1 code implementation • 28 Jan 2024 • Angus Dempster, Geoffrey I. Webb, Daniel F. Schmidt
Logistic regression is a ubiquitous method for probabilistic classification.
1 code implementation • 7 Dec 2023 • Navid Mohammadi Foumani, Chang Wei Tan, Geoffrey I. Webb, Hamid Rezatofighi, Mahsa Salehi
Our evaluation of Series2Vec on nine large real-world datasets, along with the UCR/UEA archive, shows enhanced performance compared to current state-of-the-art self-supervised techniques for time series.
no code implementations • 13 Oct 2023 • Loong Kuan Lee, Geoffrey I. Webb, Daniel F. Schmidt, Nico Piatkowski
Doing so tractably is non-trivial as we need to decompose the divergence between these distributions and therefore, require a decomposition over the marginal and conditional distributions of these models.
1 code implementation • 12 Oct 2023 • Yizhen Zheng, Huan Yee Koh, Jiaxin Ju, Anh T. N. Nguyen, Lauren T. May, Geoffrey I. Webb, Shirui Pan
We present a method for using general-purpose large language models to make inferences from scientific datasets of the form usually associated with special-purpose machine learning algorithms.
1 code implementation • 28 Sep 2023 • Ali Ismail-Fawaz, Hassan Ismail Fawaz, François Petitjean, Maxime Devanne, Jonathan Weber, Stefano Berretti, Geoffrey I. Webb, Germain Forestier
Our approach uses a new form of time series average, the ShapeDTW Barycentric Average.
no code implementations • 18 Aug 2023 • Zahra Zamanzadeh Darban, Geoffrey I. Webb, Shirui Pan, Charu C. Aggarwal, Mahsa Salehi
Our research shows the potential of contrastive representation learning to advance time series anomaly detection.
1 code implementation • 2 Aug 2023 • Angus Dempster, Daniel F. Schmidt, Geoffrey I. Webb
We show that it is possible to achieve the same accuracy, on average, as the most accurate existing interval methods for time series classification on a standard set of benchmark datasets using a single type of feature (quantiles), fixed intervals, and an 'off the shelf' classifier.
1 code implementation • 7 Jul 2023 • Ming Jin, Huan Yee Koh, Qingsong Wen, Daniele Zambon, Cesare Alippi, Geoffrey I. Webb, Irwin King, Shirui Pan
In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation.
1 code implementation • 26 May 2023 • Navid Mohammadi Foumani, Chang Wei Tan, Geoffrey I. Webb, Mahsa Salehi
We then proposed a new absolute position encoding method dedicated to time series data called time Absolute Position Encoding (tAPE).
Ranked #1 on Time Series Classification on Heartbeat
2 code implementations • 19 May 2023 • Ali Ismail-Fawaz, Angus Dempster, Chang Wei Tan, Matthieu Herrmann, Lynn Miller, Daniel F. Schmidt, Stefano Berretti, Jonathan Weber, Maxime Devanne, Germain Forestier, Geoffrey I. Webb
The measurement of progress using benchmarks evaluations is ubiquitous in computer science and machine learning.
1 code implementation • 12 Apr 2023 • Matthieu Herrmann, Chang Wei Tan, Mahsa Salehi, Geoffrey I. Webb
Time series classification (TSC) is a challenging task due to the diversity of types of feature that may be relevant for different classification tasks, including trends, variance, frequency, magnitude, and various patterns.
1 code implementation • 6 Feb 2023 • Navid Mohammadi Foumani, Lynn Miller, Chang Wei Tan, Geoffrey I. Webb, Germain Forestier, Mahsa Salehi
Time Series Classification and Extrinsic Regression are important and challenging machine learning tasks.
no code implementations • 24 Jan 2023 • Matthieu Herrmann, Chang Wei Tan, Geoffrey I. Webb
The cost of an alignment of two points is a function of the difference in the values of those points.
1 code implementation • 16 Nov 2022 • Rakshitha Godahewa, Geoffrey I. Webb, Daniel Schmidt, Christoph Bergmeir
On the other hand, in the forecasting community, general-purpose tree-based regression algorithms (forests, gradient-boosting) have become popular recently due to their ease of use and accuracy.
1 code implementation • 9 Nov 2022 • Zahra Zamanzadeh Darban, Geoffrey I. Webb, Shirui Pan, Charu C. Aggarwal, Mahsa Salehi
Time series anomaly detection has applications in a wide range of research fields and applications, including manufacturing and healthcare.
