In the event of a natural or anthropogenic disturbance, environmental resource managers require a reliable tool to quickly assess the spatial extent of potential damage to the seagrass resource. The temporal availability of the Landsat 5 Thematic Mapper (TM) imagery, 16-20 days, provides a suitable option to detect and assess damage to the seagrass resource. In this study, remote sensing Landsat 5 TM imagery is used to map the spatial extent of the seagrass resource. Various classification techniques are applied to delineate the seagrass beds in Clearwater Harbor and St. Joseph Sound, FL. This study aims to determine the most appropriate seagrass habitat mapping technique by evaluating the accuracy and validity of the resultant classification maps. Field survey data and high resolution aerial photography are available to use as ground truth information. Seagrass habitat in the study area consists of seagrass species and rhizophytic algae; thus, the species assemblage is categorized as submerged aquatic vegetation (SAV). Two supervised classification techniques, Maximum Likelihood and Mahalanobis Distance, are applied to extract the thematic features from the Landsat imagery. The Mahalanobis Distance classification (MDC) method achieves the highest overall accuracy (86%) and validation accuracy (68%) for the delineation of the presence/absence of SAV. The Maximum Likelihood classification (MLC) method achieves the highest overall accuracy (74%) and validation accuracy (70%) for the delineation of the estimated coverage of SAV for the classes of continuous and patchy seagrass habitat. The soft classification techniques, linear spectral unmixing (LSU) and artificial neural network (ANN), did not produce reasonable results for this particular study. The comparison of the MDC and MLC to the current Seagrass Aerial Photointerpretation (AP) project indicates that the classification of SAV from Landsat 5 TM imagery provides a map product with similar accuracy to the AP maps. These results support the application of remote sensing thematic feature extraction methods to analyze the spatial extent of the seagrass resource. While the remote sensing thematic feature extraction methods from Landsat 5 TM imagery are deemed adequate, the use of hyperspectral imagery and better spectral libraries may improve the identification and mapping accuracy of the seagrass resource.

In this thesis, we describe two approaches to automatically synthesize the emotional speech of a target speaker based on the hidden Markov model for his/her neutral speech. In the interpolation based method, the basic idea is the model interpolation between the neutral model of the target speaker and an emotional model selected from a candidate pool. Both the interpolation model selection and the interpolation weight computation are determined based on a model-distance measure. We propose a monophone-based Mahalanobis distance (MBMD). In the parallel model combination (PMC) based method, our basic idea is to model the mismatch between neutral model and emotional model. We train linear regression model to describe this mismatch. And then we combine the target speaker neutral model with the linear regression model. We evaluate our approach on the synthesized emotional speech of angriness, happiness, and sadness with several subjective tests. Experimental results show that the implemented system is able to synthesize speech with emotional expressiveness of the target speaker.

Non-invasive physical examination helps to make disease diagnosis with minimum injury to the body. Cardiology ultrasound is a non-invasive examination which can be used as a auxiliary tool for diagnose cardiac structure abnormalities. With more understanding of heart diseases, it has been recognized that heart failures are closely related to left ventricular systolic and diastolic function. Following Chen (2011) and Kao (2011), we study association of heart diseases with the change of gray-scale values in the cardiology ultrasound images of left ventricular systolic and diastolic. Since data obtained from ultrasound image is of matrix type with high dimensions, following the method proposed by Chen (2011) and Kao (2011), factor scores obtained from factor analysis are used as a basis for classification. We take the factor scores of normal subjects to establish the bench mark and calculate the Mahalanobis distance of each abnormal subject with the model established by the data from normal group. Later based on this distance to the normal group, cardiac function of the subject is distinguished as normal or not. In order to improve the accuracy of the classification, influential points which may cause inaccurate covariance matrix estimate on the subjects in normal group are identified. Based on concepts from optimal designs theory, some criteria are established for screening out the influential points.

