pith. sign in

arxiv: 2605.18268 · v1 · pith:3CHXWKJDnew · submitted 2026-05-18 · ⚛️ physics.plasm-ph

Time Series Extrinsic Regression of Ion Cyclotron Emission Spectra Trained on Particle-In-Cell Simulations

Ethan Attwood , J.W.S. Cook , Peter Hill This is my paper

Pith reviewed 2026-05-19 23:51 UTC · model grok-4.3

classification ⚛️ physics.plasm-ph
keywords ion cyclotron emissionparticle-in-cell simulationstime series extrinsic regressionplasma diagnosticsmagnetoacoustic cyclotron instabilityJET tokamakalpha particlesparameter inference
0
0 comments X

The pith

Time series extrinsic regression models recover bulk and fast ion parameters from ion cyclotron emission spectra with near real-time capability.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper demonstrates that time series extrinsic regression models trained on synthetic spectra can solve the inverse problem of mapping observed ion cyclotron emission spectra back to underlying plasma parameters. Training data comes from particle-in-cell simulations that sweep over reactor-relevant values of magnetic field strength, density, alpha-particle pitch angle, and concentration. A sympathetic reader would care because this offers a practical diagnostic route for extracting key plasma conditions from measurements on devices like JET. The work shows the approach achieves near real-time performance once the models are trained.

Core claim

By training Time-Series Extrinsic Regression models on synthetic ICE spectra generated from oblique propagation angle sweeps of nonlinear fully kinetic 1D3V particle-in-cell simulations of the magnetoacoustic cyclotron instability, and using a systematic scan over reactor-relevant ranges of background magnetic field strength, density, and alpha-particle velocity pitch and concentration, these bulk and fast ion parameters may be recovered from a JET ICE spectrum via TSER models with near real-time capability.

What carries the argument

Time-Series Extrinsic Regression (TSER) models trained on synthetic spectra from 1D3V particle-in-cell simulations of the magnetoacoustic cyclotron instability.

If this is right

  • Bulk plasma parameters including magnetic field strength and density can be inferred directly from observed ICE spectra.
  • Fast ion parameters such as alpha-particle pitch and concentration are recoverable with the same models.
  • The method provides near real-time inference once training is complete, enabling diagnostic use during experiments.
  • Synthetic data from the simulations is representative enough to train models that work on experimental JET spectra.
  • The inverse mapping from ICE spectrum to plasma state is solved for the scanned parameter ranges.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This regression approach could be tested on ICE data from other tokamaks to check cross-device generalization.
  • Higher-dimensional simulations might reduce discrepancies between synthetic and observed spectra.
  • The trained models could be coupled to real-time control loops for plasma parameter adjustment during discharges.
  • Similar extrinsic regression techniques might apply to spectra from other plasma instabilities for parameter recovery.

Load-bearing premise

The synthetic spectra from the particle-in-cell simulations have statistical properties sufficiently close to real JET observations for the trained models to generalize.

What would settle it

If TSER predictions of magnetic field, density, and alpha-particle parameters from actual JET ICE spectra deviate substantially from independent measurements of those same quantities, the generalization claim is falsified.

Figures

Figures reproduced from arXiv: 2605.18268 by Ethan Attwood, J.W.S. Cook, Peter Hill.

Figure 1
Figure 1. Figure 1: FIG. 1: Frequency power spectra in [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: FIG. 2: TSER results of a leave-one-out cross-validation [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: FIG. 3: Hydra-generated normalised predictions of each [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: FIG. 4: Predictions made by TSER models trained on [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
read the original abstract

Ion Cyclotron Emission (ICE) is a ubiquitous magnetised plasma phenomenon previously detected on virtually all large magnetic fusion devices and whose diagnostic potential for future power plants rests upon an accurate mapping of plasma parameters to spectra. This work demonstrates that the inverse problem is solved by training Time-Series Extrinsic Regression (TSER) models on synthetic ICE spectra from oblique propagation angle sweeps of nonlinear fully kinetic 1D3V particle-in-cell simulations of the magnetoacoustic cyclotron instability. Using datasets from a systematically constructed scan over reactor-relevant ranges of background magnetic field strength, density, and alpha-particle velocity pitch ($v_\parallel/|v|$) and concentration, we show that these bulk and fast ion parameters may be recovered from a JET ICE spectrum via TSER models with near real-time capability.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript demonstrates that Time Series Extrinsic Regression (TSER) models trained on synthetic ICE spectra—generated from oblique-angle sweeps of nonlinear fully kinetic 1D3V PIC simulations of the magnetoacoustic cyclotron instability—can recover reactor-relevant plasma parameters (background magnetic field strength, density, alpha-particle velocity pitch v_parallel/|v|, and concentration) from a JET experimental ICE spectrum, with near real-time inference capability. Training data are drawn from a systematic scan over relevant ranges of these parameters.

