Search results for "Modeling"
showing 10 items of 4489 documents
Optimal Pruned K-Nearest Neighbors: OP-KNN Application to Financial Modeling
2008
The paper proposes a methodology called OP-KNN, which builds a one hidden-layer feed forward neural network, using nearest neighbors neurons with extremely small computational time. The main strategy is to select the most relevant variables beforehand, then to build the model using KNN kernels. Multi-response sparse regression (MRSR) is used as the second step in order to rank each k-th nearest neighbor and finally as a third step leave-one-out estimation is used to select the number of neighbors and to estimate the generalization performances. This new methodology is tested on a toy example and is applied to financial modeling.
Effect of raster resolution and polygon-conversion algorithm on landslide susceptibility mapping
2016
The choice of the proper resolution in landslide susceptibility mapping is a worth considering issue. If, on the one hand, a coarse spatial resolution may describe the terrain morphologic properties with low accuracy, on the other hand, at very fine resolutions, some of the DEM-derived morphometric factors may hold an excess of details. Moreover, the landslide inventory maps are represented throughout geospatial vector data structure, therefore a conversion procedure vector-to-raster is required.This work investigates the effects of raster resolution on the susceptibility mapping in conjunction with the use of different algorithms of vector-raster conversion. The Artificial Neural Network t…
Combining Auto-Encoder with LSTM for WiFi-Based Fingerprint Positioning
2021
Although indoor positioning has long been investigated by various means, its accuracy remains concern. Several recent studies have applied machine learning algorithms to explore wireless fidelity (WiFi)-based positioning. In this paper, we propose a novel deep learning model which concatenates an auto-encoder with a long short term memory (LSTM) network for the purpose of WiFi fingerprint positioning. We first employ an auto-encoder to extract representative latent codes of fingerprints. Such an extraction is proven to be more reliable than simply using a deep neural network to extract representative features since a latent code can be reverted back to its original input. Then, a sequence o…
Applicant reactions and faking in real-life personnel selection
2011
Honkaniemi, L., Tolvanen, A. & Feldt, T. (2011). Applicant reactions and faking in real-life personnel selection. Scandinavian Journal of Psychology 52, 376–381. Faking may affect hiring decisions in personnel selection. All the antecedents of faking are still not known. The present study investigates the association between applicants’ reactions about the selection procedure and their tendency to fake. The subjects (N = 180) were real-life applicants for a fire and rescue personnel school. After completing the selection process, the applicants filled out a questionnaire about their test reactions (Chan, Schmitt, Sacco & DeSohon, 1998b) and a faking scale, the Balanced Inventory of Desirabl…
Human factor policy testing in the sequencing of manual mixed model assembly lines
2004
In this paper the human resource management in manual mixed model assembly U-lines is considered. The objective is to minimise the total conveyor stoppage time to achieve the full efficiency of the line. A model, that includes effects of the human resource, was developed in order to evaluate human factor policies impact on the optimal solution of this line sequencing problem. Different human resource management policies are introduced to cope with the particular layout of the proposed line. Several examples have been proposed to investigate the effects of line dimensions on the proposed management policies. The examples have been solved through a genetic algorithm. The obtained results conf…
The Effects of Orography on the Extratropical Transition of Tropical Cyclones: A Case Study of Typhoon Sinlaku (2008)
2018
Abstract Extratropical transition (ET) can cause high-impact weather in midlatitude regions and therefore constitutes an ongoing threat at the end of a tropical cyclone’s (TC) life cycle. Most of the ET events occur over the ocean, but some TCs recurve and undergo ET along coastal regions; however, the latter category is less investigated. Typhoon Sinlaku (2008), for example, underwent ET along the southern coast of Japan. It was one of the typhoons that occurred during the T-PARC field campaign, providing unprecedented high-resolution observational data. Sinlaku is therefore an excellent case to investigate the impact of a coastal region, and in particular orography, on the evolution of ET…
Sentinel-3/FLEX Biophysical Product Confidence Using Sentinel-2 Land-Cover Spatial Distributions
2021
The estimation of biophysical variables from remote sensing data raises important challenges in terms of the acquisition technology and its limitations. In this way, some vegetation parameters, such as chlorophyll fluorescence, require sensors with a high spectral resolution that constrains the spatial resolution while significantly increasing the subpixel land-cover heterogeneity. Precisely, this spatial variability often makes that rather different canopy structures are aggregated together, which eventually generates important deviations in the corresponding parameter quantification. In the context of the Copernicus program (and other related Earth Explorer missions), this article propose…
Comparative assessment of RAMS and WRF short-term forecasts over Eastern Iberian Peninsula using various in-situ observations, remote sensing product…
2018
The Regional Atmospheric Modeling System (RAMS) and the Weather Research and Forecasting (WRF) mesoscale models are being used for weather and air quality studies as well as forecasting tools in Numerical Weather Prediction (NWP) systems. In the current study, we perform a comparative assessment of these models under distinct typical atmospheric conditions, classified according to the dominant wind flow and cloudiness, over Eastern Iberian Peninsula. This study is focused on the model representation of key physical processes in terms of meteorology and surface variables during a 7-days period in summer 2011. The hourly outputs produced by these two models are compared not only with observed…
Reconstruction of the Parker spiral with the Reverse in situ data and MHD APproach - RIMAP
2021
The reconstruction of plasma parameters in the interplanetary medium is very important to understand the interplanetary propagation of solar eruptions and for Space Weather application purposes. Because only a few spacecraft are measuring in situ these parameters, reconstructions are currently performed by running complex numerical Magneto-hydrodynamic (MHD) simulations starting from remote sensing observations of the Sun. Current models apply full 3D MHD simulations of the corona or extrapolations of photospheric magnetic fields combined with semi-empirical relationships to derive the plasma parameters on a sphere centered on the Sun (inner boundary). The plasma is then propagated in the i…
Observed versus simulated mountain waves over Scandinavia – improvement of vertical winds, energy and momentum fluxes by enhanced model resolut…
2017
Abstract. Two mountain wave events, which occurred over northern Scandinavia in December 2013 are analysed by means of airborne observations and global and mesoscale numerical simulations with horizontal mesh sizes of 16, 7.2, 2.4 and 0.8 km. During both events westerly cross-mountain flow induced upward-propagating mountain waves with different wave characteristics due to differing atmospheric background conditions. While wave breaking occurred at altitudes between 25 and 30 km during the first event due to weak stratospheric winds, waves propagated to altitudes above 30 km and interfacial waves formed in the troposphere at a stratospheric intrusion layer during the second event. Global an…