Current Search:   Multitasking (x)

View All Items

  • CSV Spreadsheet
(1 - 10 of 10)
On Kernel-base Multi-Task Learning
Title
On Kernel-base Multi-Task Learning.
Creator
Li, Cong, Georgiopoulos, Michael, Anagnostopoulos, Georgios, Tappen, Marshall, Hu, Haiyan, Ni, Liqiang, University of Central Florida
Abstract / Description
Multi-Task Learning (MTL) has been an active research area in machine learning for two decades. By training multiple relevant tasks simultaneously with information shared across tasks, it is possible to improve the generalization performance of each task, compared to training each individual task independently. During the past decade, most MTL research has been based on the Regularization-Loss framework due to its flexibility in specifying various types of information sharing strategies, the...
Show moreMulti-Task Learning (MTL) has been an active research area in machine learning for two decades. By training multiple relevant tasks simultaneously with information shared across tasks, it is possible to improve the generalization performance of each task, compared to training each individual task independently. During the past decade, most MTL research has been based on the Regularization-Loss framework due to its flexibility in specifying various types of information sharing strategies, the opportunity it offers to yield a kernel-based methods and its capability in promoting sparse feature representations.However, certain limitations exist in both theoretical and practical aspects of Regularization-Loss-based MTL. Theoretically, previous research on generalization bounds in connection to MTL Hypothesis Space (HS)s, where data of all tasks are pre-processed by a (partially) common operator, has been limited in two aspects: First, all previous works assumed linearity of the operator, therefore completely excluding kernel-based MTL HSs, for which the operator is potentially non-linear. Secondly, all previous works, rather unnecessarily, assumed that all the task weights to be constrained within norm-balls, whose radii are equal. The requirement of equal radii leads to significant inflexibility of the relevant HSs, which may cause the generalization performance of the corresponding MTL models to deteriorate. Practically, various algorithms have been developed for kernel-based MTL models, due to different characteristics of the formulations. Most of these algorithms are a burden to develop and end up being quite sophisticated, so that practitioners may face a hard task in interpreting and implementing them, especially when multiple models are involved. This is even more so, when Multi-Task Multiple Kernel Learning (MT-MKL) models are considered. This research largely resolves the above limitations. Theoretically, a pair of new kernel-based HSs are proposed: one for single-kernel MTL, and another one for MT-MKL. Unlike previous works, we allow each task weight to be constrained within a norm-ball, whose radius is learned during training. By deriving and analyzing the generalization bounds of these two HSs, we show that, indeed, such a flexibility leads to much tighter generalization bounds, which often results to significantly better generalization performance. Based on this observation, a pair of new models is developed, one for each case: single-kernel MTL, and another one for MT-MKL. From a practical perspective, we propose a general MT-MKL framework that covers most of the prominent MT-MKL approaches, including our new MT-MKL formulation. Then, a general purpose algorithm is developed to solve the framework, which can also be employed for training all other models subsumed by this framework. A series of experiments is conducted to assess the merits of the proposed mode when trained by the new algorithm. Certain properties of our HSs and formulations are demonstrated, and the advantage of our model in terms of classification accuracy is shown via these experiments.
Show less
Date Issued
2014
Identifier
CFE0005517, ucf:50321
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0005517
THE EFFECTS ON OPERATOR PERFORMANCE AND WORKLOAD WHEN GUNNERY AND ROBOTIC CONTROL TASKS ARE PERFORMED CONCURRENTLY
Title
THE EFFECTS ON OPERATOR PERFORMANCE AND WORKLOAD WHEN GUNNERY AND ROBOTIC CONTROL TASKS ARE PERFORMED CONCURRENTLY.
Creator
Joyner, Carla, McCauley-Bell, Pamela, University of Central Florida
Abstract / Description
The purpose of this research was to examine operator workload and performance in a high risk, multi-task environment. Specifically, the research examined if a gunner of a Future Combat System, such as a Mounted Combat System, could effectively detect targets in the immediate environment while concurrently operating robotic assets in a remote environment. It also analyzed possible effects of individual difference factors, such as spatial ability and attentional control, on operator performance...