1 code implementation • 25 Mar 2022 • Angus Dempster, Daniel F. Schmidt, Geoffrey I. Webb
We present HYDRA, a simple, fast, and accurate dictionary method for time series classification using competing convolutional kernels, combining key aspects of both ROCKET and conventional dictionary methods.
no code implementations • 8 Dec 2021 • Loong Kuan Lee, Nico Piatkowski, François Petitjean, Geoffrey I. Webb
We show that we are able to compute a wide family of functionals and divergences, such as the alpha-beta divergence, between two decomposable models, i. e. chordal Markov networks, in time exponential to the treewidth of these models.
1 code implementation • 26 Nov 2021 • Matthieu Herrmann, Geoffrey I. Webb
CDTW and WDTW have been introduced because DTW is too permissive in its alignments.
1 code implementation • 14 May 2021 • Rakshitha Godahewa, Christoph Bergmeir, Geoffrey I. Webb, Rob J. Hyndman, Pablo Montero-Manso
Many businesses and industries nowadays rely on large quantities of time series data making time series forecasting an important research area.
1 code implementation • 20 Feb 2021 • Ahmed Shifaz, Charlotte Pelletier, Francois Petitjean, Geoffrey I. Webb
Elastic similarity and distance measures are a class of similarity measures that can compensate for misalignments in the time axis of time series data.
1 code implementation • 14 Feb 2021 • Geoffrey I. Webb, Francois Petitjean
Due to DTW's high computation time, lower bounds are often employed to screen poor matches.
2 code implementations • 10 Feb 2021 • Matthieu Herrmann, Geoffrey I. Webb
This threshold, provided by the similarity search process, also allows to early abandon the computation of a distance itself.
1 code implementation • 31 Jan 2021 • Chang Wei Tan, Angus Dempster, Christoph Bergmeir, Geoffrey I. Webb
We propose MultiRocket, a fast time series classification (TSC) algorithm that achieves state-of-the-art performance with a tiny fraction of the time and without the complex ensembling structure of many state-of-the-art methods.
1 code implementation • 30 Dec 2020 • Rakshitha Godahewa, Kasun Bandara, Geoffrey I. Webb, Slawek Smyl, Christoph Bergmeir
With large quantities of data typically available nowadays, forecasting models that are trained across sets of time series, known as Global Forecasting Models (GFM), are regularly outperforming traditional univariate forecasting models that work on isolated series.
2 code implementations • 16 Dec 2020 • Angus Dempster, Daniel F. Schmidt, Geoffrey I. Webb
ROCKET achieves state-of-the-art accuracy with a fraction of the computational expense of most existing methods by transforming input time series using random convolutional kernels, and using the transformed features to train a linear classifier.
no code implementations • 12 Nov 2020 • Yuan Jin, Wray Buntine, Francois Petitjean, Geoffrey I. Webb
For this task, we survey a wide range of techniques available for handling missing values, self-supervised training and pseudo-likelihood training, and adapt them to a suite of algorithms that are suitable for the task.
1 code implementation • 16 Oct 2020 • Rakshitha Godahewa, Christoph Bergmeir, Geoffrey I. Webb, Pablo Montero-Manso
Many businesses and industries require accurate forecasts for weekly time series nowadays.
1 code implementation • 11 Oct 2020 • Matthieu Herrmann, Geoffrey I. Webb
We show that EAPrunedDTW significantly improves the computation time of similarity search in the UCR Suite, and renders lower bounds dispensable.
1 code implementation • 23 Jun 2020 • Chang Wei Tan, Christoph Bergmeir, Francois Petitjean, Geoffrey I. Webb
This paper studies Time Series Extrinsic Regression (TSER): a regression task of which the aim is to learn the relationship between a time series and a continuous scalar variable; a task closely related to time series classification (TSC), which aims to learn the relationship between a time series and a categorical class label.
2 code implementations • 19 Jun 2020 • Chang Wei Tan, Christoph Bergmeir, Francois Petitjean, Geoffrey I. Webb
We refer to this problem as Time Series Extrinsic Regression (TSER), where we are interested in a more general methodology of predicting a single continuous value, from univariate or multivariate time series.
1 code implementation • 25 May 2020 • Benjamin Lucas, Charlotte Pelletier, Daniel Schmidt, Geoffrey I. Webb, François Petitjean
In this paper we present Sourcerer, a Bayesian-inspired, deep learning-based, semi-supervised DA technique for producing land cover maps from SITS data.
6 code implementations • 29 Oct 2019 • Angus Dempster, François Petitjean, Geoffrey I. Webb
Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger datasets.
no code implementations • 10 Oct 2019 • Chang Wei Tan, Francois Petitjean, Eamonn Keogh, Geoffrey I. Webb
Research into time series classification has tended to focus on the case of series of uniform length.
