Contributions to Speech Analytics based on Speech Recognition and Topic Identification

La última década ha sido testigo de importantes avances en el campo de la tecnología de reconocimiento de voz. Los sistemas comerciales existentes actualmente poseen la capacidad de reconocer habla continua de múltiples locutores, consiguiendo valores aceptables de error, y sin la necesidad de realizar procedimientos explícitos de adaptación. A pesar del buen momento que vive esta tecnología, el reconocimiento de voz dista de ser un problema resuelto. La mayoría de estos sistemas de reconocimiento se ajustan a dominios particulares y su eficacia depende de manera significativa, entre otros muchos aspectos, de la similitud que exista entre el modelo de lenguaje utilizado y la tarea específica para la cual se está empleando. Esta dependencia cobra aún más importancia en aquellos escenarios en los cuales las propiedades estadísticas del lenguaje varían a lo largo del tiempo, como por ejemplo, en dominios de aplicación que involucren habla espontánea y múltiples temáticas. En los últimos años se ha evidenciado un constante esfuerzo por mejorar los sistemas de reconocimiento para tales dominios. Esto se ha hecho, entre otros muchos enfoques, a través de técnicas automáticas de adaptación. Estas técnicas son aplicadas a sistemas ya existentes, dado que exportar el sistema a una nueva tarea o dominio puede requerir tiempo a la vez que resultar costoso. Las técnicas de adaptación requieren fuentes adicionales de información, y en este sentido, el lenguaje hablado puede aportar algunas de ellas. El habla no sólo transmite un mensaje, también transmite información acerca del contexto en el cual se desarrolla la comunicación hablada (e.g. acerca del tema sobre el cual se está hablando). Por tanto, cuando nos comunicamos a través del habla, es posible identificar los elementos del lenguaje que caracterizan el contexto, y al mismo tiempo, rastrear los cambios que ocurren en estos elementos a lo largo del tiempo. Esta información podría ser capturada y aprovechada por medio de técnicas de recuperación de información (information retrieval) y de aprendizaje de máquina (machine learning). Esto podría permitirnos, dentro del desarrollo de mejores sistemas automáticos de reconocimiento de voz, mejorar la adaptación de modelos del lenguaje a las condiciones del contexto, y por tanto, robustecer al sistema de reconocimiento en dominios con condiciones variables (tales como variaciones potenciales en el vocabulario, el estilo y la temática). En este sentido, la principal contribución de esta Tesis es la propuesta y evaluación de un marco de contextualización motivado por el análisis temático y basado en la adaptación dinámica y no supervisada de modelos de lenguaje para el robustecimiento de un sistema automático de reconocimiento de voz. Esta adaptación toma como base distintos enfoque de los sistemas mencionados (de recuperación de información y aprendizaje de máquina) mediante los cuales buscamos identificar las temáticas sobre las cuales se está hablando en una grabación de audio. Dicha identificación, por lo tanto, permite realizar una adaptación del modelo de lenguaje de acuerdo a las condiciones del contexto. El marco de contextualización propuesto se puede dividir en dos sistemas principales: un sistema de identificación de temática y un sistema de adaptación dinámica de modelos de lenguaje. Esta Tesis puede describirse en detalle desde la perspectiva de las contribuciones particulares realizadas en cada uno de los campos que componen el marco propuesto: _ En lo referente al sistema de identificación de temática, nos hemos enfocado en aportar mejoras a las técnicas de pre-procesamiento de documentos, asimismo en contribuir a la definición de criterios más robustos para la selección de index-terms. – La eficiencia de los sistemas basados tanto en técnicas de recuperación de información como en técnicas de aprendizaje de máquina, y específicamente de aquellos sistemas que particularizan en la tarea de identificación de temática, depende, en gran medida, de los mecanismos de preprocesamiento que se aplican a los documentos. Entre las múltiples operaciones que hacen parte de un esquema de preprocesamiento, la selección adecuada de los términos de indexado (index-terms) es crucial para establecer relaciones semánticas y conceptuales entre los términos y los documentos. Este proceso también puede verse afectado, o bien por una mala elección de stopwords, o bien por la falta de precisión en la definición de reglas de lematización. En este sentido, en este trabajo comparamos y evaluamos diferentes criterios para el preprocesamiento de los documentos, así como también distintas estrategias para la selección de los index-terms. Esto nos permite no sólo reducir el tamaño de la estructura de indexación, sino también mejorar el proceso de identificación de temática. – Uno de los aspectos más importantes en cuanto al rendimiento de los sistemas de identificación de temática es la asignación de diferentes pesos a los términos de acuerdo a su contribución al contenido del documento. En este trabajo evaluamos y proponemos enfoques alternativos a los esquemas tradicionales de ponderado de términos (tales como tf-idf ) que nos permitan mejorar la especificidad de los términos, así como también discriminar mejor las temáticas de los documentos. _ Respecto a la adaptación dinámica de modelos de lenguaje, hemos dividimos el proceso de contextualización en varios pasos. – Para la generación de modelos de lenguaje basados en temática, proponemos dos tipos de enfoques: un enfoque supervisado y un enfoque no supervisado. En el primero de ellos nos basamos en las etiquetas de temática que originalmente acompañan a los documentos del corpus que empleamos. A partir de estas, agrupamos los documentos que forman parte de la misma temática y generamos modelos de lenguaje a partir de dichos grupos. Sin embargo, uno de los objetivos que se persigue en esta Tesis es evaluar si el uso de estas etiquetas para la generación de modelos es óptimo en términos del rendimiento del reconocedor. Por esta razón, nosotros proponemos un segundo enfoque, un enfoque no supervisado, en el cual el objetivo es agrupar, automáticamente, los documentos en clusters temáticos, basándonos en la similaridad semántica existente entre los documentos. Por medio de enfoques de agrupamiento conseguimos mejorar la cohesión conceptual y semántica en cada uno de los clusters, lo que a su vez nos permitió refinar los modelos de lenguaje basados en temática y mejorar el rendimiento del sistema de reconocimiento. – Desarrollamos diversas estrategias para generar un modelo de lenguaje dependiente del contexto. Nuestro objetivo es que este modelo refleje el contexto semántico del habla, i.e. las temáticas más relevantes que se están discutiendo. Este modelo es generado por medio de la interpolación lineal entre aquellos modelos de lenguaje basados en temática que estén relacionados con las temáticas más relevantes. La estimación de los pesos de interpolación está basada principalmente en el resultado del proceso de identificación de temática. – Finalmente, proponemos una metodología para la adaptación dinámica de un modelo de lenguaje general. El proceso de adaptación tiene en cuenta no sólo al modelo dependiente del contexto sino también a la información entregada por el proceso de identificación de temática. El esquema usado para la adaptación es una interpolación lineal entre el modelo general y el modelo dependiente de contexto. Estudiamos también diferentes enfoques para determinar los pesos de interpolación entre ambos modelos. Una vez definida la base teórica de nuestro marco de contextualización, proponemos su aplicación dentro de un sistema automático de reconocimiento de voz. Para esto, nos enfocamos en dos aspectos: la contextualización de los modelos de lenguaje empleados por el sistema y la incorporación de información semántica en el proceso de adaptación basado en temática. En esta Tesis proponemos un marco experimental basado en una arquitectura de reconocimiento en ‘dos etapas’. En la primera etapa, empleamos sistemas basados en técnicas de recuperación de información y aprendizaje de máquina para identificar las temáticas sobre las cuales se habla en una transcripción de un segmento de audio. Esta transcripción es generada por el sistema de reconocimiento empleando un modelo de lenguaje general. De acuerdo con la relevancia de las temáticas que han sido