Significance. If the central claim holds, the work provides a potentially useful fast diagnostic for inferring bulk and fast-ion parameters from ICE spectra in fusion devices. The systematic construction of the simulation dataset over reactor-relevant ranges is a clear strength, as is the focus on near real-time applicability. However, the significance hinges on whether the synthetic spectra reproduce the statistical properties of real JET observations; without that, the method remains an unvalidated simulation-to-simulation exercise.

major comments (2)
  1. [Abstract and §4] Abstract and §4 (Results): The claim that bulk and fast-ion parameters 'may be recovered' from a JET ICE spectrum is presented without quantitative error bars, cross-validation statistics, or direct comparison to alternative inversion techniques. This information is load-bearing for assessing whether the TSER models achieve useful accuracy on experimental data.
  2. [§3] §3 (Simulation and Dataset Construction): The generalization from synthetic to experimental spectra rests on the untested assumption that the 1D3V PIC spectra reproduce the peak locations, widths, relative amplitudes, and noise characteristics of real JET ICE observations. No similarity metrics, direct overlay comparisons, or statistical tests between synthetic and experimental spectra are reported, which directly affects the validity of applying the trained models to JET data.
minor comments (2)
  1. [§2] Clarify the precise TSER algorithm family, feature extraction steps, and any regularization or hyperparameter selection procedure used in the regression.
  2. [§3] Add explicit statements of the number of simulations, the exact ranges and sampling of the scanned parameters (B, n, v_parallel/|v|, alpha concentration), and the train/validation/test split sizes.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments, which help clarify the scope and limitations of our work. We address each major comment below and indicate the revisions we will make to the manuscript.

read point-by-point responses

  1. Referee: [Abstract and §4] Abstract and §4 (Results): The claim that bulk and fast-ion parameters 'may be recovered' from a JET ICE spectrum is presented without quantitative error bars, cross-validation statistics, or direct comparison to alternative inversion techniques. This information is load-bearing for assessing whether the TSER models achieve useful accuracy on experimental data.

    Authors: We agree that quantitative metrics strengthen the presentation of results on experimental data. In the revised manuscript we will expand §4 to report cross-validation statistics (including mean absolute error and R² scores) obtained on the synthetic dataset, together with uncertainty estimates on the parameters inferred from the JET spectrum. Direct comparison against alternative inversion methods lies outside the primary scope of this study, which introduces the TSER approach; we will add a short paragraph noting this as a natural direction for future work. revision: yes

  2. Referee: [§3] §3 (Simulation and Dataset Construction): The generalization from synthetic to experimental spectra rests on the untested assumption that the 1D3V PIC spectra reproduce the peak locations, widths, relative amplitudes, and noise characteristics of real JET ICE observations. No similarity metrics, direct overlay comparisons, or statistical tests between synthetic and experimental spectra are reported, which directly affects the validity of applying the trained models to JET data.

    Authors: We accept that explicit similarity metrics between the synthetic and experimental spectra are not provided in the current version. The 1D3V PIC simulations employ a well-established model of the magnetoacoustic cyclotron instability, and the parameter scan is constructed over reactor-relevant ranges. In the revision we will add a dedicated paragraph in §3 that (i) states the modeling assumptions, (ii) provides qualitative comparison of synthetic spectral features with published JET ICE characteristics, and (iii) explicitly notes the absence of quantitative similarity metrics as a limitation. This clarifies the scope without altering the central methodological contribution. revision: yes

