A study for the self similarity smile detection

[EN]This work makes an extensive experimental study of smile detection testing the Local Binary Patterns (LBP) combined with self similarity (LAC) as main descriptors of the image, along with the powerful Support Vector Machines classifier. Results show that error rates can be acceptable and the self similarity approach for the detection of smiles is suitable for real-time interaction, although there is still room for improvement.

High precision swept volume approximation with conservative error bounds

In technical design processes in the automotive industry, digital prototypes rapidly gain importance, because they allow for a detection of design errors in early development stages. The technical design process includes the computation of swept volumes for maintainability analysis and clearance checks. The swept volume is very useful, for example, to identify problem areas where a safety distance might not be kept. With the explicit construction of the swept volume an engineer gets evidence on how the shape of components that come too close have to be modified.rnIn this thesis a concept for the approximation of the outer boundary of a swept volume is developed. For safety reasons, it is essential that the approximation is conservative, i.e., that the swept volume is completely enclosed by the approximation. On the other hand, one wishes to approximate the swept volume as precisely as possible. In this work, we will show, that the one-sided Hausdorff distance is the adequate measure for the error of the approximation, when the intended usage is clearance checks, continuous collision detection and maintainability analysis in CAD. We present two implementations that apply the concept and generate a manifold triangle mesh that approximates the outer boundary of a swept volume. Both algorithms are two-phased: a sweeping phase which generates a conservative voxelization of the swept volume, and the actual mesh generation which is based on restricted Delaunay refinement. This approach ensures a high precision of the approximation while respecting conservativeness.rnThe benchmarks for our test are amongst others real world scenarios that come from the automotive industry.rnFurther, we introduce a method to relate parts of an already computed swept volume boundary to those triangles of the generator, that come closest during the sweep. We use this to verify as well as to colorize meshes resulting from our implementations.

A Data-Analytic Strategy for Protein-Biomarker Discovery: Profiling of High-Dimensional Proteomic Data for Cancer Detection

With recent advances in mass spectrometry techniques, it is now possible to investigate proteins over a wide range of molecular weights in small biological specimens. This advance has generated data-analytic challenges in proteomics, similar to those created by microarray technologies in genetics, namely, discovery of "signature" protein profiles specific to each pathologic state (e.g., normal vs. cancer) or differential profiles between experimental conditions (e.g., treated by a drug of interest vs. untreated) from high-dimensional data. We propose a data analytic strategy for discovering protein biomarkers based on such high-dimensional mass-spectrometry data. A real biomarker-discovery project on prostate cancer is taken as a concrete example throughout the paper: the project aims to identify proteins in serum that distinguish cancer, benign hyperplasia, and normal states of prostate using the Surface Enhanced Laser Desorption/Ionization (SELDI) technology, a recently developed mass spectrometry technique. Our data analytic strategy takes properties of the SELDI mass-spectrometer into account: the SELDI output of a specimen contains about 48,000 (x, y) points where x is the protein mass divided by the number of charges introduced by ionization and y is the protein intensity of the corresponding mass per charge value, x, in that specimen. Given high coefficients of variation and other characteristics of protein intensity measures (y values), we reduce the measures of protein intensities to a set of binary variables that indicate peaks in the y-axis direction in the nearest neighborhoods of each mass per charge point in the x-axis direction. We then account for a shifting (measurement error) problem of the x-axis in SELDI output. After these pre-analysis processing of data, we combine the binary predictors to generate classification rules for cancer, benign hyperplasia, and normal states of prostate. Our approach is to apply the boosting algorithm to select binary predictors and construct a summary classifier. We empirically evaluate sensitivity and specificity of the resulting summary classifiers with a test dataset that is independent from the training dataset used to construct the summary classifiers. The proposed method performed nearly perfectly in distinguishing cancer and benign hyperplasia from normal. In the classification of cancer vs. benign hyperplasia, however, an appreciable proportion of the benign specimens were classified incorrectly as cancer. We discuss practical issues associated with our proposed approach to the analysis of SELDI output and its application in cancer biomarker discovery.

