Ces vingt dernières années, la quantité d’images et de vidéos transmises a augmenté significativement, ce qui est principalement lié à l’essor de Facebook et Netflix. Même si les capacités de transmission s’améliorent, ce nombre croissant d’images et de vidéos transmises exige des méthodes de compression plus efficaces. Cette thèse a pour but d’améliorer par l’apprentissage deux composants clés des standards modernes de compression d’image, à savoir la transformée et la prédiction intra. Plus précisément, des réseaux de neurones profonds sont employés car ils ont un grand pouvoir d’approximation, ce qui est nécessaire pour apprendre une approximation fidèle d’une transformée optimale (ou d’un filtre de prédiction intra optimal) appliqué à des pixels d’image. En ce qui concerne l’apprentissage d’une transformée pour la compression d’image via des réseaux de neurones, un défi est d’apprendre une transformée unique qui est efficace en termes de compromis débit-distorsion, à différents débits. C’est pourquoi deux approches sont proposées pour relever ce défi. Dans la première approche, l’architecture du réseau de neurones impose une contrainte de parcimonie sur les coefficients transformés. Le niveau de parcimonie offre un contrôle sur le taux de compression. Afin d’adapter la transformée à différents taux de compression, le niveau de parcimonie est stochastique pendant la phase d’apprentissage. Dans la deuxième approche, l’efficacité en termes de compromis débit-distorsion est obtenue en minimisant une fonction de débit-distorsion pendant la phase d’apprentissage. Pendant la phase de test, les pas de quantification sont progressivement agrandis selon un schéma afin de compresser à différents débits avec une unique transformée apprise. Concernant l’apprentissage d’un filtre de prédiction intra pour la compression d’image via des réseaux de neurones, le problème est d’obtenir un filtre appris qui s’adapte à la taille du bloc d’image à prédire, à l’information manquante dans le contexte de prédiction et au bruit de quantification variable dans ce contexte. Un ensemble de réseaux de neurones est conçu et entraîné de façon à ce que le filtre appris soit adaptatif à ces égards. / Over the last twenty years, the amount of transmitted images and videos has increased noticeably, mainly urged on by Facebook and Netflix. Even though broadcast capacities improve, this growing amount of transmitted images and videos requires increasingly efficient compression methods. This thesis aims at improving via learning two critical components of the modern image compression standards, which are the transform and the intra prediction. More precisely, deep neural networks are used for this task as they exhibit high power of approximation, which is needed for learning a reliable approximation of an optimal transform (or an optimal intra prediction filter) applied to image pixels. Regarding the learning of a transform for image compression via neural networks, a challenge is to learn an unique transform that is efficient in terms of rate-distortion while keeping this efficiency when compressing at different rates. That is why two approaches are proposed to take on this challenge. In the first approach, the neural network architecture sets a sparsity on the transform coefficients. The level of sparsity gives a direct control over the compression rate. To force the transform to adapt to different compression rates, the level of sparsity is stochastically driven during the training phase. In the second approach, the rate-distortion efficiency is obtained by minimizing a rate-distortion objective function during the training phase. During the test phase, the quantization step sizes are gradually increased according a scheduling to compress at different rates using the single learned transform. Regarding the learning of an intra prediction filter for image compression via neural networks, the issue is to obtain a learned filter that is adaptive with respect to the size of the image block to be predicted, with respect to missing information in the context of prediction, and with respect to the variable quantization noise in this context. A set of neural networks is designed and trained so that the learned prediction filter has this adaptibility.

