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 Experiment Video

Updated: Jul 15, 2026

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

Cycle-Aware Masked Self-Supervised Learning for Parkinson's Disease Diagnosis Using Wearable Time-Series Data in

Yun Yang, Chuxiong Huang, Xulong Wang

    IEEE Transactions on Bio-Medical Engineering
    |July 13, 2026
    PubMed
    Summary

    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

    Self-Healing Ion-Conductive Binder for High-Performance SiO<sub><i>x</i></sub> Anodes in Lithium-Ion Batteries.

    ACS applied materials & interfaces·2025
    Same author

    Cross-linking γ-Polyglutamic Acid as a Multifunctional Binder for High-Performance SiO<sub></sub> Anode in Lithium-Ion Batteries.

    ACS applied materials & interfaces·2024
    Same author

    Acetyl transferase EP300 deficiency leads to chronic replication stress mediated by defective fork protection at stalled replication forks.

    bioRxiv : the preprint server for biology·2023
    Same author

    HYDROMORPHONE MITIGATES CARDIOPULMONARY BYPASS-INDUCED ACUTE LUNG INJURY BY REPRESSING PYROPTOSIS OF ALVEOLAR MACROPHAGES.

    Shock (Augusta, Ga.)·2023
    Same author

    Epigenetic Control of Translation Checkpoint and Tumor Progression via RUVBL1-EEF1A1 Axis.

    Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2023
    Same author

    Nephron sparing surgery for a patient with a complicated solitary functioning kidney and a giant pT3 renal cell carcinoma: A case report.

    Frontiers in surgery·2023

    This study introduces a new self-supervised learning method for Parkinson's Disease (PD) using wearable sensors. The cycle-aware approach improves motor symptom analysis by learning from unlabeled data, enhancing diagnostic accuracy.

    Area of Science:

    • Biomedical Engineering
    • Neuroscience
    • Machine Learning

    Background:

    • Parkinson's Disease (PD) is a progressive neurodegenerative disorder impacting motor function.
    • Wearable sensors offer continuous monitoring of motor symptoms in daily life.
    • Limited labeled data hinders supervised learning for PD analysis.

    Purpose of the Study:

    • To develop a novel self-supervised learning framework for analyzing wearable sensor data in PD.
    • To address the challenge of data scarcity in supervised learning for PD monitoring.
    • To leverage unlabeled sensor data for pre-training models to detect motor patterns.

    Main Methods:

    • Proposed a cycle-aware masked self-supervised learning framework.
    • Introduced cycle-level masking exploiting activity periodicity for time-series data.

    More Related Videos

    Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation
    06:32

    Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

    Published on: July 14, 2023

    Related Experiment Videos

    Last Updated: Jul 15, 2026

    Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
    10:28

    Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

    Published on: July 24, 2019

    Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation
    06:32

    Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

    Published on: July 14, 2023

  • Pre-trained models on unlabeled wearable sensor data.

    • Main Results:

    • The proposed method outperformed state-of-the-art self-supervised learning baselines.
    • Achieved 3%-5% absolute accuracy improvement in clinical diagnostic tasks.
    • Demonstrated consistent gains in daily activity recognition.

    Conclusions:

    • Cycle-aware inductive bias enhances self-supervised learning for time-series clinical analysis.
    • The framework shows potential for improving Parkinson's Disease diagnosis.
    • Effective for analyzing motor symptoms using wearable sensor data.