Current Search: Learning Models (x)
View All Items
(1 - 20 of 33)
Pages
- Title
- PREDICTING ANXIETY FROM PARENT AND CHILDHOOD VARIABLES.
- Creator
-
Fisak, Brian, Negy, Charles, University of Central Florida
- Abstract / Description
-
The high prevalence rate, significant distress and impairment, and persistence of childhood anxiety disorders highlight the need for continued theoretical conceptualization and research into the developmental pathways associated these disorders. In response to this need, one goal this project was to examination and identify variables associated with the development and/or maintenance of child anxiety disorders. A second goal of this project was to examine the potential role of learning from...
Show moreThe high prevalence rate, significant distress and impairment, and persistence of childhood anxiety disorders highlight the need for continued theoretical conceptualization and research into the developmental pathways associated these disorders. In response to this need, one goal this project was to examination and identify variables associated with the development and/or maintenance of child anxiety disorders. A second goal of this project was to examine the potential role of learning from parents as a risk factor in the development of child anxiety, with a particular emphasis on three learning mechanisms: modeling, information transfer, and reinforcement of anxious behaviors. The third goal of this project was to compare and contrast the developmental predictors of anxiety in White versus Hispanic samples. Data was collected from a sample of mothers in the community with at least one child between the ages of 6 and 12, and an unrelated sample of young adults. Significant predictors of anxiety were identified in both samples, and the hypothesis that anxiety may, in part, be learned from parents was supported in both samples. In addition, results indicated different sets of predictors of anxiety in White versus Hispanic participants. Limitations and implications of the findings are discussed.
Show less - Date Issued
- 2006
- Identifier
- CFE0001261, ucf:46916
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001261
- Title
- Online, Supervised and Unsupervised Action Localization in Videos.
- Creator
-
Soomro, Khurram, Shah, Mubarak, Heinrich, Mark, Hu, Haiyan, Bagci, Ulas, Yun, Hae-Bum, University of Central Florida
- Abstract / Description
-
Action recognition classifies a given video among a set of action labels, whereas action localization determines the location of an action in addition to its class. The overall aim of this dissertation is action localization. Many of the existing action localization approaches exhaustively search (spatially and temporally) for an action in a video. However, as the search space increases with high resolution and longer duration videos, it becomes impractical to use such sliding window...
Show moreAction recognition classifies a given video among a set of action labels, whereas action localization determines the location of an action in addition to its class. The overall aim of this dissertation is action localization. Many of the existing action localization approaches exhaustively search (spatially and temporally) for an action in a video. However, as the search space increases with high resolution and longer duration videos, it becomes impractical to use such sliding window techniques. The first part of this dissertation presents an efficient approach for localizing actions by learning contextual relations between different video regions in training. In testing, we use the context information to estimate the probability of each supervoxel belonging to the foreground action and use Conditional Random Field (CRF) to localize actions. In the above method and typical approaches to this problem, localization is performed in an offline manner where all the video frames are processed together. This prevents timely localization and prediction of actions/interactions - an important consideration for many tasks including surveillance and human-machine interaction. Therefore, in the second part of this dissertation we propose an online approach to the challenging problem of localization and prediction of actions/interactions in videos. In this approach, we use human poses and superpixels in each frame to train discriminative appearance models and perform online prediction of actions/interactions with Structural SVM. Above two approaches rely on human supervision in the form of assigning action class labels to videos and annotating actor bounding boxes in each frame of training videos. Therefore, in the third part of this dissertation we address the problem of unsupervised action localization. Given unlabeled videos without annotations, this approach aims at: 1) Discovering action classes using a discriminative clustering approach, and 2) Localizing actions using a variant of Knapsack problem.
Show less - Date Issued
- 2017
- Identifier
- CFE0006917, ucf:51685
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006917
- Title
- MODELING THE INFLUENCES OF PERSONALITY PREFERENCES ON THE SELECTION OF INSTRUCTIONAL STRATEGIES ININTELLIGENT TUTORING SYSTEMS.
- Creator
-
Sottilare, Robert, Proctor, Michael, University of Central Florida
- Abstract / Description
-
This thesis hypothesizes that a method for selecting instructional strategies (specifically media) based in part on a relationship between learning style preference and personality preference provides more relevant and understandable feedback to students and thereby higher learning effectiveness. This research investigates whether personality preferences are valid predictors of learning style preferences. Since learning style preferences are a key consideration in instructional strategies and...
Show moreThis thesis hypothesizes that a method for selecting instructional strategies (specifically media) based in part on a relationship between learning style preference and personality preference provides more relevant and understandable feedback to students and thereby higher learning effectiveness. This research investigates whether personality preferences are valid predictors of learning style preferences. Since learning style preferences are a key consideration in instructional strategies and instructional strategies are a key consideration in learning effectiveness, this thesis contributes to a greater understanding of the relationship between personality preferences and effective learning in intelligent tutoring systems (ITS). This research attempts to contribute to the goal of a "truly adaptive ITS" by first examining relationships between personality preferences and learning style preferences; and then by modeling the influences of personality on learning strategies to optimize feedback for each student. This thesis explores the general question "what can personality preferences contribute to learning in intelligent tutoring systems?" So, why is it important to evaluate the relationship between personality preferences and learning strategies in ITS? "While one-on-one human tutoring is still superior to ITS in general, this approach is idiosyncratic and not feasible to deliver to [any large population] in any cost-effective manner." (Loftin, 2004). Given the need for ITS in large, distributed populations (i.e. the United States Army), it is important to explore methods of increasing ITS performance and adaptability. Findings of this research include that the null hypothesis that "there is no dependency between personality preference variables and learning style preference variables" was partly rejected. Highly significant correlations between the personality preferences, openness and extraversion, were established for both the active-reflective and sensing-intuitive learning style preferences. Discussion of other relationships is provided.
