Search results for "SARIMA"

showing 4 items of 4 documents

Application of LSTM architectures for next frame forecasting in Sentinel-1 images time series

2020

L'analyse prédictive permet d'estimer les tendances des évènements futurs. De nos jours, les algorithmes Deep Learning permettent de faire de bonnes prédictions. Cependant, pour chaque type de problème donné, il est nécessaire de choisir l'architecture optimale. Dans cet article, les modèles Stack-LSTM, CNN-LSTM et ConvLSTM sont appliqués à une série temporelle d'images radar sentinel-1, le but étant de prédire la prochaine occurrence dans une séquence. Les résultats expérimentaux évalués à l'aide des indicateurs de performance tels que le RMSE et le MAE, le temps de traitement et l'index de similarité SSIM, montrent que chacune des trois architectures peut produire de bons résultats en fon…

[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]FOS: Computer and information sciencesApprentissage profondComputer Science - Machine LearningImage and Video Processing (eess.IV)[INFO.INFO-NE] Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]PrévisionComputer Science - Neural and Evolutionary ComputingDeep Learning AlgorithmsPrédiction[INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]Electrical Engineering and Systems Science - Image and Video ProcessingLand cover change[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]Machine Learning (cs.LG)SARIMA[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV][INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]FOS: Electrical engineering electronic engineering information engineeringSatellite imagesNeural and Evolutionary Computing (cs.NE)LSTMPredictionForecastingImages satellitaires
researchProduct

Tourism recovery amid COVID-19: The case of Lombardy, Italy

2021

Travel restrictions and social distancing imposed to curb the spread of the new coronavirus have been strongly hitting tourism since March 2020. Tourism forecasting literature addressed the effects of shocks in contexts characterized by a predictable route to recovery. COVID-19 is without precedents. In this article, monthly overnight stays for the period January 2010 to December 2020 are used to estimate the impact of the pandemic in Lombardy, Italy’s most affected region. A model-based approach is implemented, and the number of overnight stays up to December 2023 is forecasted. Four models are compared. Estimation results from an augmented SARIMA model suggest that, provided a new lockdo…

Coronavirus pandemic2019-20 coronavirus outbreakCoronavirus disease 2019 (COVID-19)Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)Social distanceGeography Planning and DevelopmentTourism forecastingmedicine.disease_causeSettore SECS-P/06 - Economia ApplicataSARIMAGeographyEconomySettore SECS-S/06 -Metodi Mat. dell'Economia e d. Scienze Attuariali e Finanz.Tourism Leisure and Hospitality ManagementmedicineTourismOvernights staysCoronavirus
researchProduct

Laika rindu analīzes metodes akciju cenu prognozēšanā

2020

Bakalaura darba mērķis izpētīt laika rindu analīzes metožu pielietojuma iespējas akciju cenu analīzē un prognozēšanā, kā arī novērtēt dažāda veida modeļu izmantošanas potenciālu konkrēta uzņēmuma akciju cenu prognozēšanā. Darbā sniegts laika rindu analīzes un prognozēšanas metožu pārskats, laika rindu prognozēšanas problēmu situāciju izpēte. Apskatītās metodes kā ARIMA, ARIMAX, SARIMAX un VAR tika pielietotas uzņēmuma Volkswagen akciju cenu prognozēšanā, izmantojot datus par 2009. – 2019. gadu laika periodu. Lai ņemtu vērā kopējā tirgus tendences, modeļi tika papildināti ar diviem eksogēniem mainīgiem – uzņēmuma Porsche un uzņēmuma BMW akciju cenām par iepriekš minēto periodu. Prognozēšanas…

Laika rindaspythonEkonomikaVARARIMASARIMAX
researchProduct

Wind speed stochastic models: a case study for the mediterranean area

2010

sarima forecast weatherSettore FIS/03 - Fisica Della Materia
researchProduct