identificadas, se lleva a cabo la adaptación dinámica del modelo de lenguaje. En la segunda etapa de la arquitectura de reconocimiento, usamos este modelo adaptado para realizar de nuevo el reconocimiento del segmento de audio. Para determinar los beneficios del marco de trabajo propuesto, llevamos a cabo la evaluación de cada uno de los sistemas principales previamente mencionados. Esta evaluación es realizada sobre discursos en el dominio de la política usando la base de datos EPPS (European Parliamentary Plenary Sessions - Sesiones Plenarias del Parlamento Europeo) del proyecto europeo TC-STAR. Analizamos distintas métricas acerca del rendimiento de los sistemas y evaluamos las mejoras propuestas con respecto a los sistemas de referencia. ABSTRACT The last decade has witnessed major advances in speech recognition technology. Today’s commercial systems are able to recognize continuous speech from numerous speakers, with acceptable levels of error and without the need for an explicit adaptation procedure. Despite this progress, speech recognition is far from being a solved problem. Most of these systems are adjusted to a particular domain and their efficacy depends significantly, among many other aspects, on the similarity between the language model used and the task that is being addressed. This dependence is even more important in scenarios where the statistical properties of the language fluctuates throughout the time, for example, in application domains involving spontaneous and multitopic speech. Over the last years there has been an increasing effort in enhancing the speech recognition systems for such domains. This has been done, among other approaches, by means of techniques of automatic adaptation. These techniques are applied to the existing systems, specially since exporting the system to a new task or domain may be both time-consuming and expensive. Adaptation techniques require additional sources of information, and the spoken language could provide some of them. It must be considered that speech not only conveys a message, it also provides information on the context in which the spoken communication takes place (e.g. on the subject on which it is being talked about). Therefore, when we communicate through speech, it could be feasible to identify the elements of the language that characterize the context, and at the same time, to track the changes that occur in those elements over time. This information can be extracted and exploited through techniques of information retrieval and machine learning. This allows us, within the development of more robust speech recognition systems, to enhance the adaptation of language models to the conditions of the context, thus strengthening the recognition system for domains under changing conditions (such as potential variations in vocabulary, style and topic). In this sense, the main contribution of this Thesis is the proposal and evaluation of a framework of topic-motivated contextualization based on the dynamic and non-supervised adaptation of language models for the enhancement of an automatic speech recognition system. This adaptation is based on an combined approach (from the perspective of both information retrieval and machine learning fields) whereby we identify the topics that are being discussed in an audio recording. The topic identification, therefore, enables the system to perform an adaptation of the language model according to the contextual conditions. The proposed framework can be divided in two major systems: a topic identification system and a dynamic language model adaptation system. This Thesis can be outlined from the perspective of the particular contributions made in each of the fields that composes the proposed framework: _ Regarding the topic identification system, we have focused on the enhancement of the document preprocessing techniques in addition to contributing in the definition of more robust criteria for the selection of index-terms. – Within both information retrieval and machine learning based approaches, the efficiency of topic identification systems, depends, to a large extent, on the mechanisms of preprocessing applied to the documents. Among the many operations that encloses the preprocessing procedures, an adequate selection of index-terms is critical to establish conceptual and semantic relationships between terms and documents. This process might also be weakened by a poor choice of stopwords or lack of precision in defining stemming rules. In this regard we compare and evaluate different criteria for preprocessing the documents, as well as for improving the selection of the index-terms. This allows us to not only reduce the size of the indexing structure but also to strengthen the topic identification process. – One of the most crucial aspects, in relation to the performance of topic identification systems, is to assign different weights to different terms depending on their contribution to the content of the document. In this sense we evaluate and propose alternative approaches to traditional weighting schemes (such as tf-idf ) that allow us to improve the specificity of terms, and to better identify the topics that are related to documents. _ Regarding the dynamic language model adaptation, we divide the contextualization process into different steps. – We propose supervised and unsupervised approaches for the generation of topic-based language models. The first of them is intended to generate topic-based language models by grouping the documents, in the training set, according to the original topic labels of the corpus. Nevertheless, a goal of this Thesis is to evaluate whether or not the use of these labels to generate language models is optimal in terms of recognition accuracy. For this reason, we propose a second approach, an unsupervised one, in which the objective is to group the data in the training set into automatic topic clusters based on the semantic similarity between the documents. By means of clustering approaches we expect to obtain a more cohesive association of the documents that are related by similar concepts, thus improving the coverage of the topic-based language models and enhancing the performance of the recognition system. – We develop various strategies in order to create a context-dependent language model. Our aim is that this model reflects the semantic context of the current utterance, i.e. the most relevant topics that are being discussed. This model is generated by means of a linear interpolation between the topic-based language models related to the most relevant topics. The estimation of the interpolation weights is based mainly on the outcome of the topic identification process. – Finally, we propose a methodology for the dynamic adaptation of a background language model. The adaptation process takes into account the context-dependent model as well as the information provided by the topic identification process. The scheme used for the adaptation is a linear interpolation between the background model and the context-dependent one. We also study different approaches to determine the interpolation weights used in this adaptation scheme. Once we defined the basis of our topic-motivated contextualization framework, we propose its application into an automatic speech recognition system. We focus on two aspects: the contextualization of the language models used by the system, and the incorporation of semantic-related information into a topic-based adaptation process. To achieve this, we propose an experimental framework based in ‘a two stages’ recognition architecture. In the first stage of the architecture, Information Retrieval and Machine Learning techniques are used to identify the topics in a transcription of an audio segment. This transcription is generated by the recognition system using a background language model. According to the confidence on the topics that have been identified, the dynamic language model adaptation is carried out. In the second stage of the recognition architecture, an adapted language model is used to re-decode the utterance. To test the benefits of the proposed framework, we carry out the evaluation of each of the major systems aforementioned. The evaluation is conducted on speeches of political domain using the EPPS (European Parliamentary Plenary Sessions) database from the European TC-STAR project. We analyse several performance metrics that allow us to compare the improvements of the proposed systems against the baseline ones.

