General health screening is needed to decrease the risk of pandemic in high volume areas. Thermal characterization, via infrared imaging, is an effective technique for fever detection, however, strict use requirements in combination with highly controlled environmental conditions compromise the practicality of such a system. Combining advanced processing techniques to thermograms of individuals can remove some of these requirements allowing for more flexible classification algorithms. The purpose of this research was to identify individuals who had febrile status utilizing modern thermal imaging and machine learning techniques in a minimally controlled setting. Two methods were evaluated with data that contained environmental, and acclimation noise due to data gathering technique. The first was a pretrained VGG16 Convolutional Neural Network found to have F1 score of 0.77 (accuracy of 76%) on a balanced dataset. The second was a VGG16 Feature Extractor that gives inputs to a principle components analysis and utilizes a support vector machine for classification. This technique obtained a F1 score of 0.84 (accuracy of 85%) on balanced data sets. These results demonstrate that machine learning is an extremely viable technique to classify febrile status independent of noise affiliated.

Time-lapse fluorescence live cell imaging has been widely used to study various dynamic processes in cell biology. As the initial step of image analysis, it is important to localize and segment cell edges with higher accuracy. However, fluorescence live-cell images usually have issues such as low contrast, noises, uneven illumination in comparison to immunofluorescence images. Deep convolutional neural networks, which learn features directly from training images, have successfully been applied in natural image analysis problems. However, the limited amount of training samples prevents their routine application in fluorescence live-cell image analysis. In this thesis, by exploiting the temporal coherence in time-lapse movies together with VGG-16 [1] pre-trained model, we demonstrate that we can train a deep neural network using a limited number of image frames to segment the entire time-lapse movies. We propose a novel framework, vU-net, which combines the advantages of VGG-16 [1] in feature extraction and U-net [2] in feature reconstruction. Moreover, we design an auxiliary convolutional block at the end of the architecture to enhance edge detection. We evaluate our framework using dice coefficient and the distance between the predicted edge and the ground truth on high-resolution image datasets of an adhesion marker, paxillin, acquired by a Total Internal Reflection Fluorescence (TIRF) microscope. Our results demonstrate that, on difficult datasets: (i) The testing dice coefficient of vU-net is 3.2% higher than U-net with the same amount of training images. (ii) vU-net can achieve the best prediction results of U-net with one third of training images needed by U-net. (iii) vU-net produces more robust prediction than U-net. Therefore, vU-net can be more practically applied to challenging live cell movies than U-net since it requires a small size of training sets and achieved accurate segmentation.

We explore a machine learning task, evidence recommendation (ER), the extraction of evidence from a source document to support an external claim. This task is an instance of the question answering machine learning task. We apply ER to academic publications because they cite other papers for the claims they make. Reading cited papers to corroborate claims is time-consuming and an automated ER tool could expedite it. Thus, we propose a methodology for collecting a dataset of academic papers and their references. We explore deep learning models for ER and achieve 77% accuracy with pairwise models and 75% pairwise accuracy with document-wise models.

Non-convex optimization of deep neural networks is a well-researched problem. We present a novel application of continuation methods for deep learning optimization that can potentially arrive at a better solution. In our method, we first decompose the original optimization problem into a sequence of problems using a homotopy method. To achieve this in neural networks, we derive the Continuation(C)- Activation function. First, C-Activation is a homotopic formulation of existing activation functions such as Sigmoid, ReLU or Tanh. Second, we apply a method which is standard in the parameter continuation domain, but to the best of our knowledge, novel to the deep learning domain. In particular, we use Natural Parameter Continuation with Secant approximation(NPCS), an effective training strategy that may find a superior local minimum for a non-convex optimization problem. Additionally, we extend our work on Step-up GANs, a data continuation approach, by deriving a method called Continuous(C)-SMOTE which is an extension of standard oversampling algorithms. We demonstrate the improvements made by our methods and establish a categorization of recent work done on continuation methods in the context of deep learning.