¡@¡@In this thesis, we use a hidden Markov model which can use a small amount of corpus to synthesize speech with certain quality to implement speech synthesis system for Chinese. More, the emotional speech are synthesized by the flexibility of the parametric speech in this model. We conduct model interpolation and model adaptation to synthesize speech from neutral to particular emotion without target speaker¡¦s emotional speech. In model adaptation, we use monophone-based Mahalanobis distance to select emotional models which are close to target speaker from pool of speakers, and estimate the interpolation weight to synthesize emotional speech. In model adaptation, we collect abundant of data training average voice models for each individual emotion. These models are adapted to specific emotional models of target speaker by CMLLR method. In addition, we design the Latin-square evaluation to reduce the systematic offset in the subjective tests, making results more credible and fair. We synthesize emotional speech include happiness, anger, sadness, and use Latin square design to evaluate performance in three part similarity, naturalness, and emotional expression respectively. According to result, we make a comprehensive comparison and conclusions of two method in emotional speech synthesis.

The concept of classification is used and examined by the scientific community for hundreds of years. In this historical process, different methods and algorithms have been developed and used. Today, although the classification algorithms in literature use different methods, they are acting on a similar basis. This basis is setting the desired data into classes by using defined properties, with a different discourse / an effort to establish a relationship between known features with unknown result. This study was intended to bring a different perspective to this common basis. In this study, not only the basic features of data are used, the class of the data is also included as a parameter. The aim of this method is also using the information in the algorithm that come from a known value. In other words, the class, in which the data is included, is evaluated as an input and the data set is transferred to a higher dimensional space which is a new working environment. In this new environment it is not a classification problem anymore, but a clustering problem. Although this logic is similar with Kernel Methods, the methodologies are different from the way that how they transform the working space. In the projected new space, the clusters based on calculations performed with the Mahalanobis Distance are evaluated in original space with two different heuristics which are center-based and KNN-based algorithm. In both heuristics, increase in classification success rates achieved by this methodology. For center based algorithm, which is more sensitive to new input parameter, up to 8% of enhancement is observed.

The hemlock woolly adelgid, an invasive non-native insect, is threatening eastern hemlock in Kentucky. This study examined three techniques to map the distribution of eastern hemlock using decision trees, remote sensing, and species distribution modeling. Accuracy assessments showed that eastern hemlock was best modeled using a decision tree without incorporating satellite radiance. Using the distribution from the optimal model, risk maps for susceptibility to hemlock woolly adelgid infestation were created using two species distribution models. Environmental variables related to dispersal were used to build the models and their contributions to the models assessed. The models showed similar spatial distributions of eastern hemlock at high risk of infestation.

abstract: Rapid advancements in genomic technologies have increased our understanding of rare human disease. Generation of multiple types of biological data including genetic variation from genome or exome, expression from transcriptome, methylation patterns from epigenome, protein complexity from proteome and metabolite information from metabolome is feasible. "Omics" tools provide comprehensive view into biological mechanisms that impact disease trait and risk. In spite of available data types and ability to collect them simultaneously from patients, researchers still rely on their independent analysis. Combining information from multiple biological data can reduce missing information, increase confidence in single data findings, and provide a more complete view of genotype-phenotype correlations. Although rare disease genetics has been greatly improved by exome sequencing, a substantial portion of clinical patients remain undiagnosed. Multiple frameworks for integrative analysis of genomic and transcriptomic data are presented with focus on identifying functional genetic variations in patients with undiagnosed, rare childhood conditions. Direct quantitation of X inactivation ratio was developed from genomic and transcriptomic data using allele specific expression and segregation analysis to determine magnitude and inheritance mode of X inactivation. This approach was applied in two families revealing non-random X inactivation in female patients. Expression based analysis of X inactivation showed high correlation with standard clinical assay. These findings improved understanding of molecular mechanisms underlying X-linked disorders. In addition multivariate outlier analysis of gene and exon level data from RNA-seq using Mahalanobis distance, and its integration of distance scores with genomic data found genotype-phenotype correlations in variant prioritization process in 25 families. Mahalanobis distance scores revealed variants with large transcriptional impact in patients. In this dataset, frameshift variants were more likely result in outlier expression signatures than other types of functional variants. Integration of outlier estimates with genetic variants corroborated previously identified, presumed causal variants and highlighted new candidate in previously un-diagnosed case. Integrative genomic approaches in easily attainable tissue will facilitate the search for biomarkers that impact disease trait, uncover pharmacogenomics targets, provide novel insight into molecular underpinnings of un-characterized conditions, and help improve analytical approaches that use large datasets. / Dissertation/Thesis / Doctoral Dissertation Molecular and Cellular Biology 2015