Biometrics is the study of physical or behavioral traits that establishes the identity of a person. Forensics, physical security and cyber security are some of the main fields that use biometrics. Unlike traditional authentication systems—such as password based—biometrics cannot be lost, forgotten or shared. This is possible because biometrics establishes the identity of a person based on a physiological/behavioural characteristic rather than what the person possess or remembers. Biometrics has two modes of operation: identification and authentication. Identification finds the identity of a person among a group of persons. Authentication determines if the claimed identity of a person is truthful. Biometric person authentication is an alternative to passwords or graphical patterns. It prevents shoulder surfing attacks, i.e., people watching from a short distance. Nevertheless, biometric traits of conventional authentication techniques like fingerprints, face—and to some extend iris—are easy to capture and duplicate. This denotes a security risk for modern and future applications such as digital twins, where an attacker can copy and duplicate a biometric trait in order to spoof a biometric system. Researchers have proposed ECG as biometric authentication to solve this problem. ECG authentication conceals the biometric traits and reduces the risk of an attack by duplication of the biometric trait. However, current ECG authentication solutions require 10 or more seconds of an ECG signal in order to have accurate results. The accuracy is directly proportional to the ECG signal time-length for authentication. This is inconvenient to implement ECG authentication in an end-user product because a user cannot wait 10 or more seconds to gain access in a secure manner to their device. This thesis addresses the problem of spoofing by proposing an accurate and secure ECG biometric authentication system with relatively short ECG signal length for authentication. The system consists of an ECG acquisition from lead I (two electrodes), signal processing approaches for filtration and R-peak detection, a feature extractor and an authentication process. To evaluate this system, we developed a method to calculate the Equal Error Rate—EER—with non-normal distributed data. In the authentication process, we propose an approach based on Support Vector Machine—SVM—and achieve 4.5% EER with 4 seconds of ECG signal length for authentication. This approach opens the door for a deeper understanding of the signal and hence we enhanced it by applying a hybrid approach of Convolutional Neural Networks—CNN—combined with SVM. The purpose of this hybrid approach is to improve accuracy by automatically detect and extract features with Deep Learning—in this case CNN—and then take the output into a one-class SVM classifier—Authentication; which proved to outperform accuracy for one-class ECG classification. This hybrid approach reduces the EER to 2.84% with 4 seconds of ECG signal length for authentication. Furthermore, we investigated the combination of two different biometrics techniques and we improved the accuracy to 0.46% EER, while maintaining a short ECG signal length for authentication of 4 seconds. We fuse Fingerprint with ECG at the decision level. Decision level fusion requires information that is available from any biometric technique. Fusion at different levels—such as feature level fusion—requires information about features that are incompatible or hidden. Fingerprint minutiae are composed of information that differs from ECG peaks and valleys. Therefore fusion at the feature level is not possible unless the fusion algorithm provides a compatible conversion scheme. Proprietary biometric hardware does not provide information about the features or the algorithms; therefore, features are hidden and not accessible for feature level fusion; however, the result is always available for a decision level fusion.

In today’s society, we experience an increasing challenge to provide healthcare to everyone in need due to the increasing number of patients and the shortage of medical staff. Computers have contributed to mitigating this challenge by offloading the medical staff from some of the tasks. With the rise of deep learning, countless new possibilities have opened to help the medical staff even further. One domain where deep learning can be applied is analysis of ultrasound images. In this thesis we investigate the problem of classifying standard views of the heart in ultrasound images with the help of deep learning. We conduct mainly three experiments. First, we use NasNet mobile, InceptionV3, VGG16 and MobileNet, pre-trained on ImageNet, and finetune them to ultrasound heart images. We compare the accuracy of these networks to each other and to the baselinemodel, a CNN that was proposed in [23]. Then we assess a neural network’s capability to generalize to images from ultrasound machines that the network is not trained on. Lastly, we test how the performance of the networks degrades with decreasing amount of training data. Our first experiment shows that all networks considered in this study have very similar performance in terms of accuracy with Inception V3 being slightly better than the rest. The best performance is achieved when the whole network is finetuned to our problem instead of finetuning only apart of it, while gradually unlocking more layers for training. The generalization experiment shows that neural networks have the potential to generalize to images from ultrasound machines that they are not trained on. It also shows that having a mix of multiple ultrasound machines in the training data increases generalization performance. In our last experiment we compare the performance of the CNN proposed in [23] with MobileNet pre-trained on ImageNet and MobileNet randomly initialized. This shows that the performance of the baseline model suffers the least with decreasing amount of training data and that pre-training helps the performance drastically on smaller training datasets.

