Novel educational assessment for building structures: Automatic evaluation of on-line graphics

This article presents a new automatic evaluation for on-line graphics, its application and the numerous advantages achieved applying this developed correcting method. The software application developed by the Innovation in Education Group “E4”, from the Technical University of Madrid, is oriented for the online self-assessment of the graphic drawings that students carry out as continuous training. The adaptation to the European Higher Educational Area is an important opportunity to research about the possibilities of on-line education assessment. In this way, a new software tool has been developed for continuous self-testing by undergraduates. Using this software it is possible to evaluate the graphical answer of the students. Thus, the drawings made on-line by students are automatically corrected according to the geometry (straight lines, sloping lines or second order curves) and by sizes (depending on the specific values which define the graphics).

Preliminary results of ON/OFF detection using an integrated system for Parkinson's disease monitoring

This paper describes the experimental set up of a system composed by a set of wearable sensors devices for the recording of the motion signals and software algorithms for the signal analysis. This system is able to automatically detect and assess the severity of bradykinesia, tremor, dyskinesia and akinesia motor symptoms. Based on the assessment of the akinesia, the ON-OFF status of the patient is determined for each moment. The assessment performed through the automatic evaluation of the akinesia is compared with the status reported by the patients in their diaries. Preliminary results with a total recording period of 32 hours with two PD patients are presented, where a good correspondence (88.2 +/- 3.7 %) was observed. Best (93.7 por ciento) and worst (87 por ciento) correlation results are illustrated, together with the analysis of the automatic assessment of the akinesia symptom leading to the status determination. The results obtained are promising, and if confirmed with further data, this automatic assessment of PD motor symptoms will lead to a better adjustment of medication dosages and timing, cost savings and an improved quality of life of the patients.

Supporting patient screening to identify suitable clinical trials.

To support the efficient execution of post-genomic multi-centric clinical trials in breast cancer we propose a solution that streamlines the assessment of the eligibility of patients for available trials. The assessment of the eligibility of a patient for a trial requires evaluating whether each eligibility criterion is satisfied and is often a time consuming and manual task. The main focus in the literature has been on proposing different methods for modelling and formalizing the eligibility criteria. However the current adoption of these approaches in clinical care is limited. Less effort has been dedicated to the automatic matching of criteria to the patient data managed in clinical care. We address both aspects and propose a scalable, efficient and pragmatic patient screening solution enabling automatic evaluation of eligibility of patients for a relevant set of trials. This covers the flexible formalization of criteria and of other relevant trial metadata and the efficient management of these representations.

Automatic Categorization for Improving Spanish into Spanish Sign Language Machine Translation

This paper describes a preprocessing module for improving the performance of a Spanish into Spanish Sign Language (Lengua de Signos Espanola: LSE) translation system when dealing with sparse training data. This preprocessing module replaces Spanish words with associated tags. The list with Spanish words (vocabulary) and associated tags used by this module is computed automatically considering those signs that show the highest probability of being the translation of every Spanish word. This automatic tag extraction has been compared to a manual strategy achieving almost the same improvement. In this analysis, several alternatives for dealing with non-relevant words have been studied. Non-relevant words are Spanish words not assigned to any sign. The preprocessing module has been incorporated into two well-known statistical translation architectures: a phrase-based system and a Statistical Finite State Transducer (SFST). This system has been developed for a specific application domain: the renewal of Identity Documents and Driver's License. In order to evaluate the system a parallel corpus made up of 4080 Spanish sentences and their LSE translation has been used. The evaluation results revealed a significant performance improvement when including this preprocessing module. In the phrase-based system, the proposed module has given rise to an increase in BLEU (Bilingual Evaluation Understudy) from 73.8% to 81.0% and an increase in the human evaluation score from 0.64 to 0.83. In the case of SFST, BLEU increased from 70.6% to 78.4% and the human evaluation score from 0.65 to 0.82.

