Our findings suggest that the combination of fetal and postnatal renal pelvic dilatation is able to increase the diagnostic accuracy for detecting infants who need a more comprehensive postnatal investigation for upper urinary tract obstruction.

Inverse problems are very frequent in computer vision and machine learning applications. Since noteworthy hints can be obtained from motion data, it is important to seek more robust models. The advantages of using a more general regularization matrix such as Λ=diag{λ1,…,λK} to robustify motion estimation instead of a single parameter λ (Λ=λI) are investigated and formally stated in this paper, for the optical flow problem. Intuitively, this regularization scheme makes sense, but it is not common to encounter high-quality explanations from the engineering point of view. The study is further confirmed by experimental results and compared to the nonregularized Wiener filter approach.

Nesta pesquisa, verificamos em nível local a questão de gênero na área de Tecnologia da Informação (TI) e também em situações específicas de cada grupo no ambiente acadêmico. Assim, usamos uma combinação de métodos exploratórios e quantitativos. Concluímos que, embora muitas mulheres que iniciam um curso técnico tenham afinidades com o curso, poucas desejam ingressar em um curso de graduação na mesma área. Além disso, nos cursos de graduação, há uma grande porcentagem de abandono. Muitos fatores, como estímulos ambientais, timidez, instabilidade emocional e insegurança, geralmente dão a sensação de que tudo é demais para elas, contribuindo para resultar em um número reduzido de mulheres estudando Ciência da Computação.

No abstract

Diabetic retinopathy is an anomaly responsible for causing microvascular and macrovascular damage to the retina and occurs as a consequence of the worsening of diabetes. According to the World Health Organization (WHO), diabetic retinopathy is the most common cause of avoidable blindness in patients with diabetes worldwide. Early detection is important for the efficiency of treatments. Fundus Eye Image can be used to identify early disease development and monitor the patient’s clinical condition. The diagnostic process using this type of image may require some expertise from the ophthalmologist since not all retina anomalies are clearly visible. Thus, this paper proposes the development of a classification method based on Convolutional Neural Networks, but highly dense and deeper. The proposed method obtained a total of 92% AUC in the given experiments.

This paper presents the application of new costs for one recent approach, called SingleGA, in solving One-Dimensional cutting stock problem. The cutting problem basically consists in finding the best way to obtain parts of distinct sizes (items) from the cutting of larger parts (objects) with the purpose of minimizing a specific cost or maximizing the profit. The obtained results of SingleGA are compared to the following methods: SHP, Kombi234, ANLCP300 and Symbio, found in literature, verifying its capacity to find feasible and competitive solutions. The computational results show that variations of SingleGA posses good results, improving as setup cost increases.

Surveillance system (SS) development requires hi-tech support to prevail over the shortcomings related to the massive quantity of visual information from SSs. Anything but reduced human monitoring became impossible by means of its physical and economic implications, and an advance towards an automated surveillance becomes the only way out. When it comes to a computer vision system, automatic video event comprehension is a challenging task due to motion clutter, event understanding under complex scenes, multilevel semantic event inference, contextualization of events and views obtained from multiple cameras, unevenness of motion scales, shape changes, occlusions and object interactions among lots of other impairments. In recent years, state-of-the-art models for video event classification and recognition include modeling events to discern context, detecting incidents with only one camera, low-level feature extraction and description, high-level semantic event classification, and recognition. Even so, it is still very burdensome to recuperate or label a specific video part relying solely on its content. Principal component analysis (PCA) has been widely known and used, but when combined with other techniques such as the expectation-maximization (EM) algorithm its computation becomes more efficient. This chapter introduces advances associated with the concept of Probabilistic PCA (PPCA) analysis of video event and it also aims at looking closely to ways and metrics to evaluate these less intensive EM implementations of PCA and KPCA.Comment: 25 pages, 8 figures, Available from: http://www.intechopen.com/books/principal-component-analysis-engineering-applications/em-based-mixture-models-applied-to-video-event-detection, Chapter from book "Principal Component Analysis - Engineering Applications", Dr. Parinya Sanguansat (Ed.), InTech, 2012. arXiv admin note: text overlap with arXiv:1404.1100 by other author

O câncer de mama é o principal tipo de câncer entre as mulheres. De acordo com o World Cancer Research Fund, em 2018, mais de 2 milhões de novos casos foram detectados em todo o mundo. Apesar de sua alta ocorrência, a detecção precoce proporciona um melhor prognóstico e auxilia no aumento da sobrevida do paciente oncológico. Avanços significativos nas técnicas de rastreamento, como as imagens infravermelhas, forneceram uma maneira barata e menos invasiva forma de detectar a doença. Além disso, ferramentas computacionais podem ser utilizadas para auxiliar os médicos a fornecerem um melhor diagnóstico. Assim, este artigo apresenta um método de segmentação baseado em Redes Neurais Convolucionais U-Net. Em contraste com o estado da arte, as abordagens de aprendizado de máquina têm se mostrado eficientes para a segmentação da região de interesse deste trabalho, atingindo uma acurácia de 98,24% e uma Intersecção-Sobre-União de 94,38%. O uso deste método de segmentação pode ser muito útil para tarefas de classificação, uma vez que a região de interesse é bem delimitada para extração de características.