pith. sign in

arxiv: 2512.00667 · v2 · pith:4GSJAGHMnew · submitted 2025-11-29 · 📡 eess.SY · cs.RO· cs.SY

Active Learning of Fractional-Order Viscoelastic Model Parameters for Realistic Haptic Rendering

Harun Tolasa , Gorkem Gemalmaz , Volkan Patoglu This is my paper

Pith reviewed 2026-05-21 18:46 UTC · model grok-4.3

classification 📡 eess.SY cs.ROcs.SY
keywords fractional-order viscoelastic modelshaptic renderinghuman-in-the-loop optimizationactive learningperceived realismmedical simulatorstissue modelingparameter identification
0
0 comments X

The pith

Human-in-the-loop active learning tunes fractional-order viscoelastic model parameters to deliver high perceived realism in haptic tissue rendering.

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

The paper establishes that fractional-order models, which describe viscoelastic tissue behavior including creep and relaxation with few parameters, can have their unintuitive parameters systematically optimized using qualitative human feedback in an active learning loop. This human-in-the-loop process produces parameter sets that consistently earn high realism ratings from individual users during haptic rendering. The authors further show how to aggregate many such individual optimizations into a population-level perceptual map from which broadly effective parameters can be selected. If these steps hold, medical training simulators could render biological tissues with noticeably better sim-to-real fidelity than current integer-order or untuned fractional models.

Core claim

Fractional-order viscoelastic models can be parameterized through active learning driven by human-in-the-loop qualitative feedback to achieve consistently high perceived realism ratings for each individual user. These individual results can then be rigorously combined into an aggregate perceptual map that supports selection of population-level optimal parameters, which experiments on three viscoelastic materials confirm are broadly perceived as realistic.

What carries the argument

Human-in-the-loop (HiL) active learning optimization that iteratively refines the fractional order and associated coefficients using qualitative realism feedback, followed by aggregation into a perceptual map for population-level parameter selection.

If this is right

  • Optimized parameters for each individual produce consistently high realism ratings in haptic rendering of viscoelastic materials.
  • Aggregation of individual HiL results yields a perceptual map from which population-level parameters can be extracted.
  • Generalized fractional-order models improve the match between simulated and real tissue behavior in medical training simulators.
  • The approach works across three distinct viscoelastic materials tested in human-subject experiments.

Where Pith is reading between the lines

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

  • The same HiL-plus-aggregation pipeline could be applied to other haptic domains where material memory effects matter, such as virtual surgery or robotic teleoperation.
  • Once a population map exists, new users might be matched to nearby parameter sets without running a full individual optimization.
  • If the perceptual map proves stable, it could serve as a starting point for further refinement by machine-learning surrogates of human feedback.

Load-bearing premise

Qualitative human feedback supplied during active learning can reliably locate parameter values for fractional-order models that produce high realism ratings across users.

What would settle it

A human-subject study in which participants rate the realism of haptic renderings using the HiL-optimized and aggregated parameters against a control set of non-optimized fractional or integer-order parameters, with no statistically significant improvement in average ratings.

Figures

Figures reproduced from arXiv: 2512.00667 by Gorkem Gemalmaz, Harun Tolasa, Volkan Patoglu.

Figure 1
Figure 1. Figure 1: Fractional-order standard linear solid model [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Experimental data from (a) stress relaxation experiment under a constant deformation, and (b) creep with recovery [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: (a) The experimental setup with a participant. (b) Two [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: The progression of the posterior GP model of perceived realism depicted at various trials of the HiL optimization for [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: NRMSE between each participant’s current best pre [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: Different slices from the posterior of the aggregate GP model with fixed [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Confusion matrices for the aggregate GP model. The [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: (a) The estimates of the population-level optimal parameter sets, if the individual models were trained up to 5, 15, [PITH_FULL_IMAGE:figures/full_fig_p010_9.png] view at source ↗
Figure 8
Figure 8. Figure 8: Figure 8(a) demonstrates the success of the aggregate [PITH_FULL_IMAGE:figures/full_fig_p011_8.png] view at source ↗
read the original abstract