Error models for microarray intensities

We derive the additive-multiplicative error model for microarray intensities, and describe two applications. For the detection of differentially expressed genes, we obtain a statistic whose variance is approximately independent of the mean intensity. For the post hoc calibration (normalization) of data with respect to experimental factors, we describe a method for parameter estimation.

Evidence of direct detection of interstellar deuterium in the local interstellar medium by IBEX

We report the first in situ measurements of neutral deuterium originating in the local interstellar medium (LISM) in Earth’s orbit. These measurements were performed with the IBEX-Lo camera on NASA’s interstellar boundary explorer (IBEX) satellite. All data from the spring observation periods of 2009 through 2011 have been analysed. In the three years of the IBEX mission time, the observation geometry and orbit allowed for a total observation time of 115.3 days for the LISM. However, the effects of the spinning spacecraft and the stepping through 8 energy channels mean that we are only observing the interstellar wind for a total time of 1.44 days, in which 2 counts for interstellar deuterium were collected. We report here a conservative number, because a possibility of systematic error or additional noise, though eliminated in our analysis to the best of our knowledge, only supports detection at a 1-sigma level. From these observations, we derive a ratio D/H = (5.8 ± 4.4) × 10-4 at 1 AU. After modelling the transport and loss of D and H from the termination shock to Earth’s orbit, we find that our result of D/HLISM = (1.6 ± 1.2) × 10-5 agrees with D/HLIC = (1.6 ± 0.4) × 10-5 for the local interstellar cloud. This weak interstellar signal is extracted from a strong terrestrial background signal consisting of sputter products from the sensor’s conversion surface. As reference, we accurately measure the terrestrial D/H ratio in these sputtered products and then discriminate this terrestrial background source. Because of the diminishing D and H signal at Earth’s orbit during the rising solar activity due to photoionisation losses and increased photon pressure, our result demonstrates that in situ measurements of interstellar deuterium in the inner heliosphere are only possible during solar minimum conditions.

Next-generation sequencing of HIV-1 RNA genomes: determination of error rates and minimizing artificial recombination.

Next-generation sequencing (NGS) is a valuable tool for the detection and quantification of HIV-1 variants in vivo. However, these technologies require detailed characterization and control of artificially induced errors to be applicable for accurate haplotype reconstruction. To investigate the occurrence of substitutions, insertions, and deletions at the individual steps of RT-PCR and NGS, 454 pyrosequencing was performed on amplified and non-amplified HIV-1 genomes. Artificial recombination was explored by mixing five different HIV-1 clonal strains (5-virus-mix) and applying different RT-PCR conditions followed by 454 pyrosequencing. Error rates ranged from 0.04-0.66% and were similar in amplified and non-amplified samples. Discrepancies were observed between forward and reverse reads, indicating that most errors were introduced during the pyrosequencing step. Using the 5-virus-mix, non-optimized, standard RT-PCR conditions introduced artificial recombinants in a fraction of at least 30% of the reads that subsequently led to an underestimation of true haplotype frequencies. We minimized the fraction of recombinants down to 0.9-2.6% by optimized, artifact-reducing RT-PCR conditions. This approach enabled correct haplotype reconstruction and frequency estimations consistent with reference data obtained by single genome amplification. RT-PCR conditions are crucial for correct frequency estimation and analysis of haplotypes in heterogeneous virus populations. We developed an RT-PCR procedure to generate NGS data useful for reliable haplotype reconstruction and quantification.

