View All Items
(81 - 100 of 205)
Pages
- Title
- A Predictive Model To Identify Caregivers At Risk Of Musculoskeletal Disorders.
- Creator
-
Ali, Abdulelah, Lee, Gene, Elshennawy, Ahmad, Rabelo, Luis, Rahal, Ahmad, University of Central Florida
- Abstract / Description
-
Healthcare systems face several challenges due to the aging workforce, recruitment shortages, increasing patient acuteness, and increasing patient size and weight. The most costly, leading, and prevalent problem in the healthcare industry and nursing professions is work-related Musculoskeletal Disorders (MSDs). MSDs are common among caregivers because of the nature of their work, which requires repetitive heavy physical activity. The development of MSDs among caregivers negatively impacts the...
Show moreHealthcare systems face several challenges due to the aging workforce, recruitment shortages, increasing patient acuteness, and increasing patient size and weight. The most costly, leading, and prevalent problem in the healthcare industry and nursing professions is work-related Musculoskeletal Disorders (MSDs). MSDs are common among caregivers because of the nature of their work, which requires repetitive heavy physical activity. The development of MSDs among caregivers negatively impacts the quality of care, and incurs high costs such as worker compensation, days away from work, turnover, rehabilitation, and lower productivity. Therefore, it is essential to determine the factors that contribute to musculoskeletal disorder injuries among caregivers, in order to reduce or eliminate risks within healthcare environments which might cause such ramifications. This dissertation develops a framework to identify risk factors for MSDs and to determine which ones show significant contribution to be included in a developed predictive model. The data was obtained from caregivers who work in Saudi Arabian healthcare institutions, with 104 participating nurses to determine which risk factors would be included in the predictive model. Logistic regression analysis was used to investigate the association of the identified work related and non-work related risk factors for musculoskeletal disorders in healthcare organizations among caregivers. The development of the predictive model provides insights into risk factors which can guide the development of policies and recommendations to reduce and eliminate the development of MSDs among caregivers.
Show less - Date Issued
- 2016
- Identifier
- CFE0006065, ucf:50967
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006065
- Title
- Hydromorphology of the Econlockhatchee River.
- Creator
-
Baker, John, Wang, Dingbao, Hagen, Scott, Chopra, Manoj, University of Central Florida
- Abstract / Description
-
Climate change and human activities alter the hydrologic systems and exerted global scale impacts on our environment with significant implications for water resources. Climate change can be characterized by the change of precipitation and temperature, and both precipitation pattern change and global warming are associated with the increase in frequency of flooding or drought and low flows. With increasing water demand from domestic, agricultural, commercial, and industrial sectors, humans are...
Show moreClimate change and human activities alter the hydrologic systems and exerted global scale impacts on our environment with significant implications for water resources. Climate change can be characterized by the change of precipitation and temperature, and both precipitation pattern change and global warming are associated with the increase in frequency of flooding or drought and low flows. With increasing water demand from domestic, agricultural, commercial, and industrial sectors, humans are increasingly becoming a significant component of the hydrologic cycle. Human activities have transformed hydrologic processes at spatial scales ranging from local to global. Human activities affecting watershed hydrology include land use change, dam construction and reservoir operation, groundwater pumping, surface water withdrawal, irrigation, return flow, and others. In this thesis, the hydromorphology (i.e., the change of coupled hydrologic and human systems) of the Econlockhatchee River (Econ River for short) is studied. Due to the growth of the Orlando metropolitan area the Econ basin has been substantially urbanized with drastic change of the land cover. The land use / land cover change from 1940s to 2000s has been quantified by compiling existing land cover data and digitizing aerial photography images. Rainfall data have been analyzed to determine the extent that climate change has affected the river flow compared to land use change. The changes in stream flow at the annual scale and low flows are analyzed. The Econ River has experienced minimal changes in the amount of annual streamflow but significant changes to the amount of low flows. These changes are due to urbanization and other human interferences.
Show less - Date Issued
- 2013
- Identifier
- CFE0005126, ucf:50692
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005126
- Title
- Assessment of Instructional Presentation For Emergency Evacuation Assistive Technology.
- Creator
-
Boyce, Michael, Smither, Janan, Joseph, Dana, Hancock, Peter, Bowers, Clint, Wilson, Darren, University of Central Florida
- Abstract / Description
-
It is often the case that emergency first responders are well equipped and trained to deal with a situation that involves evacuation of someone with a physical disability. However, emergency responders are not always the first line of defense, or they may be otherwise occupied with assisting others. This research examined the effects of instructions for emergency stair travel devices on untrained or novice users. It was hypothesized that through redesign of the evacuation instructions,...
Show moreIt is often the case that emergency first responders are well equipped and trained to deal with a situation that involves evacuation of someone with a physical disability. However, emergency responders are not always the first line of defense, or they may be otherwise occupied with assisting others. This research examined the effects of instructions for emergency stair travel devices on untrained or novice users. It was hypothesized that through redesign of the evacuation instructions, untrained individuals would be able to successfully prepare an evacuation chair and secure someone with a disability more effectively and efficiently. A pre-post study design was used with an instructional redesign occurring as the manipulation between phases. There was an improved subjective understanding and improved performance metrics, such as reduced time on task and a reduction of the number of instructional glances, across three evacuation chairs when using the redesigned instruction sets. The study demonstrated that visual instruction style can account for a significant portion of explained variance in the operation of emergency stair travel devices. It also showed that improvements in instruction style can reduce time on task across device type and age group. The study failed to demonstrate that there was a performance decrement for older adults in comparison to younger adults because of the cognitive slowing of older adult information processing abilities. Results from this study can be used to support future iterations of the Emergency Stair Travel Device Standard (RESNA ED-1) to ensure that instructional design is standardized and optimized for the best performance possible.
Show less - Date Issued
- 2014
- Identifier
- CFE0005136, ucf:50694
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005136
- Title
- Weakly Labeled Action Recognition and Detection.
- Creator
-
Sultani, Waqas, Shah, Mubarak, Bagci, Ulas, Qi, GuoJun, Yun, Hae-Bum, University of Central Florida
- Abstract / Description
-
Research in human action recognition strives to develop increasingly generalized methods thatare robust to intra-class variability and inter-class ambiguity. Recent years have seen tremendousstrides in improving recognition accuracy on ever larger and complex benchmark datasets, comprisingrealistic actions (")in the wild(") videos. Unfortunately, the all-encompassing, dense, globalrepresentations that bring about such improvements often benefit from the inherent characteristics,specific to...
