Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network

Automated tissue characterization is one of the most crucial components of a computer aided diagnosis (CAD) system for interstitial lung diseases (ILDs). Although much research has been conducted in this field, the problem remains challenging. Deep learning techniques have recently achieved impressive results in a variety of computer vision problems, raising expectations that they might be applied in other domains, such as medical image analysis. In this paper, we propose and evaluate a convolutional neural network (CNN), designed for the classification of ILD patterns. The proposed network consists of 5 convolutional layers with 2×2 kernels and LeakyReLU activations, followed by average pooling with size equal to the size of the final feature maps and three dense layers. The last dense layer has 7 outputs, equivalent to the classes considered: healthy, ground glass opacity (GGO), micronodules, consolidation, reticulation, honeycombing and a combination of GGO/reticulation. To train and evaluate the CNN, we used a dataset of 14696 image patches, derived by 120 CT scans from different scanners and hospitals. To the best of our knowledge, this is the first deep CNN designed for the specific problem. A comparative analysis proved the effectiveness of the proposed CNN against previous methods in a challenging dataset. The classification performance (~85.5%) demonstrated the potential of CNNs in analyzing lung patterns. Future work includes, extending the CNN to three-dimensional data provided by CT volume scans and integrating the proposed method into a CAD system that aims to provide differential diagnosis for ILDs as a supportive tool for radiologists.

Artificial Neural Nets with Interaction of Afferents

The aim is to obtain computationally more powerful, neuro physiologically founded, artificial neurons and neural nets. Artificial Neural Nets (ANN) of the Perceptron type evolved from the original proposal by McCulloch an Pitts classical paper [1]. Essentially, they keep the computing structure of a linear machine followed by a non linear operation. The McCulloch-Pitts formal neuron (which was never considered by the author’s to be models of real neurons) consists of the simplest case of a linear computation of the inputs followed by a threshold. Networks of one layer cannot compute anylogical function of the inputs, but only those which are linearly separable. Thus, the simple exclusive OR (contrast detector) function of two inputs requires two layers of formal neurons

Dendritic-Like Reliable Computation in Artificial Neurons

Dendritic computation is a term that has been in neuro physiological research for a long time [1]. It is still controversial and far for been clarified within the concepts of both computation and neurophysiology [2], [3]. In any case, it hasnot been integrated neither in a formal computational scheme or structure, nor into formulations of artificial neural nets. Our objective here is to formulate a type of distributed computation that resembles dendritic trees, in such a way that it shows the advantages of neural network distributed computation, mostly the reliability that is shown under the existence of holes (scotomas) in the computing net, without ?blind spots?.

Self-learning of fault diagnosis identification

A good and early fault detection and isolation system along with efficient alarm management and fine sensor validation systems are very important in today¿s complex process plants, specially in terms of safety enhancement and costs reduction. This paper presents a methodology for fault characterization. This is a self-learning approach developed in two phases. An initial, learning phase, where the simulation of process units, without and with different faults, will let the system (in an automated way) to detect the key variables that characterize the faults. This will be used in a second (on line) phase, where these key variables will be monitored in order to diagnose possible faults. Using this scheme the faults will be diagnosed and isolated in an early stage where the fault still has not turned into a failure.

Contribución a las nuevas tendencias en el diseño de tuberías en construcción naval

