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

Search research articles

Related Experiment Video

Updated: Mar 21, 2026

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

FPGA implementation of neuro-fuzzy system with improved PSO learning.

Cihan Karakuzu¹, Fuat Karakaya², Mehmet Ali Çavuşlu³

¹Bilecik Şeyh Edebali University, Faculty of Engineering, Department of Computer Engineering, Gülümbe Campus, 11210, Bilecik, Turkey.

Neural Networks : the Official Journal of the International Neural Network Society

|May 3, 2016

Summary

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

Retraction notice to: Fuzzy controller training using particle swarm optimization for nonlinear system control.

ISA transactions·2009

Same author

Fuzzy controller training using particle swarm optimization for nonlinear system control.

ISA transactions·2007

See all related articles

This study introduces the first hardware implementation of a neuro-fuzzy system (NFS) on a field-programmable gate array (FPGA), utilizing improved particle swarm optimization (iPSO) for efficient parameter learning and reduced hardware resource usage.

Area of Science:

* Computer Engineering
* Artificial Intelligence
* Hardware Acceleration

Background:

* Neuro-fuzzy systems (NFS) offer a powerful approach to complex problem-solving by integrating neural networks and fuzzy logic.
* Efficient hardware implementations are crucial for real-time applications of NFS.
* Existing NFS implementations often face challenges with resource utilization and computational complexity.

Purpose of the Study:

* To present the first hardware implementation of a neuro-fuzzy system (NFS) on a field-programmable gate array (FPGA).
* To introduce a novel, memory- and multiplier-free functional approach for Gaussian membership functions in NFS.
* To demonstrate the metaheuristic learning capability of NFS using an improved particle swarm optimization (iPSO) algorithm.

Main Methods:

Keywords:

FPGA implementation Metaheuristic learning Neuro-fuzzy network System identification VHDL

Related Experiment Videos

Last Updated: Mar 21, 2026

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

* Hardware implementation of NFS and its metaheuristic learning using improved particle swarm optimization (iPSO) on a Xilinx Virtex5 FPGA.
* Development of a new functional approximation for Gaussian membership functions, eliminating the need for memory and multipliers.
* Testing the implementation on dynamic system identification and license plate detection tasks.

Main Results:

* The proposed NFS hardware implementation achieves effectiveness comparable to existing literature methods.
* The novel membership function approach significantly reduces hardware resource requirements.
* The iPSO algorithm successfully optimizes NFS parameters in the hardware implementation.

Conclusions:

* The presented FPGA-based NFS with iPSO learning offers an efficient and effective solution for complex computational tasks.
* The memory- and multiplier-free membership function approximation contributes to reduced hardware footprint.
* This work paves the way for more accessible and resource-efficient neuro-fuzzy hardware applications.