Show moreResearch in human action recognition strives to develop increasingly generalized methods thatare robust to intra-class variability and inter-class ambiguity. Recent years have seen tremendousstrides in improving recognition accuracy on ever larger and complex benchmark datasets, comprisingrealistic actions (")in the wild(") videos. Unfortunately, the all-encompassing, dense, globalrepresentations that bring about such improvements often benefit from the inherent characteristics,specific to datasets and classes, that do not necessarily reflect knowledge about the entity to berecognized. This results in specific models that perform well within datasets but generalize poorly.Furthermore, training of supervised action recognition and detection methods need several precisespatio-temporal manual annotations to achieve good recognition and detection accuracy. For instance,current deep learning architectures require millions of accurately annotated videos to learnrobust action classifiers. However, these annotations are quite difficult to achieve.In the first part of this dissertation, we explore the reasons for poor classifier performance whentested on novel datasets, and quantify the effect of scene backgrounds on action representationsand recognition. We attempt to address the problem of recognizing human actions while trainingand testing on distinct datasets when test videos are neither labeled nor available during training. Inthis scenario, learning of a joint vocabulary, or domain transfer techniques are not applicable. Weperform different types of partitioning of the GIST feature space for several datasets and computemeasures of background scene complexity, as well as, for the extent to which scenes are helpfulin action classification. We then propose a new process to obtain a measure of confidence in eachpixel of the video being a foreground region using motion, appearance, and saliency together in a3D-Markov Random Field (MRF) based framework. We also propose multiple ways to exploit theforeground confidence: to improve bag-of-words vocabulary, histogram representation of a video,and a novel histogram decomposition based representation and kernel.iiiThe above-mentioned work provides probability of each pixel being belonging to the actor, however,it does not give the precise spatio-temporal location of the actor. Furthermore, above frameworkwould require precise spatio-temporal manual annotations to train an action detector. However,manual annotations in videos are laborious, require several annotators and contain humanbiases. Therefore, in the second part of this dissertation, we propose a weakly labeled approachto automatically obtain spatio-temporal annotations of actors in action videos. We first obtain alarge number of action proposals in each video. To capture a few most representative action proposalsin each video and evade processing thousands of them, we rank them using optical flow andsaliency in a 3D-MRF based framework and select a few proposals using MAP based proposal subsetselection method. We demonstrate that this ranking preserves the high-quality action proposals.Several such proposals are generated for each video of the same action. Our next challenge is toiteratively select one proposal from each video so that all proposals are globally consistent. Weformulate this as Generalized Maximum Clique Graph problem (GMCP) using shape, global andfine-grained similarity of proposals across the videos. The output of our method is the most actionrepresentative proposals from each video. Using our method can also annotate multiple instancesof the same action in a video can also be annotated. Moreover, action detection experiments usingannotations obtained by our method and several baselines demonstrate the superiority of ourapproach.The above-mentioned annotation method uses multiple videos of the same action. Therefore, inthe third part of this dissertation, we tackle the problem of spatio-temporal action localization in avideo, without assuming the availability of multiple videos or any prior annotations. The action islocalized by employing images downloaded from the Internet using action label. Given web images,we first dampen image noise using random walk and evade distracting backgrounds withinimages using image action proposals. Then, given a video, we generate multiple spatio-temporalaction proposals. We suppress camera and background generated proposals by exploiting opticalivflow gradients within proposals. To obtain the most action representative proposals, we propose toreconstruct action proposals in the video by leveraging the action proposals in images. Moreover,we preserve the temporal smoothness of the video and reconstruct all proposal bounding boxesjointly using the constraints that push the coefficients for each bounding box toward a commonconsensus, thus enforcing the coefficient similarity across multiple frames. We solve this optimizationproblem using the variant of two-metric projection algorithm. Finally, the video proposalthat has the lowest reconstruction cost and is motion salient is used to localize the action. Ourmethod is not only applicable to the trimmed videos, but it can also be used for action localizationin untrimmed videos, which is a very challenging problem.Finally, in the third part of this dissertation, we propose a novel approach to generate a few properlyranked action proposals from a large number of noisy proposals. The proposed approach beginswith dividing each proposal into sub-proposals. We assume that the quality of proposal remainsthe same within each sub-proposal. We, then employ a graph optimization method to recombinethe sub-proposals in all action proposals in a single video in order to optimally build new actionproposals and rank them by the combined node and edge scores. For an untrimmed video, we firstdivide the video into shots and then make the above-mentioned graph within each shot. Our methodgenerates a few ranked proposals that can be better than all the existing underlying proposals. Ourexperimental results validated that the properly ranked action proposals can significantly boostaction detection results.Our extensive experimental results on different challenging and realistic action datasets, comparisonswith several competitive baselines and detailed analysis of each step of proposed methodsvalidate the proposed ideas and frameworks.
Show less - Date Issued
- 2017
- Identifier
- CFE0006801, ucf:51809
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006801
- Title
- The Impact of Automation and Stress on Human Performance in UAV Operation.
- Creator
-
Lin, Jinchao, Matthews, Gerald, Reinerman, Lauren, Szalma, James, Funke, Gregory, University of Central Florida
- Abstract / Description
-
The United States Air Force (USAF) has increasing needs for unmanned aerial vehicle (UAV) operators. Automation may enable a single operator to manage multiple UAVs at the same time. Multi-UAV operation may require a unique set of skills and the need for new operators calls for targeting new populations for recruitment. The objective of this research is to develop a simulation environment for studying the role of individual differences in UAV operation under different task configurations and...
Show moreThe United States Air Force (USAF) has increasing needs for unmanned aerial vehicle (UAV) operators. Automation may enable a single operator to manage multiple UAVs at the same time. Multi-UAV operation may require a unique set of skills and the need for new operators calls for targeting new populations for recruitment. The objective of this research is to develop a simulation environment for studying the role of individual differences in UAV operation under different task configurations and investigate predictors of performance and stress. Primarily, the study examined the impact of levels of automation (LOAs), as well as task demands, on task performance, stress and operator reliance on automation. Two intermediate LOAs were employed for two surveillance tasks included in the simulation of UAV operation. Task demand was manipulated via the high and low frequency of events associated with additional tasks included in the simulation. The task demand and LOA manipulations influenced task performance generally as expected. The task demand manipulations elicited higher subjective distress and workload. LOAs did not affect operator workload but affected reliance behavior. Also, this study examined the role of individual differences in simulated UAV operation. A variety of individual difference factors were associated with task performance and with subjective stress response. Video gaming experience was linked to lower distress and better performance, suggesting possible transfer of skills. Some gender differences were revealed in stress response, task performance, but all the gender effects became insignificant with gaming experience controlled. Generally, the effects of personality were consistent with previous studies, except some novel findings with the performance metrics. Additionally, task demand was found to moderate the influence of personality factors on stress response and performance metrics. Specifically, conscientiousness was associated with higher subjective engagement and performance when demands were higher. This study supports future research which aims to improve the dynamic interfaces in UAV operation, optimize operator reliance on automation, and identify individuals with the highest aptitude for multi-UAV control.
