Introducing non-linear analysis into sustained speech characterization to improve sleep apnea detection

We present a novel approach for detecting severe obstructive sleep apnea (OSA) cases by introducing non-linear analysis into sustained speech characterization. The proposed scheme was designed for providing additional information into our baseline system, built on top of state-of-the-art cepstral domain modeling techniques, aiming to improve accuracy rates. This new information is lightly correlated with our previous MFCC modeling of sustained speech and uncorrelated with the information in our continuous speech modeling scheme. Tests have been performed to evaluate the improvement for our detection task, based on sustained speech as well as combined with a continuous speech classifier, resulting in a 10% relative reduction in classification for the first and a 33% relative reduction for the fused scheme. Results encourage us to consider the existence of non-linear effects on OSA patients' voices, and to think about tools which could be used to improve short-time analysis.

Improving automatic detection of obstructive sleep apnea through nonlinear analysis of sustained speech

We present a novel approach for the detection of severe obstructive sleep apnea (OSA) based on patients' voices introducing nonlinear measures to describe sustained speech dynamics. Nonlinear features were combined with state-of-the-art speech recognition systems using statistical modeling techniques (Gaussian mixture models, GMMs) over cepstral parameterization (MFCC) for both continuous and sustained speech. Tests were performed on a database including speech records from both severe OSA and control speakers. A 10 % relative reduction in classification error was obtained for sustained speech when combining MFCC-GMM and nonlinear features, and 33 % when fusing nonlinear features with both sustained and continuous MFCC-GMM. Accuracy reached 88.5 % allowing the system to be used in OSA early detection. Tests showed that nonlinear features and MFCCs are lightly correlated on sustained speech, but uncorrelated on continuous speech. Results also suggest the existence of nonlinear effects in OSA patients' voices, which should be found in continuous speech.

Evaluación de la contribución y el impacto de las tecnologías del habla en la detección automática del Síndrome de la Apnea Obstructiva del Sueño = Contributions and impact assessment of speech technologies on the automatic detection of severe Obstructive Sleep Apnea syndrome