En la situación actual, tanto las posibilidades de contratar como los resultados económicos de un astillero, dependen de su capacidad para construir un buque en el plazo mas corto posible. Dentro de los trabajos de diseño y construcción de de un buque el trabajo de tuberías ha sido el que tradicionalmente ha condicionado los plazos de construcción. En este estudio se considerara que se han tenido en cuenta los criterios necesarios para que las instalaciones del buque funcionen correctamente y se verá como los sistemas de diseño influyen en el coste y plazo del buque y, por tanto, en la productividad del astillero. Se estudian los distintos procesos de diseño, fabricación y montaje de tuberías, la evolución de estos procesos a lo largo del tiempo, los módulos de armamento que se realizan en los astilleros, los modelos de cámara de máquinas, y los sistemas de ayuda al diseño por ordenador. El autor, en su puesto de Jefe de la Oficina Tecnológica de la Factoría de Sevilla de Astilleros Españoles en los últimos 12 años, ha tomado parte activa en esta evolución, formando parte de un equipo que ha situado a este astillero entre los mas avanzarlos de Europa. Todo lo anterior sirve de base para la segunda parte de este estudio, donde se abordan las que, en opinión del autor, son las nuevas tendencias en el diseño de tuberías en la construcción naval. V Integración del CAD/CAM o CIM : CAD = computer aided design o diseño asistido por ordenador, CAM = computer aided manufacturing o fabricación asistida por ordenador, CIM = computer integrated manufacturing o fabricación integrada por ordenador. Se estudia la integración de los procesos de diseño con el resto de los procesos de gestión y de producción de un astillero, proponiéndose un modelo de cómo el autor ve esta integración. Se comenta la actual tendencia a pasar de las automatizaciones duras con maquinas especializadas para cada proceso, a las automatizaciones blandas en las que un robot puede realizar distintos procesos modificando su programación. Se estudian las nuevas posibilidades de la normal i zacio'n, de los planos parametrizados y de la tecnología de grupos aportando algunos ejemplos. Se estudia también como los procesos anteriores conducirán a una optimización del producto en sí, es decir a conseguir mejores buques. En las conclusiones destacamos como el camino que tienen los países desarrollados, como el nuestro, para mantener una industria competitiva de construcción naval va por la mecanización de los procesos constructivos siguiendo las tendencias anteriores y obteniendo buques optimizados. vi SUMMARY Under the present situation the possibilities to contract and the economical results of a Shipyard depend on its capacity to build a ship within the shortest time. i Within the works of design and construction of a ship, piping work has traditionally conditioned the construction time. In this study it shall be considered that the necessary criteria for the ship installations to operate correctly have been taken into account and it shall be noticed how the design systems influence on the cost and time of a ship and therefore on the Shipyard's productivity. Studies are made of different design processes, manufacturing and installation of piping, evolution of these processes along the time, outfitting modules made in the Shipyard, engine room models and computerized design aid systems. The author, in his post of Chief of the Technological Office of Sevilla Shipyard of Astilleros Españoles for the last 12 years, has taken an active part in this evolution, making part of a team which has placed this Shipyard among the most advanced in Europe. All of the above is used for the second part of this study, whereby an approach is made to those who, in the author's opinion, are the new trends in the piping design of shipbuilding. vii Integration of CAD/CAM or CIM: CAD = computer aided design, CAM = computer aided manufacturing, CIM = computer integrated manufacturing. i A study is made of the integration of design processes with the remaining step and production Shipyard processes, proposing a model of how the author views this integration. Comments are made on the present trend to go from hard automations with specialized machines for each process to soft automations, in which a robot can carry out different processes modifying its programmes. Studies are made of: New possibility of standardization, parametrized drawings and group technology, bringing some examples. It is also studied how the above processes shall lead to optimize the product itself, that is, to obtain better ships. In the conclusions we stand out how the way of developed countries (as ours) to maintain a competitive shipbuilding industry is by computerizing constructive processes, following the above trends and obtaining better ships.

Programmed design of ship forms

This paper describes a new category of CAD applications devoted to the definition and parameterization of hull forms, called programmed design. Programmed design relies on two prerequisites. The first one is a product model with a variety of types large enough to face the modeling of any type of ship. The second one is a design language dedicated to create the product model. The main purpose of the language is to publish the modeling algorithms of the application in the designer knowledge domain to let the designer create parametric model scripts. The programmed design is an evolution of the parametric design but it is not just parametric design. It is a tool to create parametric design tools. It provides a methodology to extract the design knowledge by abstracting a design experience in order to store and reuse it. Programmed design is related with the organizational and architectural aspects of the CAD applications but not with the development of modeling algorithms. It is built on top and relies on existing algorithms provided by a comprehensive product model. Programmed design can be useful to develop new applications, to support the evolution of existing applications or even to integrate different types of application in a single one. A three-level software architecture is proposed to make the implementation of the programmed design easier. These levels are the conceptual level based on the design language, the mathematical level based on the geometric formulation of the product model and the visual level based on the polyhedral representation of the model as required by the graphic card. Finally, some scenarios of the use of programmed design are discussed. For instance, the development of specialized parametric hull form generators for a ship type or a family of ships or the creation of palettes of hull form components to be used as parametric design patterns. Also two new processes of reverse engineering which can considerably improve the application have been detected: the creation of the mathematical level from the visual level and the creation of the conceptual level from the mathematical level. © 2012 Elsevier Ltd. All rights reserved. 1. Introduction