Show moreThe purpose of this research was to examine operator workload and performance in a high risk, multi-task environment. Specifically, the research examined if a gunner of a Future Combat System, such as a Mounted Combat System, could effectively detect targets in the immediate environment while concurrently operating robotic assets in a remote environment. It also analyzed possible effects of individual difference factors, such as spatial ability and attentional control, on operator performance and workload. The experimental conditions included a gunner baseline and concurrent task conditions where participants simultaneously performed gunnery tasks and one of the following tasks: monitor an unmanned ground vehicle (UGV) via a video feed (Monitor), manage a semi-autonomous UGV, and teleoperate a UGV (Teleop). The analysis showed that the asset condition significantly impacted gunnery performance with the gunner baseline having the highest number of targets detected (M = 13.600 , SD = 2.353), and concurrent Teleop condition the lowest (M = 9.325 , SD = 2.424). The research also found that high spatial ability participants tended to detect more targets than low spatial ability participants. Robotic task performance was also affect by the asset condition. The results showed that the robotic target detection rate was lower for the concurrent task conditions. A significant difference was seen between the UGV-baseline (80.1%) when participants performed UGV tasks only and UGV-concurrent conditions (67.5%) when the participants performed UGV tasks concurrently with gunnery tasks. Overall, this study revealed that there were performance decrements for the gunnery tasks as well as the robotic tasks when the tasks were performed concurrently.
Show less
Date Issued
2006
Identifier
CFE0000979, ucf:46704
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0000979
Life Long Learning in Sparse Learning Environments
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
PLUNGERS AND PRODUCTIVITY: A STUDENT ARTIST'S SURVIVAL GUIDE TO MULTI-TASKING
Title
PLUNGERS AND PRODUCTIVITY: A STUDENT ARTIST'S SURVIVAL GUIDE TO MULTI-TASKING.
Creator
Wansa, Amanda, Chicurel, Steven, University of Central Florida
Abstract / Description
To be a fully functioning theatre practitioner, the developing student artist becomes equipped with a practical skill set that is ordinarily cultivated through formal training and study. Typically, organized study leads him/her to focus on a specific facet of the business: acting, directing, design, etc. However, students often develop a vast array of talents and skills within the profession and find themselves standing at a crossroads between what "kind" of artist to be; what singular aspect...
Show moreTo be a fully functioning theatre practitioner, the developing student artist becomes equipped with a practical skill set that is ordinarily cultivated through formal training and study. Typically, organized study leads him/her to focus on a specific facet of the business: acting, directing, design, etc. However, students often develop a vast array of talents and skills within the profession and find themselves standing at a crossroads between what "kind" of artist to be; what singular aspect of the arts on which to focus. Why not do it all? For those students who "do it all", there is an additional challenge: the artist who is a student immersed in daytime study and nighttime production obligations has to wear two caps. One is that of the learner and one is that of the employee, the producer, and perhaps even the teacher. When are these caps traded or are they both worn through all processes? This thesis will reveal my creative and practical processes from two productions at the University of Central Florida for which I played on- and offstage roles: I worked as a Sound Designer and featured actor in Sophie Treadwell's Machinal; I was the Vocal Director for Urinetown: The Musical, and also played Penelope Pennywise, a leading role. I will describe the challenges and successes of each project by examining the following evidence: my personal process with each piece, demonstrated through reflection and examples from the work; interviews with those involved in the productions as well as outside reviews and feedback; and research of each play. Research will include production history, intent of authors, and aspects that informed my work both onstage and off. Did multi-tasking sacrifice the quality of my work for any of my delegated tasks? Did I enjoy more success in my progress in time management, the ability to solve problems, and collaboration process with fellow artists, or in the actual on-stage products? What aspects of my training in my graduate program added to the quality of my work on these productions? Does being a multi-tasking artist help or hurt one's career in theatre?
Show less
Date Issued
2009
Identifier
CFE0002579, ucf:48283
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0002579
Improved Multi-Task Learning Based on Local Rademacher Analysis
Title
Improved Multi-Task Learning Based on Local Rademacher Analysis.
Creator
Yousefi, Niloofar, Mollaghasemi, Mansooreh, Rabelo, Luis, Zheng, Qipeng, Anagnostopoulos, Georgios, Xanthopoulos, Petros, Georgiopoulos, Michael, University of Central Florida
Abstract / Description
Considering a single prediction task at a time is the most commonly paradigm in machine learning practice. This methodology, however, ignores the potentially relevant information that might be available in other related tasks in the same domain. This becomes even more critical where facing the lack of a sufficient amount of data in a prediction task of an individual subject may lead to deteriorated generalization performance. In such cases, learning multiple related tasks together might offer...