Structural health monitoringby using transmissibility

El control del estado en el que se encuentran las estructuras ha experimentado un gran auge desde hace varias décadas, debido a que los costes de rehabilitación de estructuras tales como los oleoductos, los puentes, los edificios y otras más son muy elevados. En las últimas dos décadas, se han desarrollado una gran cantidad de métodos que permiten identificar el estado real de una estructura, basándose en modelos físicos y datos de ensayos. El ensayo modal es el más común; mediante el análisis modal experimental de una estructura se pueden determinar parámetros como la frecuencia, los modos de vibración y la amortiguación y también la función de respuesta en frecuencia de la estructura. Mediante estos parámetros se pueden implementar diferentes indicadores de daño. Sin embargo, para estructuras complejas y grandes, la implementación de metodologías basadas en la función de respuesta en frecuencia requeriría realizar hipótesis sobre la fuerza utilizada para excitar la estructura. Dado que el análisis modal operacional utiliza solamente las señales de respuesta del sistema para extraer los parámetros dinámicos estructurales y, por tanto, para evaluar el estado de una estructura, el uso de la transmisibilidad sería posible. En este sentido, dentro del análisis modal operacional, la transmisibilidad ha concentrado mucha atención en el mundo científico en la última década. Aunque se han publicado muchos trabajos sobre el tema, en esta Tesis se proponen diferentes técnicas para evaluar el estado de una estructura basándose exclusivamente en la transmisibilidad. En primer lugar, se propone un indicador de daño basado en un nuevo parámetro, la coherencia de transmisibilidad; El indicador se ha valido mediante resultados numéricos y experimentales obtenidos sobre un pórtico de tres pisos. En segundo lugar, la distancia de Mahalanobis se aplica sobre la transmisibilidad como procedimiento para detectar variaciones estructurales provocadas por el daño. Este método se ha validado con éxito sobre una viga libre-libre ensayada experimentalmente. En tercer lugar, se ha implementado una red neuronal basada en medidas de transmisibilidad como metodología de predicción de daño sobre una viga simulada numéricamente. ABSTRACT Structural health monitoring has experienced a huge development from several decades ago since the cost of rehabilitation of structures such as oil pipes, bridges and tall buildings is very high. In the last two decades, a lot of methods able to identify the real stage of a structure have been developed basing on both models and experimental data. Modal testing is the most common; by carrying out the experimental modal analysis of a structure, some parameters, such as frequency, mode shapes and damping, as well as the frequency response function of the structure can be obtained. From these parameters, different damage indicators have been proposed. However, for complex and large structures, any frequency domain approach that relies on frequency response function estimation would be of difficult application since an assumption of the input excitations to the system should be carried out. Operational modal analysis uses only output signals to extract the structural dynamic parameters and, therefore, to identify the structural stage. In this sense, within operational modal analysis, transmissibility has attracted a lot of attention in the scientific field in the last decade. In this work new damage detection approaches based on transmissibility are developed. Firstly, a new theory of transmissibility coherence is developed and it is tested with a three-floor-structure both in simulation and in experimental data analysis; secondly, Mahalanobis distance is taken into use with the transmissibility, and a free-free beam is used to test the approach performance; thirdly, neural networks are used in transmissibility for structural health monitoring; a simulated beam is used to validate the proposed method.