Circularity Check

0 steps flagged

No circularity: training on independent PIC simulations and inference on separate JET spectra

full rationale

The paper trains TSER models on synthetic spectra generated from a parameter scan of 1D3V PIC simulations of the magnetoacoustic cyclotron instability. These simulations are constructed independently of the target JET experimental spectra. The central claim is that the trained models recover bulk and fast-ion parameters when applied to an actual JET ICE spectrum. This workflow does not reduce any prediction to a quantity fitted on the same data by construction, nor does it rely on a self-citation chain that substitutes for external validation. The derivation chain therefore remains self-contained against the external experimental benchmark; any limitation lies in simulation fidelity rather than internal circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the fidelity of existing PIC methods and the assumption that the chosen parameter scan spans the relevant physical regimes; no new physical constants or entities are introduced.

axioms (1)
  • domain assumption The magnetoacoustic cyclotron instability is the dominant mechanism producing the observed ICE spectra in both the simulations and the JET experiment.
    Invoked in the abstract when linking synthetic spectra to experimental signals.

pith-pipeline@v0.9.0 · 5665 in / 1256 out tokens · 44340 ms · 2026-05-19T23:51:58.884367+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

52 extracted references · 52 canonical work pages

  1. [1]

    Todd, Diagnostic systems in demo: engineering design issues, inAIP Conference Proceedings, Vol

    T. Todd, Diagnostic systems in demo: engineering design issues, inAIP Conference Proceedings, Vol. 1612 (Amer- ican Institute of Physics, 2014) pp. 9–16

    work page 2014

  2. [2]

    Cottrell and R

    G. Cottrell and R. Dendy, Superthermal radiation from fusion products in jet, Physical review letters60, 33 (1988)

    work page 1988

  3. [3]

    G. A. Cottrell, V. P. Bhatnagar, O. Da Costa, R. O. Dendy, J. Jacquinot, K. G. McClements, D. C. McCune, M. F. F. Nave, P. Smeulders, and D. F. H. Start, Ion cyclotron emission measurements during jet deuterium- tritium experiments, Nuclear Fusion33, 1365 (1993)

    work page 1993

  4. [4]

    F¨ ul¨ op and M

    T. F¨ ul¨ op and M. Lisak, Ion cyclotron emission from fu- sion products and beam ions in the tokamak fusion test reactor, Nuclear fusion38, 761 (1998)

    work page 1998

  5. [5]

    S. Sato, M. Ichimura, Y. Yamaguchi, M. Katano, Y. Imai, T. Murakami, Y. Miyake, T. Yokoyama, S. Moriyama, T. Kobayashi,et al., Observation of ion cyclotron emis- sion owing to dd fusion product h ions in jt-60u, Plasma and Fusion Research5, S2067 (2010)

    work page 2010

  6. [6]

    Dendy and K

    R. Dendy and K. McClements, Ion cyclotron emission from fusion-born ions in large tokamak plasmas: a brief review from jet and tftr to iter, Plasma Physics and con- trolled fusion57, 044002 (2015)

    work page 2015

  7. [7]

    McClements, R

    K. McClements, R. D’Inca, R. Dendy, L. Carbajal, S. C. Chapman, J. W. S. Cook, R. Harvey, W. Heidbrink, and S. D. Pinches, Fast particle-driven ion cyclotron emission (ice) in tokamak plasmas and the case for an ice diagnos- tic in iter, Nuclear Fusion55, 043013 (2015)

    work page 2015

  8. [8]

    N. N. Gorelenkov, Ion cyclotron emission studies: retro- spects and prospects, Plasma Physics Reports42, 430 (2016). 7

    work page 2016

  9. [9]

    K. G. McClements, A. Brisset, B. Chapman, S. C. Chap- man, R. O. Dendy, P. Jacquet, V. G. Kiptily, M. Mantsi- nen, B. C. G. Reman, and J. Contributors, Observations and modelling of ion cyclotron emission observed in jet plasmas using a sub-harmonic arc detection system dur- ing ion cyclotron resonance heating, Nuclear Fusion58, 096020 (2018)

    work page 2018

  10. [10]

    Ochoukov, V

    R. Ochoukov, V. Bobkov, B. Chapman, R. Dendy, M. Dunne, H. Faugel, M. Garc´ ıa-Mu˜ noz, B. Geiger, P. Hennequin, K. McClements,et al., Observations of core ion cyclotron emission on asdex upgrade tokamak, Review of Scientific Instruments89(2018)

    work page 2018

  11. [11]

