Computed tomography (CT) is routinely used for diagnosing lung disease and developing treatment plans using images of intricate lung structure with submillimeter resolution. Automated segmentation of anatomical structures in such images is important to enable efficient processing in clinical and research settings. Convolution neural networks (ConvNets) are largely successful at performing image segmentation with the ability to learn discriminative abstract features that yield generalizable predictions. However, constraints in hardware memory do not allow deep networks to be trained with high-resolution volumetric CT images. Restricted by memory constraints, current applications of ConvNets on volumetric medical images use a subset of the full image; limiting the capacity of the network to learn informative global patterns. Local patterns, such as edges, are necessary for precise boundary localization, however, they suffer from low specificity. Global information can disambiguate structures that are locally similar. The central thesis of this doctoral work is that both local and global information is important for segmentation of anatomical structures in medical images. A novel multi-scale ConvNet is proposed that divides the learning task across multiple networks; each network learns features over different ranges of scales. It is hypothesized that multi-scale ConvNets will lead to improved segmentation performance, as no compromise needs to be made between image resolution, image extent, and network depth. Three multi-scale models were designed to specifically target segmentation of three pulmonary structures: lungs, fissures, and lobes. The proposed models were evaluated on a diverse datasets and compared to architectures that do not use both local and global features. The lung model was evaluated on humans and three animal species; the results demonstrated the multi-scale model outperformed single scale models at different resolutions. The fissure model showed superior performance compared to both a traditional Hessian filter and a standard U-Net architecture that is limited in global extent. The results demonstrated that multi-scale ConvNets improved pulmonary CT segmentation by incorporating both local and global features using multiple ConvNets within a constrained-memory system. Overall, the proposed pipeline achieved high accuracy and was robust to variations resulting from different imaging protocols, reconstruction kernels, scanners, lung volumes, and pathological alterations; demonstrating its potential for enabling high-throughput image analysis in clinical and research settings.

A portion of teachers in the United States educational system don'€™t use data to inform and improve their instruction resulting in actionable change. A gap exists between teachers having and interpreting data and making meaning in such a way that leads to actionable change in instruction. The purpose of this case study was to investigate how teachers used data to alter instruction and identify factors that inhibited or supported teachers in using data to drive instructional practice. This study was guided by Ackoff'€™s theory of action cycle, which included interaction, dialogue, data discoveries, and team response to data. The research questions asked how teams used data and what factors inhibited and supported the use of data. Three teams were observed. Eleven classroom teachers, the building principal and the district professional development director were interviewed. The teacher team criteria included that teachers met weekly and used, at a minimum, common formative assessments. The school and district mission, vision and value statements were collected as artifacts to see how these documents supported the use of data. Open and axial coding exposed themes and patterns. Results indicated that teachers commonly omitted one or more phases in a data cycle; however, when teachers worked through all phases of a data cycle, actionable change in instruction resulted, and factors that both inhibited and supported teacher use of data to guide instruction were evident throughout all aspects of the study. The project, a white paper, summarized the study and provided research-based recommendations based on the study. These recommendations focus on building teacher capacity and relationships. This study may generate social change through educational equity. Equity is achieved when teachers use data to inform instruction so that learners of all abilities may have access to learning.

