University of Maryland, Baltimore County
Not a member yet
17643 research outputs found
Sort by
Time series analysis using deep feedforward neural networks
No full textDeep neural networks can be used for abstraction and as a preprocessing step for other machine learning classifiers. Our goal was to develop methods for a more accurate automated seizure detection. Deep architectures have been used for classification of events, and shown in this research to be an effective way of classifying multichannel high resolution medical data. The medical data used in this thesis was gathered from an electroencephalograph (EEG) used in a hospital setting on seizure patients. To demonstrate the ability of deep architectures to learn and abstract from input data, the signals from the EEG that contained both seizure and non seizure data were given both as featurized data and raw data to the deep architecture. In addition to the multiple types of data preparation, a patients EEG data was tested not only against their own EEG signal training data but other patients as well. This study supports the effectiveness of deep feed forward neural networks for usage in the seizure classification scenario, as well as highlights some of the difficulties associated with training deep neural networks, as shown through experimental results
Recoloring Web Pages For Color Vision Deficiency Users
No full textColor vision begins with the activation cone cells. When one of the cone cells dys- function, color vision deficiency (CVD) ensues. Due to CVD, users become unable to differentiate as many colors a normal person can. Lack of this ability results in less rich web experience, incomprehension of basic information and thus frustration. Solutions such as carefully choosing colors while designing or recolor web pages for CVD users exist. We first present the improvement in the time complexity of an existing tool SPRWeb[6] to re- color web pages. After that we present our tool, FBRecolor, which explores the foreground- background relationship between colors in a web page. Using this relationship we propose FBRecolor, which preserves naturalness, pair-differentiability and subjectivity. In the last part, we add an additional step in to FBRecolor to ensure that the contrast in the parsed color pairs meets the required W3C guidelines[5]. In evaluation, we found that FBRecolor does significantly better in preserving pair-differentiability and produces lower total cost solutions than SPRWeb. Quantitative experimentation of extension to FBRecolor shows that contrast ratio in each replacement pair is more than 4.5 as required for readability
Human-Assisted Machine Vision for the Visually Impaired
No full textApproximately 285 million people in the world are estimated to be visually impaired. In the increasingly complex urban world, indoor and outdoor navigation has become a difficult task for the visually impaired individuals, especially those who use wheelchairs and walking canes. They have limited travel choices and rely mostly on the pedestrian environment. Sidewalks and pedestrian crossings are important for their daily travel. Despite of having the laws that govern proper standards for accessibility-compatible sidewalks, time accessibility of sidewalks gets damaged over a period of time. Due to accessibility issues on sidewalks, travelling independently becomes difficult for the visually impaired wheelchair and walking cane users and they seek support from navigation systems. Real time navigation systems for the visually impaired pedestrians, assist them by notifying about any dangers in their path and navigates them around the obstacles. Machine vision based navigation systems lack a priori contextual information which is necessary for detecting obstacles in real time. Also, use of sensors like RADAR and LIDAR for real time obstacle detection increases the power requirements. Thus, having a priori accessibility maps containing geospatial data of accessibility issue locations is helpful for notifying visually impaired individuals in real time mode. We present WheelNav - a system which uses human-assisted machine vision for developing accurate sidewalk accessibility maps for the navigation of visually impaired individuals. A group of users called Volunteers, crowdsource geotagged images and other relevant information of sidewalk accessibility issues they observe in their city through a smartphone application. Further, computer vision technique called Perspective Transformation is used for identifying the accurate positions of sidewalk accessibility issue objects in crowdsourced images for creating accessibility map. This process is assisted by human workers called Turkers who use Amazon Mechanical Turk and provide feedback about the estimates of real world dimensions of objects in crowdsourced images
Sources and fluxes of carbon and nutrients in human-impacted watersheds and estuaries