Structural health monitoringby using transmissibility

El control del estado en el que se encuentran las estructuras ha experimentado un gran auge desde hace varias décadas, debido a que los costes de rehabilitación de estructuras tales como los oleoductos, los puentes, los edificios y otras más son muy elevados. En las últimas dos décadas, se han desarrollado una gran cantidad de métodos que permiten identificar el estado real de una estructura, basándose en modelos físicos y datos de ensayos. El ensayo modal es el más común; mediante el análisis modal experimental de una estructura se pueden determinar parámetros como la frecuencia, los modos de vibración y la amortiguación y también la función de respuesta en frecuencia de la estructura. Mediante estos parámetros se pueden implementar diferentes indicadores de daño. Sin embargo, para estructuras complejas y grandes, la implementación de metodologías basadas en la función de respuesta en frecuencia requeriría realizar hipótesis sobre la fuerza utilizada para excitar la estructura. Dado que el análisis modal operacional utiliza solamente las señales de respuesta del sistema para extraer los parámetros dinámicos estructurales y, por tanto, para evaluar el estado de una estructura, el uso de la transmisibilidad sería posible. En este sentido, dentro del análisis modal operacional, la transmisibilidad ha concentrado mucha atención en el mundo científico en la última década. Aunque se han publicado muchos trabajos sobre el tema, en esta Tesis se proponen diferentes técnicas para evaluar el estado de una estructura basándose exclusivamente en la transmisibilidad. En primer lugar, se propone un indicador de daño basado en un nuevo parámetro, la coherencia de transmisibilidad; El indicador se ha valido mediante resultados numéricos y experimentales obtenidos sobre un pórtico de tres pisos. En segundo lugar, la distancia de Mahalanobis se aplica sobre la transmisibilidad como procedimiento para detectar variaciones estructurales provocadas por el daño. Este método se ha validado con éxito sobre una viga libre-libre ensayada experimentalmente. En tercer lugar, se ha implementado una red neuronal basada en medidas de transmisibilidad como metodología de predicción de daño sobre una viga simulada numéricamente. ABSTRACT Structural health monitoring has experienced a huge development from several decades ago since the cost of rehabilitation of structures such as oil pipes, bridges and tall buildings is very high. In the last two decades, a lot of methods able to identify the real stage of a structure have been developed basing on both models and experimental data. Modal testing is the most common; by carrying out the experimental modal analysis of a structure, some parameters, such as frequency, mode shapes and damping, as well as the frequency response function of the structure can be obtained. From these parameters, different damage indicators have been proposed. However, for complex and large structures, any frequency domain approach that relies on frequency response function estimation would be of difficult application since an assumption of the input excitations to the system should be carried out. Operational modal analysis uses only output signals to extract the structural dynamic parameters and, therefore, to identify the structural stage. In this sense, within operational modal analysis, transmissibility has attracted a lot of attention in the scientific field in the last decade. In this work new damage detection approaches based on transmissibility are developed. Firstly, a new theory of transmissibility coherence is developed and it is tested with a three-floor-structure both in simulation and in experimental data analysis; secondly, Mahalanobis distance is taken into use with the transmissibility, and a free-free beam is used to test the approach performance; thirdly, neural networks are used in transmissibility for structural health monitoring; a simulated beam is used to validate the proposed method.

Longitudinal Changes in Response to a Cycle-Run Field Test of Young Male National "Talent identification" and Senior Elite Triathlon Squads.

This study investigated the changes in cardiorespiratory response and running performance of 9 male ?Talent Identification? (TID) and 6 male Senior Elite (SE) Spanish National Squad triathletes during a specific cycle-run test. The TID and SE triathletes (initial age 15.2±0.7 vs. 23.8±5.6 years, p=0.03; tests through the competitive period and the preparatory period, respectively, of two consecutive seasons: Test 1 was an incremental cycle test to determine the ventilatory threshold (Thvent); Test 2 (C-R) was 30 min constant load cycling at the Thvent power output followed by a 3-km time trial run; and Test 3 (R) was an isolated 3-km time trial control run, in randomized counterbalanced order. In both seasons the time required to complete the C-R 3-km run was greater than for R in TID (11:09±00:24 vs. 10:45±00:16 min:ss, pmenor que 0.01; and 10:24±00:22 vs. 10:04±00:14, p=0.006, for season 2005/06 and 2006/07, respectively) and SE (10:15±00:19 vs. 09:45±00:30, pmenor que 0.001 and 09:51±00:26 vs. 09:46±00:06, p= 0.02 for season 2005/06 and 2006/07, respectively). Compared to the first season, completion of the time trial run was faster in the second season (6.6%, pmenor que 0.01 and 6.4%, pmenor que 0.01, for C-R and R test, respectively) only in TID. Changes in post-cycling run performance were accompanied by changes in pacing strategy but only slight or non-significant changes in the cardiorespiratory response. Thus, the negative effect of cycling on performance may persist, independently of the period, over two consecutive seasons in TID and SE triathletes; however A improvements over time suggests that monitoring running pacing strategy after cycling may be a useful tool to control performance and training adaptations in TID. O2max 77.0±5.6 vs. 77.8±3.6 mL·kg-1·min-1, NS) underwent three TE D EP C C

Computerized Three-Dimmensional Craniofacial Reconstruction from Skulls Based on Landmarks.

Human identification from a skull is a critical process in legal and forensic medicine, specially when no other means are available. Traditional clay-based methods attempt to generate the human face, in order to identify the corresponding person. However, these reconstructions lack of objectivity and consistence, since they depend on the practitioner. Current computerized techniques are based on facial models, which introduce undesired facial features when the final reconstruction is built. This paper presents an objective 3D craniofacial reconstruction technique, implemented in a graphic application, without using any facial template. The only information required by the software tool is the 3D image of the target skull and three parameters: age, gender and Body Mass Index (BMI) of the individual. Complexity is minimized, since the application database only consists of the anthropological information provided by soft tissue depth values in a set of points of the skull.

