An investigation of location effect on trip production using artificial neural networks

As traffic congestion exuberates and new roadway construction is severely constrained because of limited availability of land, high cost of land acquisition, and communities' opposition to the building of major roads, new solutions have to be sought to either make roadway use more efficient or reduce travel demand. There is a general agreement that travel demand is affected by land use patterns. However, traditional aggregate four-step models, which are the prevailing modeling approach presently, assume that traffic condition will not affect people's decision on whether to make a trip or not when trip generation is estimated. Existing survey data indicate, however, that differences exist in trip rates for different geographic areas. The reasons for such differences have not been carefully studied, and the success of quantifying the influence of land use on travel demand beyond employment, households, and their characteristics has been limited to be useful to the traditional four-step models. There may be a number of reasons, such as that the representation of influence of land use on travel demand is aggregated and is not explicit and that land use variables such as density and mix and accessibility as measured by travel time and congestion have not been adequately considered. This research employs the artificial neural network technique to investigate the potential effects of land use and accessibility on trip productions. Sixty two variables that may potentially influence trip production are studied. These variables include demographic, socioeconomic, land use and accessibility variables. Different architectures of ANN models are tested. Sensitivity analysis of the models shows that land use does have an effect on trip production, so does traffic condition. The ANN models are compared with linear regression models and cross-classification models using the same data. The results show that ANN models are better than the linear regression models and cross-classification models in terms of RMSE. Future work may focus on finding a representation of traffic condition with existing network data and population data which might be available when the variables are needed to in prediction.

Freeway travel time estimation and prediction using dynamic neural networks

Providing transportation system operators and travelers with accurate travel time information allows them to make more informed decisions, yielding benefits for individual travelers and for the entire transportation system. Most existing advanced traveler information systems (ATIS) and advanced traffic management systems (ATMS) use instantaneous travel time values estimated based on the current measurements, assuming that traffic conditions remain constant in the near future. For more effective applications, it has been proposed that ATIS and ATMS should use travel times predicted for short-term future conditions rather than instantaneous travel times measured or estimated for current conditions. ^ This dissertation research investigates short-term freeway travel time prediction using Dynamic Neural Networks (DNN) based on traffic detector data collected by radar traffic detectors installed along a freeway corridor. DNN comprises a class of neural networks that are particularly suitable for predicting variables like travel time, but has not been adequately investigated for this purpose. Before this investigation, it was necessary to identifying methods for data imputation to account for missing data usually encountered when collecting data using traffic detectors. It was also necessary to identify a method to estimate the travel time on the freeway corridor based on data collected using point traffic detectors. A new travel time estimation method referred to as the Piecewise Constant Acceleration Based (PCAB) method was developed and compared with other methods reported in the literatures. The results show that one of the simple travel time estimation methods (the average speed method) can work as well as the PCAB method, and both of them out-perform other methods. This study also compared the travel time prediction performance of three different DNN topologies with different memory setups. The results show that one DNN topology (the time-delay neural networks) out-performs the other two DNN topologies for the investigated prediction problem. This topology also performs slightly better than the simple multilayer perceptron (MLP) neural network topology that has been used in a number of previous studies for travel time prediction.^

