Desenvolvimento de um sistema acústico de posicionamento capaz de estimar, em tempo real, a posição tridimensional de objetos dentro do tanque de ensaios do DEEC.A obtenção desta posição "ground truth" é fundamental para o apoio a ensaios de sistemas de navegação subaquáticos e para o controlo de veículos robóticos tais como AUV's e ROV's. / Development of an acoustic positioning system, capable of estimating, in real time, the three-dimensional position of an object inside the DEEC's test tank. The ability to obtain this ground truth position is fundamental to support tests of underwater navigation systems, and to the control of robotic vehicles such as AUV's and ROV's.

Este trabalho propõe um método de solução iterativa para abordar a integração do planeamento táctico (dimensionamento de lotes) e operacional (sequenciamento) numa produção industrial com setups dependentes da sequencia. Este método quebra o problema da integração em dois. No primeiro sub-problema do planeamento táctico, o plano de produção é optimizado sem ter em conta setups necessários. O sequenciamento dos produtos é depois definido usando estratégias de pesquisa local que irão conceber regras para complementarem o primeiro sub-problema. De seguida, o planeamento táctico é repetido, considerando as novas regras definidas anteriormente. O algoritmo continua iterativamente até que as funções objectivo dos dois níveis convirjam. De modo a analisar resultados obtidos, dois experimentos computacionais são propostos. O primeiro para comparar o método iterativo com outros métodos de solução encontrados na literatura para problemas similares, nomeadamente meta-heuristicas e modelos MIP. Por fim, a investigação foi focada num caso de uma indústria de nutrição animal, onde o setup de produção é dependente da sequência e normalmente não-triangular, podendo produtos evitarem limpeza se produzidos entre outros dois que de outro modo necessitariam de setup. O propósito do segundo experimento é avaliar os eventuais ganhos a uma abordagem hierárquica usualmente usada nesta indústria. / This work proposes an iterative solution method to address the integration of the tactical (lot-sizing) and operational (scheduling) levels in production planning with sequence dependent setups. This method breaks the integrated lot-sizing and scheduling problem into two. In the first sub-problem, at the tactical level, the production plan is optimized with production setups disregarded. The production scheduling solution is then defined using local search strategies that will also construct rules for the tactical level. After that, the tactical level is optimized again, considering the rules defined from the operational level. The algorithm continues iteratively until objective functions from both levels converge. In order to analyse results, two computational experiments are proposed. The first is performed to compare the solution method proposed with mixed-integer programming models and meta-heuristics from the literature. Then the research will focus on an animal-feed industry case, in which production setup is sequence dependent and usually presents non-triangular setups, so products can avoid cleaning setups if produced between two products that otherwise would require a setup. The purpose of the second experiment is to evaluate the potential gains to a hierarchical approach usually used in this industry.

No description available.

All data acquired from oceanic water features is hard and crucial work. It's hard due to the difficulty to obtain the same data given the unfavourable conditions.It requires, therefore, equipment that are reliable in the measurements of the desired characteristics and robust equipment, that is to say, equipment that are capable to withstand unfavorable and variable conditions in spatial and temporal terms. Due to these same spatial and temporal changes, the traditional methods do not prove to be the most adequate, because these methods do not have sufficient capacity to sample measurements of the dynamic characteristics of oceanographic processes.Thus, to obtain such measurements the use of the autonomous robotic systems proves to be important. With these systems, it is ensured a faster, more efficient and systematic sampling and is not subject to human error. The data acquisition is then a crucial work to understand how oceanographic process happens and varies in time and space. This work proposes an implementation of an algorithm to perform the tracking of the thermocline, from the stratification model of the oceanic water.This model is a parametric model. This work will also take into account the capacity to perform measurements with a sampling capable of adapting the depth control of the underwater vehicle.The stratification of the oceanic water happens when exists different features between different layers. One of these layers is the thermocline. At this layer, the water temperature decreases rapidly with increasing depth. The characterization of the thermocline is so important to marine biology, given the high concentration of phytoplankton in this level, as for acoustic communications equipments or military services, given the special characteristics of speed sound in this level.The model of this stratification will be used to aid in the thermocline's tracking process. This model will serve as a basis for the algorithm to adapt the control in order to carry out the tracking with the greatest success, in real time. This algorithm will focus on the variations in the vertical temperature gradient.The algorithm responsible detect and track of the thermocline will be run on a profiler. The profiler is a vehicle that moves along the vertical axis. However, when subject to tides, the natural process in aquatic environments drifts along the horizontal axis. A set of sensors capable of measuring the water temperature and the depth at which the vehicle is below water shall be placed in this vehicle. These sensors will be important to calculate the vertical gradient.