Show less - Date Issued
- 2017
- Identifier
- CFE0006951, ucf:51630
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006951
- Title
- Asylum in Crisis: Structural Violence and Refugees in Siracusa, Italy.
- Creator
-
Kersch, Adam, Mishtal, Joanna, Matejowsky, Ty, Toyne, J. Marla, Geiger, Vance, University of Central Florida
- Abstract / Description
-
In recent years, unprecedented numbers of migrants have arrived in Italy due to political, religious, ethnic and economic instabilities in West and North Africa and the Middle East. Simultaneously, the Eurozone Crisis and neoliberal austerity measures left the Italian government struggling to administer healthcare and legal services to all migrants. This study investigates the provision of essential services by the Italian state and two non-governmental organizations (NGOs), Emergency and...
Show moreIn recent years, unprecedented numbers of migrants have arrived in Italy due to political, religious, ethnic and economic instabilities in West and North Africa and the Middle East. Simultaneously, the Eurozone Crisis and neoliberal austerity measures left the Italian government struggling to administer healthcare and legal services to all migrants. This study investigates the provision of essential services by the Italian state and two non-governmental organizations (NGOs), Emergency and ARCI, respectively providing free medical and legal services, to incoming migrants in Siracusa, Italy. It analyzes migrants' perceptions of these services and evolving goals in Europe. Building upon preliminary fieldwork conducted in 2014, in January to July 2015 I undertook six months of participant observation in a migrant reception center and legal offices in Siracusa. During my research I conducted 72 unstructured and semi-structured interviews with migrants, NGO activists, lawyers, and doctors, and state physicians. This study analyzes Emergency's role as an entrance to the Italian healthcare system and ARCI as a facilitator of legal aid to migrants. I argue that the clinic's position on the outskirts of Siracusa functions as a means of exclusion, exacerbating divides between the local population and incoming migrants. Additionally, I provide insight into the provision of legal services to migrants in Siracusa, as well as how these migrants navigate geopolitical and legislative borders, and these borders' roles within the politics of the European Union and neoliberal ideologies. I argue that selective enforcement of asylum legislation and dearth of legal aid to migrants motivates many migrants to clandestinely flee Italy to seek futures in other European nations, consequently moving (")burdens(") of migrant reception. This research contributes to public policy and scholarship on health and migration policy as well as politics of conflict, while shedding light on the critical role of NGOs in a complex humanitarian crisis occurring in Southern Europe.
Show less - Date Issued
- 2016
- Identifier
- CFE0006126, ucf:51166
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006126
- Title
- Investigation of Tactile Displays for Robot to Human Communication.
- Creator
-
Barber, Daniel, Reinerman, Lauren, Jentsch, Florian, Lackey, Stephanie, Leonessa, Alexander, University of Central Florida
- Abstract / Description
-
Improvements in autonomous systems technology and a growing demand within military operations are spurring a revolution in Human-Robot Interaction (HRI). These mixed-initiative human-robot teams are enabled by Multi-Modal Communication (MMC), which supports redundancy and levels of communication that are more robust than single mode interaction. (Bischoff (&) Graefe, 2002; Partan (&) Marler, 1999). Tactile communication via vibrotactile displays is an emerging technology, potentially...
Show moreImprovements in autonomous systems technology and a growing demand within military operations are spurring a revolution in Human-Robot Interaction (HRI). These mixed-initiative human-robot teams are enabled by Multi-Modal Communication (MMC), which supports redundancy and levels of communication that are more robust than single mode interaction. (Bischoff (&) Graefe, 2002; Partan (&) Marler, 1999). Tactile communication via vibrotactile displays is an emerging technology, potentially beneficial to advancing HRI. Incorporation of tactile displays within MMC requires developing messages equivalent in communication power to speech and visual signals used in the military. Toward that end, two experiments were performed to investigate the feasibility of a tactile language using a lexicon of standardized tactons (tactile icons) within a sentence structure for communication of messages for robot to human communication. Experiment one evaluated tactons from the literature with standardized parameters grouped into categories (directional, dynamic, and static) based on the nature and meaning of the patterns to inform design of a tactile syntax. Findings of this experiment revealed directional tactons showed better performance than non-directional tactons, therefore syntax for experiment two composed of a non-directional and a directional tacton was more likely to show performance better than chance. Experiment two tested the syntax structure of equally performing tactons identified from experiment one, revealing participants' ability to interpret tactile sentences better than chance with or without the presence of an independent work imperative task. This finding advanced the state of the art in tactile displays from one to two word phrases facilitating inclusion of the tactile modality within MMC for HRI.
Show less - Date Issued
- 2012
- Identifier
- CFE0004778, ucf:49800
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004778
- Title
- The Relevance of Benjamin Franklin's and Thomas Jefferson's Technical Writing for Modern Communicators.
- Creator
-
Fecko, Kristin, Jones, Dan, Cavanagh, Thomas, Flammia, Madelyn, University of Central Florida
- Abstract / Description
-
Today's technical communicators enjoy an increasingly broader role and influence in the workplace, and are often given latitude to use engaging rhetoric and personal touches in many kinds of communications. Historical documents, particularly those that are substantially removed from our own era, can offer fresh approaches and insight into the enduring elements of successful communication. This study explores the technical writings of Benjamin Franklin and Thomas Jefferson and considers their...
