Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 53 for “"Leave-one-out"”.
-
Analytic Study of Performance of Error Estimators for Linear Discriminant Analysis with Applications in Genomics
… its commonly used estimators, resubstitution and leave-one-out, as well as their marginal and mixed moments, in the context of the Linear Discriminant Analysis (LDA) classification rule. In the first part of this dissertation, we obtain the joint sampling distribution of the actual and estimated …
-
Recursive methods for statistical prediction with applications
… and it is especially useful in calculating the leave-one-out estimates. Two cross validation functions (Kullback-Leibler and least squares cross validation) for estimating the smoothing parameter in the generalized smoothing splines are discussed. The simulation results showed that these two …
-
Near-Surface Air Temperature in Complex Terrain: Daily Predictions of Fine-Scale (30 m) Temperature in the Snake Range, Nevada, USA
… temperature is arguably the most important component of the mountain climate, and scientists have been studying it for centuries. Recently, researchers have used arrays of inexpensive temperature sensors to observe and understand temperature across the landscape. Much of this work has focused on …
-
Localized Method of Approximate Particular Solutions for Solving Fourth-Order PDEs
… suitable shape parameter; calculated using LOOCV(Leave-One-Out-Cross-Validation) Algorithm. The effectiveness of this Method was evident when we compared the results from two numerical examples.</p>
-
Biologically-Interpretable Disease Classification Based on Gene Expression Data
… Our classifier achieves high-accuracy on leave-one-out cross-validation on both two-class and multi-class data. Our technique has the potential to be the method of choice for researchers interested in disease and tissue classification.
-
Multi-scale Deep Nearest Neighbors
… k-NN. Our approach is based on minimizing the leave-one-out 1-NN classification error in the embedding space. Directly optimizing for such a rule is not tractable due to its discontinuous nature. We propose Multi-scale Deep Nearest Neighbour (MsDNN) which is a differentiable loss function that …
-
Effects of discrete wavelet compression on automated mammographic shape recognition
… and stellate. Presently this classification is done by experienced radiologists. In order to increase the speed and decrease the cost of diagnosis, automated recognition systems are being developed. This study analyses an automated classification procedure and its sensitivity to wavelet based …
-
Topics in multivariate covariance estimation and time series analysis.
… covariance regularization methods into one framework. The original idea and known extensions involve cross-validating in potentially high di- mensions, and can be highly computational. We propose using the Kullback-Leibler divergence as an optimization method to estimate a linear …
-
Development of pharmacophore and CoMFA studies for sigma2 receptor ligands
… of each calculation and molecule. With "leave-one-out" cross validation, the numbers of optimal components was determined. No cross validation was performed in a training set using the optimal components for each analysis. After the completion of a test set, it was verified that CoMIFA …
-
Determination of Reservoir Characteristics Using Geostatistical Analysis
… of lithologic reservoirs because only one secondary attribute is incorporated. To decrease the uncertainty and improve the definition of the final estimate, two modified techniques, cokriging with multiple secondary attributes and block cokriging with multiple secondary attributes, are …
-
Análisis de encuestas basado en diseño y modelos muestrales: una comparación entre métodos de inferencia aplicados al estudio de la vocación emprendedora en alumnos universitarios
… de datos binarios correlacionados. Se propone la formulación de modelos marginales y de modelos mixtos basados en las funciones de verosimilitud completa y condicional, con enlace logístico. El diagnóstico del modelo no resulta posible debido a: (a) la falta de una función de verosimilitud …
-
Development of pharmacophore and comfa study of rigid and flexible sigma 2 receptor ligands
… molecules (R2 = 0.999) from B3LYP/6-31G*. The "leave-one-out" cross validation method gave (q2 = 0.602) using four optimal components with optimized geometries and atomic charges. This analysis produced a standard error of estimate of 0.028. The CoMFA results derived from the B3LYP/6-31G* method …
-
Ancestry determination using geometric morphometrics
… focused specifically on features routinely used to make ancestry assessments using traditional morphological and morphometric techniques, are used to classify ancestry using discriminant function analyses with leave-one-out cross validation. Landmarks and semilandmarks were captured …
-
Ανάπτυξη συστήματος επεξεργασίας δεδομένων τηλεπισκόπησης για αυτόματη ανίχνευση και ταξινόμηση περιοχών με περιβαλλοντικές αλλοιώσεις
… της πρώτης και δεύτερης τάξης αυτής. Η μέθοδος leave one out χρησιμοποιείται για τον εντοπισμό των χαρακτηριστικών που μπορούν να διαχωρίσουν τα δείγματα ανά ζεύγη τάξεων στα οποία αντιστοιχίζεται και ένας ξεχωριστός και ανεξάρτητος γραμμικός ταξινομητής. Η τελική ταξινόμηση γίνεται με τη μέθοδο …
-
A regularization framework for active learning from imbalanced data
… is robust to noisy, imbalanced samples, and outputs confidence scores along with its predications. These goals address critical steps along the entire classification pipeline that pertain to collecting data, training, and classifying. To this end, we investigate the merits of a classification …
-
Learning manifolds with the Parametrized Self-Organizing Map and Unsupervised Kernel Regression
… and it can be regularized automatically by using leave-one-out cross-validation without additional computational cost. The low dimensional coordinates (latent variables) together with a mapping from latent space to data space are retrieved by minimizing some error criterion. The third part …
-
Leveraging Machine Learning to Identify Proteomic Biomarkers of Tibial Bone Stress Reinjury
Bone stress injuries (BSIs) are experienced by up to 20% of runners, with one in five of these athletes sustaining an additional BSI [1], [2]. Yet the underlying biological factors contributing to refracture risk remain elusive. In this study, we present a longitudinal exploration of 1500 serum …
-
Investigation of Quatitative Image Features From Pretreatment Ct and Fdg-Pet Scans In Stage Iii Nsclc Patients Undergoing Defintive Radiation Therapy
… could provide prognostic information to improve outcome models. Our goal for this work was to determine if it may one day be feasible to incorporate QIFs into personalized cancer care. QIFs were used to quantitatively characterize patient disease as seen on imaging. A leave-one-out …
-
In vivo and ex vivo techniques using elastic scattering spectroscopy for diagnosis of malignancy in the thyroid gland
… The spectra were analyzed using principal component analysis, linear discriminant analysis and leave one out technique. The in vivo ESS study was conceptually designed and IRB approval from Boston Medical Campus was obtained. RESULTS: The ex vivo study showed that ESS could predict the …
-
Statistical Methods for Complex and/or High Dimensional Data
… $p/n$ tending to a finite number, and data with outlier observations. First, we propose a non-negative feature selection and/or feature grouping (nnFSG) method. It deals with a general series of sign-constrained high-dimensional regression problems, which allows the regression coefficients to …
Page 1 of 3