The work presented in this thesis consists of three main topics: document segmentation and classification into text and score, efficient computation with binary representations, and deep learning architectures for polyphonic music transcription and classification. In the case of musical documents, an important problem is separating text from musical score by detecting the corresponding boundary boxes. A new algorithm is proposed for pixel-wise classification of digital documents in musical score and text. It is based on a bag-of-visual-words approach and random forest classification. A robust technique for identifying bounding boxes of text and music score from the pixel-wise classification is also proposed. For efficient processing of learned models, we turn our attention to binary representations. When dealing with binary data, the use of bit-packing and bit-wise computation can reduce computational time and memory requirements considerably. Efficiency is a key factor when processing large scale datasets and in industrial applications. SPmat is an optimized framework for binary image processing. We propose a bit-packed representation for binary images that encodes both pixels and square neighborhoods, and design SPmat, an optimized framework for binary image processing, around it. Bit-packing and bit-wise computation can also be used for efficient forward propagation in deep neural networks. Quantified deep neural networks have recently been proposed with the goal of improving computational time performance and memory requirements while maintaining as much as possible classification performance. A particular type of quantized neural networks are binary neural networks in which the weights and activations are constrained to $-1$ and $+1$. In this thesis, we describe and evaluate Espresso, a novel optimized framework for fast inference of binary neural networks that takes advantage of bit-packing and bit-wise computations. Espresso is self contained, written in C/CUDA and provides optimized implementations of all the building blocks needed to perform forward propagation. Following the recent success, we further investigate Deep neural networks. They have achieved state-of-the-art results and outperformed traditional machine learning methods in many applications such as: computer vision, speech recognition, and machine translation. However, in the case of music information retrieval (MIR) and audio analysis, shallow neural networks are commonly used. The effectiveness of deep and very deep architectures for MIR and audio tasks has not been explored in detail. It is also not clear what is the best input representation for a particular task. We therefore investigate deep neural networks for the following audio analysis tasks: polyphonic music transcription, musical genre classification, and urban sound classification. We analyze the performance of common classification network architectures using different input representations, paying specific attention to residual networks. We also evaluate the robustness of these models in case of degraded audio using different combinations of training/testing data. Through experimental evaluation we show that residual networks provide consistent performance improvements when analyzing degraded audio across different representations and tasks. Finally, we present a convolutional architecture based on U-Net that can improve polyphonic music transcription performance of different baseline transcription networks. / Graduate

In this thesis we study deep learning architectures for the problem of human action recognition in image sequences, i.e. the problem of automatically recognizing what people are doing in a given video. As unlabeled video data is easily accessible these days, we first explore models that can learn meaningful representations of sequences without actually having to know what is happening in the sequences at hand. More specifically, we first explore the convolutional restricted Boltzmann machine (RBM) and show how a stack of convolutional RBMs can be used to learn and extract features from sequences in an unsupervised way. Using the classical Fisher vector pipeline to encode the extracted features we apply them on the task of action classification. We move on to feature extraction using larger, deep convolutional neural networks and propose a novel architecture which expresses the processing steps of the classical Fisher vector pipeline as network layers. By contrast to other methods where these steps are performed consecutively and the corresponding parameters are learned in an unsupervised manner, defining them as a single neural network allows us to refine the whole model discriminatively in an end to end fashion. We show that our method achieves significant improvements in comparison to the classical Fisher vector extraction chain and results in a comparable performance to other convolutional networks, while largely reducing the number of required trainable parameters. Finally, we explore how the proposed architecture can be modified into a hybrid network that combines the benefits of both unsupervised and supervised training methods, resulting in a model that learns a semi-supervised Fisher vector descriptor of the input data. We evaluate the proposed model at image classification and action recognition problems and show how the model's classification performance improves as the amount of unlabeled data increases during training.

Diana.sobieraj@hhchealth.org / Objective To systematically review the literature and to quantitatively evaluate the efficacy and safety of extended pharmacologic treatment of venous thromboembolism (VTE) through network meta-analysis (NMA). Methods A systematic literature search (MEDLINE, Embase, Cochrane CENTRAL, through September 2014) and searching of reference lists of included studies and relevant reviews was conducted to identify randomized controlled trials of patients who completed initial anticoagulant treatment for VTE and then randomized for the extension study; compared extension of anticoagulant treatment to placebo or active control; and reported at least one outcome of interest (VTE or a composite of major bleeding or clinically relevant non-major bleeding). A random-effects Frequentist approach to NMA was used to calculate relative risks with 95% confidence intervals. Results Ten trials (n=11,079) were included. Risk of bias (assessed with the Cochrane tool) was low in most domains assessed across the included trials. Apixaban (2.5mg and 5mg), dabigatran, rivaroxaban, idraparinux and vitamin K antagonists (VKA) each significantly reduced the risk of VTE recurrence compared to placebo, ranging from a 73% reduction with idraparinux to 86% with VKAs. With exception of idraparinux, all active therapies significantly reduced VTE recurrence risk versus aspirin, ranging from a 73% reduction with either apixaban 2.5mg or rivaroxaban to 80% with VKAs. Apixaban and aspirin were the only therapies that did not increase composite bleeding risk significantly compared to placebo. All active therapies except aspirin increased risk of composite bleeding by 2 to 4-fold compared to apixaban 2.5mg, with no difference found between the two apixaban doses. Conclusion Extended treatment of VTE is a reasonable approach to provide continued protection from VTE recurrence although bleeding risk is variable across therapeutic options. Our results indicate that apixaban, dabigatran, rivaroxaban, idraparinux and VKAs all reduced VTE recurrence when compared to placebo. Apixaban appears to have a more favorable safety profile compared to other therapies. / Revisión por pares