Effective medical simulators necessitate realistic haptic rendering of biological tissues that exhibit viscoelastic material properties, such as creep and stress relaxation. Fractional-order models provide an effective means of describing intrinsically time-dependent viscoelastic dynamics with few parameters, as they naturally capture memory effects. However, due to the unintuitive, frequency-dependent coupling among the order of the fractional element and other parameters, determining appropriate parameter values for fractional-order models that yield high perceived realism remains a significant challenge. In this study, we propose a systematic means of determining the parameters of fractional-order viscoelastic models that optimizes the perceived realism of haptic rendering across general populations. First, we demonstrate that the parameters of fractional-order models can be effectively optimized through active learning, using qualitative feedback-based human-in-the-loop (HiL) optimization, to ensure consistently high realism ratings for each individual. Second, we propose a rigorous method to combine HiL optimization results into an aggregate perceptual map trained on the entire dataset, and demonstrate how to select population-level optimal parameters from this representation that are broadly perceived as realistic across general populations. Finally, we provide evidence of the effectiveness of the generalized fractional-order viscoelastic model parameters for three viscoelastic materials by characterizing their perceived realism through human-subject experiments. Overall, generalized fractional-order viscoelastic models established through the proposed HiL optimization and aggregation approach possess the potential to significantly improve the sim-to-real transition performance of medical training simulators.

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 / 1 minor

Summary. The paper claims that fractional-order viscoelastic models can be effectively parameterized for high perceived realism in haptic rendering by using active learning with human-in-the-loop (HiL) optimization based on qualitative feedback. It first optimizes parameters individually, then aggregates results across subjects into a population-level perceptual map from which broadly realistic parameters are selected, and finally validates the approach via human-subject experiments on three viscoelastic materials, asserting potential for improved sim-to-real performance in medical training simulators.

Significance. If the results hold, the work provides a systematic, perception-driven method to tune fractional-order models that naturally capture memory effects and time-dependent viscoelastic behavior with few parameters. The HiL approach with qualitative feedback offers a direct route to realism that avoids purely mathematical fitting, which could meaningfully advance haptic fidelity in medical simulators where sim-to-real gaps remain a practical barrier.

major comments (2)
  1. [Aggregation and population-level selection procedure] The aggregation procedure for deriving population-level parameters from per-subject HiL optima (described in the method for combining results into an aggregate perceptual map) lacks any reported validation on held-out subjects. The central claim that the selected parameters are 'broadly perceived as realistic across general populations' therefore rests on an untested assumption of low inter-subject variability; if variability in preferred fractional orders or coefficients is substantial, the aggregate map could systematically underperform for new users, directly undermining the asserted sim-to-real improvement.
  2. [Human-subject experiments and results] The human-subject experiments on three materials report no quantitative metrics (e.g., mean realism ratings with standard deviations, statistical comparisons to baselines, or error analysis), nor details on the active learning query selection and feedback aggregation steps. Without these, the evidence for 'consistently high realism ratings' and overall effectiveness remains insufficient to support the effectiveness claims.
minor comments (1)
  1. [Model formulation] Notation for the fractional-order element and its coupling to other viscoelastic parameters could be clarified with an explicit equation or diagram early in the methods, as the unintuitive frequency-dependent interactions are central to the motivation.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive feedback. We address each major comment below and outline the revisions we will make to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Aggregation and population-level selection procedure] The aggregation procedure for deriving population-level parameters from per-subject HiL optima (described in the method for combining results into an aggregate perceptual map) lacks any reported validation on held-out subjects. The central claim that the selected parameters are 'broadly perceived as realistic across general populations' therefore rests on an untested assumption of low inter-subject variability; if variability in preferred fractional orders or coefficients is substantial, the aggregate map could systematically underperform for new users, directly undermining the asserted sim-to-real improvement.

    Authors: We agree that explicit validation on held-out subjects is needed to substantiate the generalizability claim. In the revised manuscript we will add a leave-one-subject-out cross-validation analysis of the aggregate perceptual map, reporting prediction error on unseen subjects together with observed inter-subject variability in the per-subject optima. This will directly test the low-variability assumption and quantify the expected performance drop for new users. revision: yes

  2. Referee: [Human-subject experiments and results] The human-subject experiments on three materials report no quantitative metrics (e.g., mean realism ratings with standard deviations, statistical comparisons to baselines, or error analysis), nor details on the active learning query selection and feedback aggregation steps. Without these, the evidence for 'consistently high realism ratings' and overall effectiveness remains insufficient to support the effectiveness claims.

