Effective classification with imbalanced data is an important area of research, as high class imbalance is naturally inherent in many real-world applications, e.g. anomaly detection. Modeling such skewed data distributions is often very difficult, and non-standard methods are sometimes required to combat these negative effects. These challenges have been studied thoroughly using traditional machine learning algorithms, but very little empirical work exists in the area of deep learning with class imbalanced big data. Following an in-depth survey of deep learning methods for addressing class imbalance, we evaluate various methods for addressing imbalance on the task of detecting Medicare fraud, a big data problem characterized by extreme class imbalance. Case studies herein demonstrate the impact of class imbalance on neural networks, evaluate the efficacy of data-level and algorithm-level methods, and achieve state-of-the-art results on the given Medicare data set. Results indicate that combining under-sampling and over-sampling maximizes both performance and efficiency. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2019. / FAU Electronic Theses and Dissertations Collection

At the Castle Creek study area in east-central British Columbia a well-exposed section about 450 m wide and 30 m thick in the (Neoproterozoic) Isaac Formation was analyzed to document vertical and lateral changes in a succession of distinctively heterolithic strata. Strata are interpreted to have been deposited on a deep-marine levee that was sandwiched between its genetically related channel on one side and an erosional escarpment sculpted by an older (underlying) channel on the other. Flows that overspilled the channel (incident flow) eventually encountered the escarpment, which then set up a return flow oriented more or less opposite to the incident (from the channel) flow. This created an area of complex flow that became manifested in the sedimentary record as a highly tabular succession of intricately interstratified sand and mud overlain by an anomalously thick, plane-parallel interlaminated sand-mud unit capped finally by a claystone.

This thesis shows how children’s learning is influenced and modified by the teaching environment. The metacognitive, self-regulatory learning behaviours of sixteen kindergarten students were examined in order to determine how students perceive learning, either by adopting deep approaches, where the focus is on understanding and meaning, or surface approaches, where the meeting of institutional demands frequently subjugate the former goals. The data have been analysed within a qualitative paradigm from a phenomenographic perspective. The study addresses three issues: the nature and frequency of the strategic learning behaviours displayed by the students; the contribution strategic behaviours make to the adoption of deep or surface learning approaches; and how metacognitive teaching environments influence higher-order thinking. Findings reveal that where teachers had metcognitive training, the frequency of strategy use increased irrespective of student performance. High achieving students used more strategic behaviours, used them with greater efficiency, and tended to display more of the characteristics of deep approach learners. This study suggests that many of the differential outcomes evident amongst students may be substantially reduced through early and consistent training within a teaching environment conductive to the development of metacognitive, self-regulatory behaviours and deep learning approaches / Doctor of Philosophy (PhD)

Typescript. Copies of three papers (2 published), co-authored by the author, in back. Bibliography: leaves 179-186.

The current study examined cognitive effects of unilateral subthalamic nucleus (STN) deep brain stimulation (DBS) in Parkinson's disease (PD) patients. Neuropsychological evaluations were conducted at baseline and follow-up. Data was collected from 28 unilateral STN DBS patients (15 English- and 13 Spanish-speaking), and 15 English-speaking matched PD control patients. English-speaking DBS patients demonstrated significant declines in verbal fluency and attention/executive function, whereas PD control patients did not experience significant cognitive decline. Cognitive performance did not differ based on side of DBS. Spanish-speaking DBS patients experienced significant declines in verbal fluency, confrontational naming and visuospatial abilities. Among Spanish-speaking DBS patients, older age and later age of disease onset predicted verbal fluency decline, even after controlling for education.

The Mid Ocean Ridge system with its volcanism and related hydrothermal activity has been a subject for many studies since the discovery of high temperature hydrothermal vents at the ridge surfaces in the 1970´s. This thesis focuses on deep sea hydrothermal activity on a superfast spreading ridge, the SouthernEast Pacific Rise (SEPR).The ridge is located in the South Pacific, off the coast of South America, and separates the Nazca Plate and the Pacific Plate. A fossil high temperature hydrothermal zone hosted by a fault was sampled 80 m below the lava/dike transition zone in the Pito Deep (a tectonic window intothe SEPR). Geochemical data from the fault zone indicates that cold (<150°C)and hot (<390°) fluids coexisted at the same time whilst the hydrothermal system was active. A numerical model (HYDROTHERM) developed by the USGS was used to recreate the geological settings in the SEPR in order to try to model the hydrothermal activity and fluid flow. The model solves two governingpartial differential equations numerically, the water component flow equation(Darcy law for flow in porous media) and the thermal energy transport equation(conservation of enthalpy for the water component and the porous media). The result of the modeling indicates that cold seawater can penetrate from the relatively permeable volcanic material into a highly permeable fault zone in the sheeted dike unit. The cooler seawater fluid flows down the fault zone,reheats and flows up again in a narrow upflow zone at the edge of the fracture/sheeted dike boundary. The result is a horizontal temperature gradient created in the fractured zone supporting the theory that hot and cold fluids can coexist in a fault hosted hydrothermal zone.