La presente Tesis analiza las posibilidades que ofrecen en la actualidad las tecnologías del habla para la detección de patologías clínicas asociadas a la vía aérea superior. El estudio del habla que tradicionalmente cubre tanto la producción como el proceso de transformación del mensaje y las señales involucradas, desde el emisor hasta alcanzar al receptor, ofrece una vía de estudio alternativa para estas patologías. El hecho de que la señal emitida no solo contiene este mensaje, sino también información acerca del locutor, ha motivado el desarrollo de sistemas orientados a la identificación y verificación de la identidad de los locutores. Estos trabajos han recibido recientemente un nuevo impulso, orientándose tanto hacia la caracterización de rasgos que son comunes a varios locutores, como a las diferencias existentes entre grabaciones de un mismo locutor. Los primeros resultan especialmente relevantes para esta Tesis dado que estos rasgos podrían evidenciar la presencia de características relacionadas con una cierta condición común a varios locutores, independiente de su identidad. Tal es el caso que se enfrenta en esta Tesis, donde los rasgos identificados se relacionarían con una de la patología particular y directamente vinculada con el sistema de físico de conformación del habla. El caso del Síndrome de Apneas Hipopneas durante el Sueno (SAHS) resulta paradigmático. Se trata de una patología con una elevada prevalencia mundo, que aumenta con la edad. Los pacientes de esta patología experimentan episodios de cese involuntario de la respiración durante el sueño, que se prolongan durante varios segundos y que se reproducen a lo largo de la noche impidiendo el correcto descanso. En el caso de la apnea obstructiva, estos episodios se deben a la imposibilidad de mantener un camino abierto a través de la vía aérea, de forma que el flujo de aire se ve interrumpido. En la actualidad, el diagnostico de estos pacientes se realiza a través de un estudio polisomnográfico, que se centra en el análisis de los episodios de apnea durante el sueño, requiriendo que el paciente permanezca en el hospital durante una noche. La complejidad y el elevado coste de estos procedimientos, unidos a las crecientes listas de espera, han evidenciado la necesidad de contar con técnicas rápidas de detección, que si bien podrían no obtener tasas tan elevadas, permitirían reorganizar las listas de espera en función del grado de severidad de la patología en cada paciente. Entre otros, los sistemas de diagnostico por imagen, así como la caracterización antropométrica de los pacientes, han evidenciado la existencia de patrones anatómicos que tendrían influencia directa sobre el habla. Los trabajos dedicados al estudio del SAHS en lo relativo a como esta afecta al habla han sido escasos y algunos de ellos incluso contradictorios. Sin embargo, desde finales de la década de 1980 se conoce la existencia de patrones específicos relativos a la articulación, la fonación y la resonancia. Sin embargo, su descripción resultaba difícilmente aprovechable a través de un sistema de reconocimiento automático, pero apuntaba la existencia de un nexo entre voz y SAHS. En los últimos anos las técnicas de procesado automático han permitido el desarrollo de sistemas automáticos que ya son capaces de identificar diferencias significativas en el habla de los pacientes del SAHS, y que los distinguen de los locutores sanos. Por contra, poco se conoce acerca de la conexión entre estos nuevos resultados, los sé que habían obtenido en el pasado y la patogénesis del SAHS. Esta Tesis continua la labor desarrollada en este ámbito considerando específicamente: el estudio de la forma en que el SAHS afecta el habla de los pacientes, la mejora en las tasas de clasificación automática y la combinación de la información obtenida con los predictores utilizados por los especialistas clínicos en sus evaluaciones preliminares. Las dos primeras tareas plantean problemas simbióticos, pero diferentes. Mientras el estudio de la conexión entre el SAHS y el habla requiere de modelos acotados que puedan ser interpretados con facilidad, los sistemas de reconocimiento se sirven de un elevado número de dimensiones para la caracterización y posterior identificación de patrones. Así, la primera tarea debe permitirnos avanzar en la segunda, al igual que la incorporación de los predictores utilizados por los especialistas clínicos. La Tesis aborda el estudio tanto del habla continua como del habla sostenida, con el fin de aprovechar las sinergias y diferencias existentes entre ambas. En el análisis del habla continua se tomo como punto de partida un esquema que ya fue evaluado con anterioridad, y sobre el cual se ha tratado la evaluación y optimización de la representación del habla, así como la caracterización de los patrones específicos asociados al SAHS. Ello ha evidenciado la conexión entre el SAHS y los elementos fundamentales de la señal de voz: los formantes. Los resultados obtenidos demuestran que el éxito de estos sistemas se debe, fundamentalmente, a la capacidad de estas representaciones para describir dichas componentes, obviando las dimensiones ruidosas o con poca capacidad discriminativa. El esquema resultante ofrece una tasa de error por debajo del 18%, sirviéndose de clasificadores notablemente menos complejos que los descritos en el estado del arte y de una única grabación de voz de corta duración. En relación a la conexión entre el SAHS y los patrones observados, fue necesario considerar las diferencias inter- e intra-grupo, centrándonos en la articulación característica del locutor, sustituyendo los complejos modelos de clasificación por el estudio de los promedios espectrales. El resultado apunta con claridad hacia ciertas regiones del eje de frecuencias, sugiriendo la existencia de un estrechamiento sistemático en la sección del tracto en la región de la orofaringe, ya prevista en la patogénesis de este síndrome. En cuanto al habla sostenida, se han reproducido los estudios realizados sobre el habla continua en grabaciones de la vocal /a/ sostenida. Los resultados son cualitativamente análogos a los anteriores, si bien en este caso las tasas de clasificación resultan ser más bajas. Con el objetivo de identificar el sentido de este resultado se reprodujo el estudio de los promedios espectrales y de la variabilidad inter e intra-grupo. Ambos estudios mostraron importantes diferencias con los anteriores que podrían explicar estos resultados. Sin embargo, el habla sostenida ofrece otras oportunidades al establecer un entorno controlado para el estudio de la fonación, que también había sido identificada como una fuente de información para la detección del SAHS. De su estudio se pudo observar que, en el conjunto de datos disponibles, no existen variaciones que pudieran asociarse fácilmente con la fonación. Únicamente aquellas dimensiones que describen la distribución de energía a lo largo del eje de frecuencia evidenciaron diferencias significativas, apuntando, una vez más, en la dirección de las resonancias espectrales. Analizados los resultados anteriores, la Tesis afronta la fusión de ambas fuentes de información en un único sistema de clasificación. Con ello es posible mejorar las tasas de clasificación, bajo la hipótesis de que la información presente en el habla continua y el habla sostenida es fundamentalmente distinta. Esta tarea se realizo a través de un sencillo esquema de fusión que obtuvo un 88.6% de aciertos en clasificación (tasa de error del 11.4%), lo que representa una mejora significativa respecto al estado del arte. Finalmente, la combinación de este clasificador con los predictores utilizados por los especialistas clínicos ofreció una tasa del 91.3% (tasa de error de 8.7%), que se encuentra dentro del margen ofrecido por esquemas más costosos e intrusivos, y que a diferencia del propuesto, no pueden ser utilizados en la evaluación previa de los pacientes. Con todo, la Tesis ofrece una visión clara sobre la relación entre el SAHS y el habla, evidenciando el grado de madurez alcanzado por la tecnología del habla en la caracterización