Freeway Travel Time Estimation and Prediction Using Dynamic Neural Networks

Providing transportation system operators and travelers with accurate travel time information allows them to make more informed decisions, yielding benefits for individual travelers and for the entire transportation system. Most existing advanced traveler information systems (ATIS) and advanced traffic management systems (ATMS) use instantaneous travel time values estimated based on the current measurements, assuming that traffic conditions remain constant in the near future. For more effective applications, it has been proposed that ATIS and ATMS should use travel times predicted for short-term future conditions rather than instantaneous travel times measured or estimated for current conditions. This dissertation research investigates short-term freeway travel time prediction using Dynamic Neural Networks (DNN) based on traffic detector data collected by radar traffic detectors installed along a freeway corridor. DNN comprises a class of neural networks that are particularly suitable for predicting variables like travel time, but has not been adequately investigated for this purpose. Before this investigation, it was necessary to identifying methods for data imputation to account for missing data usually encountered when collecting data using traffic detectors. It was also necessary to identify a method to estimate the travel time on the freeway corridor based on data collected using point traffic detectors. A new travel time estimation method referred to as the Piecewise Constant Acceleration Based (PCAB) method was developed and compared with other methods reported in the literatures. The results show that one of the simple travel time estimation methods (the average speed method) can work as well as the PCAB method, and both of them out-perform other methods. This study also compared the travel time prediction performance of three different DNN topologies with different memory setups. The results show that one DNN topology (the time-delay neural networks) out-performs the other two DNN topologies for the investigated prediction problem. This topology also performs slightly better than the simple multilayer perceptron (MLP) neural network topology that has been used in a number of previous studies for travel time prediction.

A research platform for artificial neural networks with applications in pediatric epilepsy

This dissertation established a state-of-the-art programming tool for designing and training artificial neural networks (ANNs) and showed its applicability to brain research. The developed tool, called NeuralStudio, allows users without programming skills to conduct studies based on ANNs in a powerful and very user friendly interface. A series of unique features has been implemented in NeuralStudio, such as ROC analysis, cross-validation, network averaging, topology optimization, and optimization of the activation function’s slopes. It also included a Support Vector Machines module for comparison purposes. Once the tool was fully developed, it was applied to two studies in brain research. In the first study, the goal was to create and train an ANN to detect epileptic seizures from subdural EEG. This analysis involved extracting features from the spectral power in the gamma frequencies. In the second application, a unique method was devised to link EEG recordings to epileptic and nonepileptic subjects. The contribution of this method consisted of developing a descriptor matrix that can be used to represent any EEG file regarding its duration and the number of electrodes. The first study showed that the inter-electrode mean of the spectral power in the gamma frequencies and its duration above a specific threshold performs better than the other frequencies in seizure detection, exhibiting an accuracy of 95.90%, a sensitivity of 92.59%, and a specificity of 96.84%. The second study yielded that Hjorth’s parameter activity is sufficient to accurately relate EEG to epileptic and non-epileptic subjects. After testing, accuracy, sensitivity and specificity of the classifier were all above 0.9667. Statistical tests measured the superiority of activity at over 99.99 % certainty. It was demonstrated that (1) the spectral power in the gamma frequencies is highly effective in locating seizures from EEG and (2) activity can be used to link EEG recordings to epileptic and non-epileptic subjects. These two studies required high computational load and could be addressed thanks to NeuralStudio. From a medical perspective, both methods proved the merits of NeuralStudio in brain research applications. For its outstanding features, NeuralStudio has been recently awarded a patent (US patent No. 7502763).

Gesture Recognition Using Neural Networks Based on HW/SW Cosimulation Platform

Hardware/software (HW/SW) cosimulation integrates software simulation and hardware simulation simultaneously. Usually, HW/SW co-simulation platform is used to ease debugging and verification for very large-scale integration (VLSI) design. To accelerate the computation of the gesture recognition technique, an HW/SW implementation using field programmable gate array (FPGA) technology is presented in this paper. The major contributions of this work are: (1) a novel design of memory controller in the Verilog Hardware Description Language (Verilog HDL) to reduce memory consumption and load on the processor. (2) The testing part of the neural network algorithm is being hardwired to improve the speed and performance. The American Sign Language gesture recognition is chosen to verify the performance of the approach. Several experiments were carried out on four databases of the gestures (alphabet signs A to Z). (3) The major benefit of this design is that it takes only few milliseconds to recognize the hand gesture which makes it computationally more efficient.

