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

Lightweight deep learning models for real-time IoT data analysis in resource-constrained environments.

Fuhid Alanazi1

  • 1Faculty of Computer and Information Systems, Islamic University of Madinah, 42351, Madinah, Saudi Arabia. alanazi@iu.edu.sa.

Scientific Reports
|May 6, 2026
PubMed
Summary
This summary is machine-generated.

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

Energy-efficient fragmentation-aware dual adaptive collision-free bit mapping MAC protocol for VANET.

Scientific reports·2026
Same author

A hierarchical and privacy-preserving intrusion detection framework for SAGIN-enabled IIot using graph neural networks and deep Q-learning.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Intelligent feature fusion with dynamic graph convolutional recurrent network for robust object detection to assist individuals with disabilities in a smart Iot edge-cloud environment.

Scientific reports·2025
Same author

Machine learning driven aggregation aware bitmap MAC protocol for energy efficient data transmission in WSNs.

Scientific reports·2025
Same author

RETRACTED ARTICLE: Enhancing communication for people with hearing disabilities through robust sign language recognition using deep learning and the internet of things.

Disability and rehabilitation. Assistive technology·2025
Same author

Ascertaining sustainability for affordable energy generation with non-renewable sources using computational intelligence algorithm.

Scientific reports·2025
Same journal

Peripheral B-cell receptor repertoire predicts immune-related adverse events following immune checkpoint inhibitor therapy in advanced renal cell carcinoma.

Scientific reports·2026
Same journal

Effects of black soldier fly (Hermetia illucens L.) larvae zoocompost on the mineral element content of blue honeysuckle berries.

Scientific reports·2026
Same journal

Investigation on absorption refrigeration performance of R1243zf with imidazolium ionic liquid as the working pairs.

Scientific reports·2026
Same journal

DeepTriage-CN: integrating clinical text with vital signs for emergency department admission prediction in an aging population.

Scientific reports·2026
Same journal

Gold nanoparticles as dual-action antiviral agents: disruption of SARS-CoV-2 viral envelopes and RNA integrity.

Scientific reports·2026
Same journal

Comparison of capillary microsampling and venous blood for multi-pathogen serosurveillance.

Scientific reports·2026
See all related articles

This study introduces a cross-layer framework for real-time IoT data analytics, optimizing lightweight AI for constrained environments. Results show communication-aware aggregation, like Rolling Window, enhances reliability and energy efficiency without compromising accuracy.

Area of Science:

  • Computer Science
  • Electrical Engineering
  • Artificial Intelligence

Background:

  • Internet of Things (IoT) growth necessitates efficient real-time data analytics.
  • Existing research often neglects wireless communication reliability's impact on machine learning in IoT.
  • Resource constraints (energy, latency, reliability) are critical for lightweight AI in IoT.

Purpose of the Study:

  • To develop and evaluate a cross-layer framework integrating lightweight ensemble learning with IoT network simulation.
  • To assess the end-to-end performance of real-time data analytics under various communication conditions.
  • To investigate the impact of data handling strategies and network protocols on AI performance in resource-constrained IoT.

Main Methods:

  • Developed a cross-layer framework combining lightweight ensemble learning with PHY-MAC layer-aware IoT network simulation.
Keywords:
Cross-layer performance analysisEnergy-efficient MAC protocolsInternet of Things (IoT)Lightweight deep learningResource-constrained networks

Related Experiment Videos

  • Investigated three data handling strategies: Baseline, Duty-Cycle-aware reporting, and Rolling Window aggregation.
  • Simulated performance using multiple MAC protocols (TDMA, CSMA, DutyCycleMAC) and PHY channel models (Ideal, AWGN, Rayleigh) in MATLAB.

    • Main Results:

    • TDMA protocol demonstrated the highest Packet Delivery Ratio (PDR), reaching 1.0 under Ideal PHY conditions.
    • The proposed Rolling Window aggregation method improved robustness and energy efficiency.
    • Accuracy and F1-score were maintained with the Rolling Window method, showing no sacrifice in predictive accuracy.

    Conclusions:

    • Communication-aware data aggregation is crucial for reliable and energy-efficient lightweight AI deployment in IoT.
    • The developed framework provides a method for evaluating end-to-end performance considering network reliability.
    • Optimizing data handling strategies alongside network protocols is key for real-world IoT AI applications.