y detección del SAHS, poniendo de manifiesto que su uso para la evaluación de los pacientes ya sería posible, y dejando la puerta abierta a futuras investigaciones que continúen el trabajo aquí iniciado. ABSTRACT This Thesis explores the potential of speech technologies for the detection of clinical disorders connected to the upper airway. The study of speech traditionally covers both the production process and post processing of the signals involved, from the speaker up to the listener, offering an alternative path to study these pathologies. The fact that utterances embed not just the encoded message but also information about the speaker, has motivated the development of automatic systems oriented to the identification and verificaton the speaker’s identity. These have recently been boosted and reoriented either towards the characterization of traits that are common to several speakers, or to the differences between records of the same speaker collected under different conditions. The first are particularly relevant to this Thesis as these patterns could reveal the presence of features that are related to a common condition shared among different speakers, regardless of their identity. Such is the case faced in this Thesis, where the traits identified would relate to a particular pathology, directly connected to the speech production system. The Obstructive Sleep Apnea syndrome (OSA) is a paradigmatic case for analysis. It is a disorder with high prevalence among adults and affecting a larger number of them as they grow older. Patients suffering from this disorder experience episodes of involuntary cessation of breath during sleep that may last a few seconds and reproduce throughout the night, preventing proper rest. In the case of obstructive apnea, these episodes are related to the collapse of the pharynx, which interrupts the air flow. Currently, OSA diagnosis is done through a polysomnographic study, which focuses on the analysis of apnea episodes during sleep, requiring the patient to stay at the hospital for the whole night. The complexity and high cost of the procedures involved, combined with the waiting lists, have evidenced the need for screening techniques, which perhaps would not achieve outstanding performance rates but would allow clinicians to reorganize these lists ranking patients according to the severity of their condition. Among others, imaging diagnosis and anthropometric characterization of patients have evidenced the existence of anatomical patterns related to OSA that have direct influence on speech. Contributions devoted to the study of how this disorder affects scpeech are scarce and somehow contradictory. However, since the late 1980s the existence of specific patterns related to articulation, phonation and resonance is known. By that time these descriptions were virtually useless when coming to the development of an automatic system, but pointed out the existence of a link between speech and OSA. In recent years automatic processing techniques have evolved and are now able to identify significant differences in the speech of OSAS patients when compared to records from healthy subjects. Nevertheless, little is known about the connection between these new results with those published in the past and the pathogenesis of the OSA syndrome. This Thesis is aimed to progress beyond the previous research done in this area by addressing: the study of how OSA affects patients’ speech, the enhancement of automatic OSA classification based on speech analysis, and its integration with the information embedded in the predictors generally used by clinicians in preliminary patients’ examination. The first two tasks, though may appear symbiotic at first, are quite different. While studying the connection between speech and OSA requires simple narrow models that can be easily interpreted, classification requires larger models including a large number dimensions for the characterization and posterior identification of the observed patterns. Anyhow, it is clear that any progress made in the first task should allow us to improve our performance on the second one, and that the incorporation of the predictors used by clinicians shall contribute in this same direction. The Thesis considers both continuous and sustained speech analysis, to exploit the synergies and differences between them. On continuous speech analysis, a conventional speech processing scheme, designed and evaluated before this Thesis, was taken as a baseline. Over this initial system several alternative representations of the speech information were proposed, optimized and tested to select those more suitable for the characterization of OSA-specific patterns. Evidences were found on the existence of a connection between OSA and the fundamental constituents of the speech: the formants. Experimental results proved that the success of the proposed solution is well explained by the ability of speech representations to describe these specific OSA-related components, ignoring the noisy ones as well those presenting low discrimination capabilities. The resulting scheme obtained a 18% error rate, on a classification scheme significantly less complex than those described in the literature and operating on a single speech record. Regarding the connection between OSA and the observed patterns, it was necessary to consider inter-and intra-group differences for this analysis, and to focus on the articulation, replacing the complex classification models by the long-term average spectra. Results clearly point to certain regions on the frequency axis, suggesting the existence of a systematic narrowing in the vocal tract section at the oropharynx. This was already described in the pathogenesis of this syndrome. Regarding sustained speech, similar experiments as those conducted on continuous speech were reproduced on sustained phonations of vowel / a /. Results were qualitatively similar to the previous ones, though in this case perfomance rates were found to be noticeably lower. Trying to derive further knowledge from this result, experiments on the long-term average spectra and intraand inter-group variability ratios were also reproduced on sustained speech records. Results on both experiments showed significant differences from the previous ones obtained from continuous speech which could explain the differences observed on peformance. However, sustained speech also provided the opportunity to study phonation within the controlled framework it provides. This was also identified in the literature as a source of information for the detection of OSA. In this study it was found that, for the available dataset, no sistematic differences related to phonation could be found between the two groups of speakers. Only those dimensions which relate energy distribution along the frequency axis provided significant differences, pointing once again towards the direction of resonant components. Once classification schemes on both continuous and sustained speech were developed, the Thesis addressed their combination into a single classification system. Under the assumption that the information in continuous and sustained speech is fundamentally different, it should be possible to successfully merge the two of them. This was tested through a simple fusion scheme which obtained a 88.6% correct classification (11.4% error rate), which represents a significant improvement over the state of the art. Finally, the combination of this classifier with the variables used by clinicians obtained a 91.3% accuracy (8.7% error rate). This is within the range of alternative, but costly and intrusive schemes, which unlike the one proposed can not be used in the preliminary assessment of patients’ condition. In the end, this Thesis has shed new light on the underlying connection between OSA and speech, and evidenced the degree of maturity reached by speech technology on OSA characterization and detection, leaving the door open for future research which shall continue in the multiple directions that have been pointed out and left as future work.