Memoria para optar al título de Ingeniero Civil Mecánico / Dentro del área de mantenimiento, el monitorear un equipo puede ser de gran utilidad ya que permite advertir cualquier anomalía en el funcionamiento interno de éste, y así, se puede corregir cualquier desperfecto antes de que se produzca una falla de mayor gravedad. En data mining, detección de anomalías es el ejercicio de identificar elementos anómalos, es decir, aquellos elementos que difieren a lo común dentro de un set de datos. Detección de anomalías tiene aplicación en diferentes dominios, por ejemplo, hoy en día se utiliza en bancos para detectar compras fraudulentas y posibles estafas a través de un patrón de comportamiento del usuario, por ese motivo se necesitan abarcar grandes cantidades de datos por lo que su desarrollo en aprendizajes de máquinas probabilísticas es imprescindible. Cabe destacar que se ha desarrollado una variedad de algoritmos para encontrar anomalías, una de las más famosas es el Isolated Forest dentro de los árboles de decisión. Del algoritmo de Isolated Forest han derivado distintos trabajos que proponen mejoras para éste, como es el Robust Random Cut Forest el cual, por un lado permite mejorar la precisión para buscar anomalías y, también, entrega la ventaja de poder realizar un estudio dinámico de datos y buscar anomalías en tiempo real. Por otro lado, presenta la desventaja de que entre más atributos contengan los sets de datos más tiempo de cómputo tendrá para detectar una anomalía. Por ende, se utilizará un método de reducción de atributos, también conocido como reducción de dimensión, por último se estudiará como afectan tanto en efectividad y eficiencia al algoritmo sin reducir la dimensión de los datos. En esta memoria se analiza el algoritmo Robust Random Cut Forest para finalmente entregar una posible mejora a éste. Para poner en prueba el algoritmo se realiza un experimento de barras de acero, donde se obtienen como resultado sus vibraciones al ser excitado por un ruido blanco. Estos datos se procesan en tres escenarios distintos: Sin reducción de dimensiones, análisis de componentes principales(principal component analysis) y autoencoder. En base a esto, el primer escenario (sin reducción de dimensiones) servirá para establecer un punto de orientación, para ver como varían el escenario dos y tres en la detección de anomalía, en efectividad y eficiencia. %partida para detección de anomalía, luego se ver si esta mejora Luego, se realiza el estudio en el marco de tres escenarios para detectar puntos anómalos; En los resultados se observa una mejora al reducir las dimensiones en cuanto a tiempo de cómputo (eficiencia) y en precisión (efectividad) para encontrar una anomalía, finalmente los mejores resultados son con análisis de componentes principales (principal component analysis).

No description available.

Image to Image translation has been triggered a huge interests among the different topics in deep learning recent years. It provides a mapping function to encode the noisy input images into a high dimensional signal and translate it to the desired output images. The mapping can be one to one, many to one or one to many. Due to the uncertainty from the mapping functions, when extend the methods in video field, the flickering problems emerges. Even a slight change among the frames may bring a obvious change in the output images. In this thesis, we provide a two-stream solution as CFNet for the flickering problems in video colorizations. Compared with the frame-by-frame methods by the previous work, CFNet has a great improvement in allevaiting the flickering problems in video colorizations, especially for the video clips with large objects and still background. Compared with the baseline with frame by frame methods, CFNet improved the PSNR from 27 to 30, which is a great progress.