Integration of design tools and knowledge capture into a CAD system: a case study

onceptual design phase is partially supported by product lifecycle management/computer-aided design (PLM/CAD) systems causing discontinuity of the design information flow: customer needs — functional requirements — key characteristics — design parameters (DPs) — geometric DPs. Aiming to address this issue, it is proposed a knowledge-based approach is proposed to integrate quality function deployment, failure mode and effects analysis, and axiomatic design into a commercial PLM/CAD system. A case study, main subject of this article, was carried out to validate the proposed process, to evaluate, by a pilot development, how the commercial PLM/CAD modules and application programming interface could support the information flow, and based on the pilot scheme results to propose a full development framework.

Seed image analysis and taxonomy of Diplotaxis DC. (Brassicaceae, Brassiceae)

The genus Diplotaxis, comprising 32 or 34 species, plus several additional infraspecific taxa, displays a considerable degree of heterogeneity in the morphology, molecular markers, chromosome numbers and geographical amplitude of the species. The taxonomic relationships within the genus Diplotaxis were investigated by phenetic characterisation of germplasm belonging to 27 taxa of the genus, because there is an increasing interest in Diplotaxis, since some of its species (D. tenuifolia, D. muralis) are gathered or cultivated for human consumption, whereas others are frequent arable weeds (D. erucoides) in many European vineyards. Using a computer-aided vision system, 33 morpho-colorimetric features of seeds were electronically measured. The data were used to implement a statistical classifier, which is able to discriminate the taxa within the genus Diplotaxis, in order to compare the resulting species grouping with the current infrageneric systematics of this genus. Despite the high heterogeneity of the samples, due to the great intra-population variability, the stepwise Linear Discriminant Analysis method, applied to distinguish the groups, was able to reach over 80% correct identification. The results obtained allowed us to confirm the current taxonomic position of most taxa and suggested the taxonomic position of others for reconsideration.

TCAD for PV: a fast method for accurately modelling metal impurity evolution during solar cell processing

Coupled device and process silumation tools, collectively known as technology computer-aided design (TCAD), have been used in the integrated circuit industry for over 30 years. These tools allow researchers to quickly converge on optimized devide designs and manufacturing processes with minimal experimental expenditures. The PV industry has been slower to adopt these tools, but is quickly developing competency in using them. This paper introduces a predictive defect engineering paradigm and simulation tool, while demonstrating its effectiveness at increasing the performance and throughput of current industrial processes. the impurity-to-efficiency (I2E) simulator is a coupled process and device simulation tool that links wafer material purity, processing parameters and cell desigh to device performance. The tool has been validated with experimental data and used successfully with partners in industry. The simulator has also been deployed in a free web-accessible applet, which is available for use by the industrial and academic communities.

Dispersive optical bistability in quantum wells with logarithmic gain

We present an analytical model for studying optical bistability in semiconductor lasers that exhibit a logarithmic dependence of the optical gain on carrier concentration. Model results are shown for a Fabry–Pérot quantum-well laser and compared with the predictions of a commercial computer-aided design (CAD) software tool.

Information integration: generating functional models from structural ones

Information integration is a very important topic. Reusing the knowledge and having common representations have been (and it is) an active research topic in the process systems community. Conventional (structural) But only structural models have been dealt with so far. In this paper the issue of integration is related with two types of different knowledge, functional and structural. Functional representation and analysis have proved very useful, but still it is developed and presented in a completely isolated way from the classic structural description of the process. This paper presents an architecture to integrate both representations.

HAZOP studies using a functional modeling framework

In this paper we present a tool to perform guided HAZOP studies using a functional modeling framework: D-higraphs. It is a formalism that gathers in a single model structural (ontological) and functional information about the process considered. In this paper it is applied to an industrial case showing that the proposed methodology fits its purposes and fulfills some of the gaps and drawbacks existing in previous reported HAZOP assistant tools.