Vocal tract settings in speakers suffering from obstructive sleep apnea síndrome

Automatic systems based on speech signal analysis for the early dete ction of obstructive sleep apnea (OSA) have achieved fairly high performance rates in recent years. However, a satisfactory explanation of these results has not been available. This presentation aims at explaining via an examination of the long-term spectra of OSA patients and normal control speakers these systems’ ability to discover OSA speakers on the base of all-purpose cepstral coefficients. An in terpretation of the long- term spectra in terms of the underlying tract settings suggests that the speech of OSA patients is characterized by a pharyngeal narrowing that may be captured by acoustic cues of the spectral contour of windowed speech frames. A novel interpretation of long-term spectra in terms of the first principal component of the temporal sequence of short-term amplitude-spectra is also discussed.

GMM-based classifiers for the automatic detection of obstructive sleep apnea

The aim of automatic pathological voice detection systems is to serve as tools, to medical specialists, for a more objective, less invasive and improved diagnosis of diseases. In this respect, the gold standard for those system include the usage of a optimized representation of the spectral envelope, either based on cepstral coefficients from the mel-scaled Fourier spectral envelope (Mel-Frequency Cepstral Coefficients) or from an all-pole estimation (Linear Prediction Coding Cepstral Coefficients) forcharacterization, and Gaussian Mixture Models for posterior classification. However, the study of recently proposed GMM-based classifiers as well as Nuisance mitigation techniques, such as those employed in speaker recognition, has not been widely considered inpathology detection labours. The present work aims at testing whether or not the employment of such speaker recognition tools might contribute to improve system performance in pathology detection systems, specifically in the automatic detection of Obstructive Sleep Apnea. The testing procedure employs an Obstructive Sleep Apnea database, in conjunction with GMM-based classifiers looking for a better performance. The results show that an improved performance might be obtained by using such approach.