Research lines in Hyperthermia at the Bioinstrumentation Laboratory of the Centre for Biomedical Technology

The Bioinstrumentation Laboratory belongs to the Centre for Biomedical Technology (CTB) of the Technical University of Madrid and its main objective is to provide the scientific community with devices and techniques for the characterization of micro and nanostructures and consequently finding their best biomedical applications. Hyperthermia (greek word for “overheating”) is defined as the phenomenon that occurs when a body is exposed to an energy generating source that can produce a rise in temperature (42-45ºC) for a given time [1]. Specifically, the aim of the hyperthermia methods used in The Bioinstrumentation Laboratory is the development of thermal therapies, some of these using different kinds of nanoparticles, to kill cancer cells and reduce the damage on healthy tissues. The optical hyperthermia is based on noble metal nanoparticles and laser irradiation. This kind of nanoparticles has an immense potential associated to the development of therapies for cancer on account of their Surface Plasmon Resonance (SPR) enhanced light scattering and absorption. In a short period of time, the absorbed light is converted into localized heat, so we can take advantage of these characteristics to heat up tumor cells in order to obtain the cellular death [2]. In this case, the laboratory has an optical hyperthermia device based on a continuous wave laser used to kill glioblastoma cell lines (1321N1) in the presence of gold nanorods (Figure 1a). The wavelength of the laser light is 808 nm because the penetration of the light in the tissue is deeper in the Near Infrared Region. The first optical hyperthermia results show that the laser irradiation produces cellular death in the experimental samples of glioblastoma cell lines using gold nanorods but is not able to decrease the cellular viability of cancer cells in samples without the suitable nanorods (Figure 1b) [3]. The generation of magnetic hyperthermia is performed through changes of the magnetic induction in magnetic nanoparticles (MNPs) that are embedded in viscous medium. The Figure 2 shows a schematic design of the AC induction hyperthermia device in magnetic fluids. The equipment has been manufactured at The Bioinstrumentation Laboratory. The first block implies two steps: the signal selection with frequency manipulation option from 9 KHz to 2MHz, and a linear output up to 1500W. The second block is where magnetic field is generated ( 5mm, 10 turns). Finally, the third block is a software control where the user can establish initial parameters, and also shows the temperature response of MNPs due to the magnetic field applied [4-8]. The Bioinstrumentation Laboratory in collaboration with the Mexican company MRI-DT have recently implemented a new research line on Nuclear Magnetic Resonance Hyperthermia, which is sustained on the patent US 7,423,429B2 owned by this company. This investigation is based on the use of clinical MRI equipment not only for diagnosis but for therapy [9]. This idea consists of two main facts: Magnetic Resonance Imaging can cause focal heating [10], and the differentiation in resonant frequency between healthy and cancer cells [11]. To produce only heating in cancer cells when the whole body is irradiated, it is necessary to determine the specific resonant frequency of the target, using the information contained in the spectra of the area of interest. Then, special RF pulse sequence is applied to produce fast excitation and relaxation mechanism that generates temperature increase of the tumor, causing cellular death or metabolism malfunction that stops cellular division

A computer vision approach for weeds identification through Support Vector Machines

This paper outlines an automatic computervision system for the identification of avena sterilis which is a special weed seed growing in cereal crops. The final goal is to reduce the quantity of herbicide to be sprayed as an important and necessary step for precision agriculture. So, only areas where the presence of weeds is important should be sprayed. The main problems for the identification of this kind of weed are its similar spectral signature with respect the crops and also its irregular distribution in the field. It has been designed a new strategy involving two processes: image segmentation and decision making. The image segmentation combines basic suitable image processing techniques in order to extract cells from the image as the low level units. Each cell is described by two area-based attributes measuring the relations among the crops and weeds. The decision making is based on the SupportVectorMachines and determines if a cell must be sprayed. The main findings of this paper are reflected in the combination of the segmentation and the SupportVectorMachines decision processes. Another important contribution of this approach is the minimum requirements of the system in terms of memory and computation power if compared with other previous works. The performance of the method is illustrated by comparative analysis against some existing strategies.

An image segmentation based on a genetic algorithm for determining soil coverage by crop residues

Determination of the soil coverage by crop residues after ploughing is a fundamental element of Conservation Agriculture. This paper presents the application of genetic algorithms employed during the fine tuning of the segmentation process of a digital image with the aim of automatically quantifying the residue coverage. In other words, the objective is to achieve a segmentation that would permit the discrimination of the texture of the residue so that the output of the segmentation process is a binary image in which residue zones are isolated from the rest. The RGB images used come from a sample of images in which sections of terrain were photographed with a conventional camera positioned in zenith orientation atop a tripod. The images were taken outdoors under uncontrolled lighting conditions. Up to 92% similarity was achieved between the images obtained by the segmentation process proposed in this paper and the templates made by an elaborate manual tracing process. In addition to the proposed segmentation procedure and the fine tuning procedure that was developed, a global quantification of the soil coverage by residues for the sampled area was achieved that differed by only 0.85% from the quantification obtained using template images. Moreover, the proposed method does not depend on the type of residue present in the image. The study was conducted at the experimental farm “El Encín” in Alcalá de Henares (Madrid, Spain).

Novel Inductor‐less Conversion Strategy Based on Multiphase Transformer‐Coupled Converters: Analysis, Design and Applications

