TY - GEN
T1 - Quantum-based interval selection of the Semi-classical Signal Analysis method
AU - Piliouras, Evangelos
AU - Laleg-Kirati, Taous-Meriem
N1 - KAUST Repository Item: Exported on 2020-12-22
PY - 2020/12/18
Y1 - 2020/12/18
N2 - Semi-classical Signal Analysis (SCSA) is a signal representation algorithm utilizing the Schrödinger eigenvalue problem. The algorithm has found many applications, from signal processing to machine learning and denoising due to its adaptive and localized nature. So far, the algorithm’s design parameter was tuned heuristically, without using the knowledge of the quantum mechanical principles residing in the SCSA formulation. In this work, we extend the SCSA framework by calculating the bounds of the reconstruction parameter. The derived bounds are effectively the sampling theorem for SCSA, which is of paramount importance for the application of the theory. Moreover, guidelines towards an optimal choice of the parameter are provided, eliminating the heuristic scanning step.
AB - Semi-classical Signal Analysis (SCSA) is a signal representation algorithm utilizing the Schrödinger eigenvalue problem. The algorithm has found many applications, from signal processing to machine learning and denoising due to its adaptive and localized nature. So far, the algorithm’s design parameter was tuned heuristically, without using the knowledge of the quantum mechanical principles residing in the SCSA formulation. In this work, we extend the SCSA framework by calculating the bounds of the reconstruction parameter. The derived bounds are effectively the sampling theorem for SCSA, which is of paramount importance for the application of the theory. Moreover, guidelines towards an optimal choice of the parameter are provided, eliminating the heuristic scanning step.
UR - http://hdl.handle.net/10754/666539
UR - https://ieeexplore.ieee.org/document/9287878/
U2 - 10.23919/Eusipco47968.2020.9287878
DO - 10.23919/Eusipco47968.2020.9287878
M3 - Conference contribution
SN - 978-1-7281-5001-7
BT - 2020 28th European Signal Processing Conference (EUSIPCO)
PB - IEEE
ER -