Deep generative neural networks such as the Deep Belief Network and Deep Boltzmann Machines have been used successfully to model high dimensional visual data. However, they are not robust to common variations such as occlusion and random noise. In this thesis, we explore two strategies for improving the robustness of DBNs. First, we show that a DBN with sparse connections in the first layer is more robust to variations that are not in the training set. Second, we develop a probabilistic denoising algorithm to determine a subset of the hidden layer nodes to unclamp. We show that this can be applied to any feedforward network classifier with localized first layer connections. By utilizing the already available generative model for denoising prior to recognition, we show significantly better performance over the standard DBN implementations for various sources of noise on the standard and Variations MNIST databases.

The introduction of deep reactive ion etching (DRIE) technology has greatly expanded the accessible design space for microscopic systems. Structures that are hundreds of micrometers tall with aspect ratios of 40:1, heretofore impossible, can now be achieved. However, this technology is primarily a forming technology, sculpting structures from a substrate. This work seeks to complement deep reactive ion etching by developing an electrical isolation technology to enable electro-mechanical function in these new deep reactive ion etched structures. The objective of the research is twofold. The first is to develop and characterize an electrical isolation technology for DRIE, single crystal silicon (SCS) micro-electro-mechanical systems (MEMS) using temperature gradient zone melting (TGZM) of aluminum junctions for diodic isolation. The second is to demonstrate the utility of this electrical isolation technology in the design, simulation, fabrication, and testing of a MEMS device, i.e. a micro-gyroscope, in such a way that the benefits from junction isolated, deep reactive ion etched, single crystal silicon devices are preserved.

Predicting the performance of wells in compartmentalized reservoirs can be quite challenging to most conventional reservoir engineering tools. The purpose of this research is to develop a Compartmentalized Gas Depletion Model that applies not only to conventional consolidated reservoirs (with constant formation compressibility) but also to unconsolidated reservoirs (with variable formation compressibility) by including geomechanics, permeability deterioration and compartmentalization to estimate the OGIP and performance characteristics of each compartment in such reservoirs given production data. A geomechanics model was developed using available correlation in the industry to estimate variable pore volume compressibility, reservoir compaction and permeability reduction. The geomechanics calculations were combined with gas material balance equation and pseudo-steady state equation and the model was used to predict well performance. Simulated production data from a conventional gas Simulator was used for consolidated reservoir cases while synthetic data (generated by the model using known parameters) was used for unconsolidated reservoir cases. In both cases, the Compartmentalized Depletion Model was used to analyze data, and estimate the OGIP and Jg of each compartment in a compartmentalized gas reservoir and predict the subsequent reservoir performance. The analysis was done by history-matching gas rate with the model using an optimization technique. The model gave satisfactory results with both consolidated and unconsolidated reservoirs for single and multiple reservoir layers. It was demonstrated that for unconsolidated reservoirs, reduction in permeability and reservoir compaction could be very significant especially for unconsolidated gas reservoirs with large pay thickness and large depletion pressure.

This research was carried out in support of fieldwork in the Gulf of Mexico in summers 2004 and 2005 as part of the multidisciplinary Sperm Whale Seismic Study (SWSS). Important aspects of SWSS research include oceanographic habitat characterization and studies of sperm whale foraging and diving patterns. During the SWSS 2005 cruise, acoustic volume backscatter data were collected using a 38 kHz ADCP for comparison with XBT, MODIS ocean color data, and whale dive profiles extrapolated from analysis of towed passive acoustic hydrophone array recordings of whale vocalizations. This unique data set, collected from a cyclonic eddy, was compared with non-upwelling conditions surveyed in the western Gulf and the Mississippi Canyon in summer 2004. My focus was to examine the relationship between acoustic backscatter intensity from the deep scattering layer (DSL; usually 400-600 m deep) and the depths to which whales dived. The results of the study investigate differences in DSL characteristics between divergent zones and non-divergent zones, and examine connections relating to variations in sperm whale dive patterns. The analysis of 38 kHz ADCP data showed that there were significant differences in some characteristics of the main DSL dependent on time of day. There were no significant differences in characteristics of the main DSL between divergent and non-divergent areas or between 2004 and 2005. The comparison of the 38 kHz ADCP and the 70 kHz Simrad echosounder data yielded a relationship of 4 ADCP counts for every 1 dB of Sv. This relationship was a promising start to a potential calibration for the ADCP instrument. Lastly, the analysis of localized sperm whale dive profiles identified three basic dive profiles; Deep (> 800 m), Mid-water dives to DSL depths (500 - 800 m) and Shallow (<500 m). The analysis also showed that whale dive behavior did not change based on time of day or location. It showed that whales are diving above the DSL as well as through and below, however these dives are independent of differences in DSL characteristics.