Background: Biometric identification plays a crucial role in various industries such as retail, and banking. Among the different biometric traits, iris patterns have become a reliable means of identification due to their unique features. In our thesis, we focus on evaluating and comparing different machine learning algorithms for irisrecognition. The main aim is to identify the algorithm that achieves the highestperformance for iris recognition. Objectives: The main objective of the thesis is to train, test, and evaluate the best performing model using the iris image dataset among the selected algorithmsthrough a literature review. Additionally, the goal is to compare different algorithms for a biometric recognition system that relies on iris features. Methods: Our research is supported by an extensive literature review that usesa wide range of scholarly articles specifically focused on iris recognition. Experimentation is also used to determine the most accurate machine-learning algorithm interms of accuracy. Results: Our experimentation results revealed that the accuracy rates for all themodels were as follows: CNN obtained the highest accuracy at 98.7%, while SVM and the SVM combination with hamming distance achieved 86% and 80%, respectively. Based on our research findings, we conclude that including hamming distancewith SVM did not result in improved accuracy compared to other classification algorithms. Finally, CNN achieved high accuracy in comparison to different algorithmsfor iris recognition. Conclusions: To achieve our research goals, we divided the dataset into three parts: 60% for training, 20% for testing, and another 20% for validation. Different techniques were used to train the algorithm with the training dataset. The results aretested for every algorithm to determine its accuracy. Among the selected algorithms, the convolutional neural network delivered an accurate performance with an accuracy of 98.7%. By employing performance metrics, we have effectively addressed theresearch questions and identified the most accurate algorithm for the iris recognitionsystem.

Background: The train communication network is vulnerable to intrusion assaultsbecause of the openness of the ethernet communication protocol. Therefore, an intru-sion detection system must be incorporated into the train communication network.There are many algorithms available in Machine Learning(ML) to develop the Intru-sion Detection System(IDS). Majorly, depending on the accuracy and execution timeof the algorithm, it is decided as the best. Performance metrics like F1 score, preci-sion, recall, and support are compared to see how well the algorithm fits the modelwhile training. The following thesis will detect the anomalies in the Train ControlManagement System(TCMS) and then the comparison of various algorithms will beheld in order to declare the accurate algorithm. Objectives: In this thesis work, we aim to research anomaly detection in a train’sreal-time ethernet using an IDS. The main objectives of this thesis include per-forming Principal Component Analysis(PCA) and feature selection using RandomForest(RF) for simplifying the complexity of the dataset by reducing dimensionalityand extracting significant features. Followed by, choosing the most consistent algo-rithm for anomaly detection from the selected algorithms by evaluating performanceparameters, especially accuracy and execution time after training the models usingML algorithms. Method: This thesis necessitates one research methodology which is experimen-tation, to answer our research questions. For RQ1, experimentation will help usgain better insights into the dataset to extract valuable and essential features as apart of feature selection using RF and dimensionality reduction using PCA. RQ2also uses experimentation because it provides better accuracy and reliability. Afterpre-processing, the data will be used to train the algorithms and will be evaluatedusing various methods. Results: In this study, we have analysed data using EDA, reduced dimensionalityand feature selection using PCA and RF algorithm respectively. We used five su-pervised machine learning methods namely, Support Vector Machine(SVM), NaiveBayes, Decision Tree, K-nearest Neighbor(KNN), and Random Forest(RF). Aftertesting and utilizing the "KDDCup 1999" pre-processed dataset from the Universityof California Irvine(UCI) ML repository, Decision Tree model has been concludedas the best-performing algorithm with an accuracy of 98.89% in 0.098 seconds, incomparison to other models. Conclusions: Five models have been trained using the five ML techniques foranomaly detection using an IDS. We concluded that the decision tree trained modelhas optimal performance with an accuracy of 98.89% and time of 0.098 seconds

Creating 360-degree 3D content has gained traction in the past few years, being used for Virtual Reality environments. However, creating such content is challenging because it requires a multi-camera setup or a collection of images from different perspectives. This paper proposes 3D Pano Inpainting, a pipeline capable of transforming a single equirectangular panoramic RGBD image into a complete 360° 3D virtual reality scene represented as a textured mesh. Our methodology is as follows: we estimate a consistent depth map for the input panorama; we use a pre built framework to convert the image and its depth map into a textured mesh with inpainted background edges; we account for wrapping the resulting mesh around the viewer’s perspective for better immersion in VR headsets. Additionally, we evaluate our method’s effectiveness in producing consistent novel views through the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and learned perceptual image patch similarity (LPIPS) between a rendering produced from the ground truth image and depth map to that produced from our model. Furthermore, we compare our model’s scores with those of a non-inpainted textured mesh.

