Reactive Hand Movements from Arm Kinematics and EMG Signals Based on Hierarchical Gaussian Process Dynamical Models

被引:0
|
作者
Taubert, Nick [1 ,2 ]
St Amand, Jesse [1 ,2 ]
Kumar, Prerana [1 ,2 ]
Gizzi, Leonardo [3 ]
Giese, Martin A. [1 ,2 ]
机构
[1] Univ Clin Tubingen, Sect Computat Sensomotor, Dept Cognit Neurol, CIN,HIH, Otfried Muller Str 25, D-72076 Tubingen, Germany
[2] Univ Tubingen, Otfried Muller Str 25, D-72076 Tubingen, Germany
[3] Univ Stuttgart, Inst Modelling & Simulat Biomech Syst, Chair Continuum Biomech & Mechanobiol, Stuttgart, Germany
来源
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT I | 2020年 / 12396卷
关键词
EMG; Decoding; Kinematics; Gaussian process; Dimension reduction;
D O I
10.1007/978-3-030-61609-0_11
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The prediction of finger kinematics from EMG signals is a difficult problem due to the high level of noise in recorded biological signals. In order to improve the quality of such predictions, we propose a Bayesian inference architecture that enables the combination of multiple sources of sensory information with an accurate and flexible model for the online prediction of high-dimensional kinematics. Our method integrates hierarchical Gaussian process latent variable models (GP-LVMs) for nonlinear dimension reduction with Gaussian process dynamical models (GPDMs) to represent movement dynamics in latent space. Using several additional approximations, we make the resulting sophisticated inference architecture real-time capable. Our results demonstrate that the prediction of hand kinematics can be substantially improved by inclusion of information from the online-measured arm kinematics, and by exploiting learned online generative models of finger kinematics. The proposed architecture provides a highly flexible framework for the integration of accurate generative models with high-dimensional motion in real-time inference and control problems.
引用
收藏
页码:127 / 140
页数:14
相关论文
共 9 条
  • [1] Gaussian Process Dynamical Models for hand gesture interpretation in Sign Language
    Gamage, Nuwan
    Kuang, Ye Chow
    Akmeliawati, Rini
    Demidenko, Serge
    PATTERN RECOGNITION LETTERS, 2011, 32 (15) : 2009 - 2014
  • [2] A multi-Kalman filter-based approach for decoding arm kinematics from EMG recordings
    ElMohandes, Hend
    Eldawlatly, Seif
    Audi, Josep Marcel Cardona
    Ruff, Roman
    Hoffmann, Klaus-Peter
    BIOMEDICAL ENGINEERING ONLINE, 2022, 21 (01)
  • [3] A multi-Kalman filter-based approach for decoding arm kinematics from EMG recordings
    Hend ElMohandes
    Seif Eldawlatly
    Josep Marcel Cardona Audí
    Roman Ruff
    Klaus-Peter Hoffmann
    BioMedical Engineering OnLine, 21
  • [4] Simultaneous and Proportional Estimation of Hand Kinematics From EMG During Mirrored Movements at Multiple Degrees-of-Freedom
    Muceli, Silvia
    Farina, Dario
    IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2012, 20 (03) : 371 - 378
  • [5] Finger movements classification based on fractional Fourier transform coefficients extracted from surface EMG signals
    Taghizadeh, Zahra
    Rashidi, Saeid
    Shalbaf, Ahmad
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2021, 68
  • [6] Estimating muscle activation from EMG using deep learning-based dynamical systems models
    Wimalasena, Lahiru N.
    Braun, Jonas F.
    Keshtkaran, Mohammad Reza
    Hofmann, David
    Gallego, Juan Alvaro
    Alessandro, Cristiano
    Tresch, Matthew C.
    Miller, Lee E.
    Pandarinath, Chethan
    JOURNAL OF NEURAL ENGINEERING, 2022, 19 (03)
  • [7] Event-based Low-Power and Low-Latency Regression Method for Hand Kinematics from Surface EMG
    Zanghieri, Marcello
    Benatti, Simone
    Benini, Luca
    Donati, Elisa
    2023 9TH INTERNATIONAL WORKSHOP ON ADVANCES IN SENSORS AND INTERFACES, IWASI, 2023, : 293 - 298
  • [8] A BERT Based Method for Continuous Estimation of Cross-Subject Hand Kinematics From Surface Electromyographic Signals
    Lin, Chuang
    Chen, Xingjian
    Guo, Weiyu
    Jiang, Ning
    Farina, Dario
    Su, Jingyong
    IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2023, 31 : 87 - 96
  • [9] A Real-Time Capable Linear Time Classifier Scheme for Anticipated Hand Movements Recognition from Amputee Subjects Using Surface EMG Signals
    Arunraj, M.
    Srinivasan, A.
    Arjunan, S. P.
    IRBM, 2021, 42 (04) : 277 - 293