This letter studies the effect of node mobility on application-level QoS of audio-video multipath streams in wireless ad hoc networks. The audio-video streams are transmitted with the MultiPath streaming scheme with Media Synchronization control (MPMS), which was previously proposed by the authors. We perform computer simulation with a grid topology network of IEEE 802.11b including two mobile nodes. The simulation results show that MPMS is effective in achieving high application-level QoS in mobile networks as well.

This paper proposes the MultiPath streaming scheme with Media Synchronization control (MPMS) for audio-video transmission in wireless ad hoc networks. In many audio-video streaming applications, media compensate each other from a perceptual point of view. On the basis of this property, we treat the two streams as separate transport streams, and then the source transmits them into two different routes if multiple routes to the destination are available. The multipath transmission disturbs the temporal structure of the streams; in MPMS, the disturbance is remedied by media synchronization control. In order to implement MPMS in this paper, we enhance the existing Dynamic Source Routing (DSR) protocol. We compare the application-level QoS of MPMS and three other schemes for audio-video transmission by simulation with ns-2. In the simulation, we also assess the influence of the multipath transmission on other traffic. The simulation result shows that MPMS is effective in achieving high QoS at the application-level.

In this paper, a Compensatory Neuro-Fuzzy Network (CNFN) for nonlinear system control is proposed. The compensatory fuzzy reasoning method is using adaptive fuzzy operations of neural fuzzy network that can make the fuzzy logic system more adaptive and effective. An on-line learning algorithm is proposed to automatically construct the CNFN. They are created and adapted as on-line learning proceeds via simultaneous structure and parameter learning. The structure learning is based on the fuzzy similarity measure and the parameter learning is based on backpropagation algorithm. The advantages of the proposed learning algorithm are that it converges quickly and the obtained fuzzy rules are more precise. The performance of CNFN compares excellently with other various exiting model.