Análisis de descriptores perceptuales para la caracterización del habla de pacientes de la apnea obstructiva del sueño

A día de hoy, a pesar de todos los avances médicos y tecnológicos, no existe una prueba capaz de diagnosticar el Síndrome de Apneas-Hipopneas durante el Sueño (SAHS) o Síndrome de Apnea del Sueño (SAS), con una prueba in-situ rápida y eficaz. La detección de este trastorno, se lleva a cabo con una prueba larga y costosa, en la que el paciente debe pasar una noche hospitalizado y monitorizado en todo momento. Con el fin de minimizar tiempo y costes de diagnóstico de esta patología, el Grupo de Aplicaciones de Procesado de Señales (GAPS) lleva años trabajando en el desarrollo de una herramienta de apoyo, basada en el análisis de la señal de voz, que proporcione una alternativa a los métodos de diagnóstico actuales. En definitiva, desarrollar una prueba in-situ capaz de diagnosticar esta enfermedad. El Síndrome de Apnea del Sueño (SAS) es un trastorno muy prevalente y con muy bajo índice de casos diagnosticados. Se define como un cuadro de somnolencia excesiva, trastornos cognitivos-conductuales, respiratorios, cardiacos, metabólicos o inflamatorios secundarios a episodios repetidos de obstrucción de la vía aérea superior (VAS) durante el sueño. Esta obstrucción se produce por el colapso de las partes blandas de la garganta, impidiendo una correcta respiración, y como consecuencia, interrupciones del sueño no consciente e hipoxia. En este contexto se ha desarrollado un Proyecto de Fin de Grado conjunto las Srtas. Laura Soria Simón y Bárbara Recarte Steegman. Se estructura en tres bloques: análisis perceptual conjunto, estudio de técnicas de clasificación (Laura) y estudio acústico (Bárbara). Los resultados y conclusiones correspondientes al estudio de las técnicas de clasificación de los descriptores perceptuales y global del proyecto, se recogen en el presente documento.

Application of Deadlock Risk Evaluation of Architectural Models

Software architectural evaluation is a key discipline used to identify, at early stages of a real-time system (RTS) development, the problems that may arise during its operation. Typical mechanisms supporting concurrency, such as semaphores, mutexes or monitors, usually lead to concurrency problems in execution time that are difficult to be identified, reproduced and solved. For this reason, it is crucial to understand the root causes of these problems and to provide support to identify and mitigate them at early stages of the system lifecycle. This paper aims to present the results of a research work oriented to the development of the tool called ‘Deadlock Risk Evaluation of Architectural Models’ (DREAM) to assess deadlock risk in architectural models of an RTS. A particular architectural style, Pipelines of Processes in Object-Oriented Architectures–UML (PPOOA) was used to represent platform-independent models of an RTS architecture supported by the PPOOA –Visio tool. We validated the technique presented here by using several case studies related to RTS development and comparing our results with those from other deadlock detection approaches, supported by different tools. Here we present two of these case studies, one related to avionics and the other to planetary exploration robotics. Copyright © 2011 John Wiley & Sons, Ltd.

Modelado de sistemas de inteligencia ambiental para el entrenamiento de las cualidades físicas