Show moreConsidering a single prediction task at a time is the most commonly paradigm in machine learning practice. This methodology, however, ignores the potentially relevant information that might be available in other related tasks in the same domain. This becomes even more critical where facing the lack of a sufficient amount of data in a prediction task of an individual subject may lead to deteriorated generalization performance. In such cases, learning multiple related tasks together might offer a better performance by allowing tasks to leverage information from each other. Multi-Task Learning (MTL) is a machine learning framework, which learns multiple related tasks simultaneously to overcome data scarcity limitations of Single Task Learning (STL), and therefore, it results in an improved performance. Although MTL has been actively investigated by the machine learning community, there are only a few studies examining the theoretical justification of this learning framework. The focus of previous studies is on providing learning guarantees in the form of generalization error bounds. The study of generalization bounds is considered as an important problem in machine learning, and, more specifically, in statistical learning theory. This importance is twofold: (1) generalization bounds provide an upper-tail confidence interval for the true risk of a learning algorithm the latter of which cannot be precisely calculated due to its dependency to some unknown distribution P from which the data are drawn, (2) this type of bounds can also be employed as model selection tools, which lead to identifying more accurate learning models. The generalization error bounds are typically expressed in terms of the empirical risk of the learning hypothesis along with a complexity measure of that hypothesis. Although different complexity measures can be used in deriving error bounds, Rademacher complexity has received considerable attention in recent years, due to its superiority to other complexity measures. In fact, Rademacher complexity can potentially lead to tighter error bounds compared to the ones obtained by other complexity measures. However, one shortcoming of the general notion of Rademacher complexity is that it provides a global complexity estimate of the learning hypothesis space, which does not take into consideration the fact that learning algorithms, by design, select functions belonging to a more favorable subset of this space and, therefore, they yield better performing models than the worst case. To overcome the limitation of global Rademacher complexity, a more nuanced notion of Rademacher complexity, the so-called local Rademacher complexity, has been considered, which leads to sharper learning bounds, and as such, compared to its global counterpart, guarantees faster convergence rates in terms of number of samples. Also, considering the fact that locally-derived bounds are expected to be tighter than globally-derived ones, they can motivate better (more accurate) model selection algorithms.While the previous MTL studies provide generalization bounds based on some other complexity measures, in this dissertation, we prove excess risk bounds for some popular kernel-based MTL hypothesis spaces based on the Local Rademacher Complexity (LRC) of those hypotheses. We show that these local bounds have faster convergence rates compared to the previous Global Rademacher Complexity (GRC)-based bounds. We then use our LRC-based MTL bounds to design a new kernel-based MTL model, which enjoys strong learning guarantees. Moreover, we develop an optimization algorithm to solve our new MTL formulation. Finally, we run simulations on experimental data that compare our MTL model to some classical Multi-Task Multiple Kernel Learning (MT-MKL) models designed based on the GRCs. Since the local Rademacher complexities are expected to be tighter than the global ones, our new model is also expected to exhibit better performance compared to the GRC-based models.
Show less
Date Issued
2017
Identifier
CFE0006827, ucf:51778
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0006827
EXAMINING INSTANT MESSAGING IMPACT ON LEARNING USING AN INTEGRATED WORKED-EXAMPLE FORMAT
Title
EXAMINING INSTANT MESSAGING IMPACT ON LEARNING USING AN INTEGRATED WORKED-EXAMPLE FORMAT.
Creator
Nasah, Angelique, Hirumi, Atsusi, University of Central Florida
Abstract / Description
Instant messaging with Internet-based software is a ubiquitous form of communication in industrialized nations. In fact, many educators are observing that students engage with instant messaging while simultaneously engaged in academic activity. Though this type of multitasking is pervasive, educational researchers have not examined how the practice of instant messaging impacts learning outcomes. This dissertation describes the background, empirical and theoretical foundations, methods and...
Show moreInstant messaging with Internet-based software is a ubiquitous form of communication in industrialized nations. In fact, many educators are observing that students engage with instant messaging while simultaneously engaged in academic activity. Though this type of multitasking is pervasive, educational researchers have not examined how the practice of instant messaging impacts learning outcomes. This dissertation describes the background, empirical and theoretical foundations, methods and results of a study examining the impact of instant messaging activity on learning, where instant messaging and learning are simultaneous activities. The question posed is grounded in the related areas of instant messaging practices, the Generation M profile, Cognitive Load Theory, and integration of instant messaging in K-16 classrooms. This work presents empirical evidence pointing out the necessity of conducting empirical study regarding how instant messaging activity might impact learning. Quantitative methods used to conduct the study are presented including data collection instruments. The results of the study are discussed in broad terms related to Generation M and Cognitive Load Theory. Methodological limitations related to practice opportunities for the research sample as well as the performance measure used are detailed. In addition, implications of the results in relationship to those teaching members of Generation M in K-16 classrooms as well as those designing instruction for this population are discussed. The discussion concludes with recommendations for further research in this area.
Show less
Date Issued
2008
Identifier
CFE0002113, ucf:47540
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0002113
OPTIMIZING THE DESIGN OF MULTIMODAL USER INTERFACES
Title
OPTIMIZING THE DESIGN OF MULTIMODAL USER INTERFACES.