There are many the requirements that modern power converters should fulfill. Most of the applications where these converters are used, demand smaller converters with high efficiency, improved power density and a fast dynamic response. For instance, loads like microprocessors demand aggressive current steps with very high slew rates (100A/mus and higher); besides, during these load steps, the supply voltage of the microprocessor should be kept within tight limits in order to ensure its correct performance. The accomplishment of these requirements is not an easy task; complex solutions like advanced topologies - such as multiphase converters- as well as advanced control strategies are often needed. Besides, it is also necessary to operate the converter at high switching frequencies and to use capacitors with high capacitance and low ESR. Improving the dynamic response of power converters does not rely only on the control strategy but also the power topology should be suited to enable a fast dynamic response. Moreover, in later years, a fast dynamic response does not only mean accomplishing fast load steps but output voltage steps are gaining importance as well. At least, two applications that require fast voltage changes can be named: Low power microprocessors. In these devices, the voltage supply is changed according to the workload and the operating frequency of the microprocessor is changed at the same time. An important reduction in voltage dependent losses can be achieved with such changes. This technique is known as Dynamic Voltage Scaling (DVS). Another application where important energy savings can be achieved by means of changing the supply voltage are Radio Frequency Power Amplifiers. For example, RF architectures based on ‘Envelope Tracking’ and ‘Envelope Elimination and Restoration’ techniques can take advantage of voltage supply modulation and accomplish important energy savings in the power amplifier. However, in order to achieve these efficiency improvements, a power converter with high efficiency and high enough bandwidth (hundreds of kHz or even tens of MHz) is necessary in order to ensure an adequate supply voltage. The main objective of this Thesis is to improve the dynamic response of DC-DC converters from the point of view of the power topology. And the term dynamic response refers both to the load steps and the voltage steps; it is also interesting to modulate the output voltage of the converter with a specific bandwidth. In order to accomplish this, the question of what is it that limits the dynamic response of power converters should be answered. Analyzing this question leads to the conclusion that the dynamic response is limited by the power topology and specifically, by the filter inductance of the converter which is found in series between the input and the output of the converter. The series inductance is the one that determines the gain of the converter and provides the regulation capability. Although the energy stored in the filter inductance enables the regulation and the capability of filtering the output voltage, it imposes a limitation which is the concern of this Thesis. The series inductance stores energy and prevents the current from changing in a fast way, limiting the slew rate of the current through this inductor. Different solutions are proposed in the literature in order to reduce the limit imposed by the filter inductor. Many publications proposing new topologies and improvements to known topologies can be found in the literature. Also, complex control strategies are proposed with the objective of improving the dynamic response in power converters. In the proposed topologies, the energy stored in the series inductor is reduced; examples of these topologies are Multiphase converters, Buck converter operating at very high frequency or adding a low impedance path in parallel with the series inductance. Control techniques proposed in the literature, focus on adjusting the output voltage as fast as allowed by the power stage; examples of these control techniques are: hysteresis control, V 2 control, and minimum time control. In some of the proposed topologies, a reduction in the value of the series inductance is achieved and with this, the energy stored in this magnetic element is reduced; less stored energy means a faster dynamic response. However, in some cases (as in the high frequency Buck converter), the dynamic response is improved at the cost of worsening the efficiency. In this Thesis, a drastic solution is proposed: to completely eliminate the series inductance of the converter. This is a more radical solution when compared to those proposed in the literature. If the series inductance is eliminated, the regulation capability of the converter is limited which can make it difficult to use the topology in one-converter solutions; however, this topology is suitable for power architectures where the energy conversion is done by more than one converter. When the series inductor is eliminated from the converter, the current slew rate is no longer limited and it can be said that the dynamic response of the converter is independent from the switching frequency. This is the main advantage of eliminating the series inductor. The main objective, is to propose an energy conversion strategy that is done without series inductance. Without series inductance, no energy is stored between the input and the output of the converter and the dynamic response would be instantaneous if all the devices were ideal. If the energy transfer from the input to the output of the converter is done instantaneously when a load step occurs, conceptually it would not be necessary to store energy at the output of the converter (no output capacitor COUT would be needed) and if the input source is ideal, the input capacitor CIN would not be necessary. This last feature (no CIN with ideal VIN) is common to all power converters. However, when the concept is actually implemented, parasitic inductances such as leakage inductance of the transformer and the parasitic inductance of the PCB, cannot be avoided because they are inherent to the implementation of the converter. These parasitic elements do not affect significantly to the proposed concept. In this Thesis, it is proposed to operate the converter without series inductance in order to improve the dynamic response of the converter; however, on the other side, the continuous regulation capability of the converter is lost. It is said continuous because, as it will be explained throughout the Thesis, it is indeed possible to achieve discrete regulation; a converter without filter inductance and without energy stored in the magnetic element, is capable to achieve a limited number of output voltages. The changes between these output voltage levels are achieved in a fast way. The proposed energy conversion strategy is implemented by means of a multiphase converter where the coupling of the phases is done by discrete two-winding transformers instead of coupledinductors since transformers are, ideally, no energy storing elements. This idea is the main contribution of this Thesis. The feasibility of this energy conversion strategy is first analyzed and then verified by simulation and by the implementation of experimental prototypes. Once the strategy is proved valid, different options to implement the magnetic structure are analyzed. Three different discrete transformer arrangements are studied and implemented. A converter based on this energy conversion strategy would be designed with a different approach than the one used to design classic converters since an additional design degree of freedom is available. The switching frequency can be chosen according to the design specifications without penalizing the dynamic response or the efficiency. Low operating frequencies can be chosen in order to favor the efficiency; on the other hand, high operating frequencies (MHz) can be chosen in order to favor the size of the converter. For this reason, a particular design procedure is proposed for the ‘inductorless’ conversion strategy. Finally, applications where the features of the proposed conversion strategy (high efficiency with fast dynamic response) are advantageus, are proposed. For example, in two-stage power architectures where a high efficiency converter is needed as the first stage and there is a second stage that provides the fine regulation. Another example are RF power amplifiers where the voltage is modulated following an envelope reference in order to save power; in this application, a high efficiency converter, capable of achieving fast voltage steps is required. The main contributions of this Thesis are the following: The proposal of a conversion strategy that is done, ideally, without storing energy in the magnetic element. The validation and the implementation of the proposed energy conversion strategy. The study of different magnetic structures based on discrete transformers for the implementation of the proposed energy conversion strategy. To elaborate and validate a design procedure. To identify and validate applications for the proposed energy conversion strategy. It is important to remark that this work is done in collaboration with Intel. The particular features of the proposed conversion strategy enable the possibility of solving the problems related to microprocessor powering in a different way. For example, the high efficiency achieved with the proposed conversion strategy enables it as a good candidate to be used for power conditioning, as a first stage in a two-stage power architecture for powering microprocessors.