Show less - Date Issued
- 2006
- Identifier
- CFE0001403, ucf:47074
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001403
- Title
- IMPROVING METACOMPREHENSION AND LEARNING THROUGH GRADUATED CONCEPT MODEL DEVELOPMENT.
- Creator
-
Kring, Eleni, Salas, Eduardo, University of Central Florida
- Abstract / Description
-
Mental model development, deeper levels of information processing, and elaboration are critical to learning. More so, individuals' metacomprehension accuracy is integral to making improvements to their knowledge base. In other words, without an accurate perception of their knowledge on a topic, learners may not know that knowledge gaps or misperceptions exist and, thus, would be less likely to correct them. Therefore, this study offered a dual-process approach that aimed at enhancing...
Show moreMental model development, deeper levels of information processing, and elaboration are critical to learning. More so, individuals' metacomprehension accuracy is integral to making improvements to their knowledge base. In other words, without an accurate perception of their knowledge on a topic, learners may not know that knowledge gaps or misperceptions exist and, thus, would be less likely to correct them. Therefore, this study offered a dual-process approach that aimed at enhancing metacomprehension. One path aimed at advancing knowledge structure development and, thus, mental model development. The other focused on promoting a deeper level of information processing through processes like elaboration. It was predicted that this iterative approach would culminate in improved metacomprehension and increased learning. Accordingly, using the Graduated Concept Model Development (GCMD) approach, the role of learner-generated concept model development in facilitating metacomprehension and knowledge acquisition was examined. Concept maps have had many roles in the learning process as mental model assessment tools and advanced organizers. However, this study examined the process of concept model building as an effective training tool. Whereas, concept maps functioning as advanced organizers are certainly beneficial, it would seem that the benefits of having a learner examine and amend the current state of their knowledge through concept model development would prove more effective for learning. In other words, learners looking at an advanced organizer of the training material may feel assured that they have a thorough understanding of it. Only when they are forced to create a representation of the material would the gaps and misperceptions in their knowledge base likely be revealed. In short, advanced organizers seem to rely on recognition, where concept model development likely requires recalling and understanding 'how' and 'why' the interrelationships between concepts exist. Therefore, the Graduated Concept Model Development (GCMD) technique offered in this study was based on the theory that knowledge acquisition improves when learners integrate new information into existing knowledge, assign elaborated meanings to concepts, correct misperceptions, close knowledge gaps, and strengthen accurate connections between concepts by posing targeted questions against their existing knowledge structures. This study placed an emphasis on meaningful learning and suggested a process by which newly introduced concepts would be manipulated for the purpose of improving metacomprehension by strengthening accurate knowledge structures and mental model development, and through deeper and elaborated information processing. Indeed, central to improving knowledge deficiencies and misunderstandings is metacomprehension, and the constructing of concepts maps was hypothesized to improve metacomprehension accuracy and, thus, learning. This study was a one-factor between-groups design with concept map type as the independent variable, manipulated at four levels: no concept map, concept map as advanced organizer, learner-built concept map with feedback, and learner-built concept map without feedback. The dependent variables included performance (percent correct) on a declarative and integrative knowledge assessment, mental model development, and metacomprehension accuracy. Participants were 68 (34 female, 34 male, ages 18-35, mean age = 21.43) undergraduate students from a major southeastern university. Participants were randomly assigned to one of the four experimental conditions, and analysis revealed no significant differences between the groups. Upon arrival, participants were randomly assigned to one of the four experimental conditions. Participants then progressed through the three stages of the experiment. In Stage I, participants completed forms regarding informed consent, general biographical information, and task self-efficacy. In Stage II, participants completed the self-paced tutorial based on the Distributed Dynamic Decision Making (DDD) model, a simulated military command and control environment aimed at creating events to encourage team coordination and performance (for a detailed description, see Kleinman & Serfaty, 1989). The manner by which participants worked through the tutorial was determined by their assigned concept map condition. Upon finishing each module of the tutorial, participants then completed a metacomprehension prediction question. In Stage III, participants completed the computer-based knowledge assessment test, covering both declarative and integrative knowledge, followed by the metacomprehension postdiction question. Participants then completed the card sort task, as the assessment of mental model development. Finally, participants completed a general study survey and were debriefed as to the purpose of the study. The entire experiment lasted approximately 2 to 3 hours. Results indicated that the GCMD condition showed a stronger indication of metacomprehension accuracy, via prediction measures, compared with the other three conditions (control, advanced organizer, and feedback), and, specifically, significantly higher correlations than the other three conditions in declarative knowledge. Self-efficacy measures also indicated that the higher metacomprehension accuracy correlation observed in the GCMD condition was likely the result of the intervention, and not due to differences in self-efficacy in that group of participants. Likewise, the feedback and GCMD conditions led to significantly high correlations for metacomprehension accuracy based on levels of understanding on the declarative knowledge tutorial module (Module 1). The feedback condition also showed similar responses for the integrative knowledge module (Module 2). The advanced organizer, feedback, and GCMD conditions were also found to have significantly high correlation of self-reported postdiction of performance on the knowledge assessment and the actual results of the knowledge assessment results. However, results also indicated that there were no significant findings between the four conditions in mental model assessment and knowledge assessment. Nevertheless, results support the relevance of accurate mental model development in knowledge assessment outcomes. Retrospectively, two opposing factors may have complicated efforts to detect additional differences between groups. From one side, the experimental measures may not have been rigorous enough to filter out the effect from the intervention itself. Conversely, software usability issues and the resulting limitations in experimental design may have worked negatively against the two concept mapping conditions and, inadvertently, suppressed effects of the intervention. Future research in the GCMD approach will likely review cognitive workload, concept mapping software design, and the sensitivity of the measures involved.
