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

A low-power VLSI arrhythmia classifier.

P W Leong1, M A Jabri

  • 1Dept. of Electr. Eng., Sydney Univ., NSW.

IEEE Transactions on Neural Networks
|January 1, 1995
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

STSM 2025 & 2nd African Medical Writing Congress.

La Tunisie medicale·2026
Same author

Artefacts and diagnostic pitfalls in contrast-enhanced mammography: a pictorial review.

Clinical radiology·2024
Same author

The ins and outs of male breast and anterior chest wall lesions from childhood to adulthood.

Clinical radiology·2022
Same author

An overview on the veracity of intraoral digital scanning system and utilization of iTero scanner for analyzing orthodontic study models both <i>In-Vivo</i> and <i>Ex-Vivo</i>.

Nigerian journal of clinical practice·2021
Same author

Anthelmintic activity of Tunisian chamomile (Matricaria recutita L.) against Haemonchus contortus.

Journal of helminthology·2017
Same author

Handwritten digit recognition by adaptive-subspace self-organizing map (ASSOM).

IEEE transactions on neural networks·2008
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

A novel low-power multilayer perceptron chip, Kakadu, was developed for cardiac arrhythmia classification. This chip enables implantable devices to efficiently identify abnormal heartbeats with minimal power consumption, achieving microwatt levels.

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence
  • VLSI Design

Background:

  • Cardiac arrhythmia classification is crucial for diagnosing heart conditions.
  • Existing systems often face limitations in power consumption for implantable devices.
  • Neural networks offer potential for accurate heartbeat analysis but require significant computational resources.

Purpose of the Study:

  • To design and implement a low-power multilayer perceptron chip (Kakadu) for cardiac arrhythmia classification.
  • To integrate Kakadu into an arrhythmia classification system (MATIC) for implantable devices.
  • To achieve high efficiency and minimal power consumption for continuous cardiac monitoring.

Main Methods:

  • Developed a multilayer perceptron chip named Kakadu using VLSI (very large scale integration) technology.

Related Experiment Videos

  • Designed a cardiac arrhythmia classification system (MATIC) incorporating a decision tree for timing and a neural network for heartbeat morphology identification.
  • Optimized the neural network algorithm for low power consumption within the Kakadu chip.

    • Main Results:

    • The Kakadu chip implements a (10,6,4) perceptron with a typical power consumption in the tens of microwatts.
    • When integrated into the MATIC system, the overall average power consumption is less than 25 nanowatts.
    • Demonstrated the feasibility of using a low-power neural network chip for implantable cardiac monitoring.

    Conclusions:

    • The Kakadu chip represents a significant advancement in low-power hardware for implantable cardiac arrhythmia detection.
    • The developed system (MATIC) offers a power-efficient solution for real-time analysis of heartbeats.
    • This technology paves the way for more sophisticated and long-lasting implantable cardiac monitoring devices.