Deep Learning For Time Series Classification Using New Hand-Crafted Convolution Filters

Ismail-Fawaz, Ali; Devanne, Maxime; Weber, Jonathan; Forestier, Germain

doi:10.1109/bigdata55660.2022.10020496

Cited by 9 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, they often do not seem to offer any advance on previous research. We have not seen any algorithm that can realistically claim to outperform InceptionTime (Fawaz et al 2020), nor its successor H-InceptionTime (Ismail-Fawaz et al 2022). Because of this, we restrict our attention to five deep learning algorithms.…”

Section: Deep Learningmentioning

confidence: 99%

“…InceptionTime (Fawaz et al 2020) is included since it is, to the best our knowledge, best in category for deep learning. We also evaluate two recent extensions of InceptionTime: H-InceptionTime (Ismail-Fawaz et al 2022) and LiteTime (Ismail-Fawaz et al 2023b). The relation flowchart for deep learning algorithms is shown in Fig.…”

Section: Deep Learningmentioning

confidence: 99%

“…Ismail- Fawaz et al (2022) proposed an extension of InceptionTime that included hand-craft one-dimensional convolution filters to detect very specific patterns in a time series: increasing trends, decreasing trends and peaks. Hybrid Inception (H-Inception) uses the hand-crafted filters in parallel with the first module of the Inception network.…”

Section: H-inceptiontimementioning

confidence: 99%

See 2 more Smart Citations

Bake off redux: a review and experimental evaluation of recent time series classification algorithms

Middlehurst,

Schäfer,

Bagnall

2024

Data Min Knowl Disc

View full text Add to dashboard Cite

In 2017, a research paper (Bagnall et al. Data Mining and Knowledge Discovery 31(3):606-660. 2017) compared 18 Time Series Classification (TSC) algorithms on 85 datasets from the University of California, Riverside (UCR) archive. This study, commonly referred to as a ‘bake off’, identified that only nine algorithms performed significantly better than the Dynamic Time Warping (DTW) and Rotation Forest benchmarks that were used. The study categorised each algorithm by the type of feature they extract from time series data, forming a taxonomy of five main algorithm types. This categorisation of algorithms alongside the provision of code and accessible results for reproducibility has helped fuel an increase in popularity of the TSC field. Over six years have passed since this bake off, the UCR archive has expanded to 112 datasets and there have been a large number of new algorithms proposed. We revisit the bake off, seeing how each of the proposed categories have advanced since the original publication, and evaluate the performance of newer algorithms against the previous best-of-category using an expanded UCR archive. We extend the taxonomy to include three new categories to reflect recent developments. Alongside the originally proposed distance, interval, shapelet, dictionary and hybrid based algorithms, we compare newer convolution and feature based algorithms as well as deep learning approaches. We introduce 30 classification datasets either recently donated to the archive or reformatted to the TSC format, and use these to further evaluate the best performing algorithm from each category. Overall, we find that two recently proposed algorithms, MultiROCKET+Hydra (Dempster et al. 2022) and HIVE-COTEv2 (Middlehurst et al. Mach Learn 110:3211-3243. 2021), perform significantly better than other approaches on both the current and new TSC problems.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Section: Deep Learningmentioning

confidence: 99%

Section: H-inceptiontimementioning

confidence: 99%

See 1 more Smart Citation

Bake off redux: a review and experimental evaluation of recent time series classification algorithms

Middlehurst,

Schäfer,

Bagnall

2024

Data Min Knowl Disc

View full text Add to dashboard Cite

show abstract

Finding Foundation Models for Time Series Classification with a PreText Task

Ismail-Fawaz,

Devanne,

Berretti

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

quant: a minimalist interval method for time series classification

Dempster,

Schmidt,

Webb

2024

Data Min Knowl Disc

View full text Add to dashboard Cite

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. This distillation of interval-based approaches represents a fast and accurate method for time series classification, achieving state-of-the-art accuracy on the expanded set of 142 datasets in the UCR archive with a total compute time (training and inference) of less than 15 min using a single CPU core.

show abstract

Deep Learning For Time Series Classification Using New Hand-Crafted Convolution Filters

Cited by 9 publications

References 30 publications

Bake off redux: a review and experimental evaluation of recent time series classification algorithms

Bake off redux: a review and experimental evaluation of recent time series classification algorithms

Finding Foundation Models for Time Series Classification with a PreText Task

quant: a minimalist interval method for time series classification

Contact Info

Product

Resources

About