S-Rocket: Selective Random Convolution Kernels for Time Series Classification

Abstract

Random convolution kernel transform (Rocket) is a fast, efficient, and novel approach for time series feature extraction, using a large number of randomly initialized convolution kernels, and classification of the represented features with a linear classifier, without training the kernels. Since these kernels are generated randomly, a portion of these kernels may not positively contribute in performance of the model. Hence, selection of the most important kernels and pruning the redundant and less important ones is necessary to reduce computational complexity and accelerate inference of Rocket. Selection of these kernels is a combinatorial optimization problem. In this paper, the kernels selection process is modeled as an optimization problem and a population-based approach is proposed for selecting the most important kernels. This approach is evaluated on the standard time series datasets and the results show that on average it can achieve a similar performance to the original models by pruning more than 60% of kernels. In some cases, it can achieve a similar performance using only 1% of the kernels.

Random Convolutional Kernels for Space-Detector Based Gravitational Wave Signals

“…Originally developed for experiments on the UCR archive [37], which contains signals from various domains, ROCKET raises the question of its ability to generalize to noisy signals like GW strain. Various versions of ROCKET have been developed, enabling it to be trained on multi-channel inputs, thereby reducing training time and improving accuracy [20,38,39].…”

MC-WDWCNN: an interpretable multi-channel wide-kernel wavelet convolutional neural network for strong noise-robust fault diagnosis

“…The encouraging results achieved by previous authors have alleviated the interpretability problem to some extent, but there are still instinctive limitations. First, these methods attempt to map features into the input space for interpretation, but these feature mappings still need to be explained concerning faultrelated information [23]. Second, when using CNN feature extraction, noise interference is ignored, which leads to erroneous diagnostic results [24,25].…”