Show moreToday's technical communicators enjoy an increasingly broader role and influence in the workplace, and are often given latitude to use engaging rhetoric and personal touches in many kinds of communications. Historical documents, particularly those that are substantially removed from our own era, can offer fresh approaches and insight into the enduring elements of successful communication. This study explores the technical writings of Benjamin Franklin and Thomas Jefferson and considers their usefulness to professionals today.Although the political writing of Franklin and Jefferson is more familiar, both men frequently wrote about scientific and technical subjects and were well-known in their day for these documents. Franklin created a captivating persona and arguments which carried emotional and logical appeal. Jefferson was a student of ancient rhetoric and applied classical principles of arrangement to guide readers. His fondness for statistical records led to a skill in presenting numerical data and other types of information in creative, efficient ways. By using tone, language, and description, both Franklin and Jefferson created technical narratives that are equally informative and aesthetically pleasing.The contemporary era of technical communication has been shaped by positivism, the plain language movement, and humanism, among other significant trends. Franklin's and Jefferson's approaches to technical communication both support and challenge the guiding philosophies of these movements. Their styles are reviewed in this study against the context of modern approaches. Opportunities for further historical study are also offered, including additional writings of our Founding Fathers and technical writing from the turn of the twentieth century.
Show less - Date Issued
- 2014
- Identifier
- CFE0005329, ucf:50526
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005329
- Title
- Visual Analysis of Extremely Dense Crowded Scenes.
- Creator
-
Idrees, Haroon, Shah, Mubarak, Da Vitoria Lobo, Niels, Stanley, Kenneth, Atia, George, Saleh, Bahaa, University of Central Florida
- Abstract / Description
-
Visual analysis of dense crowds is particularly challenging due to large number of individuals, occlusions, clutter, and fewer pixels per person which rarely occur in ordinary surveillance scenarios. This dissertation aims to address these challenges in images and videos of extremely dense crowds containing hundreds to thousands of humans. The goal is to tackle the fundamental problems of counting, detecting and tracking people in such images and videos using visual and contextual cues that...
Show moreVisual analysis of dense crowds is particularly challenging due to large number of individuals, occlusions, clutter, and fewer pixels per person which rarely occur in ordinary surveillance scenarios. This dissertation aims to address these challenges in images and videos of extremely dense crowds containing hundreds to thousands of humans. The goal is to tackle the fundamental problems of counting, detecting and tracking people in such images and videos using visual and contextual cues that are automatically derived from the crowded scenes.For counting in an image of extremely dense crowd, we propose to leverage multiple sources of information to compute an estimate of the number of individuals present in the image. Our approach relies on sources such as low confidence head detections, repetition of texture elements (using SIFT), and frequency-domain analysis to estimate counts, along with confidence associated with observing individuals, in an image region. Furthermore, we employ a global consistency constraint on counts using Markov Random Field which caters for disparity in counts in local neighborhoods and across scales. We tested this approach on crowd images with the head counts ranging from 94 to 4543 and obtained encouraging results. Through this approach, we are able to count people in images of high-density crowds unlike previous methods which are only applicable to videos of low to medium density crowded scenes. However, the counting procedure just outputs a single number for a large patch or an entire image. With just the counts, it becomes difficult to measure the counting error for a query image with unknown number of people. For this, we propose to localize humans by finding repetitive patterns in the crowd image. Starting with detections from an underlying head detector, we correlate them within the image after their selection through several criteria: in a pre-defined grid, locally, or at multiple scales by automatically finding the patches that are most representative of recurring patterns in the crowd image. Finally, the set of generated hypotheses is selected using binary integer quadratic programming with Special Ordered Set (SOS) Type 1 constraints.Human Detection is another important problem in the analysis of crowded scenes where the goal is to place a bounding box on visible parts of individuals. Primarily applicable to images depicting medium to high density crowds containing several hundred humans, it is a crucial pre-requisite for many other visual tasks, such as tracking, action recognition or detection of anomalous behaviors, exhibited by individuals in a dense crowd. For detecting humans, we explore context in dense crowds in the form of locally-consistent scale prior which captures the similarity in scale in local neighborhoods with smooth variation over the image. Using the scale and confidence of detections obtained from an underlying human detector, we infer scale and confidence priors using Markov Random Field. In an iterative mechanism, the confidences of detections are modified to reflect consistency with the inferred priors, and the priors are updated based on the new detections. The final set of detections obtained are then reasoned for occlusion using Binary Integer Programming where overlaps and relations between parts of individuals are encoded as linear constraints. Both human detection and occlusion reasoning in this approach are solved with local neighbor-dependent constraints, thereby respecting the inter-dependence between individuals characteristic to dense crowd analysis. In addition, we propose a mechanism to detect different combinations of body parts without requiring annotations for individual combinations.Once human detection and localization is performed, we then use it for tracking people in dense crowds. Similar to the use of context as scale prior for human detection, we exploit it in the form of motion concurrence for tracking individuals in dense crowds. The proposed method for tracking provides an alternative and complementary approach to methods that require modeling of crowd flow. Simultaneously, it is less likely to fail in the case of dynamic crowd flows and anomalies by minimally relying on previous frames. The approach begins with the automatic identification of prominent individuals from the crowd that are easy to track. Then, we use Neighborhood Motion Concurrence to model the behavior of individuals in a dense crowd, this predicts the position of an individual based on the motion of its neighbors. When the individual moves with the crowd flow, we use Neighborhood Motion Concurrence to predict motion while leveraging five-frame instantaneous flow in case of dynamically changing flow and anomalies. All these aspects are then embedded in a framework which imposes hierarchy on the order in which positions of individuals are updated. The results are reported on eight sequences of medium to high density crowds and our approach performs on par with existing approaches without learning or modeling patterns of crowd flow.We experimentally demonstrate the efficacy and reliability of our algorithms by quantifying the performance of counting, localization, as well as human detection and tracking on new and challenging datasets containing hundreds to thousands of humans in a given scene.
Show less - Date Issued
- 2014
- Identifier
- CFE0005508, ucf:50367
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005508
- Title
- When Leaders Repress: A Study of African States.
- Creator
-
Timmerman, Ashley, Dolan, Thomas, Mirilovic, Nikola, Kinsey, Barbara, University of Central Florida
- Abstract / Description
-
When do leaders choose state-sponsored repression as a response to certain threats to the state? Conventional wisdom states that authoritarian regimes will be more likely to use these repressive acts in order to maintain law and order, as well as to suppress the opposition. However, previous literature on the subject fails to recognize the effect of irregular civil wars on this decision, as well as the types of repression that will (-) or will not (-) be used against citizens. I analyze cross...
Show moreWhen do leaders choose state-sponsored repression as a response to certain threats to the state? Conventional wisdom states that authoritarian regimes will be more likely to use these repressive acts in order to maintain law and order, as well as to suppress the opposition. However, previous literature on the subject fails to recognize the effect of irregular civil wars on this decision, as well as the types of repression that will (-) or will not (-) be used against citizens. I analyze cross-sectional time series data in 46 African states between 1990 and 2010 on human rights violations and their causes. The key independent variable is irregular civil war, but I also look at the effects of protest movements and domestic terror attacks to find the levels of human rights violations and the specific type of human rights violations used. Irregular civil war is the most important indicator for human rights violations, specifically, the use of killing and disappearances to silence the opposition and end the warfare.
