Sökning: "tidsserietransformatorer"

Hittade 1 uppsats innehållade ordet tidsserietransformatorer.

  1. 1. FLEX: Force Linear to Exponential : Improving Time Series Forecasting Models For Hydrological Level Using A Scalable Ensemble Machine Learning Approach

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Koen van den Brink; [2022]
    Nyckelord :machine learning; time-series forecasting; water level forecasting; time-series transformers; recurrent neural networks; maskininlärning; tidsserieprognoser; vattenståndsprognoser; tidsserietransformatorer; återkopplade neurala nätverk;

    Sammanfattning : Time-series forecasting is an area of machine learning that can be applied to many real-life problems. It is used in areas such as water level forecasting, which aims to help people evacuate on time for floods. LÄS MER