En un ejercicio no extenuante la frecuencia cardíaca (FC) guarda una relación lineal con el consumo máximo de oxígeno (V O2max) y se suele usar como uno de los parámetros de referencia para cuantificar la capacidad del sistema cardiovascular. Normalmente la frecuencia cardíaca puede remplazar el porcentaje de V O2max en las prescripciones básicas de ejercicio para la mejora de la resistencia aeróbica. Para obtener los mejores resultados en la mejora de la resistencia aeróbica, el entrenamiento de los individuos se debe hacer a una frecuencia cardíaca suficientemente alta, para que el trabajo sea de predominio dinámico con la fosforilación oxidativa como fuente energética primaria, pero no tan elevada que pueda suponer un riesgo de infarto de miocardio para el sujeto que se está entrenando. Los programas de entrenamiento de base mínima y de base óptima, con ejercicios de estiramientos para prevenir lesiones, son algunos de los programas más adecuados para el entrenamiento de la resistencia aeróbica porque maximizan los beneficios y minimizan los riesgos para el sistema cardiovascular durante las sesiones de entrenamiento. En esta tesis, se ha definido un modelo funcional para sistemas de inteligencia ambiental capaz de monitorizar, evaluar y entrenar las cualidades físicas que ha sido validado cuando la cualidad física es la resistencia aeróbica. El modelo se ha implementado en una aplicación Android utilizando la camiseta inteligente “GOW running” de la empresa Weartech. El sistema se ha comparado en el Laboratorio de Fisiología del Esfuerzo (LFE) de la Universidad Politécnica de Madrid (UPM) durante la realización de pruebas de esfuerzo. Además se ha evaluado un sistema de guiado con voz para los entrenamientos de base mínima y de base óptima. También el desarrollo del software ha sido validado. Con el uso de cuestionarios sobre las experiencias de los usuarios utilizando la aplicación se ha evaluado el atractivo de la misma. Por otro lado se ha definido una nueva metodología y nuevos tipos de cuestionarios diseñados para evaluar la utilidad que los usuarios asignan al uso de un sistema de guiado por voz. Los resultados obtenidos confirman la validez del modelo. Se ha obtenido una alta concordancia entre las medidas de FC hecha por la aplicación Android y el LFE. También ha resultado que los métodos de estimación del VO2max de los dos sistemas pueden ser intercambiables. Todos los usuarios que utilizaron el sistema de guiado por voz para entrenamientos de 10 base mínima y de base óptimas de la resistencia aeróbica consiguieron llevar a cabo las sesiones de entrenamientos con un 95% de éxito considerando unos márgenes de error de un 10% de la frecuencia cardíaca máxima teórica. La aplicación fue atractiva para los usuarios y hubo también una aceptación del sistema de guiado por voz. Se ha obtenido una evaluación psicológica positiva de la satisfacción de los usuarios que interactuaron con el sistema. En conclusión, se ha demostrado que es posible desarrollar sistemas de Inteligencia Ambiental en dispositivos móviles para la mejora de la salud. El modelo definido en la tesis es el primero modelo funcional teórico de referencia para el desarrollo de este tipo de aplicaciones. Posteriores estudios se realizarán con el objetivo de extender dicho modelo para las demás cualidades físicas que suponen modelos fisiológicos más complejos como por ejemplo la flexibilidad. Abstract In a non-strenuous exercise, the heart rate (HR) shows a linear relationship with the maximum volume of oxygen consumption (V O2max) and serves as an indicator of performance of the cardiovascular system. The heart rate replaces the %V O2max in exercise program prescription to improve aerobic endurance. In order to achieve an optimal effect during endurance training, the athlete needs to work out at a heart rate high enough to trigger the aerobic metabolism, while avoiding the high heart rates that bring along significant risks of myocardial infarction. The minimal and optimal base training programs, followed by stretching exercises to prevent injuries, are adequate programs to maximize benefits and minimize health risks for the cardiovascular system during single session training. In this thesis, we have defined an ambient intelligence system functional model that monitors, evaluates and trains physical qualities, and it has been validated for aerobic endurance. It is based on the Android System and the “GOW Running” smart shirt. The system has been evaluated during functional assessment stress testing of aerobic endurance in the Stress Physiology Laboratory (SPL) of the Technical University of Madrid (UPM). Furthermore, a voice system, designed to guide the user through minimal and optimal base training programs, has been evaluated. Also the software development has been evaluated. By means of user experience questionnaires, we have rated the attractiveness of the android application. Moreover, we have defined a methodology and a new kind of questionnaires in order to assess the user experience with the audio exercise guide system. The results obtained confirm the model. We have a high similarity between HR measurements made of our system and the one used by SPL. We have also a high correlation between the VO2max estimations of our system and the SPL system. All users, that tried the voice guidance system for minimal and optimal base training programs, were able to perform the 95% of the training session with an error lower than the 10% of theoretical maximum heart rate. The application appeared attractive to the users, and it has also been proven that the voice guidance system was useful. As result we obtained a positive evaluation of the users' satisfaction while they interacted with the system. In conclusion, it has been demonstrated that is possible to develop mobile Ambient Intelligence applications for the improvement of healthy lifestyle. AmIRTEM model is the first theoretical reference functional model for the design of this kind of applications. Further studies will be realized in order to extend the AmIRTEM model to other physical qualities whose physiological models are more complex than the aerobic endurance.