A Research Platform for Artificial Neural Networks with Applications in Pediatric Epilepsy

This dissertation established a state-of-the-art programming tool for designing and training artificial neural networks (ANNs) and showed its applicability to brain research. The developed tool, called NeuralStudio, allows users without programming skills to conduct studies based on ANNs in a powerful and very user friendly interface. A series of unique features has been implemented in NeuralStudio, such as ROC analysis, cross-validation, network averaging, topology optimization, and optimization of the activation function’s slopes. It also included a Support Vector Machines module for comparison purposes. Once the tool was fully developed, it was applied to two studies in brain research. In the first study, the goal was to create and train an ANN to detect epileptic seizures from subdural EEG. This analysis involved extracting features from the spectral power in the gamma frequencies. In the second application, a unique method was devised to link EEG recordings to epileptic and non-epileptic subjects. The contribution of this method consisted of developing a descriptor matrix that can be used to represent any EEG file regarding its duration and the number of electrodes. The first study showed that the inter-electrode mean of the spectral power in the gamma frequencies and its duration above a specific threshold performs better than the other frequencies in seizure detection, exhibiting an accuracy of 95.90%, a sensitivity of 92.59%, and a specificity of 96.84%. The second study yielded that Hjorth’s parameter activity is sufficient to accurately relate EEG to epileptic and non-epileptic subjects. After testing, accuracy, sensitivity and specificity of the classifier were all above 0.9667. Statistical tests measured the superiority of activity at over 99.99 % certainty. It was demonstrated that 1) the spectral power in the gamma frequencies is highly effective in locating seizures from EEG and 2) activity can be used to link EEG recordings to epileptic and non-epileptic subjects. These two studies required high computational load and could be addressed thanks to NeuralStudio. From a medical perspective, both methods proved the merits of NeuralStudio in brain research applications. For its outstanding features, NeuralStudio has been recently awarded a patent (US patent No. 7502763).

Cascade artificial neural networks technique for solving ellipsometry problems

Ellipsometry is a well known optical technique used for the characterization of reflective surfaces in study and films between two media. It is based on measuring the change in the state of polarization that occurs as a beam of polarized light is reflected from or transmitted through the film. Measuring this change can be used to calculate parameters of a single layer film such as the thickness and the refractive index. However, extracting these parameters of interest requires significant numerical processing due to the noninvertible equations. Typically, this is done using least squares solving methods which are slow and adversely affected by local minima in the solvable surface. This thesis describes the development and implementation of a new technique using only Artificial Neural Networks (ANN) to calculate thin film parameters. The new method offers a speed in the orders of magnitude faster than preceding methods and convergence to local minima is completely eliminated.

Endothelin receptor B and neural crest derived melanocyte development

Neural Crest cells (NCC) constitute a unique embryonic cell population that arises between the prospective epidermis and the dorsal aspect of the neural tube of vertebrates. NCC migrate ventromedially and dorsolaterally throughout the developing embryo giving rise to the peripheral nervous system constituents and melanocytes that ultimately reside in the skin and hair follicles respectively. Mice and humans with mutations in the Endothelin receptor b (Ednrb) gene manifest strikingly similar phenotypes characterized by hypopigmentation, hearing loss and megacolon these are due to absence of melanocytes in the skin and inner ear and lack of enteric ganglia in the distal part of the gut, respectively. Piebald lethal mice and humans with Hirschsprung's disease or Waardenburg syndrome carry different mutations in the Ednrb gene. The major goals of this project were to determine whether the action of Ednrb in NCC is required prior to commitment of these cells to the melanocytic lineage and to investigate its potential participation in the actual process of commitment. In order to achieve these goals transgenic mice that express Ednrb under two different regulatory elements were created. The first, Dct-Ednrb, expresses Ednrb under the control of the DOPAchrome tautomerase (Dct) promoter to direct expression to already committed melanocyte precursors. The second, Nes-Ednrb, expresses Ednrb under the regulation of the human nestin gene second enhancer to direct expression to pre-migratory NCC. Crosses of the Dct-Ednrb mouse with piebald lethal showed that the transgene was capable of rescuing the hypopigmentation phenotype of the later. This result indicates that the action of Ednrb after NCC commit to the melanocytic lineage is sufficient for normal melanocyte development. The Dct-Ednrb was further crossed with two other hypopigmentation mutants that carry mutations in the transcription factors Sox10 and Pax3. The transgene rescued the phenotype of the Sox10 mutant only. This suggests that Ednrb interacts with Sox10 but not with Pax3 during melanocyte development. The Nes-Ednrb mice developed a hypopigmentation phenotype that was augmented when crossed with piebald lethal or lethal spotting (mutation in Edn3, the ligand for Ednrb) mice but was rescued by over expression of Edn3. These results suggest that alterations in Ednrb expression early in development affect melanocyte development. This study provides novel information necessary to better understand the early embryonic development of NCC, clarifies specific interactions between different melanogenic genes and, could eventually help in the implementation of therapies for human pigmentary genetic disorders. ^