The Cettiidae, a family of primarily small, insectivorous, Asiatic and Austronesian, mountain birds have been the subject of acoustic analysis in the past. However, until this point, an in-depth review of the songs of the entire family had yet to be undertaken. In an effort to resolve this shortcoming, the songs of 29 Cettiidae species were examined through the usage of acoustic analysis software, with specific factors such as bandwidth, frequency, and strophe duration being statistically recorded. In total 286 individuals and over 800 strophes were analyzed, with the collected data being displayed in various PCA plots. These PCA graphs were then compared to both a dated phylogenetic tree specifically created for this study, and a Mahalanobis distance vs. genetic distance plot, created using the acoustic data as well as Cytochrome b genetic data. Based on these plots, several notable trends could be observed across the entire family. While largescale divergence from the norm was noted in several pairwise comparisons of species, as well as large scale conservation within clades such as the island Horornis species, examples of convergent evolution of their songs was rather scant. It was also noted that despite the strong divergence of certain species, each genus occupied its own area of multivariate space within the PCAs. Strong statistical divergence between island and continental species was also noted in both the PCAs and the Mahalanobis graph. Meanwhile, the statistical analysis of these species unfortunately provided no clues as to the ancestral state of their songs. However, a visual analysis of every species song, mapped on the dated phylogenetic tree, suggested that two distinct linages of simple and complex songs could be traced back approximately 10 million years. This allows for speculation as to the songs of now long extinct Cettiidae species as far back as the Miocene.

This research aims to identify a method for unsupervised online anomaly detection in multivariate time series in dynamic systems in general and on the case study of Devwards IoT-system in particular. A requirement of the solution is its explainability, online learning and low computational expense. A comprehensive literature review was conducted, leading to the experimentation and analysis of various anomaly detection approaches. Of the methods evaluated, a singular recurrent neural network autoencoder emerged as the most promising, emphasizing a simple model structure that encourages stable performance with consistent outputs, regardless of the average output. While other approaches such as Hierarchical Temporal Memory models and an ensemble strategy of adaptive model pooling yielded suboptimal results. A modified version of the Residual Explainer method for enhancing explainability in autoencoders for online scenarios showed promising outcomes. The use of Mahalanobis distance for anomaly detection was explored. Feature extraction and it's implications in the context of the proposed approach is explored. Conclusively, a single, streamlined recurrent neural network appears to be the superior approach for this application, though further investigation into online learning methods is warranted. The research contributes results into the field of unsupervised online anomaly detection in multivariate time series and contributes to the Residual Explainer method for online autoencoders. Additionally, it offers data on the ineffectiveness of the Mahalanobis distance in an online anomaly detection environment.