Zero-shot video generation involves generating videos of concepts (action classes) that are not seen in the training phase. Even though the research community has explored conditional video generation for long high-resolution videos, zero-shot video remains a fairly unexplored and challenging task. Most recent works can generate videos for action-object or motion-content pairs, where both the object (content) and action (motion) are observed separately during training, yet results often lack spatial consistency between foreground and background and cannot generalize to complex scenes with multiple objects or actions. In this work, we propose Concept2Vid that generates zero-shot videos for classes that are completely unseen during training. In contrast to prior work, our model is not limited to a predefined fixed set of class-level attributes, but rather utilizes semantic information from multiple videos of the same topic to generate samples from novel classes. We evaluate qualitatively and quantitatively on the Kinetics400 and UCF101 datasets, demonstrating the effectiveness of our proposed model. / Master of Science / Humans are able to generalize unseen scenarios without explicit feedback. They can be thought of as self-learning Artificial Intelligence agents that can collect data from various modalities (video, audio, text) found in surrounding environments, to develop new knowledge and acclimate to unseen situations without explicit feedback. Many recent studies have learned how to perform this process for images, but very few have been able to extend it to videos. Videos provide rich multi-modal data, such as text, audio, and images, and hence are composed of multifaceted knowledge that can introduce more complex temporal and spatial constraints. Leveraging videos in combination with text and audio data can assist intelligent systems to learn similar to how humans do. Zero-shot video generation (ZSVG) involves generating videos of concepts that are not seen in the training phase of a machine learning model. Generating a zero-shot video requires a multitude of temporal and spatial dependencies. In generating a video, not only does the model need temporal coherence but also the understanding of object properties. Current approaches for ZSVG are not well suited due to these challenges. We propose Concept2Vid which generates zero-shot videos for classes that are completely unseen during training. In contrast to prior work, our model is not limited to a predefined fixed set of class descriptions, but rather utilizes semantic information from multiple videos of the same topic to generate samples from novel classes. We evaluate qualitatively and quantitatively on the Kinetics400 and UCF101 datasets, demonstrating the effectiveness of our proposed model.

Thesis (Ph. D.) -- University of Texas Southwestern Medical Center at Dallas, 2000. / Vita. Bibliography: 174-182.

Background. Since historical handwritten documents have played important roles in promoting the development of human civilization, many of them have been preserved through digital versions for more scientific researches. However, various degradations always exist in these documents, which could interfere in normal reading. But, binarized versions can keep meaningful contents without degradations from original document images. Document image binarization always works as a pre-processing step before complex document analysis and recognition. It aims to extract texts from a document image. A desirable binarization performance can promote subsequent processing steps positively. For getting better performance for document image binarization, efficient binarization methods are needed. In recent years, machine learning centered on deep learning has gathered substantial attention in document image binarization, for example, Convolutional Neural Networks (CNNs) are widely applied in document image binarization because of the powerful ability of feature extraction and classification. Meanwhile, Support Vector Machine (SVM) is also used in image binarization. Its objective is to build an optimal hyperplane that could maximize the margin between negative samples and positive samples, which can separate the foreground pixels and the background pixels of the image distinctly. Objectives. This thesis aims to explore how the CNN based process of deep convolutional feature extraction and an SVM classifier can be integrated well to binarize handwritten document images, and how the results are, compared with some state-of-the-art document binarization methods. Methods. To investigate the effect of the proposed method on document image binarization, it is implemented and trained. In the architecture, CNN is used to extract features from input images, afterwards these features are fed into SVM for classification. The model is trained and tested with six different datasets. Then, there is a performance comparison between the proposed model and other binarization methods, including some state-of-the-art methods on other three different datasets. Results. The performance results indicate that the proposed model not only can work well but also perform better than some other novel handwritten document binarization method. Especially, evaluation of the results on DIBCO 2013 dataset indicates that our method fully outperforms other chosen binarization methods on all the four evaluation metrics. Besides, it also has the ability to deal with some degradations, which demonstrates its generalization and learning ability are excellent. When a new kind of degradation appears, the proposed method can address it properly even though it never appears in the training datasets. Conclusions. This thesis concludes that the CNN based component and SVM can be combined together for handwritten document binarization. Additionally, in certain datasets, it outperforms some other state-of-the-art binarization methods. Meanwhile, its generalization and learning ability is outstanding when dealing with some degradations.

The thesis aims to develop a deep learning model for facial emotion recognition using Convolutional Neural Network algorithm and Multiclass Classification along with Hyper-parameter tuning using Bayesian Optimization to improve the performance of the model. The developed model recognizes seven basic emotions in images of human beings such as fear, happy, surprise, sad, neutral, disgust and angry using FER-2013 dataset.