No full textUrbanization alters watershed hydrology and has increased nutrient pollution, leading to eutrophication and hypoxia in downstream coastal ecosystems. In order to manage increased nutrient exports and loss of biogeochemical functions in urban streams and rivers it is important to better understand how management of both point and diffuse sources affects carbon and nutrients under various flow conditions. The objective of this research was to investigate the impacts of urban development on sources, transformations, and fluxes of carbon (C) and nutrients along urban headwater streams and a large coastal estuary. Chapter 1 covers the impact of headwater stream burial on nitrate uptake and stream metabolism. Chapter 2 focuses on the impact of age and extent of urban infrastructure and watershed management on hydrologic variability and pulsing of C and nutrient sources and fluxes. Chapter 3 examines the capacity of a large river-estuary system to transform and remove inputs of nitrogen (N) and C from a major metropolitan area and the world's largest advanced wastewater treatment plant. Results from Chapter 1 indicate that burial of headwater streams significantly reduces nitrate uptake, gross primary productivity, and ecosystem respiration, compared to non-buried streams, by factors of 9.6, 11, and 5, respectively. It was also estimated that at the watershed scale, stream burial decreases N uptake by 39 � 5% and C production by 105 � 103%. Results from Chapter 2 indicate that urbanized streams with higher percent impervious surface cover and older infrastructure have greater inputs of N, C, and phosphorus (P) from leaky sanitary sewers and flashier hydrology, resulting in higher concentrations and more variable and pulsed exports of C, N, and P. Results from Chapter 3 indicate that large river-estuary systems have the potential to transform and remove N loads from point-source wastewater treatment plant inputs over relatively short spatial scales. There were seasonal patterns in N removal in the Potomac River Estuary, with greater denitrification and uptake rates in the summer and fall, accompanied by lower net exports, but during the spring when flows were highest, exports were also highest. Overall, the research in this dissertation indicates that urbanization reduces nutrient retention through stream burial and increases the amount and variability of C and nutrient exports in headwater streams, while river-estuarine systems have a large capacity to assimilate nutrient inputs from major point sources
Union Market: A Story of People and Food in a Changing Place
No full textThe historical and ethnographic study of Union Market, a public market complex in Northeast Washington, D.C., examines the impact of decline and redevelopment on the social dynamics at work there from the late 1920s to present day. The social dynamics explored include the people, culture, and function of the market. This research connects the processes of urban change and identities (per)formed in the market with access to public space. People (per)form identities, regardless of intention, through such means as their appearance, food choices, and activities. These performances imbue space with sociocultural coding that tells others who and what belong there. This coding as well as processes of urban change like gentrification shape the public in public spaces. Who public includes matters because of the role these spaces play in defining communities and societal values. The story of Union Market offers an in-depth look at how public is shaped and by whom, the role of food in defining the identities of people and places, and the choices that drive urban change
Sources and fluxes of carbon and nutrients in human-impacted watersheds and estuaries
No full textUrbanization alters watershed hydrology and has increased nutrient pollution, leading to eutrophication and hypoxia in downstream coastal ecosystems. In order to manage increased nutrient exports and loss of biogeochemical functions in urban streams and rivers it is important to better understand how management of both point and diffuse sources affects carbon and nutrients under various flow conditions. The objective of this research was to investigate the impacts of urban development on sources, transformations, and fluxes of carbon (C) and nutrients along urban headwater streams and a large coastal estuary. Chapter 1 covers the impact of headwater stream burial on nitrate uptake and stream metabolism. Chapter 2 focuses on the impact of age and extent of urban infrastructure and watershed management on hydrologic variability and pulsing of C and nutrient sources and fluxes. Chapter 3 examines the capacity of a large river-estuary system to transform and remove inputs of nitrogen (N) and C from a major metropolitan area and the world's largest advanced wastewater treatment plant. Results from Chapter 1 indicate that burial of headwater streams significantly reduces nitrate uptake, gross primary productivity, and ecosystem respiration, compared to non-buried streams, by factors of 9.6, 11, and 5, respectively. It was also estimated that at the watershed scale, stream burial decreases N uptake by 39 ? 5% and C production by 105 ? 