Ontology driven description and engineering of autonomous systems: application to process system engineering

Autonomous systems refer to systems capable of operating in a real world environment without any form of external control for extended periods of time. Autonomy is a desired goal for every system as it improves its performance, safety and profit. Ontologies are a way to conceptualize the knowledge of a specific domain. In this paper an ontology for the description of autonomous systems as well as for its development (engineering) is presented and applied to a process. This ontology is intended to be applied and used to generate final applications following a model driven methodology.

Implementación de algoritmos para la manipulación de curvas concoides en diseño geométrico

Este proyecto se enmarca dentro de la Computación Simbólica y de los fundamentos matemáticos del Diseño Geométrico Asistido por ordenador (CAGD). Se abordara uno de los problemas principales en el ámbito del CAGD y que es la manipulación de las Curvas Concoide. La importancia del avance en la manipulación de las curvas concoide radica en el papel fundamental que desempeñan en múltiples aplicaciones en la actualidad dentro de campos de diversa índole tales como la medicina, la óptica, el electromagnetismo, la construcción, etc. El objetivo principal de este proyecto es el diseño e implementación de algoritmos para el estudio, cálculo y manipulación de curvas concoides, utilizando técnicas propias del Calculo Simbólico. Esta implementación se ha programado utilizando el sistema de computación simbólica Maple. El proyecto consiste en dos partes bien diferenciadas, una parte teórica y otra más practica. La primera incluye la descripción geométrica y definición formal de curvas concoide, así como las ideas y propiedades básicas. De forma más precisa, se presenta un estudio matemático sobre el análisis de racionalidad de estas curvas, explicando los algoritmos que serán implementados en las segunda parte, y que constituye el objetivo principal de este proyecto. Para cerrar esta parte, se presenta una pequeña introducción al sistema y a la programación en Maple. Por otro lado, la segunda parte de este proyecto es totalmente original, y en ella el autor desarrolla las implementaciones en Maple de los algoritmos presentados en la parte anterior, así como la creación de un paquete Maple que las recoge. Por último, se crean las paginas de ayudas en el sistema Maple para la correcta utilización del paquete matemático anteriormente mencionado. Una vez terminada la parte de implementación, se aplican los algoritmos implementados a una colección de curvas clásicas conocidas, recogiendo los datos y resultados obtenidos en un atlas de curvas. Finalmente, se presenta una recopilación de las aplicaciones más destacadas en las que las concoides desempeñan un papel importante así como una breve reseña sobre las concoides de superficies, objeto de varios estudios en la actualidad y a los que se considera que el presente proyecto les puede resultar de gran utilidad. Abstract This project is set up in the framework of Symbolic Computation as well as in the implementation of algebraic-geometric problems that arise from Computer Aided Geometric Design (C.A.G.D.) applications. We address problems related to conchoid curves. The importance of these curves is the fundamental role that they play in current applications as medicine, optics, electromagnetism, construction, etc. The main goal of this project is to design and implement some algorithms to solve problems in studying, calculating and generating conchoid curves with symbolic computation techniques. For this purpose, we program our implementations in the symbolic system “Maple". The project consists of two differentiated parts, one more theoretical part and another part more practical. The first one includes the description of conchoid curves as well as the basic ideas about the concept and its basic properties. More precisely, we introduce in this part the mathematical analysis of the rationality of the conchoids, and we present the algorithms that will be implemented. Furthermore, the reader will be brie y introduced in Maple programming. On the other hand, the second part of this project is totally original. In this more practical part, the author presents the implemented algorithms and a Maple package that includes them, as well as their help pages. These implemented procedures will be check and illustrated with some classical and well known curves, collecting the main properties of the conchoid curves obtained in a brief atlas. Finally, a compilation of the most important applications where conchoids play a fundamental role, and a brief introduction to the conchoids of surfaces, subject of several studies today and where this project could be very useful, are presented.