No description available.

Introdução: EpiDoc® é um modelo para transferência de conhecimento na área de metodologia da pesquisa. Está baseado no conceito de estratégias de colaboração para a aprendizagem (learning communities ou communities of practice) mediante a união de esforços entre os interesses comuns de um grupo de profissionais. O objetivo deste projeto é desenvolver uma plataforma de comunicação para a transferência de conhecimento e desenvolvimento de competências em uma comunidade de prática de metodologia da pesquisa em saúde. Métodos:. A plataforma de comunicação está desenvolvido com a tecnologia de páginas de servidor ASP (Active Server Pages), interagindo com uma base de dados Microsoft SQL Server 2000. Na fase da avaliação, tomou-se uma amostra de 38 pessoas para responder a pesquisa de opinião de 84 perguntas que inclui as diferentes áreas a avaliar como são os conteúdos, a tecnologia, o ambiente educativo, os problemas e dificuldades, assim como os elementos positivos do processo de aprendizagem. Resultados: A plataforma divide-se basicamente em 2 zonas, uma pública e outra privada, e pode ser observado em inglês, espanhol e português. A plataforma conta com os seguintes módulos: Controle de acesso; biblioteca; administração de cursos; apresentações; assinatura de usuários para distribuição eletrônica de materiais educativos; correio eletrônico e correio massivo; salas virtuais de Chat; foros de discussão; manipulação de documentos entre tutores e usuários; aplicação de provas de avaliação para os usuários; geração automática de certificados; métricas e relatórios de atividades. A avaliação foi feita com uma amostra de 38 estudantes de um curso de Epidemiologia Clínica. O 94 % dos estudantes ficaram satisfeitos ou muito satisfeitos com a experiência de aprendizagem. O 95% considerou que tinha adquirido novas habilidades de comunicação e colaboração ao estudar por meio virtual. Para o 76% facilitou-se o trabalho em equipe, assim como para o 84% melhorou a capacidade para aprender dos demais, interagindo entre outros. Conclusão: EpiDoc® utiliza uma plataforma ou mecanismo de comunicação baseado em tecnologias modernas por meio de Internet. Os resultados em geral confirmam que as novas tecnologias aplicadas ao processo de ensino da metodologia da pesquisa são bem recebidas por parte dos estudantes. Há uma atitude positiva em relação ao fato de incorporar esta modalidade em seus cursos regulares. / Introduction: Epidoc® is a model for the transference of knowledge in the field or research methodology. It is based on the concept of collaboration strategies for learning (learning communities or communities of practice) by the joint effort among common interests of a professional group. The objective of this project is to develop a communication platform for the knowledge transference and developing of competences in a community which practices the Research Methodology in the health field. Methods: The communication platform was designed with a technology of ASP (Active Server Pages) interacting with a Microsoft SQL Server 2000 data base. For the evaluation phase a sample of 38 people was taken to answer an opinion questionnaire of 84 questions which include the different areas to evaluate such as the contents, the technology, the learning environment, the problems and the difficulties and also all the positive elements of the learning process. Results: The communication platform is divided in two zones, one public and one private and is available in three different languajes: English, Spanish and Portuguese. The platform contains the following modules: access control; library; courses administration; presentations; subscriptions for electronic distribution of educational materials; electronic and massive mail; Chat virtual rooms; discussion forums; documents management between users and mentors; implementation of evaluation test for the users; generation of certificates; metrics and activities reports. The evaluation was implemented with a sample of 38 students from a Clinical Epidemiology course. 94% of the students were satisfied or very satisfied by the learning experience. 95% considered that they had acquired new communication and collaboration abilities at studying by the virtual way. For 76% the group work was eased as for 84% noticed an improve capacity to learn form the others, interacting among others. Conclusion: EpiDoc uses a platform of communication based in modern technologies by theinternet. In general, the results confirm that the new technologies applied to the teaching process of research methodology are very welcomed by the students. They have a positive attitude toward the fact of incorporating this modality in their regular courses.

Localization of Drosophila embryos in images is a fundamental step in an automatic computational system for the exploration of gene-gene interaction on Drosophila. Contour extraction of embryonic images is challenging due to many variations in embryonic images. In the thesis work, we develop a localization framework based on the analysis of connected components of edge pixels in a scale space. We propose criteria to select optimal scales for embryonic localization. Furthermore, we propose a scale mapping strategy to compress the range of a scale space in order to improve the efficiency of the localization framework. The effectiveness of the proposed framework and the scale mapping strategy are validated in our experiments.