No description available.

No description available.

No description available.

No description available.

Lung cancer is the leading cause of cancer death worldwide. One of the reasons is the absence of symptoms at an early stage, which means that it is only discovered at a later stage, where the treatment is more difficult [1]. Furthermore, when making a diagnosis, frequently done by reading computed tomographies (CT's), it is regularly allied with errors. One of the reasons is the variation of the opinion of the doctors regarding the diagnosis of the same nodule [2,3].The use of CADx, Computer-Aided Diagnosis, systems can be a great help for this problem by assisting doctors in diagnosis with a second opinion. Although its efficiency has already been proven [4], it often ends up not being used because doctors can not understand the "how and why" of CADx diagnostic results, and ultimately do not trust the system [5]. To increase the radiologists' confidence in the CADx system it is proposed that along with the results of malignancy prediction, there are also results with evidence that explains those malignancy results.There are some visible features in lung nodules that are correlated with malignancy. Since humans are able to visually identify these characteristics and correlate them with nodule malignancy, one way to present those evidence is to make predictions of those characteristics. To have these predictions it is proposed to use deep learning approaches. Convolutional neural networks had shown to outperform the state of the art results in medical image analysis [6]. To predict the characteristics and malignancy in CADx system, the architecture HSCNN, a deep hierarchical semantic convolutional neural network, proposed by Shen et al. [7], will be used.The Lung Image Database Consortium image collection (LIDC-IDRI) public dataset is frequently used as input for lung cancer CADx systems. The LIDC-IDRI consists of thoracic CT scans, presenting a lot of data's quantity and variability. In most of the nodules, this dataset has doctor's evaluations for 9 different characteristics. A recurrent problem in those evaluations is the subjectivity of the doctors' interpretation in what each characteristic is. In some characteristics, it can result in a great divergence in evaluations regarding the same nodule, which makes the inclusion of those evaluations as an input in CADx systems not useful as it could be. To reduce this subjectivity, it is proposed the creation of a metric that makes the characteristics classification more objective. For this, it is planned bibliographic and LIDC-IDRI dataset reviews. With that, taking into account this new metric, validated after by doctors from Hospital de São João, will be made a reclassification in LIDC-IDRI dataset. This way it could be possible to use as input all the relevant characteristics. The principal objective of this dissertation is to develop a lung nodule CADx system methodology which promotes the confidence of specialists in its use. This will be made classifying lung nodules according to relevant characteristics to diagnosis and malignancy. The reclassified LIDC-IDRI dataset will be used as an input for CADx system and the architecture used for predicting the characteristics and malignancy results will be the HSCNN. To measure the classification evaluation will be used sensitivity, sensibility, and area under the Receiver Operating Characteristic (ROC), curve. The proposed solution may be used for improving a CADx system, LNDetector, currently in development by the Center for Biomedical Engineering Research (C-BER) group from INESC-TEC in which this work will be developed.[1] - S. Sone M. Hasegawa and S. Takashima. Growth rate of small lung cancels detected on mass ct screening. Tire British Journal of Radiology, pages 1252-1259[2] - D. J. Bell S. E. Marley P. Guo H. Mann M. L. Scott L. H. Schwartz D. C. Ghiorghiu B. Zhao, Y. Tan. Exploring intra-and inter-reader variability in uni-dimensional, bi-dimensional, and volumetric measurements of solid tumors on ct scans reconstructed at different slice intervals. European journal of radiology 82, page 959-968, 2013[3] - H.T Winer-Muram. The solitary pulmonary nodule 1. Radiology, 239, pages 39-49, 2006.[4] - R. Yan J. Lee L. C. Chu C. T. Lin A. Hussien J. Rathmell B. Thomas C. Chen et al. P. Huang, S. Park. Added value of computer-aided ct image features for early lung cancer diagnosis with small pulmonary nodules: A matched case-control study. Radiology 286, page 286-295, 2017[5] - W Jorritsma, Fokie Cnossen, and Peter Van Ooijen. Improving the radiologist-cad interaction: Designing for appropriate trust. Clinical Radiology, 70, 10 2014.[6] - Tom Brosch, Youngjin Yoo, David Li, Anthony Traboulsee, and Roger Tam. Modeling the variability in brain morphology and lesion distribution in multiple sclerosis by deep learning. Volume 17, 09 2014.[7] - Simon Aberle Deni A. T. Bui Alex Hsu Willliam Shen, Shiwen X. Han. An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification. june 2018

No description available.