Show less - Date Issued
- 2004
- Identifier
- CFE0000312, ucf:46311
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000312
- Title
- A MULTI-OBJECTIVE NO-REGRET DECISION MAKING MODEL WITH BAYESIAN LEARNING FOR AUTONOMOUS UNMANNED SYSTEMS.
- Creator
-
Howard, Matthew, Qu, Zhihua, University of Central Florida
- Abstract / Description
-
The development of a multi-objective decision making and learning model for the use in unmanned systems is the focus of this project. Starting with traditional game theory and psychological learning theories developed in the past, a new model for machine learning is developed. This model incorporates a no-regret decision making model with a Bayesian learning process which has the ability to adapt to errors found in preconceived costs associated with each objective. This learning ability is...
Show moreThe development of a multi-objective decision making and learning model for the use in unmanned systems is the focus of this project. Starting with traditional game theory and psychological learning theories developed in the past, a new model for machine learning is developed. This model incorporates a no-regret decision making model with a Bayesian learning process which has the ability to adapt to errors found in preconceived costs associated with each objective. This learning ability is what sets this model apart from many others. By creating a model based on previously developed human learning models, hundreds of years of experience in these fields can be applied to the recently developing field of machine learning. This also allows for operators to more comfortably adapt to the machine's learning process in order to better understand how to take advantage of its features. One of the main purposes of this system is to incorporate multiple objectives into a decision making process. This feature can better allow its users to clearly define objectives and prioritize these objectives allowing the system to calculate the best approach for completing the mission. For instance, if an operator is given objectives such as obstacle avoidance, safety, and limiting resource usage, the operator would traditionally be required to decide how to meet all of these objectives. The use of a multi-objective decision making process such as the one designed in this project, allows the operator to input the objectives and their priorities and receive an output of the calculated optimal compromise.
Show less - Date Issued
- 2008
- Identifier
- CFE0002453, ucf:47711
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002453
- Title
- THE EFFECTS OF THE 5E LEARNING CYCLE MODEL ON STUDENTS' UNDERSTANDING OF FORCE AND MOTION CONCEPTS.
- Creator
-
Campbell, Meghann, Sweeney, Aldrin, University of Central Florida
- Abstract / Description
-
As advocated by the National Research Council [NRC] (1996) and the American Association for the Advancement of Science [AAAS] (1989), a change in the manner in which science is taught must be recognized at a national level and also embraced at a level that is reflected in every science teacher's classroom. With these ideas set forth as a guide for change,this study investigated the fifth grade students' understanding of force and motion concepts as they engaged in inquiry-based science...
Show moreAs advocated by the National Research Council [NRC] (1996) and the American Association for the Advancement of Science [AAAS] (1989), a change in the manner in which science is taught must be recognized at a national level and also embraced at a level that is reflected in every science teacher's classroom. With these ideas set forth as a guide for change,this study investigated the fifth grade students' understanding of force and motion concepts as they engaged in inquiry-based science investigations through the use of the 5E Learning Cycle. The researcher's journey through this process was also a focus of the study. Initial data were provided by a pretest indicating students' understanding of force and motion concepts. Four times weekly for a period of 14 weeks, students participated in investigations related to force and motion concepts. Their subsequent understanding of these concepts and their ability to generalize their understandings was evaluated via a posttest. Additionally, a review of lab activity sheets, other classroom-based assessments, and filmed interviews allowed for the triangulation of pertinent data necessary to draw conclusions from the study. Findings showed that student knowledge of force and motion concepts did increase although their understanding as demonstrated on paper lacked completeness versus understanding in an interview setting. Survey results also showed that after the study students believed they did not learn science best via textbook-based instruction.
Show less - Date Issued
- 2006
- Identifier
- CFE0001007, ucf:46831
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001007
- Title
- A REINFORCEMENT LEARNING TECHNIQUE FOR ENHANCING HUMAN BEHAVIOR MODELS IN A CONTEXT-BASED ARCHITECTURE.
- Creator
-
Aihe, David, Gonzalez, Avelino, University of Central Florida
- Abstract / Description
-
A reinforcement-learning technique for enhancing human behavior models in a context-based learning architecture is presented. Prior to the introduction of this technique, human models built and developed in a Context-Based reasoning framework lacked learning capabilities. As such, their performance and quality of behavior was always limited by what the subject matter expert whose knowledge is modeled was able to articulate or demonstrate. Results from experiments performed show that subject...
Show moreA reinforcement-learning technique for enhancing human behavior models in a context-based learning architecture is presented. Prior to the introduction of this technique, human models built and developed in a Context-Based reasoning framework lacked learning capabilities. As such, their performance and quality of behavior was always limited by what the subject matter expert whose knowledge is modeled was able to articulate or demonstrate. Results from experiments performed show that subject matter experts are prone to making errors and at times they lack information on situations that are inherently necessary for the human models to behave appropriately and optimally in those situations. The benefits of the technique presented is two fold; 1) It shows how human models built in a context-based framework can be modified to correctly reflect the knowledge learnt in a simulator; and 2) It presents a way for subject matter experts to verify and validate the knowledge they share. The results obtained from this research show that behavior models built in a context-based framework can be enhanced by learning and reflecting the constraints in the environment. From the results obtained, it was shown that after the models are enhanced, the agents performed better based on the metrics evaluated. Furthermore, after learning, the agent was shown to recognize unknown situations and behave appropriately in previously unknown situations. The overall performance and quality of behavior of the agent improved significantly.