    Askinazi, A

    L. Askinazi, A. Belokurov, D. Gin, V. Kornev, S. Lebe- dev, A. Shevelev, A. Tukachinsky, and N. Zhubr, Ion cy- clotron emission in nbi-heated plasmas in the tuman-3m tokamak, Nuclear Fusion58, 082003 (2018)

    work page 2018

  12. [12]

    K. E. Thome, D. C. Pace, R. I. Pinsker, M. A. Van Zee- land, W. W. Heidbrink, and M. E. Austin, Central ion cyclotron emission in the diii-d tokamak, Nuclear Fusion 59, 086011 (2019)

    work page 2019

  13. [13]

    L. Liu, X. Zhang, Y. Zhu, C. Qin, Y. Zhao, S. Yuan, Y. Mao, M. Li, K. Zhang, J. Cheng,et al., Ion cy- clotron emission driven by deuterium neutral beam injec- tion and core fusion reaction ions in east, Nuclear Fusion 60, 044002 (2020)

    work page 2020

  14. [14]

    Dendy, C

    R. Dendy, C. N. Lashmore-Davies, and K. Kam, A pos- sible excitation mechanism for observed superthermal ion cyclotron emission from tokamak plasmas, Physics of Fluids B: Plasma Physics4, 3996 (1992)

    work page 1992

  15. [15]

    R. O. Dendy, K. G. McClements, C. Lashmore-Davies, G. Cottrell, R. Majeski, and S. Cauffman, Ion cyclotron emission due to collective instability of fusion products and beam ions in tftr and jet, Nuclear fusion35, 1733 (1995)

    work page 1995

  16. [16]

    Fulop, Y

    T. Fulop, Y. I. Kolesnichenko, M. Lisak, and D. An- derson, Origin of superthermal ion cyclotron emission in tokamaks, Nuclear fusion37, 1281 (1997)

    work page 1997

  17. [17]

    Carbajal, R

    L. Carbajal, R. O. Dendy, S. C. Chapman, and J. W. S. Cook, Linear and nonlinear physics of the magnetoacous- tic cyclotron instability of fusion-born ions in relation to ion cyclotron emission, Physics of Plasmas21(2014)

    work page 2014

  18. [18]

    Ochoukov, K

    R. Ochoukov, K. McClements, R. Bilato, V. Bobkov, B. Chapman, S. Chapman, R. Dendy, M. Dreval, H. Faugel, J.-M. Noterdaeme,et al., Interpretation of core ion cyclotron emission driven by sub-alfv´ enic beam- injected ions via magnetoacoustic cyclotron instability, Nuclear Fusion59, 086032 (2019)

    work page 2019

  19. [19]

    Chapman, R

    B. Chapman, R. O. Dendy, S. C. Chapman, K. G. Mc- Clements, and R. Ochoukov, Origin of ion cyclotron emis- sion at the proton cyclotron frequency from the core of deuterium plasmas in the asdex-upgrade tokamak, Plasma Physics and Controlled Fusion62, 095022 (2020)

    work page 2020

  20. [20]

    T. W. Slade-Harajda, J. W. S. Cook, R. O. Dendy, and S. C. Chapman, Effects of deuterium-tritium mix on lin- ear growth rates of the magnetoacoustic cyclotron insta- bility in fusion plasmas, Physics of Plasmas32(2025)

    work page 2025

  21. [21]

    K. G. McClements, R. O. Dendy, C. N. Lashmore-Davies, G. A. Cottrell, S. Cauffman, and R. Majeski, Interpre- tation of ion cyclotron emission from sub-alfv´ enic fusion products in the tokamak fusion test reactor, Physics of Plasmas3, 543 (1996)

    work page 1996

  22. [22]

    B. C. G. Reman, R. O. Dendy, T. Akiyama, S. C. Chap- man, J. W. S. Cook, H. Igami, S. Inagaki, K. Saito, and G. Yun, Interpreting observations of ion cyclotron emis- sion from large helical device plasmas with beam-injected ion populations, Nuclear Fusion59, 096013 (2019)

    work page 2019

  23. [23]

    R. W. Hockney and J. W. Eastwood,Computer simula- tion using particles(CRC Press, 1988)

    work page 1988

  24. [24]

    C. K. Birdsall and A. B. Langdon,Plasma physics via computer simulation(CRC Press, 1991)

    work page 1991

  25. [25]