103%. Results from Chapter 2 indicate that urbanized streams with higher percent impervious surface cover and older infrastructure have greater inputs of N, C, and phosphorus (P) from leaky sanitary sewers and flashier hydrology, resulting in higher concentrations and more variable and pulsed exports of C, N, and P. Results from Chapter 3 indicate that large river-estuary systems have the potential to transform and remove N loads from point-source wastewater treatment plant inputs over relatively short spatial scales. There were seasonal patterns in N removal in the Potomac River Estuary, with greater denitrification and uptake rates in the summer and fall, accompanied by lower net exports, but during the spring when flows were highest, exports were also highest. Overall, the research in this dissertation indicates that urbanization reduces nutrient retention through stream burial and increases the amount and variability of C and nutrient exports in headwater streams, while river-estuarine systems have a large capacity to assimilate nutrient inputs from major point sources
Impact of Federally Qualified Health Centers on Rates of Ambulatory Care Sensitive Conditions among Medicaid and Uninsured Populations in Maryland
No full textAmbulatory Care Sensitive Conditions (ACSCs) are conditions for which hospitalization and emergency department (ED) visits can be avoided if a person has better access to ambulatory care services. Rates and costs of hospital admission and ED visits for ACSCs have increased over the decade, especially for people without health insurance and/or on Medicaid. Objectives of this dissertation were to study ACSC rates in Maryland over time, identify areas where ACSC rates had been persistently high, determine factors that were associated with ACSCs, and examine if the expansion of FQHCs had decreased ACSCs in geographical areas over the study period. The study used Maryland hospital discharge data to identify ACSCs based on the Agency for Healthcare Research and Quality (AHRQ) definition of Prevention Quality Indicators (PQIs). A Zip Code Tabulation Area (ZCTA) was used as a unit of analysis. ACSCs and all controlled factors were calculated at the ZCTA level from 2000 to 2010. Negative binomial panel models were used to determine trends, and to estimate the impact of FQHCs and other factors on ACSCs. The study found that ACSC rates among Medicaid and uninsured patients had increased over time for several conditions while such conditions among total populations remained stable or decline. In addition, variations in hospitalization and ED visits for ACSCs existed across Maryland's counties and local areas, but the rates seemed consistent within the areas over time. Proportion of populations living in poverty had the largest and consistently positive relationship with most ACSC hospitalization and ED visit rates. The relationships between ACSCs and other socioeconomic factors are varied by type of condition. Importantly, the expansion of FQHCs had a significant association with lower rates of hospitalization and ED visits for several ACSC conditions. Thus, the expansion of FQHCs is associated with better access to primary care among Medicaid and uninsured populations
A Discrete, Three-Dimensional, Force-Based Mathematical Model of Collective Cell Migration
No full textWe present a novel mathematical approach to modeling the collective cell migration process that occurs during stages eight to ten of Drosophila oogenesis. This new approach uses the forces of adhesion, repulsion, migration and stochastic fluctuation to simulate the movement of discrete cells. At the start of oogenesis, the motile and non-motile cells of this system lie in the anterior follicular epithelium. These cells form a cluster and translocate as a collective to the posterior of the egg chamber, in the direction of the developing egg chamber. Our model captures the dynamics of these cells, as well as the epithelium that encloses the egg chamber, and the nurse cells that comprise the space that the cluster migrates through. We implement this using Identical Math Cells, or IMCs. These IMCs may each represent one biological cell of the system, or can be aggregated to model the dynamics of larger biological cells. They each can be assigned unique biophysical properties, which can be used to model a heterogeneous cell population. This also increases the diversity and biological accuracy of the cell-to-cell interactions that may potentially be modeled. Using this mathematical construct we have successfully simulated the migration of this cluster of cells. We have also used this model to investigate how altering the number of motile cells in the system affects the behavior of the migrating cluster. We show that decreasing the number of motile cells results in increased migration time, which has not been shown directly, but is believed to cause the loss of viability in vivo. We also show that the forces utilized in this model are sufficient to produce rotation of the cluster. Similar rotation has been observed in vivo and this result suggests that a more complex biophysical mechanism is not necessary to produce rotation of a migrating cluster. This model was developed to capture a heterogeneous cell population and was implemented with the flexibility to allow for diverse, but precise, initial position specification over a three-dimensional domain. Therefore, we believe that this model will be useful for not only examining aspects of Drosophila oogenesis, but also for modeling other two or three-dimensional systems that have multiple cell types and where investigating the forces between these cells is of interest