Wound assessment using a smartphone image has recently emerged as a novel way to provide actionable feedback to patients and caregivers. Wound segmentation is an important step in image-based wound assessment, after which the wound area can be analyzed. Semantic segmentation algorithms for wounds assume favorable lighting conditions. However, smartphone wound imaging in natural environments can encounter adverse lighting that can cause several errors during semantic segmentation of wound images, which in turn affects the wound analysis. In this work, we study and characterize the effects of adverse lighting on the accuracy of semantic segmentation of wound images. Our findings inform a deep learning-based approach to mitigate the adverse effects. We make three main contributions in this work. First, we create the first large-scale Illumination Varying Dataset (IVDS) of 55440 images of a wound moulage captured under systematically varying illumination conditions and with different camera types and settings. Second, we characterize the effects of changing light intensity on U-Net’s wound semantic segmentation accuracy and show the luminance of images to be highly correlated with the wound segmentation performance. Especially, we show low-light conditions to deteriorate segmentation performance highly. Third, we improve the wound Dice scores of U-Net for low-light images to up to four times the baseline values using a deep learning mitigation method based on the Retinex theory. Our method works well in typical illumination levels observed in homes/clinics as well for a wide gamut of lighting like very dark conditions (20 Lux), medium-intensity lighting (750 - 1500 Lux), and even very bright lighting (6000 Lux).

Gliomas are an aggressive class of brain tumors that are associated with a better prognosis at a lower grade level. Effective differentiation and classification are imperative for early treatment. MRI scans are a popular medical imaging modality to detect and diagnosis brain tumors due to its capability to non-invasively highlight the tumor region. With the rise of deep learning, researchers have used convolution neural networks for classification purposes in this domain, specifically pre-trained networks to reduce computational costs. However, with various MRI modalities, MRI machines, and poor image scan quality cause different network structures to have different performance metrics. Each pre-trained network is designed with a different structure that allows robust results given specific problem conditions. This thesis aims to cover the gap in the literature to compare the performance of popular pre-trained networks on a controlled dataset that is different than the network trained domain. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2020. / FAU Electronic Theses and Dissertations Collection

abstract: Students seldom spontaneously collaborate with each other. A system that can measure collaboration in real time could be useful, for example, by helping the teacher locate a group requiring guidance. To address this challenge, the research presented here focuses on building and comparing collaboration detectors for different types of classroom problem solving activities, such as card sorting and handwriting. Transfer learning using different representations was also studied with a goal of building collaboration detectors for one task can be used with a new task. Data for building such detectors were collected in the form of verbal interaction and user action logs from students’ tablets. Three qualitative levels of interactivity were distinguished: Collaboration, Cooperation and Asymmetric Contribution. Machine learning was used to induce a classifier that can assign a code for every episode based on the set of features. The results indicate that machine learned classifiers were reliable and can transfer. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2020

Genome annotation is an important topic since it provides information for the foundation of downstream genomic and biological research. It is considered as a way of summarizing part of existing knowledge about the genomic characteristics of an organism. Annotating different regions of a genome sequence is known as structural annotation, while identifying functions of these regions is considered as a functional annotation. In silico approaches can facilitate both tasks that otherwise would be difficult and timeconsuming. This study contributes to genome annotation by introducing several novel bioinformatics methods, some based on machine learning (ML) approaches. First, we present Dragon PolyA Spotter (DPS), a method for accurate identification of the polyadenylation signals (PAS) within human genomic DNA sequences. For this, we derived a novel feature-set able to characterize properties of the genomic region surrounding the PAS, enabling development of high accuracy optimized ML predictive models. DPS considerably outperformed the state-of-the-art results. The second contribution concerns developing generic models for structural annotation, i.e., the recognition of different genomic signals and regions (GSR) within eukaryotic DNA. We developed DeepGSR, a systematic framework that facilitates generating ML models to predict GSR with high accuracy. To the best of our knowledge, no available generic and automated method exists for such task that could facilitate the studies of newly sequenced organisms. The prediction module of DeepGSR uses deep learning algorithms to derive highly abstract features that depend mainly on proper data representation and hyperparameters calibration. DeepGSR, which was evaluated on recognition of PAS and translation initiation sites (TIS) in different organisms, yields a simpler and more precise representation of the problem under study, compared to some other hand-tailored models, while producing high accuracy prediction results. Finally, we focus on deriving a model capable of facilitating the functional annotation of prokaryotes. As far as we know, there is no fully automated system for detailed comparison of functional annotations generated by different methods. Hence, we developed BEACON, a method and supporting system that compares gene annotation from various methods to produce a more reliable and comprehensive annotation. Overall, our research contributed to different aspects of the genome annotation.