    T. D. Arber, K. Bennett, C. S. Brady, A. Lawrence- Douglas, M. G. Ramsay, N. J. Sircombe, P. Gillies, R. G. Evans, H. Schmitz, A. R. Bell, and C. P. Ridgers, Contemporary particle-in-cell approach to laser-plasma modelling, Plasma Physics and Controlled Fusion57, 1 (2015)

    work page 2015

  26. [26]

    J. W. S. Cook, R. O. Dendy, and S. C. Chapman, Particle-in-cell simulations of the magnetoacoustic cy- clotron instability of fusion-born alpha-particles in toka- mak plasmas, Plasma Physics and Controlled Fusion55, 065003 (2013)

    work page 2013

  27. [27]

    Chapman, R

    B. Chapman, R. O. Dendy, S. C. Chapman, L. A. Hol- land, S. W. A. Irvine, and B. C. G. Reman, Compar- ing theory and simulation of ion cyclotron emission from energetic ion populations with spherical shell and ring- beam distributions in velocity-space, Plasma Physics and Controlled Fusion62, 055003 (2020)

    work page 2020

  28. [28]

    R. O. Dendy, B. Chapman-Oplopoiou, B. C. G. Re- man, and J. W. S. Cook, Mechanism for collective energy transfer from neutral beam-injected ions to fusion-born alpha particles on cyclotron timescales in a plasma, Phys- ical Review Letters130, 105102 (2023)

    work page 2023

  29. [29]

    J. W. S. Cook, Doublet splitting of fusion alpha particle driven ion cyclotron emission, Plasma Physics and Con- trolled Fusion64, 115002 (2022)

    work page 2022

  30. [30]

    Chapman, R

    B. Chapman, R. O. Dendy, S. C. Chapman, K. G. Mc- Clements, G. S. Yun, S. G. Thatipamula, and M. Kim, Nonlinear wave interactions generate high-harmonic cy- clotron emission from fusion-born protons during a kstar elm crash, Nuclear Fusion58, 096027 (2018)

    work page 2018

  31. [31]

    C. W. Tan, C. Bergmeir, F. Petitjean, and G. I. Webb, Time series extrinsic regression: Predicting numeric val- ues from time series data, Data Mining and Knowledge Discovery35, 1032 (2021)

    work page 2021

  32. [32]

    Gorelenkov and C

    N. Gorelenkov and C. Cheng, Alfv´ en cyclotron instabil- ity and ion cyclotron emission, Nuclear fusion35, 1743 (1995)

    work page 1995

  33. [33]

    Gormezano, C

    C. Gormezano, C. Challis, E. Joffrin, X. Litaudon, and A. Sips, Chapter 4: Advanced tokamak scenario devel- opment at jet, Fusion science and technology53, 958 (2008)

    work page 2008

  34. [34]

    A. C. C. Sips, for the Steady State Operation, and the Transport Physics topical groups of the International Tokamak Physics Activity, Advanced scenarios for iter operation, Plasma Physics and Controlled Fusion47, A19 (2005)

    work page 2005

  35. [35]

    Tholerus, F

    E. Tholerus, F. Casson, S. Marsden, T. Wilson, D. Brunetti, P. Fox, S. Freethy, T. Hender, S. Henderson, A. Hudoba, K. Kirov, F. Koechl, H. Meyer, S. Muldrew, C. Olde, B. Patel, C. Roach, S. Saarelma, G. Xia, and the STEP team, Flat-top plasma operational space of the step power plant, Nuclear Fusion64, 106030 (2024)

    work page 2024

  36. [36]

    Beckett, J

    G. Beckett, J. Beech-Brandt, K. Leach, Z. Payne, A. Simpson, L. Smith, A. Turner, and A. Whiting, Archer2 service description (2024)

    work page 2024

  37. [37]

    T. W. Slade-Harajda, S. C. Chapman, and R. O. Dendy, The consequences of tritium mix for simulated ion cy- clotron emission spectra from deuterium-tritium plas- 8 mas, Nuclear Fusion64, 126051 (2024)

    work page 2024

  38. [38]

    Lanti, N

    E. Lanti, N. Ohana, N. Tronko, T. Hayward-Schneider, A. Bottino, B. F. McMillan, A. Mishchenko, A. Schein- berg, A. Biancalani, P. Angelino,et al., Orb5: a global electromagnetic gyrokinetic code using the pic approach in toroidal geometry, Computer Physics Communications 251, 107072 (2020)

    work page 2020

  39. [39]