Biometrics are a convenient alternative to traditional forms of access control such as passwords and pass-cards since they rely solely on user-specific traits. Unlike alphanumeric passwords, biometrics cannot be given or told to another person, and unlike pass-cards, are always “on-hand.” Perhaps the most well-known biometrics with these properties are: face, speech, iris, and gait. This dissertation proposes a new biometric modality: gestures. A gesture is a short body motion that contains static anatomical information and changing behavioral (dynamic) information. This work considers both full-body gestures such as a large wave of the arms, and hand gestures such as a subtle curl of the fingers and palm. For access control, a specific gesture can be selected as a “password” and used for identification and authentication of a user. If this particular motion were somehow compromised, a user could readily select a new motion as a “password,” effectively changing and renewing the behavioral aspect of the biometric. This thesis describes a novel framework for acquiring, representing, and evaluating gesture passwords for the purpose of general access control. The framework uses depth sensors, such as the Kinect, to record gesture information from which depth maps or pose features are estimated. First, various distance measures, such as the log-euclidean distance between feature covariance matrices and distances based on feature sequence alignment via dynamic time warping, are used to compare two gestures, and train a classifier to either authenticate or identify a user. In authentication, this framework yields an equal error rate on the order of 1-2% for body and hand gestures in non-adversarial scenarios. Next, through a novel decomposition of gestures into posture, build, and dynamic components, the relative importance of each component is studied. The dynamic portion of a gesture is shown to have the largest impact on biometric performance with its removal causing a significant increase in error. In addition, the effects of two types of threats are investigated: one due to self-induced degradations (personal effects and the passage of time) and the other due to spoof attacks. For body gestures, both spoof attacks (with only the dynamic component) and self-induced degradations increase the equal error rate as expected. Further, the benefits of adding additional sensor viewpoints to this modality are empirically evaluated. Finally, a novel framework that leverages deep convolutional neural networks for learning a user-specific “style” representation from a set of known gestures is proposed and compared to a similar representation for gesture recognition. This deep convolutional neural network yields significantly improved performance over prior methods. A byproduct of this work is the creation and release of multiple publicly available, user-centric (as opposed to gesture-centric) datasets based on both body and hand gestures.

Understanding of the fundamental ecology of deep-sea ecosystems remains immature relative to more familiar shallow-water and terrestrial habitats, despite more than two hundred years of scientific investigation. This thesis aims to progress knowledge of deep-sea benthic ecology by the analysis of over three hundred box core samples collected from the Northwest Atlantic continental slope as part of the international NEREIDA programme. Aspects of the ecology of Peracarida (Crustacea) are studied, and this is facilitated by the coupling of a large faunal dataset with extensive environmental information. To further enhance the power of this dataset, phylogenetic and functional characteristics of assemblages are investigated. Using community phylogenetic methodology, it is demonstrated that the peracarid assemblages studied are structured more strongly by variation in environmental parameters than they are by competitive interactions. Analyses demonstrate that the intensity of bottom trawling, seafloor temperature, current speed, food availability, sediment characteristics and physical habitat heterogeneity all influence deep-sea peracarid assemblage biodiversity metrics. Further, the importance of high poriferan biomass for the promotion of peracarid assemblages of high density, biomass, richness and diversity is highlighted. Of relevance to the management of deep-sea ecosystems, the results of this thesis suggest that caution should be exercised when applying species distribution models to data-deficient environments, whilst the location of spatial closures in the NAFO Regulatory Area may not be fully optimal for the protection of all components of diverse benthic assemblages against the impacts of bottom trawling. The importance of deep-sea diversity is demonstrated by the finding of positive biodiversity – ecosystem functioning relationships. However, the form of these relationships is found to be dependent on the biodiversity and ecosystem functioning metrics employed, and a hypothesis for a generalised form of biodiversity – ecosystem functioning relationships is proposed. Finally, this thesis calls for more ambitious deep-sea ecological investigations, and it is hoped that its findings will encourage future research initiatives, helping to further illuminate this enigmatic and fascinating environment.

Biogenic “oozes” are pelagic sediments that are composed of > 30% carbonate microfossils and are estimated to cover about 50% of the ocean floor, which accounts for about 67% of calcium carbonate in oceanic surface sediments worldwide. These deposits exhibit diverse assemblages of planktonic microfossils and contribute significantly to the overall sediment supply and function of Florida’s deep-water regions. However, the composition and distribution of biogenic sediment deposits along these regions remains poorly documented. Seafloor surface sediments have been collected in situ via Johnson- Sea-Link I submersible along four of Florida’s deep-water regions during a joint research cruise between Harbor Branch Oceanographic Institute (HBOI) and Florida Atlantic University (FAU). Sedimentological analyses of the taxonomy, species diversity, and sedimentation dynamics reveal a complex interconnected development system of Florida’s deep-water habitats. Results disclose characteristic microfossil assemblages of planktonic foraminiferal ooze off the South West Florida Shelf, a foraminiferal-pteropod ooze through the Straits of Florida, and pteropod ooze deposits off Florida’s east coast. The distribution of the biogenic ooze deposits is attributed to factors such as oceanographic surface production, surface and bottom currents, off-bank transport, and deep-water sediment drifts. The application of micropaleontology, sedimentology, and oceanography facilitate in characterizing the sediment supply to Florida’s deep-water regions. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2017. / FAU Electronic Theses and Dissertations Collection