Exploring differences between phonetic classes in Sleep Apnoea Syndrome Patients using automatic speech processing techniques

This work is part of an on-going collaborative project between the medical and signal processing communities to promote new research efforts on automatic OSA (Obstructive Apnea Syndrome) diagnosis. In this paper, we explore the differences noted in phonetic classes (interphoneme) across groups (control/apnoea) and analyze their utility for OSA detection

Content Delivery System for Optimal VoD Streaming

The demand of video contents has rapidly increased in the past years as a result of the wide deployment of IPTV and the variety of services offered by the network operators. One of the services that has especially become attractive to the customers is real-time video on demand (VoD) because it offers an immediate streaming of a large variety of video contents. The price that the operators have to pay for this convenience is the increased traffic in the networks, which are becoming more congested due to the higher demand for VoD contents and the increased quality of the videos. As a solution, in this paper we propose a hierarchical network system for VoD content delivery in managed networks, which implements redistribution algorithm and a redirection strategy for optimal content distribution within the network core and optimal streaming to the clients. The system monitors the state of the network and the behavior of the users to estimate the demand for the content items and to take the right decision on the appropriate number of replicas and their best positions in the network. The system's objectives are to distribute replicas of the content items in the network in a way that the most demanded contents will have replicas closer to the clients so that it will optimize the network utilization and will improve the users' experience. It also balances the load between the servers concentrating the traffic to the edges of the network.

A Light-Weight On-Chip Monitoring Network for Dynamic Adaptation and Calibration

Current nanometer technologies suffer within-die parameter uncertainties, varying workload conditions, aging, and temperature effects that cause a serious reduction on yield and performance. In this scenario, monitoring, calibration, and dynamic adaptation become essential, demanding systems with a collection of multi purpose monitors and exposing the need for light-weight monitoring networks. This paper presents a new monitoring network paradigm able to perform an early prioritization of the information. This is achieved by the introduction of a new hierarchy level, the threshing level. Targeting it, we propose a time-domain signaling scheme over a single-wire that minimizes the network switching activity as well as the routing requirements. To validate our approach, we make a thorough analysis of the architectural trade-offs and expose two complete monitoring systems that suppose an area improvement of 40% and a power reduction of three orders of magnitude compared to previous works.

Analyzing training dependencies and posterior fusion in discriminant classification of apnoea patients based on sustained and connected speech

We present a novel approach using both sustained vowels and connected speech, to detect obstructive sleep apnea (OSA) cases within a homogeneous group of speakers. The proposed scheme is based on state-of-the-art GMM-based classifiers, and acknowledges specifically the way in which acoustic models are trained on standard databases, as well as the complexity of the resulting models and their adaptation to specific data. Our experimental database contains a suitable number of utterances and sustained speech from healthy (i.e control) and OSA Spanish speakers. Finally, a 25.1% relative reduction in classification error is achieved when fusing continuous and sustained speech classifiers. Index Terms: obstructive sleep apnea (OSA), gaussian mixture models (GMMs), background model (BM), classifier fusion.

On-chip Monitoring: A Light-Weight Interconnection Network Approach

Current nanometer technologies are subjected to several adverse effects that seriously impact the yield and performance of integrated circuits. Such is the case of within-die parameters uncertainties, varying workload conditions, aging, temperature, etc. Monitoring, calibration and dynamic adaptation have appeared as promising solutions to these issues and many kinds of monitors have been presented recently. In this scenario, where systems with hundreds of monitors of different types have been proposed, the need for light-weight monitoring networks has become essential. In this work we present a light-weight network architecture based on digitization resource sharing of nodes that require a time-to-digital conversion. Our proposal employs a single wire interface, shared among all the nodes in the network, and quantizes the time domain to perform the access multiplexing and transmit the information. It supposes a 16% improvement in area and power consumption compared to traditional approaches.