    Authors: The original submission indeed omitted these quantitative details and algorithmic specifics. We will revise the methods section to describe the active-learning query selection criterion and the exact procedure used to aggregate qualitative feedback across iterations and subjects. In the results we will report mean realism ratings with standard deviations, statistical comparisons against baseline integer-order models, and any error analysis performed. These additions will provide the quantitative support required for the effectiveness claims. revision: yes

Circularity Check

0 steps flagged

No significant circularity: approach relies on external human feedback and empirical validation.

full rationale

The paper determines fractional-order model parameters via active learning with qualitative human-in-the-loop (HiL) feedback from individual subjects, then aggregates results into a perceptual map trained on the collected dataset and validates perceived realism through separate human-subject experiments. This chain incorporates external perceptual data at each stage rather than reducing any claimed prediction or population-level result to a self-definition, fitted input renamed as output, or self-citation chain. No equations or steps in the provided text exhibit the enumerated circularity patterns; the derivation remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that fractional-order models capture viscoelastic dynamics effectively and that human feedback can guide optimization despite unintuitive parameter couplings; no free parameters are explicitly fitted in the abstract beyond the learned model parameters themselves.

free parameters (1)
  • fractional order and viscoelastic parameters
    These parameters are tuned via human-in-the-loop active learning but their specific values are not fixed a priori and depend on perceptual feedback.
axioms (1)
  • domain assumption Fractional-order models provide an effective means of describing intrinsically time-dependent viscoelastic dynamics with few parameters as they naturally capture memory effects.
    Directly stated in the abstract as the motivation for using these models over traditional approaches.

pith-pipeline@v0.9.0 · 5786 in / 1351 out tokens · 56285 ms · 2026-05-21T18:46:06.253600+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Haptic Rendering of Fractional-Order Viscoelasticity: Passivity and Rendering Fidelity

    cs.RO 2026-05 unverdicted novelty 7.0

    Unified passivity framework for fractional-order viscoelastic haptic rendering that generalizes integer-order Kelvin-Voigt, Maxwell, and SLS models with symbolic stiffness and damping expressions.

  2. Human-in-the-Loop Pareto Optimization: Trade-off Characterization for Assist-as-Needed Training and Performance Evaluation

    cs.RO 2026-03 unverdicted novelty 7.0

    A human-in-the-loop Pareto optimization framework characterizes trade-offs between performance and challenge in assist-as-needed motor training, enabling protocol design and fair evaluation even when users cannot comp...

Reference graph

Works this paper leans on

48 extracted references · 48 canonical work pages · cited by 2 Pith papers

  1. [1]

    Haptic rendering: Programming touch interaction with virtual objects,

    K. Salisbury, D. Brock, T. Massie, N. Swarup, and C. Zilles, “Haptic rendering: Programming touch interaction with virtual objects,” in Proceedings of the Symposium on Interactive 3D graphics, 1995, pp. 123–130

    work page 1995

  2. [2]

    Characterizing viscoelastic properties of human melanoma tissue using prony series,

    S. Park, A. L. Chien, I. D. Brown, and J. Chen, “Characterizing viscoelastic properties of human melanoma tissue using prony series,” Frontiers in Bioengineering and Biotechnology, vol. 11, p. 1162880, 2023. TRANSACTIONS ON HAPTICS, VOL. XX, NO. XX, XX XX 13

    work page 2023

  3. [3]

    The fractional viscoelastic response of human breast tissue cells,

    B. Carmichael, H. Babahosseini, S. N. Mahmoodi, and M. Agah, “The fractional viscoelastic response of human breast tissue cells,”Physical Biology, vol. 12, no. 4, p. 046001, 2015

    work page 2015

  4. [4]

    Noninvasive assessment of the rheological behavior of human organs using multi- frequency mr elastography: a study of brain and liver viscoelasticity,

    D. Klatt, U. Hamhaber, P. Asbach, J. Braun, and I. Sack, “Noninvasive assessment of the rheological behavior of human organs using multi- frequency mr elastography: a study of brain and liver viscoelasticity,” Physics in Medicine & Biology, vol. 52, no. 24, p. 7281, 2007

    work page 2007

  5. [5]

    The fractional viscoelastic response of human breast tissue cells,

    B. Carmichael, H. Babahosseini, S. Mahmoodi, and M. Agah, “The fractional viscoelastic response of human breast tissue cells,”Physical biology, vol. 12, no. 4, p. 046001, 2015

    work page 2015

  6. [6]

    Fractional viscoelastic models for power-law materials,

    A. Bonfanti, J. L. Kaplan, G. Charras, and A. Kabla, “Fractional viscoelastic models for power-law materials,”Soft matter, vol. 16, no. 26, pp. 6002–6020, 2020

    work page 2020

  7. [7]

    J. D. Ferry,Viscoelastic Properties of Polymers, 3rd ed. New York: John Wiley & Sons, 1980

    work page 1980

  8. [8]