Adaptive liquid-crystal phase-only passive devices

This PhD work is focused on liquid crystal based tunable phase devices with special emphasis on their design and manufacturing. In the course of the work a number of new manufacturing technologies have been implemented in the UPM clean room facilities, leading to an important improvement in the range of devices being manufactured in the laboratory. Furthermore, a number of novel phase devices have been developed, all of them including novel electrodes, and/or alignment layers. The most important manufacturing progress has been the introduction of reactive ion etching as a tool for achieving high resolution photolithography on indium-tin-oxide (ITO) coated glass and quartz substrates. Another important manufacturing result is the successful elaboration of a binding protocol of anisotropic conduction adhesives. These have been employed in high density interconnections between ITO-glass and flexible printed circuits. Regarding material characterization, the comparative study of nonstoichiometric silicon oxide (SiOx) and silica (SiO2) inorganic alignment layers, as well as the relationship between surface layer deposition, layer morphology and liquid crystal electrooptical response must be highlighted, together with the characterization of the degradation of liquid crystal devices in simulated space mission environment. A wide variety of phase devices have been developed, with special emphasis on beam steerers. One of these was developed within the framework of an ESA project, and consisted of a high density reconfigurable 1D blaze grating, with a spatial separation of the controlling microelectronics and the active, radiation exposed, area. The developed devices confirmed the assumption that liquid crystal devices with such a separation of components, are radiation hard, and can be designed to be both vibration and temperature sturdy. In parallel to the above, an evenly variable analog beam steering device was designed, manufactured and characterized, providing a narrow cone diffraction free beam steering. This steering device is characterized by a very limited number of electrodes necessary for the redirection of a light beam. As few as 4 different voltage levels were needed in order to redirect a light beam. Finally at the Wojskowa Akademia Techniczna (Military University of Technology) in Warsaw, Poland, a wedged analog tunable beam steering device was designed, manufactured and characterized. This beam steerer, like the former one, was designed to resist the harsh conditions both in space and in the context of the shuttle launch. Apart from the beam steering devices, reconfigurable vortices and modal lens devices have been manufactured and characterized. In summary, during this work a large number of liquid crystal devices and liquid crystal device manufacturing technologies have been developed. Besides their relevance in scientific publications and technical achievements, most of these new devices have demonstrated their usefulness in the actual work of the research group where this PhD has been completed. El presente trabajo de Tesis se ha centrado en el diseño, fabricación y caracterización de nuevos dispositivos de fase basados en cristal líquido. Actualmente se están desarrollando dispositivos basados en cristal líquido para aplicaciones diferentes a su uso habitual como displays. Poseen la ventaja de que los dispositivos pueden ser controlados por bajas tensiones y no necesitan elementos mecánicos para su funcionamiento. La fabricación de todos los dispositivos del presente trabajo se ha realizado en la cámara limpia del grupo. La cámara limpia ha sido diseñada por el grupo de investigación, es de dimensiones reducidas pero muy versátil. Está dividida en distintas áreas de trabajo dependiendo del tipo de proceso que se lleva a cabo. La cámara limpia está completamente cubierta de un material libre de polvo. Todas las entradas de suministro de gas y agua están selladas. El aire filtrado es constantemente bombeado dentro de la zona limpia, a fin de crear una sobrepresión evitando así la entrada de aire sin filtrar. Las personas que trabajan en esta zona siempre deben de estar protegidas con un traje especial. Se utilizan trajes especiales que constan de: mono, máscara, guantes de látex, gorro, patucos y gafas de protección UV, cuando sea necesario. Para introducir material dentro de la cámara limpia se debe limpiar con alcohol y paños especiales y posteriormente secarlos con nitrógeno a presión. La fabricación debe seguir estrictamente unos pasos determinados, que pueden cambiar dependiendo de los requerimientos de cada dispositivo. Por ello, la fabricación de dispositivos requiere la formulación de varios protocolos de fabricación. Estos protocolos deben ser estrictamente respetados a fin de obtener repetitividad en los experimentos, lo que lleva siempre asociado un proceso de fabricación fiable. Una célula de cristal líquido está compuesta (de forma general) por dos vidrios ensamblados (sándwich) y colocados a una distancia determinada. Los vidrios se han sometido a una serie de procesos para acondicionar las superficies internas. La célula se llena con cristal líquido. De forma resumida, el proceso de fabricación general es el siguiente: inicialmente, se cortan los vidrios (cuya cara interna es conductora) y se limpian. Después se imprimen las pistas sobre el vidrio formando los píxeles. Estas pistas conductoras provienen del vidrio con la capa conductora de ITO (óxido de indio y estaño). Esto se hace a través de un proceso de fotolitografía con una resina fotosensible, y un desarrollo y ataque posterior del ITO sin protección. Más tarde, las caras internas de los vidrios se acondicionan depositando una capa, que puede ser orgánica o inorgánica (un polímero o un óxido). Esta etapa es crucial para el funcionamiento del dispositivo: induce la orientación de las moléculas de cristal líquido. Una vez que las superficies están acondicionadas, se depositan espaciadores en las mismas: son pequeñas esferas o cilindros de tamaño calibrado (pocos micrómetros) para garantizar un espesor homogéneo del dispositivo. Después en uno de los sustratos se deposita un adhesivo (gasket). A continuación, los sustratos se ensamblan teniendo en cuenta que el gasket debe dejar una boca libre para que el cristal líquido se introduzca posteriormente dentro de la célula. El llenado de la célula se realiza en una cámara de vacío y después la boca se sella. Por último, la conexión de los cables a la célula y el montaje de los polarizadores se realizan fuera de la sala limpia (Figura 1). Dependiendo de la aplicación, el cristal líquido empleado y los demás componentes de la célula tendrán unas características particulares. Para el diseño de los dispositivos de este trabajo se ha realizado un estudio de superficies inorgánicas de alineamiento del cristal líquido, que será de gran importancia para la preparación de los dispositivos de fase, dependiendo de las condiciones ambientales en las que vayan a trabajar. Los materiales inorgánicos que se han estudiado han sido en este caso SiOx y SiO2. El estudio ha comprendido tanto los factores de preparación influyentes en el alineamiento, el comportamiento del cristal líquido al variar estos factores y un estudio de la morfología de las superficies obtenidas.

Conductance interaction identification by means of Boltzmann distribution and mutual information analysis in conductance-based neuron models

Conductance interaction identification by means of Boltzmann distribution and mutual information analysis in conductance-based neuron models.