Validation of the SenseWear armband in circuit resistance training with different loads

The use of the SenseWear™ armband (SWA), an objective monitor of physical activity, is a relatively new device used by researchers to measure energy expenditure. These monitors are practical, relatively inexpensive and easy-to-use. The aim of the present study was to assess the validity of SWAs for the measurement of energy expenditure (EE) in circuit resistance training (CRT) at three different intensities in moderately active, healthy subjects. The study subjects (17 females, 12 males) undertook CRT at 30, 50 and 70% of the 15 repetition maximum for each exercise component wearing an SWA as well as an Oxycon Mobile (OM) portable metabolic system (a gold standard method for measuring EE). The EE rose as exercise intensity increased, but was underestimated by the SWAs. For women, Bland-Altman plots showed a bias of 1.13 ± 1.48 METs and 32.1 ± 34.0 kcal in favour of the OM system, while for men values of 2.33 ± 1.82 METs and 75.8 ± 50.8 kcal were recorded.

Desarrollo de una aplicación software para laboratorios remotos

Las prácticas en laboratorios forman una parte muy importante de la formación en todos los programas docentes. A pesar de esta importancia, la creación de un laboratorio no es una tarea fácil, ya que el hecho de equipar un laboratorio puede suponer un gran gasto económico, tanto inicial como posterior. Como solución, surge la educación a distancia, y en concreto los laboratorios virtuales, es decir, simulaciones de un laboratorio real utilizando modelos matemáticos. Por sus características y flexibilidad se han ido desarrollando laboratorios virtuales en el ámbito docente, pero no todas las áreas cuentan con tantas posibilidades o facilidades como en la electrónica. La mayoría de los laboratorios accesibles desde Internet que hay en la actualidad dentro de la enseñanza a distancia o formación online, son virtuales. El laboratorio que se ha desarrollado tiene como principal ventaja la realización de prácticas controlando instrumentos y circuitos reales de forma remota. El proyecto consiste en realizar un sistema software para implementar un laboratorio remoto en el área de la electrónica analógica, que pueda ser utilizado como complemento a las actividades formativas que se realizan en los laboratorios de los centros de enseñanza. El sistema completo también consta de un hardware controlado mediante buses de comunicación estándar, que permite la implementación de distintos circuitos analógicos, de tal forma que se pueda realizar prácticas sobre circuitos físicos reales. Para desarrollar un laboratorio lo más real posible, la aplicación que maneja el estudiante es un visor 3D. Con la utilización de un visor 3D lo que se pretende es tener un aumento de la realidad a la hora de realizar las prácticas de laboratorio remotamente. El sistema desarrollado cuenta con un sistema de comunicación basado en un modelo cliente-servidor: • Servidor: se encarga de procesar las acciones que realiza el cliente y controla y monitoriza los instrumentos y dispositivos del sistema hardware. • Cliente: sería el usuario final, que mediante un visor 3D comunica las acciones a realizar al servidor para que éste las procese. Practices in laboratories are a very important part of training in all educational programs. Despite this importance, the establishment of a laboratory is not an easy task, since the fact of equipping a laboratory can be a great economic budget, both initial and subsequent spending. As a solution, appears the education at distance (online), and in particular the virtual labs, namely simulations of a real laboratory by using mathematical models. Virtual laboratories in the field of teaching have been developed for its features and flexibility, but not all areas have so many possibilities or facilities as in electronics. The most accessible laboratories from the Internet that are currently accessible within the distance or e-learning (on-line) are virtual. The laboratory which has been developed has as a main advantage to make practices or exercises in the fact of controlling instruments and real circuits remotely. The project consists of making a software system in order to implement a remote laboratory in the area of analog electronics that can be used as a complement to the others training activities to be carried out. The complete system also consists of a controlled hardware by standard communication buses that allow the implementation of several analog circuits, in such a way that practices can control real physical circuits. To develop a laboratory as more realistic as possible, the application that manages the student is a 3D viewer. With the use of a 3D viewer, is intended to have an increase in reality when any student wants to access to laboratory practices remotely. The developed system has a communication system based on a model Client/Server: • Server: The system that handles actions provided by the client and controls and monitors the instruments and devices in the hardware system. • Client: The end user, which using a 3D viewer, communicates the actions to be performed at the server so that it will process them.