Design and evaluation of acceleration strategies for speeding up the development of dialog applications

In this paper, we describe a complete development platform that features different innovative acceleration strategies, not included in any other current platform, that simplify and speed up the definition of the different elements required to design a spoken dialog service. The proposed accelerations are mainly based on using the information from the backend database schema and contents, as well as cumulative information produced throughout the different steps in the design. Thanks to these accelerations, the interaction between the designer and the platform is improved, and in most cases the design is reduced to simple confirmations of the “proposals” that the platform dynamically provides at each step. In addition, the platform provides several other accelerations such as configurable templates that can be used to define the different tasks in the service or the dialogs to obtain or show information to the user, automatic proposals for the best way to request slot contents from the user (i.e. using mixed-initiative forms or directed forms), an assistant that offers the set of more probable actions required to complete the definition of the different tasks in the application, or another assistant for solving specific modality details such as confirmations of user answers or how to present them the lists of retrieved results after querying the backend database. Additionally, the platform also allows the creation of speech grammars and prompts, database access functions, and the possibility of using mixed initiative and over-answering dialogs. In the paper we also describe in detail each assistant in the platform, emphasizing the different kind of methodologies followed to facilitate the design process at each one. Finally, we describe the results obtained in both a subjective and an objective evaluation with different designers that confirm the viability, usefulness, and functionality of the proposed accelerations. Thanks to the accelerations, the design time is reduced in more than 56% and the number of keystrokes by 84%.

Automatic unrestricted independent and-parallelism in logic programs

We present new algorithms which perform automatic parallelization via source-to-source transformations. The objective is to exploit goal-level, unrestricted independent andparallelism. The proposed algorithms use as targets new parallel execution primitives which are simpler and more flexible than the well-known &/2 parallel operator, which makes it possible to generate better parallel expressions by exposing more potential parallelism among the literals of a clause than is possible with &/2. The main differences between the algorithms stem from whether the order of the solutions obtained is preserved or not, and on the use of determinacy information. We briefly describe the environment where the algorithms have been implemented and the runtime platform in which the parallelized programs are executed. We also report on an evaluation of an implementation of our approach. We compare the performance obtained to that of previous annotation algorithms and show that relevant improvements can be obtained.

Automatic compile-time parallelization of CLP programs by analysis and transformation to a concurrent constraint language.

The concept of independence has been recently generalized to the constraint logic programming (CLP) paradigm. Also, several abstract domains specifically designed for CLP languages, and whose information can be used to detect the generalized independence conditions, have been recently defined. As a result we are now in a position where automatic parallelization of CLP programs is feasible. In this paper we study the task of automatically parallelizing CLP programs based on such analyses, by transforming them to explicitly concurrent programs in our parallel CC platform (CIAO) as well as to AKL. We describe the analysis and transformation process, and study its efficiency, accuracy, and effectiveness in program parallelization. The information gathered by the analyzers is evaluated not only in terms of its accuracy, i.e. its ability to determine the actual dependencies among the program variables, but also of its effectiveness, measured in terms of code reduction in the resulting parallelized programs. Given that only a few abstract domains have been already defined for CLP, and that none of them were specifically designed for dependency detection, the aim of the evaluation is not only to asses the effectiveness of the available domains, but also to study what additional information it would be desirable to infer, and what domains would be appropriate for further improving the parallelization process.

User-centric need-driven affect modeling for spoken conversational agents: design and evaluation