Show less - Date Issued
- 2008
- Identifier
- CFE0002466, ucf:47715
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002466
- Title
- Improving Student Learning in Undergraduate Mathematics.
- Creator
-
Rejniak, Gabrielle, Young, Cynthia, Brennan, Joseph, Martin, Heath, University of Central Florida
- Abstract / Description
-
The goal of this study was to investigate ways of improving student learning, par-ticularly conceptual understanding, in undergraduate mathematics courses. This studyfocused on two areas: course design and animation. The methods of study were thefollowing: Assessing the improvement of student conceptual understanding as a result of teamproject-based learning, individual inquiry-based learning and the modied empo-rium model; and Assessing the impact of animated videos on student learning with...
Show moreThe goal of this study was to investigate ways of improving student learning, par-ticularly conceptual understanding, in undergraduate mathematics courses. This studyfocused on two areas: course design and animation. The methods of study were thefollowing: Assessing the improvement of student conceptual understanding as a result of teamproject-based learning, individual inquiry-based learning and the modied empo-rium model; and Assessing the impact of animated videos on student learning with the emphasis onconcepts.For the first part of our study (impact of course design on student conceptual understanding) we began by comparing the following three groups in Fall 2010 and Fall2011:1. Fall 2010: MAC 1140 Traditional Lecture (&) Fall 2011: MAC 1140 Modied Empo-rium2. Fall 2010: MAC 1140H with Project (&) Fall 2011: MAC 1140H no Project3. Fall 2010: MAC 2147 with Projects (&) Fall 2011: MAC 2147 no ProjectsAnalysis of pre-tests and post-tests show that all three courses showed statistically significant increases, according to their respective sample sizes, during Fall 2010. However, in Fall 2011 only MAC 2147 continued to show a statistically significant increase. Therefore in Fall 2010, project-based learning - both in-class individual projects and out-of-class team projects - conclusively impacted the students' conceptual understanding. Whereas, in Fall 2011, the data for the Modified Emporium model had no statistical significance and is therefore inconclusive as to its effectiveness. In addition the difference in percent ofincrease for MAC 1140 between Fall 2010 - traditional lecture model - and Fall 2011 -modified emporium model - is not statistically significant and we cannot say that either model is a better delivery mode for conceptual learning. For the second part of our study, the students enrolled in MAC 1140H Fall 2011 and MAC 2147 Fall 2011 were given a pre-test on sequences and series before showing them an animated video related to the topic. After watching the video, students were then given the same 7 question post test to determine any improvement in the students' understanding of the topic. After two weeks of teacher-led instruction, the students tookthe same post-test again. The results of this preliminary study indicate that animated videos do impact the conceptual understanding of students when used as an introduction into a new concept. Both courses that were shown the video had statistically significant increases in the conceptual understanding of the students between the pre-test and the post-animation test.
Show less - Date Issued
- 2012
- Identifier
- CFE0004320, ucf:49481
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004320
- Title
- CONTRIBUTIONS BY INDIVIDUAL AND GROUP STRATEGIES FOR ORGANIZATIONAL LEARNING IN ARCHITECTURAL, ENGINEERING, AND CONSTRUCTION FIRMS.
- Creator
-
Beaver, Robert, Kotnour, Timothy, University of Central Florida
- Abstract / Description
-
Organizations with multiple operating requirements require support functions to assist in execution of strategic goals. This effort, in turn, requires management of engineering activities in control of projects and in sustaining facilities. High level strategies include employing engineering support that consists of a project management function encompassing technical and managerial disciplines. The architecture/engineering, and construction office (AEC) is the subject of this research....
Show moreOrganizations with multiple operating requirements require support functions to assist in execution of strategic goals. This effort, in turn, requires management of engineering activities in control of projects and in sustaining facilities. High level strategies include employing engineering support that consists of a project management function encompassing technical and managerial disciplines. The architecture/engineering, and construction office (AEC) is the subject of this research. Engineering and construction oriented organizations have experienced challenges to their abilities to learn and grow. This has potential detrimental implications for these organizations if support functions cannot keep pace with changing objectives and strategy. The competitive nature and low industry margins as well as uniqueness of projects as challenges facing engineering and construction. The differentiated nature of projects tasks also creates a need for temporary and dedicated modes of operation and thereby tends to promote highly dispersed management practices that do not dovetail very well with other organizational processes. Organizational learning is a means to enhance and support knowledge management for improving performance. The problem addressed through this research is the gap between desired and achieved individual and group learning by members of the AEC, and the members' abilities to distinguish between the need for adaptive learning or innovation. This research addresses learning by individuals and groups, and the strategies employed through an empirical study (survey). A conceptual model for organizational learning contributions by individuals and groups is presented and tested for confirmation of exploitive or explorative learning strategies for individuals, and directions composed of depth and breadth of learning. Strategies for groups are tested for internal or external search orientations and directions toward the single or multi-discipline unit. The survey is analyzed by method of principal components extraction and further interpreted to reveal factors that are correlated by Pearson product moment coefficients and tested for significance for potential relationships to factors for outcomes. Correlation across dependent variables prevented interpretation of the most significant factors for group learning strategies. However, results provide possible support for direction in supporting processes that promote networking among individuals and group structures that recognize the dual nature of knowledge - that required for technical competency and that required for success in the organization. Recommendations for practitioners include adjustments to knowledge acquisition direction, promoting external collaboration among firms, and provision of dual succession pathways through technical expertise or organizational processes for senior staff.