Maximum Likelihood Estimation of Modal Parameters in Structures Using the Expectation Maximization Algorithm

This paper presents a time-domain stochastic system identification method based on maximum likelihood estimation (MLE) with the expectation maximization (EM) algorithm. The effectiveness of this structural identification method is evaluated through numerical simulation in the context of the ASCE benchmark problem on structural health monitoring. The benchmark structure is a four-story, two-bay by two-bay steel-frame scale model structure built in the Earthquake Engineering Research Laboratory at the University of British Columbia, Canada. This paper focuses on Phase I of the analytical benchmark studies. A MATLAB-based finite element analysis code obtained from the IASC-ASCE SHM Task Group web site is used to calculate the dynamic response of the prototype structure. A number of 100 simulations have been made using this MATLAB-based finite element analysis code in order to evaluate the proposed identification method. There are several techniques to realize system identification. In this work, stochastic subspace identification (SSI)method has been used for comparison. SSI identification method is a well known method and computes accurate estimates of the modal parameters. The principles of the SSI identification method has been introduced in the paper and next the proposed MLE with EM algorithm has been explained in detail. The advantages of the proposed structural identification method can be summarized as follows: (i) the method is based on maximum likelihood, that implies minimum variance estimates; (ii) EM is a computational simpler estimation procedure than other optimization algorithms; (iii) estimate more parameters than SSI, and these estimates are accurate. On the contrary, the main disadvantages of the method are: (i) EM algorithm is an iterative procedure and it consumes time until convergence is reached; and (ii) this method needs starting values for the parameters. Modal parameters (eigenfrequencies, damping ratios and mode shapes) of the benchmark structure have been estimated using both the SSI method and the proposed MLE + EM method. The numerical results show that the proposed method identifies eigenfrequencies, damping ratios and mode shapes reasonably well even in the presence of 10% measurement noises. These modal parameters are more accurate than the SSI estimated modal parameters.

AR drone identification and navigation control at CVG-UPM

This article presents the proposal of the Computer Vision Group to the first phase of the international competition “Concurso de Ingeniería de Control 2012, Control Aut ́onomo del seguimiento de trayectorias de un vehículo cuatrirrotor”. This phase consists mainly of two parts: identifying a model and designing a trajectory controller for the AR Drone quadrotor. For the identification task, two models are proposed: a simplified model that captures only the main dynamics of the quadrotor, and a second model based on the physical laws underlying the AR Drone behavior. The trajectory controller design is based on the simplified model, whereas the physical model is used to tune the controller to attain a certain level of robust stability to model uncertainties. The controller design is simplified by the hypothesis that accurate positions sensors will be available to implement a feedback controller.

Employment rate impacts of charging the Heavy Good Vehicle corridor (Madrid-Sevilla) across Spanish regions: a Random Utility Based Multiregional Input-Output approach

The implementation of a charging policy for heavy goods vehicles in European Union (EU) member countries has been imposed to reflect costs of construction and maintenance of infrastructure as well as externalities such as congestion, accidents and environmental impact. In this context, EU countries approved the Eurovignette directive (1999/62/EC) and its amending directive (2006 /38/EC) which established a legal framework to regulate the system of tolls. Even if that regulation seek s to increase the efficien cy of freight, it will trigger direct and indirect effects on Spain’s regional economies by increasing transport costs. This paper presents the development of a multiregional Input-Output methodology (MRIO) with elastic trade coefficients to predict in terregional trade, using transport attributes integrated in multinomial logit models. This method is highly useful to carry out an ex-ante evaluation of transport policies because it involves road freight transport cost sensitivity, and determine regional distributive and substitution economic effect s of countries like Spain, characterized by socio-demographic and economic attributes, differentiated region by region. It will thus be possible to determine cost-effective strategies, given different policy scenarios. MRIO mode l would then be used to determine the impact on the employment rate of imposing a charge in the Madrid-Sevilla corridor in Spain. This methodology is important for measuring the impact on the employment rate since it is one of the main macroeconomic indicators of Spain’s regional and national economic situation. A previous research developed (DESTINO) using a MRIO method estimated employment impacts of road pricing policy across Spanish regions considering a fuel tax charge (€/liter) in the entire shortest cost path network for freight transport. Actually, it found that the variation in employment is expected to be substantial for some regions, and negligible for others. For example, in this Spanish case study of regional employment has showed reductions between 16.1% (Rioja) and 1.4% (Madrid region). This variation range seems to be related to either the intensity of freight transport in each region or dependency of regions to transport intensive economic sect ors. In fact, regions with freight transport intensive sectors will lose more jobs while regions with a predominantly service economy undergo a fairly insignificant loss of employment. This paper is focused on evaluating a freight transport vehicle-kilometer charge (€/km) in a non-tolled motorway corridor (A-4) between Madrid-Sevilla (517 Km.). The consequences of the road pricing policy implementation show s that the employment reductions are not as high as the diminution stated in the previous research because this corridor does not affect the whole freight transport system of Spain.

Language identification based on a discriminative text categorization technique

In this paper, we describe new results and improvements to a lan-guage identification (LID) system based on PPRLM previously introduced in [1] and [2]. In this case, we use as parallel phone recognizers the ones provided by the Brno University of Technology for Czech, Hungarian, and Russian lan-guages, and instead of using traditional n-gram language models we use a lan-guage model that is created using a ranking with the most frequent and discrim-inative n-grams. In this language model approach, the distance between the ranking for the input sentence and the ranking for each language is computed, based on the difference in relative positions for each n-gram. This approach is able to model reliably longer span information than in traditional language models obtaining more reliable estimations. We also describe the modifications that we have being introducing along the time to the original ranking technique, e.g., different discriminative formulas to establish the ranking, variations of the template size, the suppression of repeated consecutive phones, and a new clus-tering technique for the ranking scores. Results show that this technique pro-vides a 12.9% relative improvement over PPRLM. Finally, we also describe re-sults where the traditional PPRLM and our ranking technique are combined.