Probabilistic approach to cloud and snow detection on Advanced Very High Resolution Radiometer (AVHRR) imagery

Derivation of probability estimates complementary to geophysical data sets has gained special attention over the last years. Information about a confidence level of provided physical quantities is required to construct an error budget of higher-level products and to correctly interpret final results of a particular analysis. Regarding the generation of products based on satellite data a common input consists of a cloud mask which allows discrimination between surface and cloud signals. Further the surface information is divided between snow and snow-free components. At any step of this discrimination process a misclassification in a cloud/snow mask propagates to higher-level products and may alter their usability. Within this scope a novel probabilistic cloud mask (PCM) algorithm suited for the 1 km × 1 km Advanced Very High Resolution Radiometer (AVHRR) data is proposed which provides three types of probability estimates between: cloudy/clear-sky, cloudy/snow and clear-sky/snow conditions. As opposed to the majority of available techniques which are usually based on the decision-tree approach in the PCM algorithm all spectral, angular and ancillary information is used in a single step to retrieve probability estimates from the precomputed look-up tables (LUTs). Moreover, the issue of derivation of a single threshold value for a spectral test was overcome by the concept of multidimensional information space which is divided into small bins by an extensive set of intervals. The discrimination between snow and ice clouds and detection of broken, thin clouds was enhanced by means of the invariant coordinate system (ICS) transformation. The study area covers a wide range of environmental conditions spanning from Iceland through central Europe to northern parts of Africa which exhibit diverse difficulties for cloud/snow masking algorithms. The retrieved PCM cloud classification was compared to the Polar Platform System (PPS) version 2012 and Moderate Resolution Imaging Spectroradiometer (MODIS) collection 6 cloud masks, SYNOP (surface synoptic observations) weather reports, Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO) vertical feature mask version 3 and to MODIS collection 5 snow mask. The outcomes of conducted analyses proved fine detection skills of the PCM method with results comparable to or better than the reference PPS algorithm.

Comparison of the in-house made Carba-NP and Blue-Carba tests: Considerations for better detection of carbapenemase-producing Enterobacteriaceae

The in-house Carba-NP and Blue-Carba tests were compared using 30 carbapenemase- and 33 non-producing Enterobacteriaceae. Tests were read by three operators. 100% sensitivity was reported for both tests, but Carba-NP was slightly more specific than Blue-Carba (98.9% vs. 91.7%). We describe potential sources of error during tests' preparation and reading.

THE RELATIONSHIP BETWEEN DEGREE OF BLOOD PRESSURE REDUCTION AND MORTALITY AMONG HYPERTENSIVES IN THE HYPERTENSION DETECTION AND FOLLOW-UP PROGRAM

The relationship between degree of diastolic blood pressure (DBP) reduction and mortality was examined among hypertensives, ages 30-69, in the Hypertension Detection and Follow-up Program (HDFP). The HDFP was a multi-center community-based trial, which followed 10,940 hypertensive participants for five years. One-year survival was required for inclusion in this investigation since the one-year annual visit was the first occasion where change in blood pressure could be measured on all participants. During the subsequent four years of follow-up on 10,052 participants, 568 deaths occurred. For levels of change in DBP and for categories of variables related to mortality, the crude mortality rate was calculated. Time-dependent life tables were also calculated so as to utilize available blood pressure data over time. In addition, the Cox life table regression model, extended to take into account both time-constant and time-dependent covariates, was used to examine the relationship change in blood pressure over time and mortality.^ The results of the time-dependent life table and time-dependent Cox life table regression analyses supported the existence of a quadratic function which modeled the relationship between DBP reduction and mortality, even after adjusting for other risk factors. The minimum mortality hazard ratio, based on a particular model, occurred at a DBP reduction of 22.6 mm Hg (standard error = 10.6) in the whole population and 8.5 mm Hg (standard error = 4.6) in the baseline DBP stratum 90-104. After this reduction, there was a small increase in the risk of death. There was not evidence of the quadratic function after fitting the same model using systolic blood pressure. Methodologic issues involved in studying a particular degree of blood pressure reduction were considered. The confidence interval around the change corresponding to the minimum hazard ratio was wide and the obtained blood pressure level should not be interpreted as a goal for treatment. Blood pressure reduction was attributed, not only to pharmacologic therapy, but also to regression to the mean, and to other unknown factors unrelated to treatment. Therefore, the surprising results of this study do not provide direct implications for treatment, but strongly suggest replication in other populations. ^