It is easy to get frustrated at spoken conversational agents (SCAs), perhaps because they seem to be callous. By and large, the quality of human-computer interaction is affected due to the inability of the SCAs to recognise and adapt to user emotional state. Now with the mass appeal of artificially-mediated communication, there has been an increasing need for SCAs to be socially and emotionally intelligent, that is, to infer and adapt to their human interlocutors’ emotions on the fly, in order to ascertain an affective, empathetic and naturalistic interaction. An enhanced quality of interaction would reduce users’ frustrations and consequently increase their satisfactions. These reasons have motivated the development of SCAs towards including socio-emotional elements, turning them into affective and socially-sensitive interfaces. One barrier to the creation of such interfaces has been the lack of methods for modelling emotions in a task-independent environment. Most emotion models for spoken dialog systems are task-dependent and thus cannot be used “as-is” in different applications. This Thesis focuses on improving this, in which it concerns computational modeling of emotion, personality and their interrelationship for task-independent autonomous SCAs. The generation of emotion is driven by needs, inspired by human’s motivational systems. The work in this Thesis is organised in three stages, each one with its own contribution. The first stage involved defining, integrating and quantifying the psychological-based motivational and emotional models sourced from. Later these were transformed into a computational model by implementing them into software entities. The computational model was then incorporated and put to test with an existing SCA host, a HiFi-control agent. The second stage concerned automatic prediction of affect, which has been the main challenge towards the greater aim of infusing social intelligence into the HiFi agent. In recent years, studies on affect detection from voice have moved on to using realistic, non-acted data, which is subtler. However, it is more challenging to perceive subtler emotions and this is demonstrated in tasks such as labelling and machine prediction. In this stage, we attempted to address part of this challenge by considering the roles of user satisfaction ratings and conversational/dialog features as the respective target and predictors in discriminating contentment and frustration, two types of emotions that are known to be prevalent within spoken human-computer interaction. The final stage concerned the evaluation of the emotional model through the HiFi agent. A series of user studies with 70 subjects were conducted in a real-time environment, each in a different phase and with its own conditions. All the studies involved the comparisons between the baseline non-modified and the modified agent. The findings have gone some way towards enhancing our understanding of the utility of emotion in spoken dialog systems in several ways; first, an SCA should not express its emotions blindly, albeit positive. Rather, it should adapt its emotions to user states. Second, low performance in an SCA may be compensated by the exploitation of emotion. Third, the expression of emotion through the exploitation of prosody could better improve users’ perceptions of an SCA compared to exploiting emotions through just lexical contents. Taken together, these findings not only support the success of the emotional model, but also provide substantial evidences with respect to the benefits of adding emotion in an SCA, especially in mitigating users’ frustrations and ultimately improving their satisfactions. Resumen Es relativamente fácil experimentar cierta frustración al interaccionar con agentes conversacionales (Spoken Conversational Agents, SCA), a menudo porque parecen ser un poco insensibles. En general, la calidad de la interacción persona-agente se ve en cierto modo afectada por la incapacidad de los SCAs para identificar y adaptarse al estado emocional de sus usuarios. Actualmente, y debido al creciente atractivo e interés de dichos agentes, surge la necesidad de hacer de los SCAs unos seres cada vez más sociales y emocionalmente inteligentes, es decir, con capacidad para inferir y adaptarse a las emociones de sus interlocutores humanos sobre la marcha, de modo que la interacción resulte más afectiva, empática y, en definitiva, natural. Una interacción mejorada en este sentido permitiría reducir la posible frustración de los usuarios y, en consecuencia, mejorar el nivel de satisfacción alcanzado por los mismos. Estos argumentos justifican y motivan el desarrollo de nuevos SCAs con capacidades socio-emocionales, dotados de interfaces afectivas y socialmente sensibles. Una de las barreras para la creación de tales interfaces ha sido la falta de métodos de modelado de emociones en entornos independientes de tarea. La mayoría de los modelos emocionales empleados por los sistemas de diálogo hablado actuales son dependientes de tarea y, por tanto, no pueden utilizarse "tal cual" en diferentes dominios o aplicaciones. Esta tesis se centra precisamente en la mejora de este aspecto, la definición de modelos computacionales de las emociones, la personalidad y su interrelación para SCAs autónomos e independientes de tarea. Inspirada en los sistemas motivacionales humanos en el ámbito de la psicología, la tesis propone un modelo de generación/producción de la emoción basado en necesidades. El trabajo realizado en la presente tesis está organizado en tres etapas diferenciadas, cada una con su propia contribución. La primera etapa incluyó la definición, integración y cuantificación de los modelos motivacionales de partida y de los modelos emocionales derivados a partir de éstos. Posteriormente, dichos modelos emocionales fueron plasmados en un modelo computacional mediante su implementación software. Este modelo computacional fue incorporado y probado en un SCA anfitrión ya existente, un agente con capacidad para controlar un equipo HiFi, de alta fidelidad. La segunda etapa se orientó hacia el reconocimiento automático de la emoción, aspecto que ha constituido el principal desafío en relación al objetivo mayor de infundir inteligencia social en el agente HiFi. En los últimos años, los estudios sobre reconocimiento de emociones a partir de la voz han pasado de emplear datos actuados a usar datos reales en los que la presencia u observación de emociones se produce de una manera mucho más sutil. El reconocimiento de emociones bajo estas condiciones resulta mucho más complicado y esta dificultad se pone de manifiesto en tareas tales como el etiquetado y el aprendizaje automático. En esta etapa, se abordó el problema del reconocimiento de las emociones del usuario a partir de características o métricas derivadas del propio diálogo usuario-agente. Gracias a dichas métricas, empleadas como predictores o indicadores del grado o nivel de satisfacción alcanzado por el usuario, fue posible discriminar entre satisfacción y frustración, las dos emociones prevalentes durante la interacción usuario-agente. La etapa final corresponde fundamentalmente a la evaluación del modelo emocional por medio del agente Hifi. Con ese propósito se llevó a cabo una serie de estudios con usuarios reales, 70 sujetos, interaccionando con diferentes versiones del agente Hifi en tiempo real, cada uno en una fase diferente y con sus propias características o capacidades emocionales. En particular, todos los estudios realizados han profundizado en la comparación entre una versión de referencia del agente no dotada de ningún comportamiento o característica emocional, y una versión del agente modificada convenientemente con el modelo emocional propuesto. Los resultados obtenidos nos han permitido comprender y valorar mejor la utilidad de las emociones en los sistemas de diálogo hablado. Dicha utilidad depende de varios aspectos. En primer lugar, un SCA no debe expresar sus emociones a ciegas o arbitrariamente, incluso aunque éstas sean positivas. Más bien, debe adaptar sus emociones a los diferentes estados de los usuarios. En segundo lugar, un funcionamiento relativamente pobre por parte de un SCA podría compensarse, en cierto modo, dotando al SCA de comportamiento y capacidades emocionales. En tercer lugar, aprovechar la prosodia como vehículo para expresar las emociones, de manera complementaria al empleo de mensajes con un contenido emocional específico tanto desde el punto de vista léxico como semántico, ayuda a mejorar la percepción por parte de los usuarios de un SCA. Tomados en conjunto, los resultados alcanzados no sólo confirman el éxito del modelo emocional, sino xv que constituyen además una evidencia decisiva con respecto a los beneficios de incorporar emociones en un SCA, especialmente en cuanto a reducir el nivel de frustración de los usuarios y, en última instancia, mejorar su satisfacción.

