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.

abstract: Robot motion planning requires computing a sequence of waypoints from an initial configuration of the robot to the goal configuration. Solving a motion planning problem optimally is proven to be NP-Complete. Sampling-based motion planners efficiently compute an approximation of the optimal solution. They sample the configuration space uniformly and hence fail to sample regions of the environment that have narrow passages or pinch points. These critical regions are analogous to landmarks from planning literature as the robot is required to pass through them to reach the goal. This work proposes a deep learning approach that identifies critical regions in the environment and learns a sampling distribution to effectively sample them in high dimensional configuration spaces. A classification-based approach is used to learn the distributions. The robot degrees of freedom (DOF) limits are binned and a distribution is generated from sampling motion plan solutions. Conditional information like goal configuration and robot location encoded in the network inputs showcase the network learning to bias the identified critical regions towards the goal configuration. Empirical evaluations are performed against the state of the art sampling-based motion planners on a variety of tasks requiring the robot to pass through critical regions. An empirical analysis of robotic systems with three to eight degrees of freedom indicates that this approach effectively improves planning performance. / Dissertation/Thesis / Masters Thesis Computer Science 2020

abstract: In recent years, the widespread use of deep neural networks (DNNs) has facilitated great improvements in performance for computer vision tasks like image classification and object recognition. In most realistic computer vision applications, an input image undergoes some form of image distortion such as blur and additive noise during image acquisition or transmission. Deep networks trained on pristine images perform poorly when tested on such distortions. DNN predictions have also been shown to be vulnerable to carefully crafted adversarial perturbations. Specifically, so-called universal adversarial perturbations are image-agnostic perturbations that can be added to any image and can fool a target network into making erroneous predictions. This work proposes selective DNN feature regeneration to improve the robustness of existing DNNs to image distortions and universal adversarial perturbations. In the context of common naturally occurring image distortions, a metric is proposed to identify the most susceptible DNN convolutional filters and rank them in order of the highest gain in classification accuracy upon correction. The proposed approach called DeepCorrect applies small stacks of convolutional layers with residual connections at the output of these ranked filters and trains them to correct the most distortion-affected filter activations, whilst leaving the rest of the pre-trained filter outputs in the network unchanged. Performance results show that applying DeepCorrect models for common vision tasks significantly improves the robustness of DNNs against distorted images and outperforms other alternative approaches. In the context of universal adversarial perturbations, departing from existing defense strategies that work mostly in the image domain, a novel and effective defense which only operates in the DNN feature domain is presented. This approach identifies pre-trained convolutional features that are most vulnerable to adversarial perturbations and deploys trainable feature regeneration units which transform these DNN filter activations into resilient features that are robust to universal perturbations. Regenerating only the top 50% adversarially susceptible activations in at most 6 DNN layers and leaving all remaining DNN activations unchanged can outperform existing defense strategies across different network architectures and across various universal attacks. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2020

abstract: The advances of Deep Learning (DL) achieved recently have successfully demonstrated its great potential of surpassing or close to human-level performance across multiple domains. Consequently, there exists a rising demand to deploy state-of-the-art DL algorithms, e.g., Deep Neural Networks (DNN), in real-world applications to release labors from repetitive work. On the one hand, the impressive performance achieved by the DNN normally accompanies with the drawbacks of intensive memory and power usage due to enormous model size and high computation workload, which significantly hampers their deployment on the resource-limited cyber-physical systems or edge devices. Thus, the urgent demand for enhancing the inference efficiency of DNN has also great research interests across various communities. On the other hand, scientists and engineers still have insufficient knowledge about the principles of DNN which makes it mostly be treated as a black-box. Under such circumstance, DNN is like "the sword of Damocles" where its security or fault-tolerance capability is an essential concern which cannot be circumvented. Motivated by the aforementioned concerns, this dissertation comprehensively investigates the emerging efficiency and security issues of DNNs, from both software and hardware design perspectives. From the efficiency perspective, as the foundation technique for efficient inference of target DNN, the model compression via quantization is elaborated. In order to maximize the inference performance boost, the deployment of quantized DNN on the revolutionary Computing-in-Memory based neural accelerator is presented in a cross-layer (device/circuit/system) fashion. From the security perspective, the well known adversarial attack is investigated spanning from its original input attack form (aka. Adversarial example generation) to its parameter attack variant. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2020