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 Videos

Hybrid Deep Reinforcement Learning for Multimodal Biomedical Signal Fusion.

Bhanu Prakash Reddy Rella1, Rajesh Sura2, Rahul Kumar Konduru3

  • 1Ageno School of Business, Golden Gate University; brella@my.ggu.edu.

Journal of Visualized Experiments : Jove
|April 27, 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

Comparative evaluation of natural language processing approaches with particle swarm optimized LightGBM for anomaly detection in cloud system logs.

Scientific reports·2026
Same author

A novel diabetic retinopathy detection from fundus images using hybrid quantum convolutional neural network models.

Scientific reports·2026
Same author

Metaheuristic-driven dual-layer model for classifying Alzheimer's disease stages.

Frontiers in computational neuroscience·2026
Same author

Triboostcardio ensemble model for cardiovascular disease detection using advanced blockchain-enabled health monitoring.

Frontiers in artificial intelligence·2026
Same author

Bioinspired STHVO based MPPT control for grid connected photovoltaic water pumping systems.

Scientific reports·2026
Same author

Retraction notice to "System and method to diagnose conjunctivitis in the eye of a user" [Heliyon 10 (2024) e36248].

Heliyon·2025
Same journal

A Video Protocol of a Randomized Controlled Clinical Trial - Electrochemotherapy of Cutaneous Metastases with Reduced Dose Bleomycin (BLESS Trial).

Journal of visualized experiments : JoVE·2026
Same journal

A Standardized Ex Vivo Porcine Oromucosal Model for Evaluating Peptide Fluxes.

Journal of visualized experiments : JoVE·2026
Same journal

Lightweight English Text Classification with Deep Learning Based on Complex System Theory.

Journal of visualized experiments : JoVE·2026
Same journal

Integrating Artificial Intelligence-Assisted Translation Support into English Courses: Effects on Translation Accuracy, Perceived Stress, and Anxiety.

Journal of visualized experiments : JoVE·2026
Same journal

A Toxin-Based Counter-Selection System for Markerless Gene Deletion and High-Density Tn5 Transposon Mutagenesis in Pectobacterium brasiliense.

Journal of visualized experiments : JoVE·2026
Same journal

Seamless Multimodal Human-Robot Communication: Integration Techniques in Human-Computer Interaction.

Journal of visualized experiments : JoVE·2026
See all related articles
This summary is machine-generated.

A new Hybrid Deep Reinforcement Learning (HDRL) model enhances healthcare by fusing multimodal biomedical signals (ECG, EEG, imaging) for improved diagnostic accuracy and personalized medicine.

Area of Science:

  • Biomedical Signal Processing
  • Artificial Intelligence in Healthcare
  • Machine Learning for Diagnostics

Background:

  • Healthcare decision-making relies on integrating diverse biomedical signals like ECG, EEG, and medical imaging.
  • Traditional signal fusion methods struggle with signal variability and complexity, limiting diagnostic accuracy.
  • Advanced signal processing is crucial for personalized medicine and accurate disease classification.

Purpose of the Study:

  • To introduce a Hybrid Deep Reinforcement Learning (HDRL) model for advanced multimodal biomedical signal fusion.
  • To overcome limitations of traditional fusion techniques in handling complex and variable biomedical data.
  • To enhance decision-making and diagnostic accuracy in healthcare settings.

Main Methods:

Related Experiment Videos

  • Developed a Hybrid Deep Reinforcement Learning (HDRL) model combining Deep Neural Networks (DNNs) for feature extraction and Reinforcement Learning (RL) for dynamic fusion optimization.
  • Employed real-time feedback mechanisms for adaptive fusion policy learning.
  • Utilized RL agents, including Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO), for policy optimization.
  • Compared HDRL performance against conventional methods like DNN-based fusion and Principal Component Analysis (PCA).

    • Main Results:

    • The HDRL model demonstrated superior performance across real-world biomedical datasets compared to conventional techniques.
    • Achieved enhanced robustness in noisy conditions, leading to improved classification accuracy.
    • Showcased effectiveness in rare-event detection, a critical aspect of disease diagnosis.
    • Validated applicability in personalized medicine and disease classification tasks.

    Conclusions:

    • The proposed HDRL model offers a significant advancement in multimodal biomedical signal processing.
    • It effectively addresses the challenges posed by signal variability and complexity in traditional fusion methods.
    • HDRL provides a robust and adaptive solution for improving diagnostic accuracy and supporting personalized medicine.