Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Capecitabine maintenance therapy in metastatic colorectal cancer patients with no evidence of disease: CAMCO trial.

Future oncology (London, England)·2023
Same author

Effectiveness of an online/offline mixed-mode Tai Chi cardiac rehabilitation program on microcirculation in patients with coronary artery disease: A randomized controlled study.

Clinical hemorheology and microcirculation·2023
Same author

Adverse effects of exposure to fine particles and ultrafine particles in the environment on different organs of organisms.

Journal of environmental sciences (China)·2023
Same author

Bipedicular percutaneous kyphoplasty versus unipedicular percutaneous kyphoplasty in the treatment of asymmetric osteoporotic vertebral compression fractures: a case control study.

BMC surgery·2023
Same author

Multimodality Driven Impedance-Based Sim2Real Transfer Learning for Robotic Multiple Peg-in-Hole Assembly.

IEEE transactions on cybernetics·2023
Same author

5-ALA Improves the Low Temperature Tolerance of Common Bean Seedlings through a Combination of Hormone Transduction Pathways and Chlorophyll Metabolism.

International journal of molecular sciences·2023

Related Experiment Video

Updated: Jun 10, 2026

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

A multi-scale patch transformer for cross-sequence forecasting: Application to EMG-respiration prediction.

Zilin Chen1, Lei Zhang2, Jiaqiang Chen1

  • 1College of Computer Science, Sichuan University, Chengdu, Sichuan, 610065, China.

Neural Networks : the Official Journal of the International Neural Network Society
|May 8, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a new framework for Cross-Sequence Time Series Forecasting (CSTSF) to predict respiratory signals from electromyography. The novel approach effectively addresses limitations in current forecasting models for complex physiological data.

Keywords:
Cross sequence forecastingDeep learningMulti-scale patchTime seriesTransformer

More Related Videos

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography
09:42

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

Published on: January 24, 2025

Related Experiment Videos

Last Updated: Jun 10, 2026

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography
09:42

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

Published on: January 24, 2025

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Machine Learning

Background:

  • Accurate prediction of respiratory signals from electromyography (EMG) envelopes is vital for non-invasive assessment of respiratory muscle effort and fatigue.
  • Cross-Sequence Time Series Forecasting (CSTSF), predicting a target sequence from different source sequences, presents unique challenges not addressed by conventional forecasting.
  • Existing models often fail in CSTSF due to architectural limitations in handling differing input/output variable counts.

Purpose of the Study:

  • To develop a novel framework for Cross-Sequence Time Series Forecasting (CSTSF) applicable to predicting respiratory signals from EMG.
  • To overcome the limitations of conventional time series forecasting models in handling CSTSF tasks.
  • To introduce an effective model, the Multi-Scale Patch Transformer (MSPFormer) with an Attention-based Modality Transition (AMT) module, for CSTSF.

Main Methods:

  • A decoupled framework is proposed, separating CSTSF into intra-sequence forecasting and cross-sequence mapping stages.
  • These stages are jointly optimized using a hybrid loss function, allowing adaptation of conventional forecasting models.
  • The Multi-Scale Patch Transformer (MSPFormer) with an Attention-based Modality Transition (AMT) module is introduced for feature extraction and cross-sequence mapping.

Main Results:

  • The proposed framework and MSPFormer model demonstrated improved performance on CSTSF tasks.
  • Experiments were conducted on both a private EMG-Respiration dataset and public Traffic and Electricity datasets.
  • The model achieved superior results compared to existing state-of-the-art forecasting methods.

Conclusions:

  • The developed decoupled framework offers a robust solution for Cross-Sequence Time Series Forecasting.
  • The MSPFormer model effectively captures multi-period features and performs cross-sequence mapping.
  • This work has significant potential for applications in non-invasive physiological signal estimation and respiratory monitoring.