Show less - Date Issued
- 2009
- Identifier
- CFE0002682, ucf:48194
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002682
- Title
- Examining High School Teachers' Technology Acceptation of A Learning Management System in A Large Public School District.
- Creator
-
Foster-Hennighan, Shari, Butler, Malcolm, Hewitt, Randall, Boote, David, Swan, Bonnie, University of Central Florida
- Abstract / Description
-
The purpose of this research study was to understand high school teachers' acceptance and use of Canvas Learning Management System (LMS) (Canvas, 2011) in a large public school district. Teachers are the keystone species within the educational environment, and as such, are critical for the successful integration of technology in the classroom (Davis, Eickelmann, (&) Zaka, 2013). Therefore, in order to facilitate teacher's acceptance and use of technology for instructional purposes, those...
Show moreThe purpose of this research study was to understand high school teachers' acceptance and use of Canvas Learning Management System (LMS) (Canvas, 2011) in a large public school district. Teachers are the keystone species within the educational environment, and as such, are critical for the successful integration of technology in the classroom (Davis, Eickelmann, (&) Zaka, 2013). Therefore, in order to facilitate teacher's acceptance and use of technology for instructional purposes, those factors that influence or prevent use need to be understood. This study used a revised Technology Acceptance Model (Fathema, Shannon, (&) Ross, 2015) to determine those factors that affect teachers' actual informational and communicational use of the Canvas LMS (Canvas, 2011). This mixed methods study used a survey and interview to answer three research questions concerning acceptance, use, and departmental influence on the use of Canvas LMS. The survey data were analyzed with Exploratory Factor Analysis (EFA) and Structural Equation Modeling (SEM) in order to produce two explanatory models to address the three research questions. The semi-structured interviews were conducted with 16 teachers from one high school in a large public school district. The interview questions were transcribed, coded, and themed in order to answer research questions two and three. The analysis of the survey and interview data found that teachers were more likely to use informational rather than communicational features in Canvas. Communicational use differences were more evident than informational use among the four core subject areas, with mathematics using these features the least. For both models of survey data, the quality of the Canvas system was an influence on teacher use. The influence of teacher intent was contradictory between the two models. The findings from this study can be used to inform stakeholders of factors that influence high school teachers Canvas use, and recommendations to improve integration in the future.
Show less - Date Issued
- 2019
- Identifier
- CFE0007631, ucf:52478
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007631
- Title
- Model Selection via Racing.
- Creator
-
Zhang, Tiantian, Georgiopoulos, Michael, Anagnostopoulos, Georgios, Wu, Annie, Hu, Haiyan, Nickerson, David, University of Central Florida
- Abstract / Description
-
Model Selection (MS) is an important aspect of machine learning, as necessitated by the No Free Lunch theorem. Briefly speaking, the task of MS is to identify a subset of models that are optimal in terms of pre-selected optimization criteria. There are many practical applications of MS, such as model parameter tuning, personalized recommendations, A/B testing, etc. Lately, some MS research has focused on trading off exactness of the optimization with somewhat alleviating the computational...
Show moreModel Selection (MS) is an important aspect of machine learning, as necessitated by the No Free Lunch theorem. Briefly speaking, the task of MS is to identify a subset of models that are optimal in terms of pre-selected optimization criteria. There are many practical applications of MS, such as model parameter tuning, personalized recommendations, A/B testing, etc. Lately, some MS research has focused on trading off exactness of the optimization with somewhat alleviating the computational burden entailed. Recent attempts along this line include metaheuristics optimization, local search-based approaches, sequential model-based methods, portfolio algorithm approaches, and multi-armed bandits.Racing Algorithms (RAs) are an active research area in MS, which trade off some computational cost for a reduced, but acceptable likelihood that the models returned are indeed optimal among the given ensemble of models. All existing RAs in the literature are designed as Single-Objective Racing Algorithm (SORA) for Single-Objective Model Selection (SOMS), where a single optimization criterion is considered for measuring the goodness of models. Moreover, they are offline algorithms in which MS occurs before model deployment and the selected models are optimal in terms of their overall average performances on a validation set of problem instances. This work aims to investigate racing approaches along two distinct directions: Extreme Model Selection (EMS) and Multi-Objective Model Selection (MOMS). In EMS, given a problem instance and a limited computational budget shared among all the candidate models, one is interested in maximizing the final solution quality. In such a setting, MS occurs during model comparison in terms of maximum performance and involves no model validation. EMS is a natural framework for many applications. However, EMS problems remain unaddressed by current racing approaches. In this work, the first RA for EMS, named Max-Race, is developed, so that it optimizes the extreme solution quality by automatically allocating the computational resources among an ensemble of problem solvers for a given problem instance. In Max-Race, significant difference between the extreme performances of any pair of models is statistically inferred via a parametric hypothesis test under the Generalized Pareto Distribution (GPD) assumption. Experimental results have confirmed that Max-Race is capable of identifying the best extreme model with high accuracy and low computational cost. Furthermore, in machine learning, as well as in many real-world applications, a variety of MS problems are multi-objective in nature. MS which simultaneously considers multiple optimization criteria is referred to as MOMS. Under this scheme, a set of Pareto optimal models is sought that reflect a variety of compromises between optimization objectives. So far, MOMS problems have received little attention in the relevant literature. Therefore, this work also develops the first Multi-Objective Racing Algorithm (MORA) for a fixed-budget setting, namely S-Race. S-Race addresses MOMS in the proper sense of Pareto optimality. Its key decision mechanism is the non-parametric sign test, which is employed for inferring pairwise dominance relationships. Moreover, S-Race is able to strictly control the overall probability of falsely eliminating any non-dominated models at a user-specified significance level. Additionally, SPRINT-Race, the first MORA for a fixed-confidence setting, is also developed. In SPRINT-Race, pairwise dominance and non-dominance relationships are established via the Sequential Probability Ratio Test with an Indifference zone. Moreover, the overall probability of falsely eliminating any non-dominated models or mistakenly retaining any dominated models is controlled at a prescribed significance level. Extensive experimental analysis has demonstrated the efficiency and advantages of both S-Race and SPRINT-Race in MOMS.