Improving Access to Mobile Technologies Using Tactile Feedback
No full textMobile technologies offer the benefits of portability and ubiquity. However, their reliance on small visual displays and realistic settings (e.g. while on the move) can introduce a variety of usability challenges to users, causing situational-induced impairments and disabilities (SIIDs). While the sense of touch provides one solution to supporting users with SIIDs, the tactile feedback provided by current mobile technologies is relatively simple in nature, often based on the metaphorical associations arbitrarily dictated by interface designers. Furthermore, these cues are yet to be extensively evaluated outside of controlled environments. This dissertation aimed to address these limitations. Firstly, we studied the range of discernible tactile icons (tactons) that can be presented via standard mobile technologies. Findings highlighted the role of intensity in supporting tactile recognition as well as the impact of duration, interval and intensity on task time. We also examined the use of tactons in a mobile exertion application, designed to help individuals monitor and modify walking behavior. Usability tests of the application proved its utility in communicating alerts and promoting physical activity among users. Secondly, we examined the impact of situational distractors (i.e. sound and movement) on the perception of multi-parametered tactons. Results indicated the negative effects of these distractors on recognition accuracy, time taken and cognitive workload. However, some tactile designs (e.g. those encoded with stronger intensities) were found to be able to better resist such effects. Our findings highlighted the importance of evaluating mobile interfaces in more realistic contexts. Thirdly, we investigated the intuitiveness of tactile mappings between tactile parameters (e.g. intensity of vibrations) and message features (e.g. urgency of messages) for mobile notifications. A paired-comparison task was performed. Using this approach, we identified the tactile mappings rated with the highest preference scores. Tactons designed using these mappings were proved to be more effective in field-based settings. The dissertation has culminated in a set of design guidelines relating to the design and evaluation of tactons for use in mobile interactions. These guidelines may help the mobile interface developers to construct effective tactile feedback, and improve users' access to mobile technologies in distracting contexts
Predictors of Social Withdrawal and Internalizing Problems in Chinese Floating Population Children
No full textChinese floating population children are at risk for being the target of teasing and bullying, and for experiencing loneliness, lower self-esteem, and lack of opportunity to develop social skills. The overall goal of the dissertation project was to examine the factors that may contribute to Chinese floating population children's social and emotional development. First, the roles of determinants of parenting (maternal psychological well-being, acculturation to the urban culture, and social support), parenting styles (authoritarian parenting and authoritative parenting), and indigenous parenting practices (shaming/love withdrawal and maternal involvement) on Chinese floating population children's anxious shyness, regulated shyness and internalizing problems were explored. Further, the complex relations between parenting styles, child effortful control, and three child shyness subtypes (temperamental shyness, anxious shyness, and regulated shyness) were examined in moderated mediation models. Four hundred and eighty Chinese floating population mothers with preschool children residing in three cities in Guangdong Province, China participated in the study. The results showed that floating population mothers' acculturation to the urban culture was associated with greater maternal endorsement of the authoritative parenting style and less engagement in the authoritarian parenting style. Also, maternal authoritarian parenting style mediated the relation between mothers' acculturation to the urban culture and children's display of regulated shyness. Moreover, the results from the moderated mediation models indicated that floating population mothers' authoritarian parenting style was negatively associated with their children's effortful control. Child effortful control was in turn positively related to children's regulated shyness, but only for children with low levels of temperamental shyness. The results from the dissertation project contributed to the current literature on children's social withdrawal by identifying predictors of parenting, and parenting and child contributions to shyness in a unique but rapidly growing sample of floating population children. These findings have important implications for the promotion of healthy social-emotional development among floating population children in China