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

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
Neural Regulation01:37

Neural Regulation

40.3K
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.
40.3K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

103
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
103
Understanding Memory01:19

Understanding Memory

641
Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...
641
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

152
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
152

You might also read

Related Articles

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

Sort by
Same author

Design and Implementation of an Eyewear-Integrated Infrared Eye-Tracking System.

Sensors (Basel, Switzerland)·2026
Same author

Posture Assessment in Dentistry for Different Visual Aids Using 2D Markers.

Sensors (Basel, Switzerland)·2021
Same author

Advanced Assistive Maintenance Based on Augmented Reality and 5G Networking.

Sensors (Basel, Switzerland)·2020
Same author

Biometric Signals Estimation Using Single Photon Camera and Deep Learning.

Sensors (Basel, Switzerland)·2020

Related Experiment Video

Updated: Sep 18, 2025

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

Learning Online MEMS Calibration with Time-Varying and Memory-Efficient Gaussian Neural Topologies.

Danilo Pietro Pau1, Simone Tognocchi1, Marco Marcon2

  • 1System Research and Applications, STMicroelectronics, Via C. Olivetti 2, 20864 Agrate Brianza, Italy.

Sensors (Basel, Switzerland)
|June 27, 2025
PubMed
Summary

This study introduces an on-device learning method using Radial Basis Function Neural Networks (RBF-NNs) to self-calibrate Micro-Electro-Mechanical Systems-based Inertial Measurement Units (MEMS-IMUs). The AI approach effectively reduces sensor errors without external processors, improving accuracy for applications like micro aerial vehicles.

Keywords:
in-sensor tiny machine learninginertial sensor calibrationintelligent sensor processing uniton-device learningradial basis functions

More Related Videos

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.1K
Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
08:07

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

7.9K

Related Experiment Videos

Last Updated: Sep 18, 2025

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
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.1K
Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
08:07

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

7.9K

Area of Science:

  • Sensor Technology
  • Artificial Intelligence
  • Embedded Systems

Background:

  • Micro-Electro-Mechanical Systems-based Inertial Measurement Units (MEMS-IMUs) are crucial for motion tracking but suffer from real-time errors like bias and thermal stress.
  • Traditional linear calibration methods fail to address nonlinear sensor drifts, limiting IMU accuracy.
  • On-device processing capabilities are expanding, enabling complex algorithms within sensor packages.

Purpose of the Study:

  • To develop an on-device learning approach for self-calibrating MEMS-IMUs.
  • To address nonlinear error compensation in real-time sensor data.
  • To implement and validate an AI-based calibration algorithm within a digital signal processor (DSP).

Main Methods:

  • An on-device learning algorithm using Radial Basis Function Neural Networks (RBF-NNs) was devised for MEMS-IMU self-calibration.
  • The RBF-NN algorithm was implemented on a digital signal processor (DSP) integrated within the IMU, performing interleaved in-sensor learning and inference.
  • The solution was deployed in both 32-bit floating-point (fp32) and 16-bit quantized integer (int16) versions within the Intelligent Sensor Processing Unit (ISPU) of the LSM6DSO16IS IMU.

Main Results:

  • The RBF-NN models, implemented on the DSP, occupied less than 21 KiB of memory.
  • The calibration models compensated for 46%-95% of accelerometer errors and 32%-88% of gyroscope errors.
  • Attitude estimation for a micro aerial vehicle (MAV) achieved a low error of 2.84°.

Conclusions:

  • The proposed on-device learning approach effectively self-calibrates MEMS-IMUs using RBF-NNs with low computational complexity.
  • The solution is deployable on resource-constrained embedded systems like the ISPU, enabling real-time, independent sensor recalibration.
  • This method significantly improves IMU accuracy for motion-sensing applications, demonstrated by enhanced MAV attitude estimation.