    Zener,Elasticity and Anelasticity of Metals

    C. Zener,Elasticity and Anelasticity of Metals. Chicago: University of Chicago Press, 1948

    work page 1948

  9. [9]

    A method of analyzing experimental results obtained from elasto–viscous bodies,

    A. Gemant, “A method of analyzing experimental results obtained from elasto–viscous bodies,”Physics, vol. 7, no. 8, pp. 311–317, 1936. [Online]. Available: https://pubs.aip.org/aip/jap/article/7/8/311/1026892

    work page 1936

  10. [10]

    A generalized derivative model for an elastomer damper,

    R. L. Bagley and P. J. Torvik, “A generalized derivative model for an elastomer damper,”Shock and Vibration Bulletin, vol. 49, pp. 135–143, 1979

    work page 1979

  11. [11]

    A theoretical basis for the application of fractional calculus to viscoelasticity,

    R. Bagley and P. Torvik, “A theoretical basis for the application of fractional calculus to viscoelasticity,”Journal of Rheology, vol. 27, no. 3, pp. 201–210, 1983. [Online]. Available: https: //doi.org/10.1122/1.549724

    work page doi:10.1122/1.549724 1983

  12. [12]

    Applications of fractional calculus to the theory of viscoelasticity,

    R. C. Koeller, “Applications of fractional calculus to the theory of viscoelasticity,”Journal of Applied Mechanics, vol. 51, no. 2, pp. 299–307, 1984. [Online]. Available: https://doi.org/10.1115/1.3167616

    work page doi:10.1115/1.3167616 1984

  13. [13]

    Virtual environments for medical training: Graphical and haptic simulation of laparoscopic com- mon bile duct exploration,

    C. Basdogan, C.-H. Ho, and M. A. Srinivasan, “Virtual environments for medical training: Graphical and haptic simulation of laparoscopic com- mon bile duct exploration,”IEEE/ASME Transactions on Mechatronics, vol. 6, no. 3, pp. 269–285, 2001

    work page 2001

  14. [14]

    Haptic rendering in virtual environ- ments,

    C. Basdogan and M. A. Srinivasan, “Haptic rendering in virtual environ- ments,” inHandbook of Virtual Environments: Design, Implementation, and Applications, K. M. Stanney, Ed. Mahwah, NJ: Lawrence Erlbaum Associates, 2002, pp. 117–134

    work page 2002

  15. [15]

    Stability of haptic systems with fractional order controllers,

    O. Tokatli and V . Patoglu, “Stability of haptic systems with fractional order controllers,” inIEEE International Conference on Intelligent Robots and Systems, 2015, pp. 1172–1177

    work page 2015

  16. [16]

    Using fractional order elements for haptic rendering,

    O. Tokatlı and V . Patoglu, “Using fractional order elements for haptic rendering,” inProceedings of the International Symposium on Robotics Research, Levante, Italy, 2015

    work page 2015

  17. [17]

    Fractional order admittance control for physical human-robot interaction,

    Y . Aydin, O. Tokatli, V . Patoglu, and C. Basdogan, “Fractional order admittance control for physical human-robot interaction,” inIEEE World Haptics Conference, 2017, pp. 257–262

    work page 2017

  18. [18]

    Stable physical human-robot interaction using fractional order admittance control,

    Y . Aydin, O. Tokatli, V . Patoglu, and C. Basdogan, “Stable physical human-robot interaction using fractional order admittance control,”IEEE Transactions on Haptics, vol. 11, no. 3, pp. 464–475, 2018

    work page 2018

  19. [19]

    A computational multicriteria optimization approach to controller design for physical human-robot interaction,

    Y . Aydin, O. Tokatli, V . Patoglu, and C. Basdogan, “A computational multicriteria optimization approach to controller design for physical human-robot interaction,”IEEE Transactions on Robotics, vol. 36, no. 6, pp. 1791–1804, 2020

    work page 2020

  20. [20]

    A variable-fractional order admittance controller for pHRI,

    D. Sirintuna, Y . Aydin, O. Caldiran, O. Tokatli, V . Patoglu, and C. Bas- dogan, “A variable-fractional order admittance controller for pHRI,” in IEEE International Conference on Robotics and Automation, 2020, pp. 10 162–10 168

    work page 2020

  21. [21]

    Bayesian classification with Gaussian processes,

    C. Williams and D. Barber, “Bayesian classification with Gaussian processes,”IEEE Transactions on Pattern Analysis and Machine Intel- ligence, vol. 20, no. 12, pp. 1342–1351, 1998

    work page 1998

  22. [22]