Enigmatic faunal declines at La Selva, Costa Rica: Patterns and processes in a collapsing neotropical herpetofauna

Amphibian populations are declining even in pristine areas in many parts of the world, and in the Neotropics most such enigmatic amphibian declines have occurred in mid- to high-elevation sites. However, amphibian populations have also declined at La Selva Biological Station in the lowlands of Costa Rica, and similar declines in populations of lizards have occurred at the site as well. To set the stage for describing amphibian declines at La Selva, I thoroughly review knowledge of amphibian decline and amphibian conservation in Central America: I describe general patterns in biodiversity, evaluate major patterns in and ecological correlates of threat status, review trends in basic and applied conservation literature, and recommend directions for future research. I then synthesize data on population densities of amphibians, as well as ecologically similar reptiles, over a 35-year periods using quantitative datasets from a range of studies. This synthesis identifies assemblage-wide declines of approximately 75% for both amphibians and reptiles between 1970 and 2005. Because these declines defy patterns most commonly reported in the Neotropics, it is difficult to assess causality evoking known processes associated with enigmatic decline events. I conduct a 12-month pathogen surveillance program to evaluate infection of frogs by the amphibian chytrid fungus, an emerging pathogen linked to decline events worldwide Although lowland forests are generally believed to be too warm for presence or adverse population effects of chytridiomycosis, I present evidence for seasonal patterns in infection prevalence with highest prevalence in the coolest parts of the year. Finally, I conducted a 16-month field experiment to explore the role of changes to dynamics of leaf litter, a critical resource for both frogs and lizards. Population responses by frogs and lizards indicate that litter regulates population densities of frogs and lizards, particularly those species with the highest decline rate. My work illustrates that sites that are assumed to be pristine are likely impacted by a variety of novel stressors, and that even fauna within protected areas may be suffering unexpected declines.

Spatio-temporal patterns and nutrient status of macroalgae in a heavily managed region of Biscayne Bay, Florida, USA

The coastal bays of South Florida are located downstream of the Florida Everglades, where a comprehensive restoration plan will strongly impact the hydrology of the region. Submerged aquatic vegetation communities are common components of benthic habitats of Biscayne Bay, and will be directly affected by changes in water quality. This study explores community structure, spatio-temporal dynamics, and tissue nutrient content of macroalgae to detect and describe relationships with water quality. The macroalgal community responded to strong variability in salinity; three distinctive macroalgal assemblages were correlated with salinity as follows: (1) low-salinity, dominated by Chara hornemannii and a mix of filamentous algae; (2) brackish, dominated by Penicillus capitatus, Batophora oerstedii, and Acetabularia schenckii; and (3) marine, dominated by Halimeda incrassata and Anadyomene stellata. Tissue-nutrient content was variable in space and time but tissues at all sites had high nitrogen and N:P values, demonstrating high nitrogen availability and phosphorus limitation in this region. This study clearly shows that distinct macroalgal assemblages are related to specific water quality conditions, and that macroalgal assemblages can be used as community-level indicators within an adaptive management framework to evaluate performance and restoration impacts in Biscayne Bay and other regions where both freshwater and nutrient inputs are modified by water management decisions.