Patrol team language identification system for DARPA RATS P1 evaluation

This paper describes the language identification (LID) system developed by the Patrol team for the first phase of the DARPA RATS (Robust Automatic Transcription of Speech) program, which seeks to advance state of the art detection capabilities on audio from highly degraded communication channels. We show that techniques originally developed for LID on telephone speech (e.g., for the NIST language recognition evaluations) remain effective on the noisy RATS data, provided that careful consideration is applied when designing the training and development sets. In addition, we show significant improvements from the use of Wiener filtering, neural network based and language dependent i-vector modeling, and fusion.

Automatic segmentation of abdominal aortic aneurysm from medical images based on active shape models and texture models

A semi-automatic segmentation algorithm for abdominal aortic aneurysms (AAA), and based on Active Shape Models (ASM) and texture models, is presented in this work. The texture information is provided by a set of four 3D magnetic resonance (MR) images, composed of axial slices of the abdomen, where lumen, wall and intraluminal thrombus (ILT) are visible. Due to the reduced number of images in the MRI training set, an ASM and a custom texture model based on border intensity statistics are constructed. For the same reason the shape is characterized from 35-computed tomography angiography (CTA) images set so the shape variations are better represented. For the evaluation, leave-one-out experiments have been held over the four MRI set.

Programming assignments automatic grading: review of tools and implementations

Automatic grading of programming assignments is an important topic in academic research. It aims at improving the level of feedback given to students and optimizing the professor time. Several researches have reported the development of software tools to support this process. Then, it is helpfulto get a quickly and good sight about their key features. This paper reviews an ample set of tools forautomatic grading of programming assignments. They are divided in those most important mature tools, which have remarkable features; and those built recently, with new features. The review includes the definition and description of key features e.g. supported languages, used technology, infrastructure, etc. The two kinds of tools allow making a temporal comparative analysis. This analysis infrastructure, etc. The two kinds of tools allow making a temporal comparative analysis. This analysis shows good improvements in this research field, these include security, more language support, plagiarism detection, etc. On the other hand, the lack of a grading model for assignments is identified as an important gap in the reviewed tools. Thus, a characterization of evaluation metrics to grade programming assignments is provided as first step to get a model. Finally new paths in this research field are proposed.