Show less - Date Issued
- 2014
- Identifier
- CFE0005428, ucf:50412
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005428
- Title
- Novel Immunogens of Cellular Immunity Revealed using in vitro Human Cell-Based Approach.
- Creator
-
Schanen, Brian, Self, William, Warren, William, Khaled, Annette, Seal, Sudipta, Zervos, Antonis, University of Central Florida
- Abstract / Description
-
Nanotechnology has undergone rapid expansion largely as a result of its enormous potential for applications as biomaterials, drug delivery vehicles, cancer therapeutics, and immunopotentiators. Despite this wave of interest and broad appeal for nanoparticles, evidence of their effect to the human immune system remains scarce. Concerns rise as studies on nanoparticle toxicology continue to emerge indicating that nanomaterials can be acutely toxic and can have long term inflammatory effects as...
Show moreNanotechnology has undergone rapid expansion largely as a result of its enormous potential for applications as biomaterials, drug delivery vehicles, cancer therapeutics, and immunopotentiators. Despite this wave of interest and broad appeal for nanoparticles, evidence of their effect to the human immune system remains scarce. Concerns rise as studies on nanoparticle toxicology continue to emerge indicating that nanomaterials can be acutely toxic and can have long term inflammatory effects as seen in animal models. Based on these findings and the rise in the development of nanoparticle technologies targeting in vivo applications, the urgency to characterize nanomaterial immunogenicity is paramount.Nanoparticles harbor great potential because they possess unique physicochemical properties compared to their larger counter parts as a result of quantum-size effects and their inherent large surface area to volume ratio. These physicochemical properties govern how a nanoparticle will behave in its environment. However, researchers have only just begun to catalogue the biological effect these properties illicit. We took it upon ourselves to investigate nanoparticle size-induced effects using TiO2, one of the most widely manufactured nanoparticles, as a model. We studied these effects in dendritic cells across a human donor pool. We examined dendritic cells because they have an inimitable functional role bridging the innate and adaptive arms of immunity. From this work we found that TiO2 nanoparticles can activate human dendritic cells to become pro-inflammatory in a size-dependent manner as compared to its micron-sized counterpart, revealing novel immune cell recognition and activation by a crystalline nanomaterial.Having identified nanomaterial size as a contributing feature of nanoparticle induced immunopotentiation, we became interested if additional physicochemical properties such as surface reactivity or catalytic behavior could also be immunostimulatory. Moreover, because we witnessed a stimulatory effect to dendritic cells following nanoparticle treatment, we were curious how these nanoparticle-touched dendritic cells would impact adaptive immunity. Since TiO2 acts as an oxidant we chose an antioxidant nanoparticle, CeO2, as a counterpart to explore how divergent nanoparticle surface reactivity impacts innate and adaptive immunity. We focused on the effect these nanoparticles had on human dendritic cells and TH cells as a strategy towards defining their impact to cellular immunity. Combined, we report that TiO2 nanoparticles potentiate DC maturation inducing the secretion of IL-12p70 and IL-1?, while treatment with CeO2 nanoparticles induced IL-10, a hallmark of suppression. When delivered to T cells alone TiO2 nanoparticles induced stronger proliferation in comparison to CeO2 which stimulated TReg differentiation. When co-cultured in allogeneic T cell assays, the materials directed alternate TH polarization whereby TiO2 drives largely a TH1 dominate response, whereas CeO2 was largely TH2 bias. Combined, we report a novel immunomodulatory capacity of nanomaterials with catalytic activity. While unintentional exposure to these nanomaterials could pose a serious health risk, development and targeted use of such immunomodulatory nanoparticles could provide researchers with new tools for novel adjuvant strategies or therapeutics.
Show less - Date Issued
- 2012
- Identifier
- CFE0004629, ucf:49927
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004629
- Title
- Mediated Physicality: Inducing Illusory Physicality of Virtual Humans via Their Interactions with Physical Objects.
- Creator
-
Lee, Myungho, Welch, Gregory, Wisniewski, Pamela, Hughes, Charles, Bruder, Gerd, Wiegand, Rudolf, University of Central Florida
- Abstract / Description
-
The term virtual human (VH) generally refers to a human-like entity comprised of computer graphics and/or physical body. In the associated research literature, a VH can be further classified as an avatar(-)a human-controlled VH, or an agent(-)a computer-controlled VH. Because of the resemblance with humans, people naturally distinguish them from non-human objects, and often treat them in ways similar to real humans. Sometimes people develop a sense of co-presence or social presence with the...
Show moreThe term virtual human (VH) generally refers to a human-like entity comprised of computer graphics and/or physical body. In the associated research literature, a VH can be further classified as an avatar(-)a human-controlled VH, or an agent(-)a computer-controlled VH. Because of the resemblance with humans, people naturally distinguish them from non-human objects, and often treat them in ways similar to real humans. Sometimes people develop a sense of co-presence or social presence with the VH(-)a phenomenon that is often exploited for training simulations where the VH assumes the role of a human. Prior research associated with VHs has primarily focused on the realism of various visual traits, e.g., appearance, shape, and gestures. However, our sense of the presence of other humans is also affected by other physical sensations conveyed through nearby space or physical objects. For example, we humans can perceive the presence of other individuals via the sound or tactile sensation of approaching footsteps, or by the presence of complementary or opposing forces when carrying a physical box with another person. In my research, I exploit the fact that these sensations, when correlated with events in the shared space, affect one's feeling of social/co-presence with another person. In this dissertation, I introduce novel methods for utilizing direct and indirect physical-virtual interactions with VHs to increase the sense of social/co-presence with the VHs(-)an approach I refer to as mediated physicality. I present results from controlled user studies, in various virtual environment settings, that support the idea that mediated physicality can increase a user's sense of social/co-presence with the VH, and/or induced realistic social behavior. I discuss relationships to prior research, possible explanations for my findings, and areas for future research.
Show less - Date Issued
- 2019
- Identifier
- CFE0007485, ucf:52687
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007485
- Title
- THE INTEGRATED USER EXPERIENCE EVALUATION MODEL: A SYSTEMATIC APPROACH TO INTEGRATING USER EXPERIENCE DATA SOURCES.
