Results 101 to 110 of about 196,185 (268)

GAUSSIAN PROCESSES FOR MACHINE LEARNING [PDF]

International Journal of Neural Systems, 2004
Gaussian processes (GPs) are natural generalisations of multivariate Gaussian random variables to infinite (countably or continuous) index sets. GPs have been applied in a large number of fields to a diverse range of ends, and very many deep theoretical analyses of various properties are available. This paper gives an introduction to Gaussian processes
openaire   +3 more sources

A Practical Noise2Noise Denoising Pipeline for High‐Throughput Raman Spectroscopy

Advanced Engineering Materials, EarlyView.
A lightweight and reproducible denoising pipeline for high‐throughput Raman spectroscopy is introduced, based on a 1D convolutional autoencoder trained with a Noise2Noise strategy. Using only repeated short‐exposure acquisitions, the method suppresses stochastic noise without reference spectra, enabling reliable spectral reconstruction while preserving
David Martin‐Calle, Cesar Alvarez‐Llamas, Vincent Motto‐Ros, Christophe Dujardin, Jérémie Margueritat, David Rodney   +5 more
wiley   +1 more source

SCADA based nonparametric models for condition monitoring of a wind turbine

The Journal of Engineering, 2019
High operation and maintenance costs for offshore wind turbines push up the LCOE of offshore wind energy. Unscheduled maintenance due to unanticipated failures is the most prominent driver of the maintenance cost which reinforces the drive towards ...
Ravi Kumar Pandit, David Infield, David Infield   +2 more
doaj   +1 more source

Influence of Scan Strategies in Electron Beam Powder Bed Fusion on Solidification, Microstructure, and High‐Temperature Compressive Properties of γ′‐Strengthened Inconel 738LC

Advanced Engineering Materials, EarlyView.
Experiments and thermophysical simulations were conducted to investigate the electron beam powder bed fusion electron beam (PBF‐EB/M) process for the γ′‐strengthened nickel‐based superalloy Inconel 738LC. The results demonstrate the impact of process‐induced microstructural variations on high‐temperature mechanical behavior, providing a basis for ...
Jan Niklas Petenati, Karthik Kumar Banku, Prasanth Bondi, Ivan Zhirnov, Yangyiwei Yang, Gordon Schmidt, Jürgen Christen, Georg Hasemann, Manja Krüger, Bai‐Xiang Xu, Bilal Gökce, Silja‐Katharina Rittinghaus   +11 more
wiley   +1 more source

POLYNOMIAL-GAUSSIAN VECTORS AND POLYNOMIAL-GAUSSIAN PROCESSES

Demonstratio Mathematica, 2001
Let \({\mathbf X}_d=(X_1,\dots, X_d)\) denote a \(d\)-dimensional r.v., the density of which is a product of a nonnegative polynomial in \(x_1\) and a \(d\)-dimensional Gaussian density. \({\mathbf X}_d\) has a \(d\)-dimensional polynomial-Gaussian distribution \((\text{PGD}_d)\).
Plucińska, Agnieszka, Bisińska, Monika
openaire   +2 more sources

On the Effect of Creep on Local Lattice Orientation in Single‐Crystal Ni‐Based Superalloy Microstructures

Advanced Engineering Materials, EarlyView.
During creep of a single‐crystal Ni‐based superalloy, the overall crystal orientation is observed to remain constant while the microstructure evolves. Despite the lack of macroscopic rotation, small (<1°) rotations are observed on the submicron size scale and are accommodated by counteracting rotations over the scale of several micrometers.
E. J. Payton, E. B. Dursun, G. Eggeler, L. Agudo Jácome   +3 more
wiley   +1 more source

Analytical approach for the calculation of promoter activities based on fluorescent protein expression data

Engineering Biology, 2017
Characterisation of promoters, repressors, enhancers and so on, is not only essential for unravelling the inner workings of gene regulation, but also to enable the rational engineering of novel synthetic elements. Each putative regulatory region requires
Konstantinos Markakis, Aitor De Las Heras, Alistair Elfick   +2 more
doaj   +1 more source

Integration of OpenCV‐Based Microscopic Adhesive Volume Measurement Into a Pyiron Workflow for Automated Data Analysis

Advanced Engineering Materials, EarlyView.
Residual adhesive after electrode loading in adhesive‐assisted resistance spot welding is quantified through a traceable experimental‐to‐digital workflow. Chromatic confocal topography provides calibrated surface‐height data, while OpenCV detects the electrode imprint and integrates adhesive height into comparable volume metrics.
Sung‐Min Wi, Jiangdong Zhao
wiley   +1 more source

Uniform Amorphization of Crystalline Silicon Surfaces Enabled by Deep Ultraviolet Femtosecond Laser Pulses

Advanced Engineering Materials, EarlyView.
Deep‐UV (258 nm) femtosecond pulses enable uniform amorphous silicon writing on Si(100)/(111) with a six‐fold larger fluence amorphization window than NIR methods. Optimized fluence and overlap yield 20–45 nm uniform and continuous amorphous layers. Microscopy shows sharp interfaces, and real‐time reflectivity reveals nanosecond melt–resolidification ...
Wissal Benali, Magali Gregoire, Matys Guyard, Tatiana Itina, David Grojo, Pol Sopeña   +5 more
wiley   +1 more source

Gaussian Process Landmarking on Manifolds

SIAM Journal on Mathematics of Data Science, 2019
As a means of improving analysis of biological shapes, we propose an algorithm for sampling a Riemannian manifold by sequentially selecting points with maximum uncertainty under a Gaussian process model. This greedy strategy is known to be near-optimal in the experimental design literature, and appears to outperform the use of user-placed landmarks in ...
Tingran Gao, Shahar Z. Kovalsky, Ingrid Daubechies   +2 more
openaire   +3 more sources