Show less - Date Issued
- 2016
- Identifier
- CFE0006203, ucf:51094
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006203
- 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
- Examining the Effects of Self-Regulated Strategy Development in Combination with Video Self-Modeling on Writing by Third Grade Students with Learning Disabilities.
- Creator
-
Miller, Katie, Little, Mary, Dieker, Lisa, Pearl, Cynthia, Roberts, Sherron, University of Central Florida
- Abstract / Description
-
This research examined the effects of self-regulated strategy development (SRSD), a cognitive strategy instructional method, on opinion writing by third grade students with learning disabilities. A video self-modeling (VSM) component was added to the SRSD method. A multiple probe across participants, single-subject design was used to determine the effectiveness of the SRSD instructional strategy, (POW + TREE), in combination with video self-modeling. Data from various components of writing,...
Show moreThis research examined the effects of self-regulated strategy development (SRSD), a cognitive strategy instructional method, on opinion writing by third grade students with learning disabilities. A video self-modeling (VSM) component was added to the SRSD method. A multiple probe across participants, single-subject design was used to determine the effectiveness of the SRSD instructional strategy, (POW + TREE), in combination with video self-modeling. Data from various components of writing, including essay elements, length of responses, time spent writing, and overall writing quality, were collected and assessed to determine the effectiveness of the intervention. All students who received the intervention improved their overall writing performance on opinion essays as measured by the number of opinion essay elements, including topic sentence, reasons, examples, and ending. During the maintenance phase of the intervention, students who received a VSM booster session increased their total number of opinion essay elements back to mastery levels.
Show less - Date Issued
- 2013
- Identifier
- CFE0004893, ucf:49674
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004893
- Title
- DATA MINING METHODS FOR MALWARE DETECTION.
- Creator
-
Siddiqui, Muazzam, Wang, Morgan, University of Central Florida
- Abstract / Description
-
This research investigates the use of data mining methods for malware (malicious programs) detection and proposed a framework as an alternative to the traditional signature detection methods. The traditional approaches using signatures to detect malicious programs fails for the new and unknown malwares case, where signatures are not available. We present a data mining framework to detect malicious programs. We collected, analyzed and processed several thousand malicious and clean programs to...
Show moreThis research investigates the use of data mining methods for malware (malicious programs) detection and proposed a framework as an alternative to the traditional signature detection methods. The traditional approaches using signatures to detect malicious programs fails for the new and unknown malwares case, where signatures are not available. We present a data mining framework to detect malicious programs. We collected, analyzed and processed several thousand malicious and clean programs to find out the best features and build models that can classify a given program into a malware or a clean class. Our research is closely related to information retrieval and classification techniques and borrows a number of ideas from the field. We used a vector space model to represent the programs in our collection. Our data mining framework includes two separate and distinct classes of experiments. The first are the supervised learning experiments that used a dataset, consisting of several thousand malicious and clean program samples to train, validate and test, an array of classifiers. In the second class of experiments, we proposed using sequential association analysis for feature selection and automatic signature extraction. With our experiments, we were able to achieve as high as 98.4% detection rate and as low as 1.9% false positive rate on novel malwares.
Show less - Date Issued
- 2008
- Identifier
- CFE0002303, ucf:47870
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002303
- Title
- EVOLVING MODELS FROM OBSERVED HUMAN PERFORMANCE.
- Creator
-
Fernlund, Hans Karl Gustav, Gonzalez, Avelino J., University of Central Florida
- Abstract / Description
-
To create a realistic environment, many simulations require simulated agents with human behavior patterns. Manually creating such agents with realistic behavior is often a tedious and time-consuming task. This dissertation describes a new approach that automatically builds human behavior models for simulated agents by observing human performance. The research described in this dissertation synergistically combines Context-Based Reasoning, a paradigm especially developed to model tactical...
Show moreTo create a realistic environment, many simulations require simulated agents with human behavior patterns. Manually creating such agents with realistic behavior is often a tedious and time-consuming task. This dissertation describes a new approach that automatically builds human behavior models for simulated agents by observing human performance. The research described in this dissertation synergistically combines Context-Based Reasoning, a paradigm especially developed to model tactical human performance within simulated agents, with Genetic Programming, a machine learning algorithm to construct the behavior knowledge in accordance to the paradigm. This synergistic combination of well-documented AI methodologies has resulted in a new algorithm that effectively and automatically builds simulated agents with human behavior. This algorithm was tested extensively with five different simulated agents created by observing the performance of five humans driving an automobile simulator. The agents show not only the ability/capability to automatically learn and generalize the behavior of the human observed, but they also capture some of the personal behavior patterns observed among the five humans. Furthermore, the agents exhibited a performance that was at least as good as agents developed manually by a knowledgeable engineer.
Show less - Date Issued
- 2004
- Identifier
- CFE0000013, ucf:46068
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000013
- Title
- THE EFFECT OF SOCIAL PRESENCE ON TEACHER TECHNOLOGY ACCEPTANCE, CONTINUANCE INTENTION, AND PERFORMANCE IN AN ONLINE TEACHER PROFESSIONAL DEVELOPMENT COURSE.