- Creator
-
Champney, Roberto, Malone, Linda, University of Central Florida
- Abstract / Description
-
Evaluating the user experience (UX) associated with product interaction is a challenge for current human-systems developers. This is largely due to a lack of theoretical guidance for directing how best to assess the UX and a paucity of tools to support such evaluation. This dissertation provided a framework and tools for guiding and supporting evaluation of the user experience. This doctoral research involved reviewing the literature on UX, using this knowledge to build first build a...
Show moreEvaluating the user experience (UX) associated with product interaction is a challenge for current human-systems developers. This is largely due to a lack of theoretical guidance for directing how best to assess the UX and a paucity of tools to support such evaluation. This dissertation provided a framework and tools for guiding and supporting evaluation of the user experience. This doctoral research involved reviewing the literature on UX, using this knowledge to build first build a theoretical model of the UX construct and later develop a theoretical model to for the evaluation of UX in order to aid evaluators – the integrated User eXperience EValuation (iUXEV), and empirically validating select components of the model through three case studies. The developed evaluation model was subjected to a three phase validation process that included the development and application of different components of the model separately. The first case study focused on developing a tool and method for assessing the affective component of UX which resulted in lessons learned for the integration of the tool and method into the iUXEV model. The second case study focused on integrating several tools that target different components of UX and resulted in a better understanding of how the data could be utilized as well as identify the need for an integration method to bring the data together. The third case study focused on the application of the results of an usability evaluation on an organizational setting which resulted in the identification of challenges and needs faced by practitioners. Taken together, this body of research, from the theoretically-driven iUXEV model to the newly developed emotional assessment tool, extends the user experience / usability body of knowledge and state-of-practice for interaction design practitioners who are challenged with holistic user experience evaluations, thereby advancing the state-of-the-art in UX design and evaluation.
Show less - Date Issued
- 2009
- Identifier
- CFE0002761, ucf:48098
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002761
- Title
- Transparency in human-agent teaming and its effect on complacent behavior.
- Creator
-
Wright, Julia, Hancock, Peter, Szalma, James, Jentsch, Florian, Chen, Jessie, University of Central Florida
- Abstract / Description
-
This study examined how transparency of an intelligent agent's reasoning affected complacent behavior in a route selection task in a simulated environment. Also examined was how the information available to the operator affected those results.In two experiments, participants supervised a three-vehicle convoy as it traversed a simulated environment and re-routed the convoy when needed with the assistance of an intelligent agent, RoboLeader. Participants were randomly assigned to an Agent...
Show moreThis study examined how transparency of an intelligent agent's reasoning affected complacent behavior in a route selection task in a simulated environment. Also examined was how the information available to the operator affected those results.In two experiments, participants supervised a three-vehicle convoy as it traversed a simulated environment and re-routed the convoy when needed with the assistance of an intelligent agent, RoboLeader. Participants were randomly assigned to an Agent Reasoning Transparency condition. Participants received communications from a commander confirming either the presence or absence of activity in the area. They also received information regarding potential events along their route via icons that appeared on a map displaying the convoy route and surrounding area. Participants in Experiment 1 (low information setting) received information about their current route only; they did not receive any information about the suggested alternate route. Participants in Experiment 2 (high information setting) received information about both their current route and the agent recommended an alternative route. In the first experiment, access to agent reasoning was found to be an effective deterrent to complacent behavior when the operator has limited information about their task environment. However, the addition of information that created ambiguity for the operator encouraged complacency, resulting in reduced performance and poorer trust calibration. Agent reasoning did not increase response time or workload and appeared to have improved performance on the secondary task. These findings align with studies that have shown ambiguous information can increase workload and encourage complacency, as such, caution should be exercised when considering how transparent to make agent reasoning and what information should be included.In the second experiment, access to agent reasoning was found to have little effect on complacent behavior when the operator had complete information about the task environment. However, the addition of information that created ambiguity for the operator appeared to encourage complacency, as indicated by reduced performance and shorter decision times. Agent reasoning transparency did not increase overall workload, and operators reported higher satisfaction with their performance and reduced mental demand. Access to agent reasoning did not improve operators' secondary task performance, situation awareness, or operator trust. However, when agent reasoning transparency included ambiguous information complacent behavior was again encouraged. Unlike the first experiment, there were notable differences in complacent behavior, performance, operator trust, and situation awareness due to individual difference factors. As such, these findings would suggest that when the operator has complete information regarding their task environment, access to agent reasoning may be beneficial, but not dramatically so. However, individual difference factors will greatly influence performance outcomes. The amount of information the operator has regarding the task environment has a profound effect on the proper use of the agent. Increased environmental information resulted in more rejections of the agent recommendation regardless of the transparency of agent reasoning. The addition of agent reasoning transparency appeared to be effective at keeping the operator engaged, while complacent behavior appeared to be encouraged both when agent reasoning was either not transparent or so transparent as to become ambiguous. Even so, operators reported lower trust and usability for the agent than when environmental information was limited. Situation awareness (SA2) scores were also higher in the high information environment when agent reasoning was either not transparent or so transparent as to become ambiguous, compared to the low information environment. However, when a moderate amount of agent reasoning was available to the operator, the amount of information available to the operator had no effect on the operators' complacent behavior, subjective trust, or SA. These findings indicate that some negative outcomes resulting from the incongruous transparency of agent reasoning may be mitigated by increasing the information the operator has regarding the task environment.
Show less - Date Issued
- 2016
- Identifier
- CFE0006422, ucf:51469
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006422
- Title
- Human-Robot Interaction For Multi-Robot Systems.
- Creator
-
Lewis, Bennie, Sukthankar, Gita, Hughes, Charles, Laviola II, Joseph, Boloni, Ladislau, Hancock, Peter, University of Central Florida
- Abstract / Description
-
Designing an effective human-robot interaction paradigm is particularly important for complex tasks such as multi robot manipulation that require the human and robot to work together in a tightly coupled fashion. Although increasing the number of robots can expand the area that therobots can cover within a bounded period of time, a poor human-robot interface will ultimately compromise the performance of the team of robots. However, introducing a human operator to the team of robots, does not...
