A tale of two toolkits, report the third: on the usage and performance of HIVE-COTE v1.0

Abstract

The Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) is a heterogeneous meta ensemble for time series classification. Since it was first proposed in 2016, the algorithm has undergone some minor changes and there is now a configurable, scalable and easy to use version available in two open source repositories. We present an overview of the latest stable HIVE-COTE, version 1.0, and describe how it differs to the original. We provide a walkthrough guide of how to use the classifier, and conduct extensive experimental evaluation of its predictive performance and resource usage. We compare the performance of HIVE-COTE to three recently proposed algorithms using the aeon toolkit.

References in corpus (6)

• ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels
• TS-CHIEF: A Scalable and Accurate Forest Algorithm for Time Series Classification
• The Heterogeneous Ensembles of Standard Classification Algorithms (HESCA): the Whole is Greater than the Sum of its Parts
• Scalable Dictionary Classifiers for Time Series Classification
• Is rotation forest the best classifier for problems with continuous features?
• A tale of two toolkits, report the first: benchmarking time series classification algorithms for correctness and efficiency

Cited by in corpus (5)

• MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification
• Improving Position Encoding of Transformers for Multivariate Time Series Classification
• Time-Series Classification in Smart Manufacturing Systems: An Experimental Evaluation of State-of-the-Art Machine Learning Algorithms
• The Temporal Dictionary Ensemble (TDE) Classifier for Time Series Classification
• An ensemble of convolution-based methods for fault detection using vibration signals