A dynamic fuzzy video compression control algorithm for wireless Advanced Driver Assistance Systems

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F25%3A10257739" target="_blank" >RIV/61989100:27240/25:10257739 - isvavai.cz</a>

Result on the web

<a href="https://www.sciencedirect.com/science/article/pii/S0952197625008152" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0952197625008152</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.engappai.2025.110815" target="_blank" >10.1016/j.engappai.2025.110815</a>

Result language

angličtina

Original language name

A dynamic fuzzy video compression control algorithm for wireless Advanced Driver Assistance Systems

Original language description

As video-based Advanced Driver Assistance Systems (ADAS) become integral to modern vehicle safety, the demand for reliable, high-performance wireless solutions for retrofitting vehicles have grown. This study introduces a wireless ADAS that employs a novel dynamic video compression control algorithm, integrating a hardware-based Motion Joint Photographic Experts Group (MJPEG) compression engine with adaptive fuzzy logic control strategies. The system dynamically adjusts video compression levels based on real-time conditions such as wireless data rates and available bandwidth, addressing key challenges in maintaining video quality and minimizing latency in wireless environments. The adaptive control is governed by two distinct fuzzy control strategies: Fuzzy Rule-Based (FRB) and Evolutionary Fuzzy Rules (EFR). Both strategies were optimized using nature-inspired algorithms, including Differential Evolution (DE), Particle Swarm Optimization (PSO), and Genetic Programming (GP). Among these, the EFR-based control was found to offer the best overall performance. Key performance indicators such as compression efficiency, latency, and throughput rates were thoroughly evaluated. Experimental results demonstrated that the EFR-based system provided up to a 35% improvement in compression efficiency compared to traditional methods, reduced video latency by approximately 20%, and optimized data throughput. Furthermore, the EFR-based control showcased enhanced generalization capabilities, outperforming FRB-based control under previously unobserved conditions, which is critical for real-world vehicular applications where network conditions may vary significantly. The implementation of artificial intelligence in the form of EFR significantly enhanced the system&apos;s ability to adapt to varying data rates and environmental conditions, making it a promising solution for real-time video compression in computationally constrained embedded systems. © 2025 The Authors

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

20202 - Communication engineering and systems

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Engineering Applications of Artificial Intelligence

ISSN

0952-1976

e-ISSN

1873-6769

Volume of the periodical

153

Issue of the periodical within the volume

Neuveden

Country of publishing house

GB - UNITED KINGDOM

Number of pages

17

Pages from-to

nestránkováno

UT code for WoS article

001480984000001

EID of the result in the Scopus database

2-s2.0-105003378617