Patterns and ecosystem consequences of shark declines in the ocean

Whereas many land predators disappeared before their ecological roles were studied, the decline of marine apex predators is still unfolding. Large sharks in particular have experienced rapid declines over the last decades. In this study, we review the documented changes in exploited elasmobranch communities in coastal, demersal, and pelagic habitats, and synthesize the effects of sharks on their prey and wider communities. We show that the high natural diversity and abundance of sharks is vulnerable to even light fishing pressure. The decline of large predatory sharks reduces natural mortality in a range of prey, contributing to changes in abundance, distribution, and behaviour of small elasmobranchs, marine mammals, and sea turtles that have few other predators. Through direct predation and behavioural modifications, top-down effects of sharks have led to cascading changes in some coastal ecosystems. In demersal and pelagic communities, there is increasing evidence of mesopredator release, but cascading effects are more hypothetical. Here, fishing pressure on mesopredators may mask or even reverse some ecosystem effects. In conclusion, large sharks can exert strong top-down forces with the potential to shape marine communities over large spatial and temporal scales. Yet more empirical evidence is needed to test the generality of these effects throughout the ocean.

Switching patterns and steady-state analysis of grid-connected and stand-alone single-stage boost-inverters for PV applications

Renewable or sustainable energy (SE) sources have attracted the attention of many countries because the power generated is environmentally friendly, and the sources are not subject to the instability of price and availability. This dissertation presents new trends in the DC-AC converters (inverters) used in renewable energy sources, particularly for photovoltaic (PV) energy systems. A review of the existing technologies is performed for both single-phase and three-phase systems, and the pros and cons of the best candidates are investigated. In many modern energy conversion systems, a DC voltage, which is provided from a SE source or energy storage device, must be boosted and converted to an AC voltage with a fixed amplitude and frequency. A novel switching pattern based on the concept of the conventional space-vector pulse-width-modulated (SVPWM) technique is developed for single-stage, boost-inverters using the topology of current source inverters (CSI). The six main switching states, and two zeros, with three switches conducting at any given instant in conventional SVPWM techniques are modified herein into three charging states and six discharging states with only two switches conducting at any given instant. The charging states are necessary in order to boost the DC input voltage. It is demonstrated that the CSI topology in conjunction with the developed switching pattern is capable of providing the required residential AC voltage from a low DC voltage of one PV panel at its rated power for both linear and nonlinear loads. In a micro-grid, the active and reactive power control and consequently voltage regulation is one of the main requirements. Therefore, the capability of the single-stage boost-inverter in controlling the active power and providing the reactive power is investigated. It is demonstrated that the injected active and reactive power can be independently controlled through two modulation indices introduced in the proposed switching algorithm. The system is capable of injecting a desirable level of reactive power, while the maximum power point tracking (MPPT) dictates the desirable active power. The developed switching pattern is experimentally verified through a laboratory scaled three-phase 200W boost-inverter for both grid-connected and stand-alone cases and the results are presented.

Patterns and effects of notetaking by learning -disabled and nondisabled adolescents: A comparative study

This study analyzes the qualitative and quantitative patterns of notetaking by learning disabled (LD) and nondisabled (ND) adolescents and the effectiveness of notetaking and review as measured by the subjects' ability to recall information presented during a lecture. The study also examines relationships between certain learner characteristics and notetaking. The following notetaking variables were investigated: note completeness, number of critical ideas recorded, levels of processing information, organizational strategies, fluency of notes, and legibility of notes. The learner characteristics examined pertained to measures on achievement, short-term memory, listening comprehension, and verbal ability.^ Students from the 11th and 12th grades were randomly selected from four senior high schools in Dade County, Florida. Seventy learning disabled and 79 nondisabled subjects were shown a video tape lecture and required to take notes. The lecture conditions controlled for presentation rate, prior knowledge, information density, and difficulty level. After 8 weeks, their notes were returned to the subjects for a review period, and a posttest was administered.^ Results of this study suggest significant differences (p $\le$.01) in the patterns of notetaking between LD and ND groups not due to differences in the learner characteristics listed above. In addition, certain notetaking variables such as process levels, number of critical ideas, and note completeness were found to be significantly correlated to learning outcome. Further, deficiencies in the spontaneous use of organizational strategies and abbreviations adversely affected the notetaking effectiveness of learning disabled students.^ Both LD and ND subjects recalled more information recorded in their notes than not recorded. This difference was significant only for the ND group. By contrast, LD subjects compensated for their poor notetaking skills and recalled significantly more information not recorded on their notes than did ND subjects. The major implications of these findings suggest that LD and ND subjects exhibit very different entry behaviors when asked to perform a notetaking task; hence, teaching approaches to notetaking must differ as well. ^