- Creator
-
Smith, Jo, Sivo, Stephen, University of Central Florida
- Abstract / Description
-
The purpose of this study was to determine if the Technology Acceptance Model (TAM) could explain the relationship between teacher's acceptance of an online teacher professional development course and their continuance intentions regarding online teacher professional development (oTPD). This study focused on the perceptions of the teachers as opposed to the design or implementation of oTPD. The participants (N=517) were mostly teachers (88.8%) enrolled in a statewide online course to...
Show moreThe purpose of this study was to determine if the Technology Acceptance Model (TAM) could explain the relationship between teacher's acceptance of an online teacher professional development course and their continuance intentions regarding online teacher professional development (oTPD). This study focused on the perceptions of the teachers as opposed to the design or implementation of oTPD. The participants (N=517) were mostly teachers (88.8%) enrolled in a statewide online course to provide classroom teachers with the latest knowledge of research-based instructional reading strategies. The course was offered over a 10-14 week period during the Spring 2006 semester through a public state university. Structural equation modeling was used to create a path analytic model extending the TAM to include two additional constructs: sociability and social presence. In addition, gains in instructional reading strategies knowledge (performance) were examined. Using this expanded version of the TAM, the study examined the causal relationships between sociability, social presence, perceived usefulness, perceived ease of use, continuance intention, and gains. Online distance education research has indicated that social presence can influence post-secondary students' attitude and persistence within a web-based course. However a paucity of research exists on how technology acceptance and social presence impacts teachers within an online teacher professional development setting. Path analysis, univariate analysis of variance, and independent t-tests in SPSS v12.0 for Windows were used to analyze the data. The results suggest that the hypothesized extended model was a good fit. The model did indicate that both perceived ease of use and perceived usefulness were determinants of teachers' intent to continue using oTPD for future professional development needs.
Show less - Date Issued
- 2006
- Identifier
- CFE0001455, ucf:47064
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001455
- Title
- TOWARDS A SELF-CALIBRATING VIDEO CAMERA NETWORK FOR CONTENT ANALYSIS AND FORENSICS.
- Creator
-
Junejo, Imran, Foroosh, Hassan, University of Central Florida
- Abstract / Description
-
Due to growing security concerns, video surveillance and monitoring has received an immense attention from both federal agencies and private firms. The main concern is that a single camera, even if allowed to rotate or translate, is not sufficient to cover a large area for video surveillance. A more general solution with wide range of applications is to allow the deployed cameras to have a non-overlapping field of view (FoV) and to, if possible, allow these cameras to move freely in 3D space....
Show moreDue to growing security concerns, video surveillance and monitoring has received an immense attention from both federal agencies and private firms. The main concern is that a single camera, even if allowed to rotate or translate, is not sufficient to cover a large area for video surveillance. A more general solution with wide range of applications is to allow the deployed cameras to have a non-overlapping field of view (FoV) and to, if possible, allow these cameras to move freely in 3D space. This thesis addresses the issue of how cameras in such a network can be calibrated and how the network as a whole can be calibrated, such that each camera as a unit in the network is aware of its orientation with respect to all the other cameras in the network. Different types of cameras might be present in a multiple camera network and novel techniques are presented for efficient calibration of these cameras. Specifically: (i) For a stationary camera, we derive new constraints on the Image of the Absolute Conic (IAC). These new constraints are shown to be intrinsic to IAC; (ii) For a scene where object shadows are cast on a ground plane, we track the shadows on the ground plane cast by at least two unknown stationary points, and utilize the tracked shadow positions to compute the horizon line and hence compute the camera intrinsic and extrinsic parameters; (iii) A novel solution to a scenario where a camera is observing pedestrians is presented. The uniqueness of formulation lies in recognizing two harmonic homologies present in the geometry obtained by observing pedestrians; (iv) For a freely moving camera, a novel practical method is proposed for its self-calibration which even allows it to change its internal parameters by zooming; and (v) due to the increased application of the pan-tilt-zoom (PTZ) cameras, a technique is presented that uses only two images to estimate five camera parameters. For an automatically configurable multi-camera network, having non-overlapping field of view and possibly containing moving cameras, a practical framework is proposed that determines the geometry of such a dynamic camera network. It is shown that only one automatically computed vanishing point and a line lying on any plane orthogonal to the vertical direction is sufficient to infer the geometry of a dynamic network. Our method generalizes previous work which considers restricted camera motions. Using minimal assumptions, we are able to successfully demonstrate promising results on synthetic as well as on real data. Applications to path modeling, GPS coordinate estimation, and configuring mixed-reality environment are explored.
Show less - Date Issued
- 2007
- Identifier
- CFE0001743, ucf:47296
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001743
- Title
- THE REALM OF SELF-REGULATED LEARNING (SRL): AN EXAMINATION OF SRL IN AN ELEMENTARY CLASSROOM SETTING AND ITS RELEVANCY TO TRENDS IN OUR CURRENT CURRICULA.
- Creator
-
Lutfi , Duaa, Olan, Elsie, University of Central Florida
- Abstract / Description
-
Teaching and instructing students is a necessity, but creating ways to challenge them is a priority. This thesis focuses on Barry Zimmerman and Timothy Clearly's Self-Regulation Empowerment Program (SREP). This model uses a problem-solving approach in establishing Self-Regulated Learning (SRL) strategies in students' learning. Stemming from interdisciplinary questions such as, "what will help students be successful in and outside the classroom?" and "how do teachers challenge students without...
