Spike Detection with Continuous Wavelet Transform Based Model Driven Machine Learning Methods

Ámon, Attila Miklós and Cornelis, Bram and Kovács, Péter and Dózsa, Tamás (2025) Spike Detection with Continuous Wavelet Transform Based Model Driven Machine Learning Methods. In: 2025 33rd European Signal Processing Conference (EUSIPCO). European Association for Signal Processing (EURASIP), Leuven, pp. 1797-1801. ISBN 9789464593624

Text Spike_Detection_with_Continuous_Wavelet_Transform_Based_Model_Driven_Machine_Learning_Methods4.pdf Restricted to Repository staff only Download (770kB) | Request a copy

Abstract

In this paper, we detect spike-like measurement errors in accelerometer sensor signals using continuous wavelet transform based machine learning methods. The wavelet coefficients are computed in automatic feature extraction layers (CWT layers), producing sparse representations of the input signals. The proposed methods ensure low model complexity, which allows real-time application. We complement a previously proposed variable projection based method to estimate wavelet coefficients with a numerical quadrature based approach. We present a qualitative and quantitative comparison of the CWT layers. To demonstrate the generality of the method, we introduce support vector machines supplemented with CWT layers in addition to previously used neural networks. Sensor fault detection experiments are conducted on real measurements using a low-cost accelerometer. The results of the experiments show that the proposed method achieves perfect accuracy on our dataset while outperforms previously used approaches in terms of interpretability and online usage. In addition to convincing classification accuracy, our results illustrate the interpretability of the proposed model driven machine learning framework.

Actions (login required)

View Item