L’Imagerie par résonance magnétique (IRM) est un outil fondamental pour l’exploration in vivo du développement du cerveau chez le fœtus, le bébé et l’enfant. Elle fournit plusieurs paramètres quantitatifs qui reflètent les changements des propriétés tissulaires au cours du développement en fonction de différents processus de maturation. Cependant, l’évaluation fiable de la maturation de la substance blanche est encore une question ouverte: d'une part, aucun de ces paramètres ne peut décrire toute la complexité des changements sous-jacents; d'autre part, aucun d'eux n’est spécifique d’un processus de développement ou d’une propriété tissulaire particulière. L’implémentation d’approches multiparamétriques combinant les informations complémentaires issues des différents paramètres IRM devrait permettre d’améliorer notre compréhension du développement du cerveau. Dans ce travail de thèse, je présente deux exemples de telles approches et montre leur pertinence pour l'étude de la maturation des faisceaux de substance blanche. La première approche fournit une mesure globale de la maturation basée sur la distance de Mahalanobis calculée à partir des différents paramètres IRM (temps de relaxation T1 et T2, diffusivités longitudinale et transverse du tenseur de diffusion DTI) chez des nourrissons (âgés de 3 à 21 semaines) et des adultes. Cette approche offre une meilleure description de l’asynchronisme de maturation à travers les différents faisceaux que les approches uniparamétriques. De plus, elle permet d'estimer les délais relatifs de maturation entre faisceaux. La seconde approche vise à quantifier la myélinisation des tissus cérébraux, en calculant la fraction de molécules d’eau liées à la myéline (MWF) en chaque voxel des images. Cette approche est basée sur un modèle tissulaire avec trois composantes ayant des caractéristiques de relaxation spécifiques, lesquelles ont été pré-calibrées sur trois jeunes adultes sains. Elle permet le calcul rapide des cartes MWF chez les nourrissons et semble bien révéler la progression de la myélinisation à l’échelle cérébrale. La robustesse de cette approche a également été étudiée en simulations. Une autre question cruciale pour l'étude du développement de la substance blanche est l'identification des faisceaux dans le cerveau des enfants. Dans ce travail de thèse, je décris également la création d'un atlas préliminaire de connectivité structurelle chez des enfants âgés de 17 à 81 mois, permettant l'extraction automatique des faisceaux à partir des données de tractographie. Cette approche a démontré sa pertinence pour l'évaluation régionale de la maturation de la substance blanche normale chez l’enfant. Pour finir, j’envisage dans la dernière partie du manuscrit les applications potentielles des différentes méthodes précédemment décrites pour l’étude fine des réseaux de substance blanche dans le cadre de deux exemples spécifiques de pathologies : les épilepsies focales et la leucodystrophie métachromatique. / Magnetic Resonance Imaging (MRI) is a fundamental tool for in vivo investigation of brain development in newborns, infants and children. It provides several quantitative parameters that reflect changes in tissue properties during development depending on different undergoing maturational processes. However, reliable evaluation of the white matter maturation is still an open question: on one side, none of these parameters can describe the whole complexity of the undergoing changes; on the other side, neither of them is specific to any particular developmental process or tissue property. Developing multiparametric approaches combining complementary information from different MRI parameters is expected to improve our understanding of brain development. In this PhD work, I present two examples of such approaches and demonstrate their relevancy for investigation of maturation across different white matter bundles. The first approach provides a global measure of maturation based on the Mahalanobis distance calculated from different MRI parameters (relaxation times T1 and T2, longitudinal and transverse diffusivities from Diffusion Tensor Imaging, DTI) in infants (3-21 weeks) and adults. This approach provides a better description of the asynchronous maturation across the bundles than univariate approaches. Furthermore, it allows estimating the relative maturational delays between the bundles. The second approach aims at quantifying myelination of brain tissues by calculating Myelin Water Fraction (MWF) in each image voxel. This approach is based on a 3-component tissue model, with each model component having specific relaxation characteristics that were pre-calibrated in three healthy adult subjects. This approach allows fast computing of the MWF maps from infant data and could reveal progression of the brain myelination. The robustness of this approach was further investigated using computer simulations. Another important issue for studying white matter development in children is bundles identification. In the last part of this work I also describe creation of a preliminary atlas of white matter structural connectivity in children aged 17-81 months. This atlas allows automatic extraction of the bundles from tractography datasets. This approach demonstrated its relevance for evaluation of regional maturation of normal white matter in children. Finally, in the last part of the manuscript I describe potential future applications of the previously developed methods to investigation of the white matter in cases of two specific pathologies: focal epilepsy and metachromatic leukodystrophy.