Creator
Reeves, Leah, Stanney, Kay, University of Central Florida
Abstract / Description
Due to a current lack of principle-driven multimodal user interface design guidelines, designers may encounter difficulties when choosing the most appropriate display modality for given users or specific tasks (e.g., verbal versus spatial tasks). The development of multimodal display guidelines from both a user and task domain perspective is thus critical to the achievement of successful human-system interaction. Specifically, there is a need to determine how to design task information...
Show moreDue to a current lack of principle-driven multimodal user interface design guidelines, designers may encounter difficulties when choosing the most appropriate display modality for given users or specific tasks (e.g., verbal versus spatial tasks). The development of multimodal display guidelines from both a user and task domain perspective is thus critical to the achievement of successful human-system interaction. Specifically, there is a need to determine how to design task information presentation (e.g., via which modalities) to capitalize on an individual operator's information processing capabilities and the inherent efficiencies associated with redundant sensory information, thereby alleviating information overload. The present effort addresses this issue by proposing a theoretical framework (Architecture for Multi-Modal Optimization, AMMO) from which multimodal display design guidelines and adaptive automation strategies may be derived. The foundation of the proposed framework is based on extending, at a functional working memory (WM) level, existing information processing theories and models with the latest findings in cognitive psychology, neuroscience, and other allied sciences. The utility of AMMO lies in its ability to provide designers with strategies for directing system design, as well as dynamic adaptation strategies (i.e., multimodal mitigation strategies) in support of real-time operations. In an effort to validate specific components of AMMO, a subset of AMMO-derived multimodal design guidelines was evaluated with a simulated weapons control system multitasking environment. The results of this study demonstrated significant performance improvements in user response time and accuracy when multimodal display cues were used (i.e., auditory and tactile, individually and in combination) to augment the visual display of information, thereby distributing human information processing resources across multiple sensory and WM resources. These results provide initial empirical support for validation of the overall AMMO model and a sub-set of the principle-driven multimodal design guidelines derived from it. The empirically-validated multimodal design guidelines may be applicable to a wide range of information-intensive computer-based multitasking environments.
Show less
Date Issued
2007
Identifier
CFE0001636, ucf:47237
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0001636
Holding off on the fun stuff: Academic media multitasking and binge watching among college students
Title
Holding off on the fun stuff: Academic media multitasking and binge watching among college students.
Creator
Merrill, Kelly, Rubenking, Bridget, Kinnally, William, Sellnow, Deanna, University of Central Florida
Abstract / Description
College students are often faced with the temptation of engaging in academic media multitasking and binge watching or completing their academic coursework in a timely and effective manner. A quantitative survey (N = 651) explored trait individual differences in self-control and academic delay of gratification and situational individual differences in enjoyment, reward, procrastination, regret, and guilt as predictors of academic media multitasking frequency, binge watching frequency, and...
Show moreCollege students are often faced with the temptation of engaging in academic media multitasking and binge watching or completing their academic coursework in a timely and effective manner. A quantitative survey (N = 651) explored trait individual differences in self-control and academic delay of gratification and situational individual differences in enjoyment, reward, procrastination, regret, and guilt as predictors of academic media multitasking frequency, binge watching frequency, and binge watching duration. Stepwise regressions reveal that self-control is not a predictor of these media behaviors, while age and greater enjoyment were the only predictors of academic media multitasking and gender and greater enjoyment were the only predictors of binge watching duration. On the other hand, the other five variables provided insight on what predicted binge watching frequency: academic delay of gratification, reward, procrastination, regret, and guilt. Greater self-control also led to greater academic delay of gratification. Lastly, there were small positive correlations between all of the media behaviors except for academic media multitasking and binge watching frequency. Practical and theoretical implications are discussed.
Show less
Date Issued
2018
Identifier
CFE0007053, ucf:51989
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0007053
Effects of Signal Probability on Multitasking-Based Distraction in Driving, Cyberattack (&) Battlefield Simulation
Title
Effects of Signal Probability on Multitasking-Based Distraction in Driving, Cyberattack (&) Battlefield Simulation.
Creator
Sawyer, Benjamin, Karwowski, Waldemar, Hancock, Peter, Xanthopoulos, Petros, University of Central Florida
Abstract / Description
Multitasking-based failures of perception and action are the focus of much research in driving, where they are attributed to distraction. Similar failures occur in contexts where the construct of distraction is little used. Such narrow application was attributed to methodology which cannot precisely account for experimental variables in time and space, limiting distraction's conceptual portability to other contexts. An approach based upon vigilance methodology was forwarded as a solution, and...
