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

Distributed Loads: Problem Solving01:21

Distributed Loads: Problem Solving

731
Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...
731
Neural Circuits01:25

Neural Circuits

1.6K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.6K
Fast Decoupled and DC Powerflow01:24

Fast Decoupled and DC Powerflow

286
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
286
Neural Regulation01:37

Neural Regulation

40.0K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
40.0K

You might also read

Related Articles

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

Sort by
Same author

Multimorbidity burden and patterns associated with DeepBrainNet-derived brain-age gap in dementia-free older adults: A community-based study.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Design and Synthesis of Novel Pyridazinone Derivatives as Cardiac Myosin Activator for the Systolic Heart Failure.

Archiv der Pharmazie·2026
Same author

Intratumoral and peritumoral habitat imaging derived from multi-b-value Diffusion-Weighted imaging in rectal Cancer: Associations with tumor microenvironment and prognosis.

European journal of radiology·2026
Same author

Applications of a continuum model for brush gels.

International journal of solids and structures·2026
Same author

Strategic locations of white matter hyperintensities associated with cognitive impairment across the cognitive spectrum among rural older adults: a population-based study.

Alzheimer's research & therapy·2026
Same author

Internet-based interventions for informal caregivers of dementia: an evidence gap map.

Geriatric nursing (New York, N.Y.)·2026

Related Experiment Video

Updated: Sep 11, 2025

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

659

Decentralized Distributed Sequential Neural Networks Inference on Low-Power Microcontrollers in Wireless Sensor

Yernazar Bolat1, Iain Murray2, Yifei Ren3

  • 1School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth, WA 6102, Australia.

Sensors (Basel, Switzerland)
|August 14, 2025
PubMed
Summary

This study introduces a novel Decentralized Distributed Sequential Neural Network (DDSNN) for low-power microcontrollers in Tiny Machine Learning applications. DDSNN enables efficient, decentralized inference, achieving high accuracy and reducing latency for IoT devices.

Keywords:
IoTdeep neural networkdistributed inferenceedge AIneural network partitioningpredictive maintenancetiny machine learningwireless sensor networks

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.4K
Implantation and Control of Wireless, Battery-free Systems for Peripheral Nerve Interfacing
07:13

Implantation and Control of Wireless, Battery-free Systems for Peripheral Nerve Interfacing

Published on: October 20, 2021

3.4K

Related Experiment Videos

Last Updated: Sep 11, 2025

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

659
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.4K
Implantation and Control of Wireless, Battery-free Systems for Peripheral Nerve Interfacing
07:13

Implantation and Control of Wireless, Battery-free Systems for Peripheral Nerve Interfacing

Published on: October 20, 2021

3.4K

Area of Science:

  • Computer Science
  • Electrical Engineering
  • Artificial Intelligence

Background:

  • Internet of Things (IoT) adoption drives demand for low-power microcontrollers (MCUs) for edge data processing.
  • Deploying deep neural networks (DNNs) on resource-constrained MCUs faces challenges in memory, computation, and energy.
  • Existing solutions like cloud inference and model compression present trade-offs in bandwidth, privacy, and accuracy.

Purpose of the Study:

  • To introduce a novel Decentralized Distributed Sequential Neural Network (DDSNN) for Tiny Machine Learning (TinyML) on low-power MCUs.
  • To enable fully decentralized inference in wireless sensor networks (WSNs) by partitioning DNNs across multiple MCUs.
  • To address the limitations of traditional centralized or compressed DNN approaches for edge computing.

Main Methods:

  • Developed a DDSNN architecture by partitioning a pre-trained LeNet model across multiple low-power MCUs.
  • Implemented a decentralized inference strategy for real-time data processing in a wireless sensor network.
  • Validated the DDSNN approach in a practical predictive maintenance scenario using industrial pump vibration data.

Main Results:

  • DDSNN achieved 99.01% accuracy, matching the baseline non-distributed model.
  • Inference latency was reduced by approximately 50% compared to non-distributed methods.
  • Demonstrated practical feasibility and significant enhancement over traditional approaches in realistic conditions.

Conclusions:

  • DDSNN offers an effective solution for deploying DNNs on resource-constrained MCUs in TinyML applications.
  • The decentralized approach maintains high accuracy while significantly improving inference speed and efficiency.
  • DDSNN is a viable method for real-time edge analytics in IoT and WSNs, particularly for predictive maintenance.