I feel you: the design and evaluation of a domotic affect-sensitive spoken conversational agent

We describe the work on infusion of emotion into a limited-task autonomous spoken conversational agent situated in the domestic environment, using a need-inspired task-independent emotion model (NEMO). In order to demonstrate the generation of affect through the use of the model, we describe the work of integrating it with a natural-language mixed-initiative HiFi-control spoken conversational agent (SCA). NEMO and the host system communicate externally, removing the need for the Dialog Manager to be modified, as is done in most existing dialog systems, in order to be adaptive. The first part of the paper concerns the integration between NEMO and the host agent. The second part summarizes the work on automatic affect prediction, namely, frustration and contentment, from dialog features, a non-conventional source, in the attempt of moving towards a more user-centric approach. The final part reports the evaluation results obtained from a user study, in which both versions of the agent (non-adaptive and emotionally-adaptive) were compared. The results provide substantial evidences with respect to the benefits of adding emotion in a spoken conversational agent, especially in mitigating users' frustrations and, ultimately, improving their satisfaction.

Systems and technologies for objective evaluation of technical skills in laparoscopic surgery

Minimally invasive surgery is a highly demanding surgical approach regarding technical requirements for the surgeon, who must be trained in order to perform a safe surgical intervention. Traditional surgical education in minimally invasive surgery is commonly based on subjective criteria to quantify and evaluate surgical abilities, which could be potentially unsafe for the patient. Authors, surgeons and associations are increasingly demanding the development of more objective assessment tools that can accredit surgeons as technically competent. This paper describes the state of the art in objective assessment methods of surgical skills. It gives an overview on assessment systems based on structured checklists and rating scales, surgical simulators, and instrument motion analysis. As a future work, an objective and automatic assessment method of surgical skills should be standardized as a means towards proficiency-based curricula for training in laparoscopic surgery and its certification.

Towards the automatic generation of card games through Grammar-Guided Genetic Programming

We demonstrate generating complete and playable card games using evolutionary algorithms. Card games are represented in a previously devised card game description language, a context-free grammar. The syntax of this language allows us to use grammar-guided genetic programming. Candidate card games are evaluated through a cascading evaluation function, a multi-step process where games with undesired properties are progressively weeded out. Three representa- tive examples of generated games are analysed. We observed that these games are reasonably balanced and have skill ele- ments, they are not yet entertaining for human players. The particular shortcomings of the examples are discussed in re- gard to the generative process to be able to generate quality games

Application of NMR techniques for the evaluation of fruit internal quality and physical properties of food