Contribución al desarrollo de técnicas CAD para el diseño de antenas impresas y dispositivos pasivos de microondas basadas en el método de elementos finitos

El objetivo principal de esta tesis es el desarrollo de herramientas numéricas basadas en técnicas de onda completa para el diseño asistido por ordenador (Computer-Aided Design,‘CAD’) de dispositivos de microondas. En este contexto, se desarrolla una herramienta numérica basada en el método de los elementos finitos para el diseño y análisis de antenas impresas mediante algoritmos de optimización. Esta técnica consiste en dividir el análisis de una antena en dos partes. Una parte de análisis 3D que se realiza sólo una vez en cada punto de frecuencia de la banda de funcionamiento donde se sustituye una superficie que contiene la metalización del parche por puertas artificiales. En una segunda parte se inserta entre las puertas artificiales en la estructura 3D la superficie soportando una metalización y se procede un análisis 2D para caracterizar el comportamiento de la antena. La técnica propuesta en esta tesis se puede implementar en un algoritmo de optimización para definir el perfil de la antena que permite conseguir los objetivos del diseño. Se valida experimentalmente dicha técnica empleándola en el diseño de antenas impresas de banda ancha para diferentes aplicaciones mediante la optimización del perfil de los parches. También, se desarrolla en esta tesis un procedimiento basado en el método de descomposición de dominio y el método de los elementos finitos para el diseño de dispositivos pasivos de microonda. Se utiliza este procedimiento en particular para el diseño y sintonía de filtros de microondas. En la primera etapa de su aplicación se divide la estructura que se quiere analizar en subdominios aplicando el método de descomposición de dominio, este proceso permite analizar cada segmento por separado utilizando el método de análisis adecuado dado que suele haber subdominios que se pueden analizar mediante métodos analíticos por lo que el tiempo de análisis es más reducido. Se utilizan métodos numéricos para analizar los subdominios que no se pueden analizar mediante métodos analíticos. En esta tesis, se utiliza el método de los elementos finitos para llevar a cabo el análisis. Además de la descomposición de dominio, se aplica un proceso de barrido en frecuencia para reducir los tiempos del análisis. Como método de orden reducido se utiliza la técnica de bases reducidas. Se ha utilizado este procedimiento para diseñar y sintonizar varios ejemplos de filtros con el fin de comprobar la validez de dicho procedimiento. Los resultados obtenidos demuestran la utilidad de este procedimiento y confirman su rigurosidad, precisión y eficiencia en el diseño de filtros de microondas. ABSTRACT The main objective of this thesis is the development of numerical tools based on full-wave techniques for computer-aided design ‘CAD’ of microwave devices. In this context, a numerical technique based on the finite element method ‘FEM’ for the design and analysis of printed antennas using optimization algorithms has been developed. The proposed technique consists in dividing the analysis of the antenna in two stages. In the first stage, the regions of the antenna which do not need to be modified during the CAD process are initially characterized only once from their corresponding matrix transfer function (Generalized Admittance matrix, ‘GAM’). The regions which will be modified are defined as artificial ports, precisely the regions which will contain the conducting surfaces of the printed antenna. In a second stage, the contour shape of the conducting surfaces of the printed antenna is iteratively modified in order to achieve a desired electromagnetic performance of the antenna. In this way, a new GAM of the radiating device which takes into account each printed antenna shape is computed after each iteration. The proposed technique can be implemented with a genetic algorithm to achieve the design objectives. This technique is validated experimentally and applied to the design of wideband printed antennas for different applications by optimizing the shape of the radiating device. In addition, a procedure based on the domain decomposition method and the finite element method has been developed for the design of microwave passive devices. In particular, this procedure can be applied to the design and tune of microwave filters. In the first stage of its implementation, the structure to be analyzed is divided into subdomains using the domain decomposition method; this process allows each subdomains can be analyzed separately using suitable analysis method, since there is usually subdomains that can be analyzed by analytical methods so that the time of analysis is reduced. For analyzing the subdomains that cannot be analyzed by analytical methods, we use the numerical methods. In this thesis, the FEM is used to carry out the analysis. Furthermore the decomposition of the domain, a frequency sweep process is applied to reduce analysis times. The reduced order model as the reduced basis technique is used in this procedure. This procedure is applied to the design and tune of several examples of microwave filters in order to check its validity. The obtained results allow concluding the usefulness of this procedure and confirming their thoroughness, accuracy and efficiency for the design of microwave filters.