Výsledky vyhledávání

Report

Probabilistic water demand forecasting using quantile regression algorithms

Autor: Papacharalampous, Georgia, Langousis, Andreas

Machine and statistical learning algorithms can be reliably automated and applied at scale. Therefore, they can constitute a considerable asset for designing practical forecasting systems, such as those related to urban water demand. Quantile regress

Externí odkaz: http://arxiv.org/abs/2104.07985

Zobrazit plný text záznamu

Report

Global-scale massive feature extraction from monthly hydroclimatic time series: Statistical characterizations, spatial patterns and hydrological similarity

Autor: Papacharalampous, Georgia, Tyralis, Hristos, Papalexiou, Simon Michael, Langousis, Andreas, Khatami, Sina, Volpi, Elena, Grimaldi, Salvatore

Publikováno v: Science of the Total Environment 767 (2021) 144612

Hydroclimatic time series analysis focuses on a few feature types (e.g., autocorrelations, trends, extremes), which describe a small portion of the entire information content of the observations. Aiming to exploit a larger part of the available infor

Externí odkaz: http://arxiv.org/abs/2010.12833

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Report

ITSO: A novel Inverse Transform Sampling-based Optimization algorithm for stochastic search

Autor: Bakas, Nikolaos P., Plevris, Vagelis, Langousis, Andreas, Chatzichristofis, Savvas A.

Publikováno v: Stochastic Environmental Research and Risk Assessment, 36 (2021), pp. 67-76

Optimization algorithms appear in the core calculations of numerous Artificial Intelligence (AI) and Machine Learning methods, as well as Engineering and Business applications. Following recent works on the theoretical deficiencies of AI, a rigor con

Externí odkaz: http://arxiv.org/abs/2001.02500

Zobrazit plný text záznamu

Report

A Gradient Free Neural Network Framework Based on Universal Approximation Theorem

Autor: Bakas, Nikolaos P., Langousis, Andreas, Nicolaou, Mihalis, Chatzichristofis, Savvas A.

We present a numerical scheme for computation of Artificial Neural Networks (ANN) weights, which stems from the Universal Approximation Theorem, avoiding laborious iterations. The proposed algorithm adheres to the underlying theory, is highly fast, a

Externí odkaz: http://arxiv.org/abs/1909.13563

Zobrazit plný text záznamu

Report

Super ensemble learning for daily streamflow forecasting: Large-scale demonstration and comparison with multiple machine learning algorithms

Autor: Tyralis, Hristos, Papacharalampous, Georgia, Langousis, Andreas

Publikováno v: Neural Computing and Applications 33 (2021) 3053-3068

Daily streamflow forecasting through data-driven approaches is traditionally performed using a single machine learning algorithm. Existing applications are mostly restricted to examination of few case studies, not allowing accurate assessment of the

Externí odkaz: http://arxiv.org/abs/1909.04131

Zobrazit plný text záznamu