Search results for " PREDICTION"
showing 6 items of 366 documents
Dataset related to article "Development and external validation of a clinical prediction model for functional impairment after intracranial tumor sur…
2021
Anonymised clinical database containing information (Age, sex, prior surgery, tumor histology and maximum diameter, expected major brain vessel or cranial nerve manipulation, resection in eloquent areas and the posterior fossa, and surgical approach were recorded) about patients of Fondazione IRCCS Istituto Besta analysed for the article “Development and external validation of a clinical prediction model for functional impairment after intracranial tumor surgery”
A methodology for the control of the residual lifetimes of carbon fibre reinforced composite pressure vessels
2005
International audience; Pressure vessels must be periodically proof tested. Traditional techniques for metal vessels are inapplicable for composite vessels as the latter do not break by crack propagation so that the reasoning behind the traditional testing procedures is not appropriate. Damage accumulation leading to the degradation of a composite vessel is by fibre failure. Fibres show a wide distribution in strengths and loading a composite inevitably breaks some. The method which has been developed is supported by an analysis of delayed fibre failure due to the relaxation of the resin around fibre breaks. This provokes overloading of intact fibres neighbouring breaks. The time until a cr…
How many longitudinal covariate measurements are needed for risk prediction?
2014
Abstract Objective In epidemiologic follow-up studies, many key covariates, such as smoking, use of medication, blood pressure, and cholesterol, are time varying. Because of practical and financial limitations, time-varying covariates cannot be measured continuously, but only at certain prespecified time points. We study how the number of these longitudinal measurements can be chosen cost-efficiently by evaluating the usefulness of the measurements for risk prediction. Study Design and Setting The usefulness is addressed by measuring the improvement in model discrimination between models using different amounts of longitudinal information. We use simulated follow-up data and the data from t…
DOBRO : a prediction error correcting robot under drifts
2016
We propose DOBRO, a light online learning module, which is equipped with a smart correction policy helping making decision to correct or not the given prediction depending on how likely the correction will lead to a better prediction performance. DOBRO is a standalone module requiring nothing more than a time series of prediction errors and it is flexible to be integrated into any black-box model to improve its performance under drifts. We performed evaluation in a real-world application with bus arrival time prediction problem. The obtained results show that DOBRO improved prediction performance significantly meanwhile it did not hurt the accuracy when drift does not happen.
E-Sports y brecha de género: la percepción de las profesionales españolas
2019
The present paper aims to identify the causes of under-representation of women in E-sports. According to a genre perspective, interest in videogames at the amateur level is quite similar. However, in its professional level, female participation becomes very limited. The fact that physical effort is irrelevant (a requirement for ?traditional sports?) could be considered a variable that would negatively affect greater to equality in the conditions of access and participation of women in electronic sports. Against any predictions, the data on the presence of women are elocuent: few women, with much lower wages than men to remunerate same skills, and a general complaint by the female profession…
Urban Flood Prediction through GIS-Based Dual-Coupled Hydraulic Models
2022
Propagation of pluvial floods in urban areas, occurring with return time periods of few years, can be well solved using dual models accounting for the mutual relationship between the water level in the streets and the discharges inside the sewer pipes. The extended WEC-flood model (EWEC), based on the use of unstructured triangular meshes and a diffusive formulation of the momentum equations in both the 2D and the 1D lower domains, is presented along with its novelty, limits, and advantages. The model is then applied to a small computational domain in the Palermo area, where only some ‘hard’ data given by one rain gauge has been used for calibration and validation, along with ot…