Show moreMultitasking-based failures of perception and action are the focus of much research in driving, where they are attributed to distraction. Similar failures occur in contexts where the construct of distraction is little used. Such narrow application was attributed to methodology which cannot precisely account for experimental variables in time and space, limiting distraction's conceptual portability to other contexts. An approach based upon vigilance methodology was forwarded as a solution, and highlighted a fundamental human performance question: Would increasing the signal probability (SP) of a secondary task increase associated performance, as is seen in the prevalence effect associated with vigilance tasks? Would it reduce associated performance, as is seen in driving distraction tasks? A series of experiments weighed these competing assumptions. In the first, a psychophysical task, analysis of accuracy and response data revealed an interaction between the number of concurrent tasks and SP of presented targets. The question was further tested in the applied contexts of driving, cyberattack and battlefield target decision-making. In line with previous prevalence effect inquiry, presentation of stimuli at higher SP led to higher accuracy. In line with existing distraction work, performance of higher numbers of concurrent tasks tended to elicit slower response times. In all experiments raising either number of concurrent tasks or SP of targets resulted in greater subjective workload, as measured by the NASA TLX, even when accompanied by improved accuracy. It would seem that (")distraction(") in previous experiments has been an aggregate effect including both delayed response time and prevalence-based accuracy effects. These findings support the view that superior experimental control of SP reveals nomothetic patterns of performance that allow better understanding and wider application of the distraction construct both within and in diverse contexts beyond driving.
Show less
Date Issued
2015
Identifier
CFE0006388, ucf:51522
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0006388
Impacts of Complexity and Timing of Communication Interruptions on Visual Detection Tasks
Title
Impacts of Complexity and Timing of Communication Interruptions on Visual Detection Tasks.
Creator
Stader, Sally, Mouloua, Mustapha, Hancock, Peter, Neider, Mark, Kincaid, John, University of Central Florida
Abstract / Description
Auditory preemption theory suggests two competing assumptions for the attention-capturing and performance-altering properties of auditory tasks. In onset preemption, attention is immediately diverted to the auditory channel. Strategic preemption involves a decision process in which the operator maintains focus on more complex auditory messages. The limitation in this process is that the human auditory, or echoic, memory store has a limit of 2 to 5 seconds, after which the message must be...
Show moreAuditory preemption theory suggests two competing assumptions for the attention-capturing and performance-altering properties of auditory tasks. In onset preemption, attention is immediately diverted to the auditory channel. Strategic preemption involves a decision process in which the operator maintains focus on more complex auditory messages. The limitation in this process is that the human auditory, or echoic, memory store has a limit of 2 to 5 seconds, after which the message must be processed or it decays. In contrast, multiple resource theory suggests that visual and auditory tasks may be efficiently time-shared because two different pools of cognitive resources are used. Previous research regarding these competing assumptions has been limited and equivocal. Thus, the current research focused on systematically examining the effects of complexity and timing of communication interruptions on visual detection tasks. It was hypothesized that both timing and complexity levels would impact detection performance in a multi-task environment. Study 1 evaluated the impact of complexity and timing of communications occurring before malfunctions in an ongoing visual detection task. Twenty-four participants were required to complete each of the eight timing blocks that included simple or complex communications occurring simultaneously, and at 2, 5, or 8 seconds before detection events. For simple communications, participants repeated three pre-recorded words. However, for complex communications, they generated three words beginning with the same last letter of a word prompt. Results indicated that complex communications at two seconds or less occurring before a visual detection event significantly impacted response time with a 1.3 to 1.6 second delay compared to all the other timings. Detection accuracy for complex communication tasks under the simultaneous condition was significantly degraded compared to simple communications at five seconds or more prior to the task. This resulted in a 20% decline in detection accuracy. Additionally, participants' workload ratings for complex communications were significantly higher than simple communications. Study 2 examined the timing of communications occurring at the corresponding seconds after the visual detection event. Twenty-four participants were randomly assigned to the communication complexity and timing blocks as in study 1. The results did not find significant performance effects of timing or complexity of communications on detection performance. However the workload ratings for the 2 and 5 second complex communication presentations were higher compared to the same simple communication conditions. Overall, these findings support the strategic preemption assumption for well-defined, complex communications. The onset preemption assumption for simple communications was not supported. These results also suggest that the boundaries of the multiple resource theory assumption may exist up to the limits of the echoic memory store. Figures of merit for task performance under the varying levels of timing and complexity are presented. Several theoretical and practical implications are discussed.
Show less
Date Issued
2014
Identifier
CFE0005420, ucf:50415
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0005420