Los alimentos son sistemas complejos, formados por diversas estructuras a diferentes escalas: macroscópica y microscópica. Muchas propiedades de los alimentos, que son importantes para su procesamiento, calidad y tratamiento postcosecha, están relacionados con su microestructura. La presente tesis doctoral propone una metodología completa para la determinación de la estructura de alimentos desde un punto de vista multi-escala, basándose en métodos de Resonancia Magnética Nuclear (NMR). Las técnicas de NMR son no invasivas y no destructivas y permiten el estudio tanto de macro- como de microestructura. Se han utilizado distintos procedimientos de NMR dependiendo del nivel que se desea estudiar. Para el nivel macroestructural, la Imagen de Resonancia Magnética (MRI) ha resultado ser muy útil para la caracterización de alimentos. Para el estudio microestructural, la MRI requiere altos tiempos de adquisición, lo que hace muy difícil la transferencia de esta técnica a aplicaciones en industria. Por tanto, la optimización de procedimientos de NMR basados en secuencias relaxometría 2D T1/T2 ha resultado ser una estrategia primordial en esta tesis. Estos protocolos de NMR se han implementado satisfactoriamente por primera vez en alto campo magnético. Se ha caracterizado la microestructura de productos alimentarios enteros por primera vez utilizando este tipo de protocolos. Como muestras, se han utilizado dos tipos de productos: modelos de alimentos y alimentos reales (manzanas). Además, como primer paso para su posterior implementación en la industria agroalimentaria, se ha mejorado una línea transportadora, especialmente diseñada para trabajar bajo condiciones de NMR en trabajos anteriores del grupo LPF-TAGRALIA. Se han estudiado y seleccionado las secuencias más rápidas y óptimas para la detección de dos tipos de desórdenes internos en manzanas: vitrescencia y roturas internas. La corrección de las imágenes en movimiento se realiza en tiempo real. Asimismo, se han utilizado protocolos de visión artificial para la clasificación automática de manzanas potencialmente afectadas por vitrescencia. El presente documento está dividido en diferentes capítulos: el Capítulo 2 explica los antecedentes de la presente tesis y el marco del proyecto en el que se ha desarrollado. El Capítulo 3 recoge el estado del arte. El Capítulo 4 establece los objetivos de esta tesis doctoral. Los resultados se dividen en cinco sub-secciones (dentro del Capítulo 5) que corresponden con los trabajos publicados bien en revistas revisadas por pares, bien en congresos internacionales o bien como capítulos de libros revisados por pares. La Sección 5.1. es un estudio del desarrollo de la vitrescencia en manzanas mediante MRI y lo relaciona con la posición de la fruta dentro de la copa del árbol. La Sección 5.2 presenta un trabajo sobre macro- y microestructura en modelos de alimentos. La Sección 5.3 es un artículo en revisión en una revista revisada por pares, en el que se hace un estudio microestrcutural no destructivo mediante relaxometría 2D T1/T2. la Sección 5.4, hace una comparación entre manzanas afectadas por vitrescencia mediante dos técnicas: tomografía de rayos X e MRI, en manzana. Por último, en la Sección 5.5 se muestra un trabajo en el que se hace un estudio de secuencias de MRI en línea para la evaluación de calidad interna en manzanas. Los siguientes capítulos ofrecen una discusión y conclusiones (Capítulo 6 y 7 respectivamente) de todos los capítulos de esta tesis doctoral. Finalmente, se han añadido tres apéndices: el primero con una introducción de los principios básicos de resonancia magnética nuclear (NMR) y en los otros dos, se presentan sendos estudios sobre el efecto de las fibras en la rehidratación de cereales de desayuno extrusionados, mediante diversas técnicas. Ambos trabajos se presentaron en un congreso internacional. Los resultados más relevantes de la presente tesis doctoral, se pueden dividir en tres grandes bloques: resultados sobre macroestructura, resultados sobre microestructura y resultados sobre MRI en línea. Resultados sobre macroestructura: - La imagen de resonancia magnética (MRI) se aplicó satisfactoriamente para la caracterización de macroestructura. En particular, la reconstrucción 3D de imágenes de resonancia magnética permitió identificar y caracterizar dos tipos distintos de vitrescencia en manzanas: central y radial, que se caracterizan por el porcentaje de daño y la conectividad (número de Euler). - La MRI proveía un mejor contraste para manzanas afectadas por vitrescencia que las imágenes de tomografía de rayos X (X-Ray CT), como se pudo verificar en muestras idénticas de manzana. Además, el tiempo de adquisición de la tomografía de rayos X fue alrededor de 12 veces mayor (25 minutos) que la adquisición de las imágenes de resonancia magnética (2 minutos 2 segundos). Resultados sobre microestructura: - Para el estudio de microestructura (nivel subcelular) se utilizaron con éxito secuencias de relaxometría 2D T1/T2. Estas secuencias se usaron por primera vez en alto campo y sobre piezas de alimento completo, convirtiéndose en una forma no destructiva de llevar a cabo estudios de microestructura. - El uso de MRI junto con relaxometría 2D T1/T2 permite realizar estudios multiescala en alimentos de forma no destructiva. Resultados sobre MRI en línea: - El uso de imagen de resonancia magnética en línea fue factible para la identificación de dos tipos de desórdenes internos en manzanas: vitrescencia y podredumbre interna. Las secuencias de imagen tipo FLASH resultaron adecuadas para la identificación en línea de vitrescencia en manzanas. Se realizó sin selección de corte, debido a que la vitrescencia puede desarrollarse en