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

A capacitive-piezoelectric hybrid MEMS microphone with signal fusion for enhancing signal-to-noise ratio.

Microsystems & nanoengineering·2026
Same author

EEG-based decoding of auditory attention to conversations with turn-taking speakers.

Hearing research·2026
Same author

Temporal variation in the acoustic dynamic range is a confounding factor in EEG-based tracking of absolute auditory attention to speech.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Synchronized EEG with two galvanically-separated miniature wireless behind-the-ear EEG sensors.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Effects of speaker and listener sex on auditory attention decoding performance.

Hearing research·2025
Same author

EEG-Based Decoding of Selective Visual Attention in Superimposed Videos.

IEEE journal of biomedical and health informatics·2025

Related Experiment Video

Updated: May 24, 2025

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

15.0K

A Distributed Neural Network Architecture for Dynamic Sensor Selection With Application to Bandwidth-Constrained

Thomas Strypsteen, Alexander Bertrand

    IEEE Journal of Biomedical and Health Informatics
    |March 3, 2025
    PubMed
    Summary

    This study introduces dynamic sensor selection for deep neural networks, optimizing sensor subsets per input to extend wireless sensor network (WSN) lifetime. The approach improves energy efficiency with minimal impact on accuracy.

    More Related Videos

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    8.9K
    Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
    05:30

    Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

    Published on: September 8, 2023

    472

    Related Experiment Videos

    Last Updated: May 24, 2025

    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

    15.0K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    8.9K
    Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
    05:30

    Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

    Published on: September 8, 2023

    472

    Area of Science:

    • Machine Learning
    • Wireless Sensor Networks
    • Signal Processing

    Background:

    • Traditional sensor selection in deep neural networks (DNNs) is static, limiting adaptability and efficiency.
    • Wireless sensor networks (WSNs) face challenges in energy consumption and network lifetime due to continuous data transmission.
    • Optimizing sensor usage is crucial for extending the operational duration of WSNs, especially in resource-constrained environments.

    Purpose of the Study:

    • To develop a dynamic sensor selection method for DNNs that adapts to individual input samples.
    • To enhance the lifetime of wireless sensor networks (WSNs) by intelligently managing sensor transmissions.
    • To improve the robustness and efficiency of DNNs operating with variable sensor subsets.

    Main Methods:

    • Proposed a dynamic sensor selection approach for DNNs, jointly learned with the task model end-to-end.
    • Utilized the Gumbel-Softmax trick for discrete sensor selection decisions via backpropagation.
    • Integrated a dynamic spatial filter to enhance DNN robustness with varying node subsets.
    • Developed a distributed algorithm for optimal channel selection across WSN nodes.

    Main Results:

    • The dynamic sensor selection approach achieved performance close to centralized methods in a body-sensor network use case.
    • Demonstrated significant reductions in transmission energy consumption in wireless sensor networks.
    • Showcased a limited decrease in task accuracy (max 4% absolute) despite energy savings.
    • Validated the framework's effectiveness for extending the lifetime of body-sensor networks.

    Conclusions:

    • Dynamic sensor selection is a practical and effective method for optimizing DNNs and extending WSN lifetime.
    • The proposed distributed algorithm offers a near-optimal solution with minimal inter-node cooperation.
    • This framework provides a viable solution for energy-efficient operation of body-sensor networks.