Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Transition metal-coordinated metastable [MoS<sub>4</sub>]<sup>2-</sup> cluster for SO<sub>2</sub>-facilitated gaseous mercury adsorption from wet flue gas.

Journal of environmental sciences (China)·2026

Same author

The first-in-human ENCIT01 trial comparing second- versus third-generation L1CAM-specific CAR T cells in patients with primary refractory or relapsed neuroblastoma.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026

Same author

Seroprevalence and associated risk factors for feline panleukopenia virus infection among managed giant pandas in China.

Veterinary research·2026

Same author

A novel chemical engineering system design for synergistic SO<sub>2</sub> reduction and CH<sub>4</sub>/CO<sub>2</sub> reforming.

Environmental research·2026

Same author

Machine learning model-guided selective use of temporary diverting ileostomy in rectal cancer surgery: a randomized controlled trial.

Nature communications·2026

Same author

Generation of HBV cccDNA using single-stranded M13 phage DNA for authentic minichromosome functionality.

Journal of virology·2026

Same journal

Logic, inference, understanding: cross-domain generalization for generative language models.

Frontiers in artificial intelligence·2026

Same journal

Label tree semantic losses for rich multi-class medical image segmentation.

Frontiers in artificial intelligence·2026

Same journal

Score-based generative diffusion models to synthesize full-dose FDG brain PET from MRI in epilepsy patients.

Frontiers in artificial intelligence·2026

Same journal

Resource-efficient retrieval-augmented question answering for the Indian Lok Sabha dataset.

Frontiers in artificial intelligence·2026

Same journal

Violation detection in power operation sites based on multi-scale detection and few-shot learning.

Frontiers in artificial intelligence·2026

Same journal

Deep reinforcement learning-based reversible medical image encryption framework for secure IoMT environments.

Frontiers in artificial intelligence·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 29, 2025

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

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

Published on: September 8, 2023

Self-trainable and adaptive sensor intelligence for selective data generation.

Arghavan Rezvani¹, Wenjun Huang¹, Hanning Chen¹

¹Donald Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, CA, United States.

Frontiers in Artificial Intelligence

|February 6, 2025

Summary

This summary is machine-generated.

This study introduces an adaptive framework for machine learning on Internet of Things (IoT) devices. It enhances energy efficiency and data transmission by enabling models to learn and adapt post-deployment.

Keywords:

Internet of Things active learning intelligent sensing knowledge distillation machine learning near-sensor computing

More Related Videos

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

Published on: May 3, 2012

Related Experiment Videos

Last Updated: May 29, 2025

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

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

Published on: September 8, 2023

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

Published on: May 3, 2012

Area of Science:

Computer Science
Artificial Intelligence
Internet of Things

Background:

Machine learning integration in IoT devices presents energy and data transmission challenges.
Current near-sensor models lack adaptability due to rigid pre-training requirements.
Efficient data handling is crucial for complex IoT computations.

Purpose of the Study:

To develop an adaptive, resource-efficient framework for near-sensor intelligence in IoT.
To enable dynamic parameter fine-tuning of machine learning models post-deployment.
To reduce energy consumption and optimize data transmission in IoT applications.

Main Methods:

Fusion of online learning, active learning, and knowledge distillation for adaptive near-sensor models.
Online learning for dynamic post-deployment parameter fine-tuning.
Knowledge distillation to transfer insights from teacher to student models.
Active learning to minimize training data requirements.

Main Results:

Demonstrated significant improvements in energy efficiency.
Achieved substantial optimization in data transmission.
Validated framework performance on MS COCO dataset and simulated IoT environment.
Framework enables continuous adaptability without prior environment knowledge.

Conclusions:

The proposed framework offers a practical solution for resource-efficient near-sensor intelligence in IoT.
Dynamic adaptation capabilities enhance the applicability of machine learning in real-world IoT scenarios.
The method effectively balances model performance with resource constraints.