1 code implementation • 26 Jun 2023 • Leonardos Pantiskas, Kees Verstoep, Mark Hoogendoorn, Henri Bal
Nowadays, the deployment of deep learning models on edge devices for addressing real-world classification problems is becoming more prevalent.
1 code implementation • 14 Oct 2022 • Leonardos Pantiskas, Kees Verstoep, Mark Hoogendoorn, Henri Bal
We also show that if we keep the transformation method constant, there is a statistically significant difference in accuracy results when applying it across different dimensions, with accuracy differences ranging from 0. 23 to 47. 79 percentage points.
1 code implementation • 4 Apr 2022 • Leonardos Pantiskas, Kees Verstoep, Mark Hoogendoorn, Henri Bal
We show that we achieve speedup ranging from 9x to 53x compared to ROCKET during inference on an edge device, on datasets with comparable accuracy.
no code implementations • 29 Sep 2021 • Leonardos Pantiskas, Kees Verstoep, Mark Hoogendoorn, Henri Bal
Specifically, utilizing a wavelet scattering transformation of the time series and distributed feature selection, we manage to create a solution which employs just 2, 5% of the ROCKET features, while achieving accuracy comparable to recent deep learning solutions.
1 code implementation • 22 Jul 2021 • Luis P. Silvestrin, Leonardos Pantiskas, Mark Hoogendoorn
Time-series forecasting plays an important role in many domains.
1 code implementation • IEEE Symposium Series on Computational Intelligence (SSCI) 2021 • Leonardos Pantiskas, Kees Verstoep, Henri Bal
We apply it on two datasets and we show that we gain interpretability without degrading the accuracy compared to the original temporal convolutional models.