10 code implementations • 11 Sep 2019 • Hassan Ismail Fawaz, Benjamin Lucas, Germain Forestier, Charlotte Pelletier, Daniel F. Schmidt, Jonathan Weber, Geoffrey I. Webb, Lhassane Idoumghar, Pierre-Alain Muller, François Petitjean
TSC is the area of machine learning tasked with the categorization (or labelling) of time series.
2 code implementations • 25 Jun 2019 • Ahmed Shifaz, Charlotte Pelletier, Francois Petitjean, Geoffrey I. Webb
We demonstrate that TS-CHIEF can be trained on 130k time series in 2 days, a data quantity that is beyond the reach of any TSC algorithm with comparable accuracy.
1 code implementation • 26 Nov 2018 • Charlotte Pelletier, Geoffrey I. Webb, Francois Petitjean
The experimental results show that TempCNNs are more accurate than RF and RNNs, that are the current state of the art for SITS classification.
4 code implementations • 31 Aug 2018 • Benjamin Lucas, Ahmed Shifaz, Charlotte Pelletier, Lachlan O'Neill, Nayyar Zaidi, Bart Goethals, Francois Petitjean, Geoffrey I. Webb
We demonstrate on a 1M time series Earth observation dataset that Proximity Forest retains this accuracy on datasets that are many orders of magnitude greater than those in the UCR repository, while learning its models at least 100, 000 times faster than current state of the art models Elastic Ensemble and COTE.
1 code implementation • 29 Aug 2018 • Chang Wei Tan, Francois Petitjean, Geoffrey I. Webb
One of the key time series classification algorithms, the nearest neighbor algorithm with DTW distance (NN-DTW) is very expensive to compute, due to the quadratic complexity of DTW.
no code implementations • 26 Aug 2018 • Mahardhika Pratama, Witold Pedrycz, Geoffrey I. Webb
DEVFNN is developed under the stacked generalization principle via the feature augmentation concept where a recently developed algorithm, namely gClass, drives the hidden layer.
no code implementations • 7 Aug 2018 • Fengxiang He, Tongliang Liu, Geoffrey I. Webb, DaCheng Tao
Specifically, by treating the unlabelled data as noisy negative examples, we could automatically label a group positive and negative examples whose labels are identical to the ones assigned by a Bayesian optimal classifier with a consistency guarantee.
1 code implementation • 29 Jan 2018 • Nayyar A. Zaidi, Geoffrey I. Webb, Francois Petitjean, Germain Forestier
These hypotheses lead to the concept of the sweet path, a path through the 3-d space of alternative drift rates, forgetting rates and bias/variance profiles on which generalization error will be minimized, such that slow drift is coupled with low forgetting and low bias, while rapid drift is coupled with fast forgetting and low variance.
no code implementations • 12 Sep 2017 • Wilhelmiina Hämäläinen, Geoffrey I. Webb
We present theoretical analysis and a suite of tests and procedures for addressing a broad class of redundant and misleading association rules we call \emph{specious rules}.
4 code implementations • 25 Aug 2017 • Francois Petitjean, Wray Buntine, Geoffrey I. Webb, Nayyar Zaidi
The main result of this paper is to show that improved parameter estimation allows BNCs to outperform leading learning methods such as Random Forest for both 0-1 loss and RMSE, albeit just on categorical datasets.
1 code implementation • 2 Apr 2017 • Geoffrey I. Webb, Loong Kuan Lee, François Petitjean, Bart Goethals
Concept drift is a major issue that greatly affects the accuracy and reliability of many real-world applications of machine learning.
1 code implementation • 24 Jan 2017 • Nayyar A. Zaidi, Yang Du, Geoffrey I. Webb
It is often motivated by the limitation of some learners to qualitative data.
no code implementations • 12 Nov 2015 • Geoffrey I. Webb, Roy Hyde, Hong Cao, Hai Long Nguyen, Francois Petitjean
This supports the development of the first comprehensive set of formal definitions of types of concept drift.
no code implementations • 4 Sep 2015 • Nayyar A. Zaidi, Geoffrey I. Webb, Mark J. Carman, Francois Petitjean
For some learning tasks there is power in learning models that are not only Deep but also Broad.
1 code implementation • 26 Jun 2015 • Francois Petitjean, Tao Li, Nikolaj Tatti, Geoffrey I. Webb
It combines (1) a novel definition of the expected support for a sequential pattern - a concept on which most interestingness measures directly rely - with (2) SkOPUS: a new branch-and-bound algorithm for the exact discovery of top-k sequential patterns under a given measure of interest.