Show moreTeaching and instructing students is a necessity, but creating ways to challenge them is a priority. This thesis focuses on Barry Zimmerman and Timothy Clearly's Self-Regulation Empowerment Program (SREP). This model uses a problem-solving approach in establishing Self-Regulated Learning (SRL) strategies in students' learning. Stemming from interdisciplinary questions such as, "what will help students be successful in and outside the classroom?" and "how do teachers challenge students without stifling their creativity?" this purpose of this study aims to explore the realm of Self-Regulated Learning (SRL). The present study further examines if SRL strategies and practices foster learning and are prevalent in current trends and curricula such as, Marzano and Common Core. After thorough analysis of student observations and coding of data, the findings concluded that SRL strategies fostered student learning. Students studied were more readily motivated to regulate their learning and attempt challenging tasks. Moreover these findings indicated an increase in student success and metacognitive knowledge, as the students were provided with more opportunities to engage in self-talk, self-reflection, strategic planning, and goal setting. Results suggested the flexibility of the SREP model and its application to current instructional practices. Implications and recommendations for further research into the SRL model across other disciplines are also presented and discussed.
Show less - Date Issued
- 2013
- Identifier
- CFH0004534, ucf:45151
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH0004534
- Title
- Analysis of Remote Tripping Command Injection Attacks in Industrial Control Systems Through Statistical and Machine Learning Methods.
- Creator
-
Timm, Charles, Caulkins, Bruce, Wiegand, Rudolf, Lathrop, Scott, University of Central Florida
- Abstract / Description
-
In the past decade, cyber operations have been increasingly utilized to further policy goals of state-sponsored actors to shift the balance of politics and power on a global scale. One of the ways this has been evidenced is through the exploitation of electric grids via cyber means. A remote tripping command injection attack is one of the types of attacks that could have devastating effects on the North American power grid. To better understand these attacks and create detection axioms to...
Show moreIn the past decade, cyber operations have been increasingly utilized to further policy goals of state-sponsored actors to shift the balance of politics and power on a global scale. One of the ways this has been evidenced is through the exploitation of electric grids via cyber means. A remote tripping command injection attack is one of the types of attacks that could have devastating effects on the North American power grid. To better understand these attacks and create detection axioms to both quickly identify and mitigate the effects of a remote tripping command injection attack, a dataset comprised of 128 variables (primarily synchrophasor measurements) was analyzed via statistical methods and machine learning algorithms in RStudio and WEKA software respectively. While statistical methods were not successful due to the non-linearity and complexity of the dataset, machine learning algorithms surpassed accuracy metrics established in previous research given a simplified dataset of the specified attack and normal operational data. This research allows future cybersecurity researchers to better understand remote tripping command injection attacks in comparison to normal operational conditions. Further, an incorporation of the analysis has the potential to increase detection and thus mitigate risk to the North American power grid in future work.
Show less - Date Issued
- 2018
- Identifier
- CFE0007257, ucf:52193
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007257
- Title
- A Study of Localization and Latency Reduction for Action Recognition.
- Creator
-
Masood, Syed, Tappen, Marshall, Foroosh, Hassan, Stanley, Kenneth, Sukthankar, Rahul, University of Central Florida
- Abstract / Description
-
The success of recognizing periodic actions in single-person-simple-background datasets, such as Weizmann and KTH, has created a need for more complex datasets to push the performance of action recognition systems. In this work, we create a new synthetic action dataset and use it to highlight weaknesses in current recognition systems. Experiments show that introducing background complexity to action video sequences causes a significant degradation in recognition performance. Moreover, this...
Show moreThe success of recognizing periodic actions in single-person-simple-background datasets, such as Weizmann and KTH, has created a need for more complex datasets to push the performance of action recognition systems. In this work, we create a new synthetic action dataset and use it to highlight weaknesses in current recognition systems. Experiments show that introducing background complexity to action video sequences causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning system parameters or by selecting better feature points. Instead, we show that the problem lies in the spatio-temporal cuboid volume extracted from the interest point locations. Having identified the problem, we show how improved results can be achieved by simple modifications to the cuboids.For the above method however, one requires near-perfect localization of the action within a video sequence. To achieve this objective, we present a two stage weakly supervised probabilistic model for simultaneous localization and recognition of actions in videos. Different from previous approaches, our method is novel in that it (1) eliminates the need for manual annotations for the training procedure and (2) does not require any human detection or tracking in the classification stage. The first stage of our framework is a probabilistic action localization model which extracts the most promising sub-windows in a video sequence where an action can take place. We use a non-linear classifier in the second stage of our framework for the final classification task. We show the effectiveness of our proposed model on two well known real-world datasets: UCF Sports and UCF11 datasets.Another application of the weakly supervised probablistic model proposed above is in the gaming environment. An important aspect in designing interactive, action-based interfaces is reliably recognizing actions with minimal latency. High latency causes the system's feedback to lag behind and thus significantly degrade the interactivity of the user experience. With slight modification to the weakly supervised probablistic model we proposed for action localization, we show how it can be used for reducing latency when recognizing actions in Human Computer Interaction (HCI) environments. This latency-aware learning formulation trains a logistic regression-based classifier that automatically determines distinctive canonical poses from the data and uses these to robustly recognize actions in the presence of ambiguous poses. We introduce a novel (publicly released) dataset for the purpose of our experiments. Comparisons of our method against both a Bag of Words and a Conditional Random Field (CRF) classifier show improved recognition performance for both pre-segmented and online classification tasks.
Show less - Date Issued
- 2012
- Identifier
- CFE0004575, ucf:49210
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004575
