No description available.

This study examines the effects of expanding the classical P300 feature space on the classification performance of data collected from a P300 speller paradigm [Farwell LA, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroenceph Clin Neurophysiol 1988;70:510-23]. Using stepwise linear discriminant analysis (SWLDA) to construct a classifier, the effects of spatial channel selection, channel referencing, data decimation, and maximum number of model features are compared with the intent of establishing a baseline not only for the SWLDA classifier, but for related P300 speller classification methods in general. By supplementing the classical P300 recording locations with posterior locations, online classification performance of P300 speller responses can be significantly improved using SWLDA and the favorable parameters derived from the offline comparative analysis.

Stylometry assumes that the essence of the individual style of an author can be captured using a number of quantitative criteria, such as the relative frequencies of noncontextual words (e.g., or, the, and, etc.). Several statistical methodologies have been developed for authorship analysis. Jockers et al. (2009) utilize Nearest Shrunken Centroid (NSC) classification, a promising classification methodology in DNA microarray analysis for authorship analysis of the Book of Mormon. Schaalje et al. (2010) develop an extended NSC classification to remedy the problem of a missing author. Dabney (2005) and Koppel et al. (2009) suggest other modifications of NSC. This paper develops a full Bayesian classifier and compares its performance to five versions of the NSC classifier using the Federalist Papers, the Book of Mormon text blocks, and the texts of seven other authors. The full Bayesian classifier was superior to all other methods.

No description available.

This study used personal interviews with Turkish female grocery shoppers to determine their shopping behaviors and attitudes. The sample was divided into two groups: deliberate and nondeliberate shoppers. The two groups were then compared in terms of their sociodemographic characteristics, importance placed on patronage motives, purchase location of selected grocery products, and their attitudinal orientations. Results are outlined and implications discussed.

No description available.

No description available.

No description available.

The time required for the identification of pathogens is an important determinant of infection-related mortality rates and disease spread for species of relevance in agriculture. Conventional identification methods require a processing time of at least one to twenty days. Therefore, inaccurate empirical treatments are often provided while awaiting further identification, such that most cases progress with further aggravation of symptoms, contamination of other animals or plants, generating economic loss from decreased yield, and increased mitigation costs. Thus, there is a need for innovative, non-destructive, and rapid analytical techniques that provide reagent-free, portable, reliable, and holistic approaches to detect diseases in real-time. Vibrational spectroscopy techniques have shown the capacity to provide relevant information for disease detection. In near infrared spectroscopy (NIRS), the absorbance from a sample is measured across several hundred wavelengths in the near infrared band (750-2500 nm) and is directly influenced by the number and type of chemical bonds present. In order to make NIRS an effective tool for field-based studies, a simplified procedure is needed such that NIRS can be used in minimally processed samples found in situ. Here, experiments involving the agricultural important bovine herpesvirus-1 (BoHV-1), bovine respiratory syncytial virus (BRSV), Mannheimia haemolytica (MH), Xanthomonas citri pv. malvacearum (Xcm) and Rhizoctonia solani (Rs) were carried out to determine if biological spectral signatures can be differentiated between samples from two classes (i.e., healthy vs. sick, control sample vs. test sample). The specific objectives were to (1) create a spectral library for each evaluated pathogen and disease, (2) identify and establish the characteristic NIR spectral signatures and trends by aquaphotomics and chemometrics-based MVA methods, (3) generate and evaluate models for discriminating representative spectra, (4) provide new biochemical information by the correlation of the results with pathogen development and disease states in living systems, and (5) support the groundwork for a portable, fast, non-destructive, and accurate diagnostic tool capable of reducing the existing time necessary for pathogen and disease detection.

Finite mixture modelling is a powerful and well-developed paradigm, having proven useful in unsupervised learning and, to a lesser extent supervised learning (mixture discriminant analysis), especially in the case(s) of data with local variation and/or latent variables. It is the aim of this thesis to improve upon mixture discriminant analysis by introducing two types of random forest analogues which are called Mix- Forests. The first MixForest is based on Gaussian mixture models from the famous family of Gaussian parsimonious clustering models and will be useful in classify- ing lower dimensional data. The second MixForest extends the technique to higher dimensional data via the use of mixtures of factor analyzers from the well-known family of parsimonious Gaussian mixture models. MixForests will be utilized in the analysis of real data to demonstrate potential increases in classification accuracy as well as inferential procedures such as generalization error estimation and variable importance measures. / Thesis / Doctor of Philosophy (PhD)