Time series classification with random convolution kernels: pooling operators and input representations matter

2024/09/02 by Mouhamadou Mansour Lo, Gildąs Morvan, Lo, Mouhamadou Mansour +7 · 1 citation
Computer Science · Engineering · Mathematics · #Advanced Chemical Sensor Technologies #Algebra over a field #Anomaly Detection Techniques and Applications #Applied mathematics #Artificial intelligence #Artificial neural network #Computer science #Convolution (computer science) #Geology #Kernel (algebra) #Mathematics #Pooling #Pure mathematics #Series (stratigraphy) #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2409.01115

published in arXiv (Cornell University) (Cornell University)

Abstract

This article presents a new approach based on MiniRocket, called SelF-Rocket, for fast time series classification (TSC). Unlike existing approaches based on random convolution kernels, it dynamically selects the best couple of input representations and pooling operator during the training process. SelF-Rocket achieves state-of-the-art accuracy on the University of California Riverside (UCR) TSC benchmark datasets.

Cited by

• NanoHydra: Energy-Efficient Time-Series Classification at the Edge

Related

• MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification
• S-Rocket: Selective Random Convolution Kernels for Time Series Classification
• SPROCKET: Extending ROCKET to Distance-Based Time-Series Transformations With Prototypes
• HYDRA: Competing convolutional kernels for fast and accurate time series classification
• Random Projections and Natural Sparsity in Time-Series Classification: A Theoretical Analysis