Application of neural-fuzzy controller for streaming video over Bluetooth 1.2 |
| |
Authors: | Guillaume F Remy Hassan B Kazemian Phil Picton |
| |
Affiliation: | (1) Faculty of Computing, London Metropolitan University, London, UK;(2) School of Technology and Design, The University of Northampton, Northampton, UK |
| |
Abstract: | This paper is to introduce an application of Computational Intelligence (CI) to Moving Picture Expert Group-4 (MPEG-4) video
compression over IEEE.802.15.1 wireless communication, known as Bluetooth 1.2, in order to improve picture quality. The 2.4 GHz
Industrial, Scientific and Medical frequency band is used for the IEEE.802.15.1 standard. IEEE.802.15.1 can be affected by
noise and interference due to other neighboring wireless devices sharing the same frequency carrier. The noise and interference
create difficulties in ascertaining an accurate real-time transmission rate at the receiving end. Furthermore, the MPEG-4
codec is an object-oriented compression system and demands a high bandwidth. It is therefore difficult to avoid excessive
delay, image quality degradation and/or data loss during MPEG-4 video transmission over standard systems. A new buffer entitled
‘buffer added’ has been introduced at the input of the Bluetooth 1.2 device. This buffer is controlled by a Rule-Based Fuzzy
(RBF) logic controller at the input and a neural-fuzzy controller (NFC) at the output. The two new fuzzy rules manipulate
and supervise the flow of video over the Bluetooth 1.2 standard. The computer simulation results illustrate the comparison
between a non-CI video transmission over Bluetooth 1.2 and the proposed design, confirming that the applications of RBF and
NFC do improve the image quality, reduce data loss and reduce time delay. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|