This thesis describes a robust and efficient design of Student-t based Robust Spatio-Temporal Prediction, namely, St-RSTP, to provide estimation based on observations over spatio-temporal neighbors. It is crucial to many applications in geographical information systems, medical imaging, urban planning, economy study, and climate forecasting. The proposed St-RSTP is more resilient to outliers or other small departures from model assumptions than its ancestor, the Spatio-Temporal Random Effects (STRE) model. STRE is a statistical model with linear order complexity for processing large scale spatiotemporal data. However, STRE has been shown sensitive to outliers or anomaly observations. In our design, the St-RSTP model assumes that the measurement error follows Student's t-distribution, instead of a traditional Gaussian distribution. To handle the analytical intractable inference of Student's t model, we propose an approximate inference algorithm in the framework of Expectation Propagation (EP). Extensive experimental evaluations, based on both simulation and real-life data sets, demonstrated the robustness and the efficiency of our Student-t prediction model compared with the STRE model. / Master of Science

京都大学 / 0048 / 新制・課程博士 / 博士(社会健康医学) / 甲第20289号 / 社医博第78号 / 社新制||医||9(附属図書館) / 京都大学大学院医学研究科社会健康医学系専攻 / (主査)教授 山田 亮, 教授 中山 健夫, 教授 古川 壽亮 / 学位規則第4条第1項該当 / Doctor of Public Health / Kyoto University / DFAM

No description available.

No description available.

No description available.

Woodpeckers are a group of avian species that cause damage to wooden power utility structures. In the southeastern United States, Tennessee Valley Authority (TVA), has accrued an estimated $5 million USD annually from woodpecker damage. Previous work has focused on effectiveness of reactive mitigation and restoration efforts with little investigation of preventative methods. To address this knowledge gap, this study will i) use species distribution model techniques to predict damage suitability across the TVA service area, ii) use Bayesian hierarchical community model techniques to estimate species richness of the woodpecker community in the service area, and iii) recommend target areas for increased preventative measures in the service area. The suitability map indicated that damage was most likely to occur in the southwestern portions of the TVA service area. Woodpecker species richness was stable across the environmental covariate values estimated with 2-3 species found throughout the service area.

No description available.

No description available.

We introduce new methods for preprocessing and normalization of data acquired by gas/liquid chromatography coupled with mass spectrometry (GC/LC-MS). Normalization is desired prior to subsequent statistical analysis to adjust variabilities in ion intensities that are not caused by biological differences. There are different sources of experimental bias including variabilities in sample collection, sample storage, poor experimental design, noise, etc. Also, instrument variability in experiments involving a large number of runs leads to a significant drift in intensity measurements. We propose new normalization methods based on bootstrapping, Gaussian process regression, non-negative matrix factorization (NMF), and Bayesian hierarchical models. These methods model the bias by borrowing information across runs and features. Another novel aspect is utilizing scan-level data to improve the accuracy of quantification. We evaluated the performance of our method using simulated and experimental data. In comparison with several existing methods, the proposed methods yielded significant improvement. Gas chromatography coupled with mass spectrometry (GC-MS) is one of the technologies widely used for qualitative and quantitative analysis of small molecules. In particular, GC coupled to single quadrupole MS can be utilized for targeted analysis by selected ion monitoring (SIM). However, to our knowledge, there are no software tools specifically designed for analysis of GS-SIM-MS data. We introduce SIMAT, a new R package for quantitative analysis of the levels of targeted analytes. SIMAT provides guidance in choosing fragments for a list of targets. This is accomplished through an optimization algorithm that has the capability to select the most appropriate fragments from overlapping peaks based on a pre-specified library of background analytes. The tool also allows visualization of the total ion chromatogram (TIC) of runs and extracted ion chromatogram (EIC) of analytes of interest. Moreover, retention index (RI) calibration can be performed and raw GC-SIM-MS data can be imported in netCDF or NIST mass spectral library (MSL) formats. We evaluated the performance of SIMAT using several experimental data sets. Our results demonstrate that SIMAT performs better than AMDIS and MetaboliteDetector in terms of finding the correct targets in the acquired GC-SIM-MS data and estimating their relative levels. / Ph. D.

<div>Prediction of player performance is a key component in the construction of baseball team rosters. Traditionally, the problem of predicting seasonal plate appearance outcomes has been approached univariately. That is, focusing on each outcome separately rather than jointly modeling the collection of outcomes. More recently, there has been a greater emphasis on joint modeling, thereby accounting for the correlations between outcomes. However, most of these state of the art prediction models are the proprietary property of teams or industrial sports entities and so little is available in open publications.</div><div><br></div><div>This dissertation introduces a joint modeling approach to predict seasonal plate appearance outcome vectors using a mixed-effects multinomial logistic-normal model. This model accounts for positive and negative correlations between outcomes both across and within player seasons. It is also applied to the important, yet unaddressed, problem of predicting performance for players moving between the Japanese and American major leagues.</div><div><br></div>This work begins by motivating the methodological choices through a comparison of state of the art procedures followed by a detailed description of the modeling and estimation approach that includes model t assessments. We then apply the method to longitudinal multinomial count data of baseball player-seasons for players moving between the Japanese and American major leagues and discuss the results. Extensions of this modeling framework to other similar data structures are also discussed.<br>