Search results for "Synthetic data"
showing 10 items of 34 documents
On the classification of dynamical data streams using novel “Anti-Bayesian” techniques
2018
Abstract The classification of dynamical data streams is among the most complex problems encountered in classification. This is, firstly, because the distribution of the data streams is non-stationary, and it changes without any prior “warning”. Secondly, the manner in which it changes is also unknown. Thirdly, and more interestingly, the model operates with the assumption that the correct classes of previously-classified patterns become available at a juncture after their appearance. This paper pioneers the use of unreported novel schemes that can classify such dynamical data streams by invoking the recently-introduced “Anti-Bayesian” (AB) techniques. Contrary to the Bayesian paradigm, tha…
Robust Conditional Independence maps of single-voxel Magnetic Resonance Spectra to elucidate associations between brain tumours and metabolites.
2020
The aim of the paper is two-fold. First, we show that structure finding with the PC algorithm can be inherently unstable and requires further operational constraints in order to consistently obtain models that are faithful to the data. We propose a methodology to stabilise the structure finding process, minimising both false positive and false negative error rates. This is demonstrated with synthetic data. Second, to apply the proposed structure finding methodology to a data set comprising single-voxel Magnetic Resonance Spectra of normal brain and three classes of brain tumours, to elucidate the associations between brain tumour types and a range of observed metabolites that are known to b…
Development of a Novel Object Detection System Based on Synthetic Data Generated from Unreal Game Engine
2022
This paper presents a novel approach to training a real-world object detection system based on synthetic data utilizing state-of-the-art technologies. Training an object detection system can be challenging and time-consuming as machine learning requires substantial volumes of training data with associated metadata. Synthetic data can solve this by providing unlimited desired training data with automatic generation. However, the main challenge is creating a balanced dataset that closes the reality gap and generalizes well when deployed in the real world. A state-of-the-art game engine, Unreal Engine 4, was used to approach the challenge of generating a photorealistic dataset for deep learnin…
Improvement in MRS parameter estimation by joint and laterally constrained inversion of MRS and TEM data
2012
We developed a new scheme for joint and laterally constrained inversion (LCI) of magnetic resonance sounding (MRS) data and transient electromagnetic (TEM) data, which greatly improves the estimation of the MRS model parameters. During the last few decades, electrical and electromagnetic methods have been widely used for groundwater investigation, but they suffer from some inherent limitations; for example, equivalent layer sequences. Furthermore, the water content information is only empirically correlated to resistivity of the formation. MRS is a noninvasive geophysical technique that directly quantifies the water content distribution from surface measurements. The resistivity informatio…
Assessment of synthetic winds through spectral modeling and validation using FAST
2016
In this paper, we analyse the simulated and measured wind data with respect to their spectral characteristics and their effect on wind turbine loads. The synthetic data is generated from a stochastic full-field turbulent wind simulator - TurbSim for neutral stability conditions. We first investigate a model for velocity spectra and, a coherence model, by comparing the model results with the measurements. In the second part we analyse the synthetic data via spectra and coherence for two cases; without and with adding coherent events. Finally, we compare wind turbine loads calculated by using FAST simulation of 5 MW reference wind turbine on the basis of simulated and measured data for the gi…
Supershape Recovery from 3D Data Sets
2006
In this paper, we apply supershapes and R-functions to surface recovery from 3D data sets. Individual supershapes are separately recovered from a segmented mesh. R-functions are used to perform Boolean operations between the reconstructed parts to obtain a single implicit equation of the reconstructed object that is used to define a global error reconstruction function. We present surface recovery results ranging from single synthetic data to real complex objects involving the composition of several supershapes and holes.
Land surface temperature retrieval from MSG1-SEVIRI data
2004
Abstract We have developed a physical-based split-window Land Surface Temperature (LST) algorithm for retrieving the surface temperature from SEVIRI/MSG1 (Spinning Enhanced Visible and Infrared Imager/Meteosat Second Generation1) data in two thermal infrared bands (IR 10.8 and IR 12.0). The proposed algorithm takes into account the SEVIRI angular dependence. The numerical values of the split-window coefficients have been obtained from a statistical regression method, using synthetic data. The look-up tables for atmospheric transmission, path radiance, and downward thermal irradiance are calculated with the MODTRAN3 code. The new LST algorithm has been tested with simulated SEVIRI/MSG1 data …
An improved anatomical MRI technique with suppression of fixative fluid artifacts for the investigation of human postmortem brain phantoms
2016
PURPOSE Phantoms are often used to assess MR system stability in multicenter studies. Postmortem brain phantoms best replicate human brain anatomy, allowing for a combined assessment of the MR system and software chain for data analysis. However, a wash-out of fixative fluid affecting T1 values and thus T1-weighted sequences such as magnetization-prepared 180 degrees radiofrequency pulses and rapid gradient-echo (MP-RAGE) has been reported for brain phantoms, hampering their immediate use. The purpose of this study was the creation of anatomical data that provide the characteristics of conventional data while avoiding this artifact. THEORY AND METHODS Two brain phantoms were scanned at seve…
Determination of β -decay ground state feeding of nuclei of importance for reactor applications
2020
12 pags., 6 figs., 3 tabs.
Efficient full decay inversion of MRS data with a stretched-exponential approximation of the distribution
2012
SUMMARY We present a new, efficient and accurate forward modelling and inversion scheme for magnetic resonance sounding (MRS) data. MRS, also called surface-nuclear magnetic resonance (surface-NMR), is the only non-invasive geophysical technique that directly detects free water in the subsurface. Based on the physical principle of NMR, protons of the water molecules in the subsurface are excited at a specific frequency, and the superposition of signals from all protons within the excited earth volume is measured to estimate the subsurface water content and other hydrological parameters. In this paper, a new inversion scheme is presented in which the entire data set is used, and multi-expone…