusion of actions with high confusion also increase the difficulty of the problem. The approach taken to solve this action recognition problem depends primarily on the dataset and the possibility of detecting and tracking the object of interest. In this dissertation, a new method for video representation is proposed and three new approaches to perform action recognition in different scenarios using varying prerequisites are presented. The prerequisites have decreasing levels of difficulty to obtain: 1) Scenario requires human detection and tracking to perform action recognition; 2) Scenario requires background and foreground separation to perform action recognition; and 3) No pre-processing is required for action recognition.First, we propose a new video representation using optical flow and particle advection. The proposed ``Particle Flow Field'' (PFF) representation has been used to generate motion descriptors and tested in a Bag of Video Words (BoVW) framework on the KTH dataset. We show that particle flow fields has better performance than other low-level video representations, such as 2D-Gradients, 3D-Gradients and optical flow. Second, we analyze the performance of the state-of-the-art technique based on the histogram of oriented 3D-Gradients in spatio temporal volumes, where human detection and tracking are required. We use the proposed particle flow field and show superior results compared to the histogram of oriented 3D-Gradients in spatio temporal volumes. The proposed method, when used for human action recognition, just needs human detection and does not necessarily require human tracking and figure centric bounding boxes. It has been tested on KTH (six actions), Weizmann (ten actions), and IXMAS (thirteen actions, 4 different views) action recognition datasets.Third, we propose using the scene context information obtained from moving and stationary pixels in the key frames, in conjunction with motion descriptors obtained using Bag of Words framework, to solve the action recognition problem on a large (50 actions) dataset with videos from the web. We perform a combination of early and late fusion on multiple features to handle the huge number of categories. We demonstrate that scene context is a very important feature for performing action recognition on huge datasets.The proposed method needs separation of moving and stationary pixels, and does not require any kind of video stabilization, person detection, or tracking and pruning of features. Our approach obtains good performance on a huge number of action categories. It has been tested on the UCF50 dataset with 50 action categories, which is an extension of the UCF YouTube Action (UCF11) Dataset containing 11 action categories. We also tested our approach on the KTH and HMDB51 datasets for comparison.Finally, we focus on solving practice problems in representing actions by bag of spatio temporal features (i.e. cuboids), which has proven valuable for action recognition in recent literature. We observed that the visual vocabulary based (bag of video words) method suffers from many drawbacks in practice, such as: (i) It requires an intensive training stage to obtain good performance; (ii) it is sensitive to the vocabulary size; (iii) it is unable to cope with incremental recognition problems; (iv) it is unable to recognize simultaneous multiple actions; (v) it is unable to perform recognition frame by frame. In order to overcome these drawbacks, we propose a framework to index large scale motion features using Sphere/Rectangle-tree (SR-tree) for incremental action detection and recognition. The recognition comprises of the following two steps: 1) recognizing the local features by non-parametric nearest neighbor (NN), and 2) using a simple voting strategy to label the action. It can also provide localization of the action. Since it does not require feature quantization it can efficiently grow the feature-tree by adding features from new training actions or categories. Our method provides an effective way for practical incremental action recognition. Furthermore, it can handle large scale datasets because the SR-tree is a disk-based data structure. We tested our approach on two publicly available datasets, the KTH dataset and the IXMAS multi-view dataset, and achieved promising results.
Show less - Date Issued
- 2012
- Identifier
- CFE0004626, ucf:49923
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004626
