[7A4] Adaptive sampling and quality of service for image transmission for e-health applications
A Salama and R Saatchi
Sheffield Hallam University, UK
Multimedia transmission over wired and wireless (hybrid) networks is increasingly needed as new services emerge and hybrid networks become more diverse and reliable, such as e-Health applications. Quantifying quality of multimedia applications transmitted over hybrid networks is valuable for measuring network performance and its optimisation. The process involves examining the images t, by quantifying distortion, noise and complementing them with traffic parameters characterised by packet delay, delay variation (jitter) and percentage of packet loss ratio (%PLR).
Processing all received packets to evaluate the quality of received images is computationally intensive. The study developed a new adaptive sampling method that allowed a subset of transmitted packets to be chosen according to variations in three synchronised traffic parameter inputs. The method integrated fuzzy logic and regression modelling of traffic parameters and adaptively adjusted the number of packets selected for processing. In comparison with random, stratified and systematic non-adaptive sampling methods, the devised sampling was more effective as it represented the traffic more closely. Statistical and neural network methods were developed to evaluate quality of service (QoS) for video streaming and Voice over Internet Protocol (VoIP) transmitted over hybrid networks.
The study resulted in development and evaluation of a multi-input adaptive sampling method and artificial intelligence and statistical-based QoS and QoE methods for audio and video applications.
Processing all received packets to evaluate the quality of received images is computationally intensive. The study developed a new adaptive sampling method that allowed a subset of transmitted packets to be chosen according to variations in three synchronised traffic parameter inputs. The method integrated fuzzy logic and regression modelling of traffic parameters and adaptively adjusted the number of packets selected for processing. In comparison with random, stratified and systematic non-adaptive sampling methods, the devised sampling was more effective as it represented the traffic more closely. Statistical and neural network methods were developed to evaluate quality of service (QoS) for video streaming and Voice over Internet Protocol (VoIP) transmitted over hybrid networks.
The study resulted in development and evaluation of a multi-input adaptive sampling method and artificial intelligence and statistical-based QoS and QoE methods for audio and video applications.