Marl Prairie/Slough Gradients; Patterns and Trends in Shark Slough and Adjacent Marl Prairies (CERP monitoring activity 3.1.3.5), First Annual Report (2005)

The work on CERP monitoring item 3.1.3.5 (Marl prairie/slough gradients) is being conducted by Florida International University (Dr Michael Ross, Project Leader), with Everglades National Park (Dr. Craig Smith) providing administrative support and technical consultation. As of January 2006 the funds transferred by ACOE to ENP, and subsequently to FIU, have been entirely expended or encumbered in salaries or wages. The project work for 2005 started rather late in the fiscal year, but ultimately accomplished the Year 1 goals of securing a permit to conduct the research in Everglades National Park, finalizing a detailed scope of work, and sampling marsh sites which are most easily accessed during the wet season. 46 plots were sampled in detail, and a preliminary vegetation classification distinguished three groups among these sites (Sawgrass marsh, sawgrass and other, and slough) which may be arranged roughly along a hydrologic gradient from least to most persistently inundated . We also made coarser observations of vegetation type at 5-m intervals along 2 transects totaling ~ 5 km. When these data were compared with similar observations made in 1998-99, it appeared that vegetation in the western portion of Northeast Shark Slough (immediately east of the L-67 extension) had shifted toward a more hydric type during the last 6 years, while vegetation further east was unchanged in this respect. Because this classification and trend analysis is based on a small fraction of the data set that will be available after the first cycle of sampling (3 years from now), the results should not be interpreted too expansively. However, they do demonstrate the potential for gaining a more comprehensive view of marsh vegetation structure and dynamics in the Everglades, and will provide a sound basis for adaptive management.

Switching Patterns and Steady-State Analysis of Grid-Connected and Stand-Alone Single-Stage Boost-Inverters for PV Applications

Renewable or sustainable energy (SE) sources have attracted the attention of many countries because the power generated is environmentally friendly, and the sources are not subject to the instability of price and availability. This dissertation presents new trends in the DC-AC converters (inverters) used in renewable energy sources, particularly for photovoltaic (PV) energy systems. A review of the existing technologies is performed for both single-phase and three-phase systems, and the pros and cons of the best candidates are investigated. In many modern energy conversion systems, a DC voltage, which is provided from a SE source or energy storage device, must be boosted and converted to an AC voltage with a fixed amplitude and frequency. A novel switching pattern based on the concept of the conventional space-vector pulse-width-modulated (SVPWM) technique is developed for single-stage, boost-inverters using the topology of current source inverters (CSI). The six main switching states, and two zeros, with three switches conducting at any given instant in conventional SVPWM techniques are modified herein into three charging states and six discharging states with only two switches conducting at any given instant. The charging states are necessary in order to boost the DC input voltage. It is demonstrated that the CSI topology in conjunction with the developed switching pattern is capable of providing the required residential AC voltage from a low DC voltage of one PV panel at its rated power for both linear and nonlinear loads. In a micro-grid, the active and reactive power control and consequently voltage regulation is one of the main requirements. Therefore, the capability of the single-stage boost-inverter in controlling the active power and providing the reactive power is investigated. It is demonstrated that the injected active and reactive power can be independently controlled through two modulation indices introduced in the proposed switching algorithm. The system is capable of injecting a desirable level of reactive power, while the maximum power point tracking (MPPT) dictates the desirable active power. The developed switching pattern is experimentally verified through a laboratory scaled three-phase 200W boost-inverter for both grid-connected and stand-alone cases and the results are presented.