Show moreDesigning an effective human-robot interaction paradigm is particularly important for complex tasks such as multi robot manipulation that require the human and robot to work together in a tightly coupled fashion. Although increasing the number of robots can expand the area that therobots can cover within a bounded period of time, a poor human-robot interface will ultimately compromise the performance of the team of robots. However, introducing a human operator to the team of robots, does not automatically improve performance due to the difficulty of teleoperating mobile robots with manipulators. The human operator's concentration is divided not only amongmultiple robots but also between controlling each robot's base and arm. This complexity substantially increases the potential neglect time, since the operator's inability to effectively attend to each robot during a critical phase of the task leads to a significant degradation in task performance.There are several proven paradigms for increasing the efficacy of human-robot interaction: 1) multimodal interfaces in which the user controls the robots using voice and gesture; 2) configurable interfaces which allow the user to create new commands by demonstrating them; 3) adaptive interfaceswhich reduce the operator's workload as necessary through increasing robot autonomy. This dissertation presents an evaluation of the relative benefits of different types of user interfaces for multi-robot systems composed of robots with wheeled bases and three degree of freedom arms. It describes a design for constructing low-cost multi-robot manipulation systems from off the shelfparts.User expertise was measured along three axes (navigation, manipulation, and coordination), and participants who performed above threshold on two out of three dimensions on a calibration task were rated as expert. Our experiments reveal that the relative expertise of the user was the key determinant of the best performing interface paradigm for that user, indicating that good user modeling is essential for designing a human-robot interaction system that will be used for an extended period of time. The contributions of the dissertation include: 1) a model for detecting operator distraction from robot motion trajectories; 2) adjustable autonomy paradigms for reducing operator workload; 3) a method for creating coordinated multi-robot behaviors from demonstrations with a single robot; 4) a user modeling approach for identifying expert-novice differences from short teleoperation traces.
Show less - Date Issued
- 2014
- Identifier
- CFE0005198, ucf:50613
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005198
- Title
- Environmental Physical(-)Virtual Interaction to Improve Social Presence with a Virtual Human in Mixed Reality.
- Creator
-
Kim, Kangsoo, Welch, Gregory, Gonzalez, Avelino, Sukthankar, Gita, Bruder, Gerd, Fiore, Stephen, University of Central Florida
- Abstract / Description
-
Interactive Virtual Humans (VHs) are increasingly used to replace or assist real humans in various applications, e.g., military and medical training, education, or entertainment. In most VH research, the perceived social presence with a VH, which denotes the user's sense of being socially connected or co-located with the VH, is the decisive factor in evaluating the social influence of the VH(-)a phenomenon where human users' emotions, opinions, or behaviors are affected by the VH. The purpose...
Show moreInteractive Virtual Humans (VHs) are increasingly used to replace or assist real humans in various applications, e.g., military and medical training, education, or entertainment. In most VH research, the perceived social presence with a VH, which denotes the user's sense of being socially connected or co-located with the VH, is the decisive factor in evaluating the social influence of the VH(-)a phenomenon where human users' emotions, opinions, or behaviors are affected by the VH. The purpose of this dissertation is to develop new knowledge about how characteristics and behaviors of a VH in a Mixed Reality (MR) environment can affect the perception of and resulting behavior with the VH, and to find effective and efficient ways to improve the quality and performance of social interactions with VHs. Important issues and challenges in real(-)virtual human interactions in MR, e.g., lack of physical(-)virtual interaction, are identified and discussed through several user studies incorporating interactions with VH systems. In the studies, different features of VHs are prototyped and evaluated, such as a VH's ability to be aware of and influence the surrounding physical environment, while measuring objective behavioral data as well as collecting subjective responses from the participants. The results from the studies support the idea that the VH's awareness and influence of the physical environment can improve not only the perceived social presence with the VH, but also the trustworthiness of the VH within a social context. The findings will contribute towards designing more influential VHs that can benefit a wide range of simulation and training applications for which a high level of social realism is important, and that can be more easily incorporated into our daily lives as social companions, providing reliable relationships and convenience in assisting with daily tasks.
Show less - Date Issued
- 2018
- Identifier
- CFE0007340, ucf:52115
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007340
- Title
- Cell Printing: An Effective Advancement for the Creation of um Size Patterns for Integration into Microfluidic BioMEMs Devices.
- Creator
-
Aubin, Megan, Hickman, James, Coffey, Kevin, Lambert, Stephen, University of Central Florida
- Abstract / Description
-
The Body-on-a-Chip (BoaC) is a microfluidic BioMEMs project that aims to replicate major organs of the human body on a chip, providing an in vitro drug testing platform without the need to resort to animal model testing. Using a human model also provides significantly more accurate drug response data, and may even open the door to personalized drug treatments. Microelectrode arrays integrated with human neuronal or human cardiac cells that are positioned on the electrodes are essential...
Show moreThe Body-on-a-Chip (BoaC) is a microfluidic BioMEMs project that aims to replicate major organs of the human body on a chip, providing an in vitro drug testing platform without the need to resort to animal model testing. Using a human model also provides significantly more accurate drug response data, and may even open the door to personalized drug treatments. Microelectrode arrays integrated with human neuronal or human cardiac cells that are positioned on the electrodes are essential components for BoaC systems. Fabricating these substrates relies heavily on chemically patterned surfaces to control the orientation and growth of the cells. Currently, cells are plated by hand onto the surface of the chemically patterned microelectrode arrays. The cells that land on the cytophobic 2-[Methoxy(Polyethyleneoxy)6-9Propyl]trimethoxysilane (PEG) coating die and detach from the surface, while the cells that land on the cytophilic diethylenetriamine (DETA) coating survive and attach to the surface exhibiting normal physiology and function. The current technique wastes a significant amount of cells, some of which are extremely expensive, and is labor intensive. Cell printing, the process of dispensing cells through a 3D printer, makes it possible to pinpoint the placement of cells onto the microelectrodes, drastically reducing the number of cells utilized. Scaled-up manufacturing is also possible due to the automation capabilities provided by printing. In this work, the specific conditions for printing each cell type is unique, the printing of human motoneurons, human sensory neurons and human cardiac cells was investigated. The viability and functionality of the printed cells are demonstrated by phase images, immunostaining and electrical signal recordings. The superior resolution of cell printing was then taken one step further by successfully printing two different cell types in close proximity to encourage controlled innervation and communication.
Show less - Date Issued
- 2017
- Identifier
- CFE0007390, ucf:52074
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007390
- Title
- INTELLIGENT DESIGN.
- Creator
-
Dudziak, Jillian, Poindexter, Carla, University of Central Florida
- Abstract / Description
-
As human beings we are designed and created in a fabric that is profound and complex. We are built with a framework where mind and body work in a concerted effort to maintain our lives automatically. A deep and defining part of our existence as humans is not just the innate desire to live but to live in consistent well-beingemotionally, physically, and mentally. I believe when we incorporate our knowledge of human physiology into our creative process then we allow ourselves a greater...