cualquier punto del volumen de la manzana. Se consiguió reducir el tiempo de adquisición, de modo que se llegaron a adquirir 1.3 frutos por segundos (758 ms por fruto). Las secuencias de imagen tipo UFLARE fueron adecuadas para la detección en línea de la podredumbre interna en manzanas. En este caso, se utilizó selección de corte, ya que se trata de un desorden que se suele localizar en la parte central del volumen de la manzana. Se consiguió reducir el tiempo de adquisicón hasta 0.67 frutos por segundo (1475 ms por fruto). En ambos casos (FLASH y UFLARE) fueron necesarios algoritmos para la corrección del movimiento de las imágenes en tiempo real. ABSTRACT Food is a complex system formed by several structures at different scales: macroscopic and microscopic. Many properties of foods that are relevant to process engineering or quality and postharvest treatments are related to their microstructure. This Ph.D Thesis proposes a complete methodology for food structure determination, in a multiscale way, based on the Nuclear Magnetic Resonance (NMR) phenomenon since NMR techniques are non-invasive and non-destructive, and allow both, macro- and micro-structure study. Different NMR procedures are used depending on the structure level under study. For the macrostructure level, Magnetic Resonance Imaging (MRI) revealed its usefulness for food characterization. For microstructure insight, MRI required high acquisition times, which is a hindrance for transference to industry applications. Therefore, optimization of NMR procedures based on T1/T2 relaxometry sequences was a key strategy in this Thesis. These NMR relaxometry protocols, are successfully implemented in high magnetic field. Microstructure of entire food products have been characterized for the first time using these protocols. Two different types of food products have been studied: food models and actual food (apples). Furthermore, as a first step for the food industry implementation, a grading line system, specially designed for working under NMR conditions in previous works of the LPF-TAGRALIA group, is improved. The study and selection of the most suitable rapid sequence to detect two different types of disorders in apples (watercore and internal breakdown) is performed and the real time image motion correction is applied. In addition, artificial vision protocols for the automatic classification of apples potentially affected by watercore are applied. This document is divided into seven different chapters: Chapter 2 explains the thesis background and the framework of the project in which it has been worked. Chapter 3 comprises the state of the art. Chapter 4 establishes de objectives of this Ph.D thesis. The results are divided into five different sections (in Chapter 5) that correspond to published peered reviewed works. Section 5.1 assesses the watercore development in apples with MRI and studies the effect of fruit location in the canopy. Section 5.2 is an MRI and 2D relaxometry study for macro- and microstructure assessment in food models. Section 5.3 is a non-destructive microstructural study using 2D T1/T2 relaxometry on watercore affected apples. Section 5.4 makes a comparison of X-ray CT and MRI on watercore disorder of different apple cultivars. Section 5.5, that is a study of online MRI sequences for the evaluation of apple internal quality. The subsequent chapters offer a general discussion and conclusions (Chapter 6 and Chapter 7 respectively) of all the works performed in the frame of this Ph.D thesis (two peer reviewed journals, one book chapter and one international congress).Finally, three appendices are included in which an introduction to NMR principles is offered and two published proceedings regarding the effect of fiber on the rehydration of extruded breakfast cereal are displayed. The most relevant results can be summarized into three sections: results on macrostructure, results on microstructure and results on on-line MRI. Results on macrostructure: - MRI was successfully used for macrostructure characterization. Indeed, 3D reconstruction of MRI in apples allows to identify two different types of watercore (radial and block), which are characterized by the percentage of damage and the connectivity (Euler number). - MRI provides better contrast for watercore than X-Ray CT as verified on identical samples. Furthermore, X-Ray CT images acquisition time was around 12 times higher (25 minutes) than MRI acquisition time (2 minutes 2 seconds). Results on microstructure: - 2D T1/T2 relaxometry were successfully applied for microstructure (subcellular level) characterization. 2D T1/T2 relaxometry sequences have been applied for the first time on high field for entire food pieces, being a non-destructive way to achieve microstructure study. - The use of MRI together with 2D T1/T2 relaxometry sequences allows a non-destructive multiscale study of food. Results on on-line MRI: - The use of on-line MRI was successful for the identification of two different internal disorders in apples: watercore and internal breakdown. FLASH imaging was a suitable technique for the on-line detection of watercore disorder in apples, with no slice selection, since watercore is a physiological disorder that may be developed anywhere in the apple volume. 1.3 fruits were imaged per second (768 ms per fruit). UFLARE imaging is a suitable sequence for the on-line detection of internal breakdown disorder in apples. Slice selection was used, as internal breakdown is usually located in the central slice of the apple volume. 0.67 fruits were imaged per second (1475 ms per fruit). In both cases (FLASH and UFLARE) motion correction was performed in real time, during the acquisition of the images.