    M. Wang, C. Wan, J. Lu, Z. Yu, B. Xiao, Y. Li, X. He, Z. Luo, Q. Yuan, Y. Hu,et al., Time series extrinsic re- gression for reconstructing missing electron temperature in tokamak, Nuclear Fusion65, 076008 (2025)

    work page 2025

  40. [40]

    Bagnall, M

    A. Bagnall, M. Middlehurst, G. Forestier, A. Ismail- Fawaz, A. Guillaume, D. Guijo-Rubio, C. W. Tan, A. Dempster, and G. I. Webb, A hands-on introduction to time series classification and regression, inProceedings of the 30th ACM SIGKDD Conference on Knowledge Dis- covery and Data Mining(2024) pp. 6410–6411

    work page 2024

  41. [41]

    Guijo-Rubio, M

    D. Guijo-Rubio, M. Middlehurst, G. Arcencio, D. F. Silva, and A. Bagnall, Unsupervised feature based algo- rithms for time series extrinsic regression, Data Mining and Knowledge Discovery38, 2141 (2024)

    work page 2024

  42. [42]

    Middlehurst and A

    M. Middlehurst and A. Bagnall, Extracting features from random subseries: A hybrid pipeline for time series clas- sification and extrinsic regression, inInternational Work- shop on Advanced Analytics and Learning on Temporal Data(Springer, 2023) pp. 113–126

    work page 2023

  43. [43]

    Middlehurst, A

    M. Middlehurst, A. Ismail-Fawaz, A. Guillaume, C. Holder, D. Guijo-Rubio, G. Bulatova, L. Tsaprounis, L. Mentel, M. Walter, P. Sch¨ afer, and A. Bagnall, Aeon: a python toolkit for learning from time series, Journal of Machine Learning Research25, 1 (2024)

    work page 2024

  44. [44]

    C. H. Lubba, S. S. Sethi, P. Knaute, S. R. Schultz, B. D. Fulcher, and N. S. Jones, Catch22: Canonical time- series characteristics: Selected through highly compara- tive time-series analysis, Data mining and knowledge dis- covery33, 1821 (2019)

    work page 2019

  45. [45]

    Dempster, D

    A. Dempster, D. F. Schmidt, and G. I. Webb, Hy- dra: Competing convolutional kernels for fast and ac- curate time series classification (2022), arXiv:2203.13652 [cs.LG]

    work page arXiv 2022

  46. [46]

    Dempster, D

    A. Dempster, D. F. Schmidt, and G. I. Webb, Minirocket: A very fast (almost) deterministic transform for time series classification, inProceedings of the 27th ACM SIGKDD conference on knowledge discovery & data min- ing(2021) pp. 248–257

    work page 2021

  47. [47]

    C. W. Tan, A. Dempster, C. Bergmeir, and G. I. Webb, Multirocket: multiple pooling operators and transforma- tions for fast and effective time series classification, arXiv preprint arXiv:2102.00457 (2021)

    work page arXiv 2021

  48. [48]

    Dempster, D

    A. Dempster, D. F. Schmidt, and G. I. Webb, Quant: A minimalist interval method for time series classification, Data Mining and Knowledge Discovery38, 2377 (2024)

    work page 2024

  49. [49]

    Lines, S

    J. Lines, S. Taylor, and A. Bagnall, Time series classifi- cation with hive-cote: The hierarchical vote collective of transformation-based ensembles, ACM Transactions on Knowledge Discovery from Data (TKDD)12, 1 (2018)

    work page 2018

  50. [50]

    Guillaume, C

    A. Guillaume, C. Vrain, and W. Elloumi, Random di- lated shapelet transform: A new approach for time se- ries shapelets, inInternational Conference on Pattern Recognition and Artificial Intelligence(Springer, 2022) pp. 653–664

    work page 2022

  51. [51]

    H. Deng, G. Runger, E. Tuv, and M. Vladimir, A time series forest for classification and feature extraction, In- formation Sciences239, 142 (2013)

    work page 2013

  52. [52]

    Middlehurst, P

    M. Middlehurst, P. Sch¨ afer, and A. Bagnall, Bake off re- dux: a review and experimental evaluation of recent time series classification algorithms, Data Mining and Knowl- edge Discovery38, 1958 (2024)

    work page 1958