PDR with a foot-mounted IMU and ramp detection

The localization of persons in indoor environments is nowadays an open problem. There are partial solutions based on the deployment of a network of sensors (Local Positioning Systems or LPS). Other solutions only require the installation of an inertial sensor on the person’s body (Pedestrian Dead-Reckoning or PDR). PDR solutions integrate the signals coming from an Inertial Measurement Unit (IMU), which usually contains 3 accelerometers and 3 gyroscopes. The main problem of PDR is the accumulation of positioning errors due to the drift caused by the noise in the sensors. This paper presents a PDR solution that incorporates a drift correction method based on detecting the access ramps usually found in buildings. The ramp correction method is implemented over a PDR framework that uses an Inertial Navigation algorithm (INS) and an IMU attached to the person’s foot. Unlike other approaches that use external sensors to correct the drift error, we only use one IMU on the foot. To detect a ramp, the slope of the terrain on which the user is walking, and the change in height sensed when moving forward, are estimated from the IMU. After detection, the ramp is checked for association with one of the existing in a database. For each associated ramp, a position correction is fed into the Kalman Filter in order to refine the INS-PDR solution. Drift-free localization is achieved with positioning errors below 2 meters for 1,000-meter-long routes in a building with a few ramps.

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.

A new approach to change detection in multispectral images by means of ERGAS index

In this letter, we propose a novel method for unsupervised change detection (CD) in multitemporal Erreur Relative Globale Adimensionnelle de Synthese (ERGAS) satellite images by using the relative dimensionless global error in synthesis index locally. In order to obtain the change image, the index is calculated around a pixel neighborhood (3x3 window) processing simultaneously all the spectral bands available. With the objective of finding the binary change masks, six thresholding methods are selected. A comparison between the proposed method and the change vector analysis method is reported. The accuracy CD showed in the experimental results demonstrates the effectiveness of the proposed method.

New Approach for Correction of Error Associated With Keratometric Estimation of Corneal Power in Keratoconus

The aim of this study was to obtain the exact value of the keratometric index (nkexact) and to clinically validate a variable keratometric index (nkadj) that minimizes this error. Methods: The nkexact value was determined by obtaining differences (DPc) between keratometric corneal power (Pk) and Gaussian corneal power (PGauss c ) equal to 0. The nkexact was defined as the value associated with an equivalent difference in the magnitude of DPc for extreme values of posterior corneal radius (r2c) for each anterior corneal radius value (r1c). This nkadj was considered for the calculation of the adjusted corneal power (Pkadj). Values of r1c ∈ (4.2, 8.5) mm and r2c ∈ (3.1, 8.2) mm were considered. Differences of True Net Power with PGauss c , Pkadj, and Pk(1.3375) were calculated in a clinical sample of 44 eyes with keratoconus. Results: nkexact ranged from 1.3153 to 1.3396 and nkadj from 1.3190 to 1.3339 depending on the eye model analyzed. All the nkadj values adjusted perfectly to 8 linear algorithms. Differences between Pkadj and PGauss c did not exceed 60.7 D (Diopter). Clinically, nk = 1.3375 was not valid in any case. Pkadj and True Net Power and Pk(1.3375) and Pkadj were statistically different (P , 0.01), whereas no differences were found between PGauss c and Pkadj (P . 0.01). Conclusions: The use of a single value of nk for the calculation of the total corneal power in keratoconus has been shown to be imprecise, leading to inaccuracies in the detection and classification of this corneal condition. Furthermore, our study shows the relevance of corneal thickness in corneal power calculations in keratoconus.

Marine mammal species detection and classification

Thesis (Ph.D.)--University of Washington, 2016-04