An Integrated Neuro-Fuzzy Approach to MPEG Video Transmission in Bluetooth

Abstract

This paper presents an integrated neuro-fuzzy (NF) scheme and a rule-based-fuzzy (RBF) scheme applications to Moving Picture Expert Group (MPEG) video transmission in Bluetooth. In a Bluetooth network, transmission rate is unpredictable due to interferences by other wireless devices or general Bluetooth channel noises. MPEG variable bit rate (VBR) video transmission is also unreliable and presents long delay and excessive data loss, due to variations in bit rate. It is therefore almost impossible to transmit MPEG VBR video over a Bluetooth channel, without data loss, excessive time delay or image quality degradation. In this work, a traffic-shaping buffer is introduced before the host controller interface (HCI) of the Bluetooth protocol stack. An integrated NF scheme reduces the burstiness of the traffic-shaper output rate to enable the MPEG VBR video to comply with the generic cell rate algorithm contract before entering the Bluetooth channel. The computer simulation results show that the application of the proposed scheme reduces excessive time delay and data loss at the HCI, as compared with a conventional video transmission in Bluetooth