Dortmund 2021 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz
AKPIK 1: AKPIK I: Data Science & Analytics
AKPIK 1.2: Vortrag
Dienstag, 16. März 2021, 16:15–16:30, AKPIKa
Adaptive predictor as trigger mechanism for cosmic rays radio signals corrupted by noise — •Clara Watanabe1,2,3, Paulo Diniz2, Joao de Mello Neto1, and Tim Huege3,4 — 1Physics Institute, Federal University of Rio de Janeiro (UFRJ) — 2Multimedia and Telecommunications Laboratory (SMT), The Alberto Luiz Coimbra Institute for Graduate Studies and Research in Engineering (COPPE), Federal University of Rio de Janeiro (UFRJ) — 3Institute for Astroparticle Physics (IAP), Karlsruhe Institute of Technology (KIT) — 4Astrophysical Institute, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium
Adaptive filtering belongs to the realm of learning algorithms, so widely used in our daily life when we hear about machine learning, artificial intelligence, pattern recognition, etc. It is formally defined as a self-designing device with time-varying parameters that are adjusted recursively in accordance with the input data.
The trigger mechanism is known to be a central task in radio detection experiments as it selects among all the voltages traces events that reach the antennas, a cosmic ray induced signal.
In this work, it is presented the efficiency of a trigger mechanism developed using the adaptive predictor filter technique, since its capability is well known in the usage for time series prediction. It is also independent from an external detector, considering only the online temporal series that arrives in the antennas in a simulated data set and noise.