    C. E. Rasmussen and C. K. I. Williams,Gaussian Processes for Machine Learning. MIT Press, 2005, vol. 7, no. 5

    work page 2005

  23. [23]

    Preference learning with Gaussian pro- cesses,

    W. Chu and Z. Ghahramani, “Preference learning with Gaussian pro- cesses,” inInternational Conference on Machine Learning, 2005, pp. 137–144

    work page 2005

  24. [24]

    Adaptive nonparametric psychophysics,

    L. Owen, J. Browder, B. Letham, G. Stocek, C. Tymms, and M. Shvartsman, “Adaptive nonparametric psychophysics,”CoRR, 2021. [Online]. Available: https://arxiv.org/abs/2104.09549

    work page arXiv 2021

  25. [25]

    Psychophysical detection testing with bayesian active learning,

    J. R. Gardner, X. Song, K. Q. Weinberger, Barbour, D. L., and J. P. Cunningham, “Psychophysical detection testing with bayesian active learning,” inProceedings of the Conference on Uncertainty in Artificial Intelligence, 2015

    work page 2015

  26. [26]

    Audiogram estimation using bayesian active learning,

    J. Schlittenlacher, R. Turner, and B. Moore, “Audiogram estimation using bayesian active learning,”The Journal of the Acoustical Society of America, vol. 144, pp. 421–430, 07 2018

    work page 2018

  27. [27]

    Bayesian active probabilistic classification for psychometric field estimation,

    X. Song, K. Sukesan, and D. Barbour, “Bayesian active probabilistic classification for psychometric field estimation,”Attention, Perception, and Psychophysics, vol. 80, 2018

    work page 2018

  28. [28]

    Stiffness in virtual contact events: A non-parametric bayesian approach,

    J. Browder, S. Bochereau, F. van Beek, and R. King, “Stiffness in virtual contact events: A non-parametric bayesian approach,” inIEEE World Haptics Conference, 2019

    work page 2019

  29. [29]

    Human preference-based learning for high- dimensional optimization of exoskeleton walking gaits,

    M. Tucker, M. Cheng, E. Novoseller, R. Cheng, Y . Yue, J. W. Bur- dick, and A. D. Ames, “Human preference-based learning for high- dimensional optimization of exoskeleton walking gaits,” inIEEE Inter- national Conference on Robotics and Systems, 2020, pp. 3423–3430

    work page 2020

  30. [30]

    Active preference-based Gaussian process regression for reward learning,

    E. Biyik, N. Huynh, M. Kochenderfer, and D. Sadigh, “Active preference-based Gaussian process regression for reward learning,” in Robotics: Science and Systems, 2020

    work page 2020

  31. [31]

    ROIAL: Region of interest active learning for characterizing exoskeleton gait preference landscapes,

    K. Li, M. Tucker, E. Biyik, E. Novoseller, J. W. Burdick, Y . Sui, D. Sadigh, Y . Yue, and A. D. Ames, “ROIAL: Region of interest active learning for characterizing exoskeleton gait preference landscapes,” in IEEE International Conference on Robotics and Automation, 2021, pp. 3212–3218

    work page 2021

  32. [32]

    Preference-based learning for exoskeleton gait optimiza- tion,

    M. Tucker, E. Novoseller, C. Kann, Y . Sui, Y . Yue, J. W. Burdick, and A. D. Ames, “Preference-based learning for exoskeleton gait optimiza- tion,” inIEEE International Conference on Robotics and Automation, 2020, pp. 2351–2357

    work page 2020

  33. [33]

    Preference-based human-in-the-loop opti- mization for perceived realism of haptic rendering,

    B. Catkin and V . Patoglu, “Preference-based human-in-the-loop opti- mization for perceived realism of haptic rendering,”IEEE Transactions on Haptics, pp. 1–6, 2023

    work page 2023

  34. [34]

    Preference-driven texture modeling through interactive generation and search,

    S. Lu, M. Zheng, M. C. Fontaine, S. Nikolaidis, and H. Culbertson, “Preference-driven texture modeling through interactive generation and search,”IEEE Transactions on Haptics, vol. 15, no. 3, pp. 508–520, 2022

    work page 2022

  35. [35]

    Human-in-the-loop optimization of perceived realism of multi-modal haptic rendering under conflicting sensory cues,