This study investigates Mio-Pliocene mass-transport deposits (MTDs) in an understudied, hydrocarbon-rich region of the northeastern Gulf of Mexico. The research utilizes a high-quality 3D seismic dataset with an area of 635 km2, along with wireline logs and biostratigraphic data. With the help of quantitative seismic geomorphology techniques, detailed mapping of MTDs suggests a complex erosional and depositional history. Deposition of a MTD unit resulted in a 180 m topographic high that substantially influenced the distribution and morphology of subsequent MTDs, specifically the bifurcation of later mass-transport flows. This bifurcation contributed to the generation of a non-shielded erosional remnant with an area of 65 km2. Depositional elements of the remnant strata are interpreted to be sediment waves. Instantaneous frequency attribute maps of the erosional remnant suggest a different lithology than the surrounding muddy MTDs; and, thus, the remnant unit is interpreted to be sandy. For the first time in literature, this research documented intra-MTD channel and lobe features. The development of a sinuous channel system encased within MTD gives new insights into mass-transport processes. This provides evidence for considering MTD as amalgamation deposits of multiple and different-type of flow events (e.g., turbidity currents and debris flows), rather than a singular event-deposit. The channel, lobe, and erosional remnant features examined in this research demonstrate reservoir-prone facies encased within MTD units, forming stratigraphic traps directly associated with mass-transport phenomena. This research contributes to the understanding of seal vs. reservoir rock development and distribution in the study area, as well as presents new developments into mass-transport deposit flow processes and their resulting morphologies.

The ultimate goal of image understanding is to transfer visual images into numerical or symbolic descriptions of the scene that are helpful for decision making. Knowing when, where, and in which direction a picture was taken, the task of geo-calibration makes it possible to use imagery to understand the world and how it changes in time. Current models for geo-calibration are mostly deterministic, which in many cases fails to model the inherent uncertainties when the image content is ambiguous. Furthermore, without a proper modeling of the uncertainty, subsequent processing can yield overly confident predictions. To address these limitations, we propose a probabilistic model for camera geo-calibration using deep neural networks. While our primary contribution is geo-calibration, we also show that learning to geo-calibrate a camera allows us to implicitly learn to understand the content of the scene.

<div>Following a natural disaster, one of the most important facet that influence a persons chances of survival/being found out is the time with which they are rescued. Traditional means of search operations involving dogs, ground robots, humanitarian intervention; are time intensive and can be a major bottleneck in search operations. The main aim of these operations is to rescue victims without critical delay in the shortest time possible which can be realized in real-time by using UAVs. With advancements in computational devices and the ability to learn from complex data, deep learning can be leveraged in real time environment for purpose of search and rescue operations. This research aims to solve the traditional means of search operation using the concept of deep learning for real time object detection and Photogrammetry for precise geo-location mapping of the objects(person,car) in real time. In order to do so, various pre-trained algorithms like Mask-RCNN, SSD300, YOLOv3 and trained algorithms like YOLOv3 have been deployed with their results compared with means of addressing the search operation in</div><div>real time.</div><div><br></div>

Deep learning has been making headlines in recent years and is often portrayed as an emerging technology on a meteoric rise towards fully sentient artificial intelligence. In reality, deep learning is the most recent renaissance of a 70 year old technology and is far from possessing true intelligence. The renewed interest is motivated by recent successes in challenging problems, the accessibility made possible by hardware developments, and dataset availability. The predecessor to deep learning, commonly known as the artificial neural network, is a computational network setup to mimic the biological neural structure found in brains. However, unlike human brains, artificial neural networks, in most cases cannot make inferences from one problem to another. As a result, developing an artificial neural network requires a large number of examples of desired behavior for a specific problem. Furthermore, developing an artificial neural network capable of solving the problem can take days, or even weeks, of computations. Two specific problems addressed in this dissertation are both input association problems. One problem challenges a neural network to identify overlapping regions in images and is used to evaluate the ability of a neural network to learn associations between inputs of similar types. The other problem asks a neural network to identify which observed wireless signals originated from observed potential sources and is used to assess the ability of a neural network to learn associations between inputs of different types. The neural network solutions to both problems introduced, discussed, and evaluated in this dissertation demonstrate deep learning’s applicability to problems which have previously attracted little attention.

Thesis (Ph. D.)--University of Hong Kong, 2007. / Title proper from title frame. Also available in printed format.

