QoS mapping of VoIP communication using self-organizing neural network

The paper proposes a QoS mapping method for VoIP communications in real network environments. To take total account of the effects of several QoS-related parameters, we use a self-organizing neural network, which can map high-dimensional data into simple geometric relationships on a low-dimensional display. For training the self-organizing neural network, we measure several QoS-related parameters, such as PSQM (perceptual speech quality measure) and PSQM+, end-to-end delay, and packet loss rate, for three VoIP systems. Evaluation results confirm that our method can effectively evaluate the total QoS level composed of several QoS-related factors.