    H. Tolasa, B. Catkin, and V . Patoglu, “Human-in-the-loop optimization of perceived realism of multi-modal haptic rendering under conflicting sensory cues,”IEEE Transactions on Haptics, vol. 18, no. 2, pp. 295– 311, 2025

    work page 2025

  36. [36]

    Meta-weighted Gaussian process experts for personal- ized forecasting of ad cognitive changes,

    O. Rudovic, Y . Utsumi, R. Guerrero, K. Peterson, D. Rueckert, and R. W. Picard, “Meta-weighted Gaussian process experts for personal- ized forecasting of ad cognitive changes,” inProceedings of Machine Learning for Healthcare Conference, vol. 106, 2019, pp. 181–196

    work page 2019

  37. [37]

    Spatially aggregated Gaussian processes with multivariate areal outputs,

    Y . Tanaka, T. Tanaka, T. Iwata, T. Kurashima, M. Okawa, Y . Akagi, and H. Toda, “Spatially aggregated Gaussian processes with multivariate areal outputs,”Advances in Neural Information Processing Systems, vol. 32, 2019

    work page 2019

  38. [38]

    A Bayesian Committee Machine,

    V . Tresp, “A Bayesian Committee Machine,”Neural Computation, vol. 12, no. 11, pp. 2719–2741, 11 2000

    work page 2000

  39. [39]

    Sparse Gaussian processes using pseudo-inputs,

    E. Snelson and Z. Ghahramani, “Sparse Gaussian processes using pseudo-inputs,” inAdvances in Neural Information Processing Systems, vol. 18. MIT Press, 2005

    work page 2005

  40. [40]

    When Gaussian process meets big data: A review of scalable gps,

    H. Liu, Y .-S. Ong, X. Shen, and J. Cai, “When Gaussian process meets big data: A review of scalable gps,”IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 11, pp. 4405–4423, 2020

    work page 2020

  41. [41]

    Ap- proximation methods for Gaussian process regression,

    J. Quinonero-Candela, C. E. Rasmussen, and C. K. I. Williams, “Ap- proximation methods for Gaussian process regression,” inLarge Scale Kernel Machines, 2007, pp. 203–223

    work page 2007

  42. [42]

    Variational learning of inducing variables in sparse Gaussian processes,

    M. Titsias, “Variational learning of inducing variables in sparse Gaussian processes,” inProceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, ser. Proceedings of Machine Learning Research, vol. 5, 2009, pp. 567–574

    work page 2009

  43. [43]

    A scalable hierarchical Gaussian process classifier,

    T. N. A. Nguyen, A. Bouzerdoum, and S. L. Phung, “A scalable hierarchical Gaussian process classifier,”IEEE Transactions on Signal Processing, vol. 67, no. 11, p. 3042–3057, 2019. [Online]. Available: https://doi.org/10.1109/TSP.2019.2911251

    work page doi:10.1109/tsp.2019.2911251 2019

  44. [44]

    Gaussian processes - iterative sparse approximations,

    L. Csat ´o, “Gaussian processes - iterative sparse approximations,” Ph.D. dissertation, Aston University, 03 2002

    work page 2002

  45. [45]

    Fractional order control - a tutorial,

    Y . Chen, I. Petras, and D. Xue, “Fractional order control - a tutorial,” inAmerican Control Conference, 2009, pp. 1397–1411

    work page 2009

  46. [46]

    Time-domain evaluation of fractional order con- trollers’ direct discretization methods,

    C. Ma and Y . Hori, “Time-domain evaluation of fractional order con- trollers’ direct discretization methods,”IEEJ Transactions on Industry Applications, vol. 124, no. 8, pp. 837–842, 2004

    work page 2004

  47. [47]

    Passivity of a class of sampled-data systems: application to haptic interfaces,

    J. Colgate and G. Schenkel, “Passivity of a class of sampled-data systems: application to haptic interfaces,” inProceedings of American Control Conference, vol. 3, 1994, pp. 3236–3240 vol.3

    work page 1994

  48. [48]

    Force-feedback surgical teleoperator: Con- troller design and palpation experiments,

    M. Mahvash, J. Gwilliam, R. Agarwal, B. Vagvolgyi, L.-M. Su, D. D. Yuh, and A. M. Okamura, “Force-feedback surgical teleoperator: Con- troller design and palpation experiments,” inSymposium on Haptic Interfaces for Virtual Environment and Teleoperator Systems, 2008, pp. 465–471. TRANSACTIONS ON HAPTICS, VOL. XX, NO. XX, XX XX 14 Harun Tolasareceived his B...

    work page 2008