Show moreAs human beings we are designed and created in a fabric that is profound and complex. We are built with a framework where mind and body work in a concerted effort to maintain our lives automatically. A deep and defining part of our existence as humans is not just the innate desire to live but to live in consistent well-beingemotionally, physically, and mentally. I believe when we incorporate our knowledge of human physiology into our creative process then we allow ourselves a greater opportunity to create an authentic connection with our intended audience. My work during the past three years has been rooted in the study of these philosophical and scientific principles. I created a series of visual experimentations that aim to assist in my understanding of human beings at an emotional and biological level. Armed with a deep desire to understand humanity, my goal is to create work that fosters positive change and has significant impact in the world. My past and present research has been focused on human emotions, the intuitive creative process and the relationship between technology and establishing social identity.
Show less - Date Issued
- 2011
- Identifier
- CFE0003693, ucf:48844
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0003693
- Title
- Towards Improving Human-Robot Interaction For Social Robots.
- Creator
-
Khan, Saad, Boloni, Ladislau, Behal, Aman, Sukthankar, Gita, Garibay, Ivan, Fiore, Stephen, University of Central Florida
- Abstract / Description
-
Autonomous robots interacting with humans in a social setting must consider the social-cultural environment when pursuing their objectives. Thus the social robot must perceive and understand the social cultural environment in order to be able to explain and predict the actions of its human interaction partners. This dissertation contributes to the emerging field of human-robot interaction for social robots in the following ways: 1. We used the social calculus technique based on culture...
Show moreAutonomous robots interacting with humans in a social setting must consider the social-cultural environment when pursuing their objectives. Thus the social robot must perceive and understand the social cultural environment in order to be able to explain and predict the actions of its human interaction partners. This dissertation contributes to the emerging field of human-robot interaction for social robots in the following ways: 1. We used the social calculus technique based on culture sanctioned social metrics (CSSMs) to quantify, analyze and predict the behavior of the robot, human soldiers and the public perception in the Market Patrol peacekeeping scenario. 2. We validated the results of the Market Patrol scenario by comparing the predicted values with the judgment of a large group of human observers cognizant of the modeled culture. 3. We modeled the movement of a socially aware mobile robot in a dense crowds, using the concept of a micro-conflict to represent the challenge of giving or not giving way to pedestrians. 4. We developed an approach for the robot behavior in micro-conflicts based on the psychological observation that human opponents will use a consistent strategy. For this, the mobile robot classifies the opponent strategy reflected by the personality and social status of the person and chooses an appropriate counter-strategy that takes into account the urgency of the robots' mission. 5. We developed an alternative approach for the resolution of micro-conflicts based on the imitation of the behavior of the human agent. This approach aims to make the behavior of an autonomous robot closely resemble that of a remotely operated one.
Show less - Date Issued
- 2015
- Identifier
- CFE0005965, ucf:50819
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005965
- Title
- Spatial and Temporal Modeling for Human Activity Recognition from Multimodal Sequential Data.
- Creator
-
Ye, Jun, Hua, Kien, Foroosh, Hassan, Zou, Changchun, Karwowski, Waldemar, University of Central Florida
- Abstract / Description
-
Human Activity Recognition (HAR) has been an intense research area for more than a decade. Different sensors, ranging from 2D and 3D cameras to accelerometers, gyroscopes, and magnetometers, have been employed to generate multimodal signals to detect various human activities. With the advancement of sensing technology and the popularity of mobile devices, depth cameras and wearable devices, such as Microsoft Kinect and smart wristbands, open a unprecedented opportunity to solve the...
Show moreHuman Activity Recognition (HAR) has been an intense research area for more than a decade. Different sensors, ranging from 2D and 3D cameras to accelerometers, gyroscopes, and magnetometers, have been employed to generate multimodal signals to detect various human activities. With the advancement of sensing technology and the popularity of mobile devices, depth cameras and wearable devices, such as Microsoft Kinect and smart wristbands, open a unprecedented opportunity to solve the challenging HAR problem by learning expressive representations from the multimodal signals recording huge amounts of daily activities which comprise a rich set of categories.Although competitive performance has been reported, existing methods focus on the statistical or spatial representation of the human activity sequence;while the internal temporal dynamics of the human activity sequence arenot sufficiently exploited. As a result, they often face the challenge of recognizing visually similar activities composed of dynamic patterns in different temporal order. In addition, many model-driven methods based on sophisticated features and carefully-designed classifiers are computationally demanding and unable to scale to a large dataset. In this dissertation, we propose to address these challenges from three different perspectives; namely, 3D spatial relationship modeling, dynamic temporal quantization, and temporal order encoding.We propose a novel octree-based algorithm for computing the 3D spatial relationships between objects from a 3D point cloud captured by a Kinect sensor. A set of 26 3D spatial directions are defined to describe the spatial relationship of an object with respect to a reference object. These 3D directions are implemented as a set of spatial operators, such as "AboveSouthEast" and "BelowNorthWest," of an event query language to query human activities in an indoor environment; for example, "A person walks in the hallway from north to south." The performance is quantitatively evaluated in a public RGBD object dataset and qualitatively investigated in a live video computing platform.In order to address the challenge of temporal modeling in human action recognition, we introduce the dynamic temporal quantization, a clustering-like algorithm to quantize human action sequences of varied lengths into fixed-size quantized vectors. A two-step optimization algorithm is proposed to jointly optimize the quantization of the original sequence. In the aggregation step, frames falling into the sample segment are aggregated by max-polling and produce the quantized representation of the segment. During the assignment step, frame-segment assignment is updated according to dynamic time warping, while the temporal order of the entire sequence is preserved. The proposed technique is evaluated on three public 3D human action datasets and achieves state-of-the-art performance.Finally, we propose a novel temporal order encoding approach that models the temporal dynamics of the sequential data for human activity recognition. The algorithm encodes the temporal order of the latent patterns extracted by the subspace projection and generates a highly compact First-Take-All (FTA) feature vector representing the entire sequential data. An optimization algorithm is further introduced to learn the optimized projections in order to increase the discriminative power of the FTA feature. The compactness of the FTA feature makes it extremely efficient for human activity recognition with nearest neighbor search based on Hamming distance. Experimental results on two public human activity datasets demonstrate the advantages of the FTA feature over state-of-the-art methods in both accuracy and efficiency.
Show less - Date Issued
- 2016
- Identifier
- CFE0006516, ucf:51367
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006516