This thesis addresses the utility of deep-water coral geochemistry and its potential to reconstruct oceanographic conditions in the Straits of Florida. Through stable isotope and elemental analyses of the carbonate skeletons and use of available geochemical proxy calibration equations, present and past environmental parameters were determined. Over the last several years, scientific expeditions to the bottom of the Straits of Florida have revealed hundreds of deep-water coral mounds and led to the collection of extensive oceanographic data, sediment samples, and deep-water coral specimens. In 2005-2006, an Autonomous Underwater Vehicle (AUV) was used to map the coral mound fields at five sites with the use of geophysical imaging technology, and the manned Johnson-Sea-Link II submersible was deployed for further exploration and sample collection. The AUV and the submersible CTD also measured numerous environmental parameters, including temperature and salinity. With the goal of reconstructing environmental parameters across the Straits of Florida, Scleractinian and gorgonian deep-water coral specimens were selected from three sites spanning the Straits. Each coral was sampled at the highest resolution possible and analyzed for stable isotopes and elemental concentrations. Resulting geochemical data, specifically d18O, d13C, Sr/Ca, and Mg/Ca, was then used with previously published and newly developed calibration equations to calculate temperature, salinity, and seawater density. Kinetic and vital effects were also examined and taken into account while reconstructing environmental parameters using the coral geochemistry. Additional reconstructions using stable isotopic values from benthic foraminifera corroborated the geochemical reconstructions, and analyses of pteropods and surface sediment samples provided further insight into the oceanographic conditions at the bottom of the Straits of Florida. Results from geochemical reconstructions agreed with in situ data, indicating that slightly warmer bottom temperatures exist on the eastern side of the Straits and salinity variability among the three sites is minimal. This suggests that the deep-water coral skeletons are sensitive recorders of the environmental conditions in which they lived. Ultimately, in situ measurements and reconstructed parameters showed that there is little variability across the bottom of the Straits and that Antarctic Intermediate Water (AAIW) is the only apparent water mass in the area at that depth. Moreover, comparison of the coral habitat from this study with others from around the world demonstrated that certain conditions are required for deep-water coral growth, and that these same parameters are common to deep-water reef systems throughout the globe. Further sampling and geochemical analyses of deep-water corals in the region may be used to gain additional insight into the oceanographic conditions surrounding the coral mounds both presently and in the past. As with other previously studied deep-water coral systems, this highlights the potential for the reconstruction of paleo environmental records from deep-water corals in the Straits of Florida.

Thesis (M.Sc.)--Memorial University of Newfoundland, 2005. / Includes bibliographical references.

A deep-sea time-lapse camera and several temperature probes were deployed on the Gulf of Mexico continental shelf at a biological community associated with a gas hydrate outcropping to study topographic and hydrologic changes over time. The deployment site, Bush Hill (GC 185), is located at 27°47.5' N and 91°15.0' W at depths of ~540m. The digital camera recorded one still image every six hours for three months in 2001, every two hours for the month of June 2002 and every six hours for the month of July 2002. Temperature probes were in place at the site for the entire experimental period. The data recovered provide a record of processes that occur at gas hydrate mounds. Biological activity was documented by identifying the fauna observed in the time-lapse record and recording the number of individuals and species in each image. 1,381 individual organisms representing 16 species were observed. Sediment resuspension and redistribution were regular occurrences during the deployment periods. By digitally analyzing the luminosity of the water column above the mound and plotting the results over time, the turbidity at the site was quantified. A significant diurnal pattern can be seen in both luminosity and temperature records, indicating a possible tidal or inertial component to deep-sea currents in this area. Contrary to expectations, there was no major change in shape or size of the gas hydrate outcrop at this site on the time frame of this study. This indicates that this particular mound was more stable than suggested by laboratory studies and prior in situ observations. The stable topography of the gas hydrate mound combined with high bacterial activity and sediment turnover appears to focus benthic predatory activity in the mound area. The frequency and recurrence of sediment resuspension indicates that short-term change in the depth and distribution of surface sediments is a feature of the benthos at the site. Because the sediment interface is a critical environment for hydrocarbon oxidation and chemosynthesis, short-term variability and heterogeneity may be important characteristics of these settings.