Quality-of-experience parameter estimation for multisensorial media using Particle Swarm Optimization

Multimedia quality of experience (QoE) accounts for the degree of delight or annoyance of the user of an application or service. Although humans have five senses, only two of these senses (i.e., sight and hearing) are stimulated by traditional multimedia contents. Therefore, the research efforts try to add additional constituents for stimulating other senses, beside sight and hearing, like smell and touch. This introduces a number of new issues like the evaluation of the QoE for audio/video sequences enriched with additional sensory effects (e.g., light effects, wind, vibration, scent). A multi-sensorial effect QoE parametric model has been introduced in literature based on mean opinion score (MOS) subjective assessment. Multiple linear regression (MLR) with the least square (LS) estimator method was used to obtain the model parameters. In this paper, an alternative approach based on the particle swarm optimization (PSO) algorithm is proposed to estimate the parameters of the multi-sensorial QoE model. In order to show that PSO enhance the estimation accuracy a comparison with LS estimator method has been performed. The results show that the PSO algorithm can provide more accurate estimation of the parameters with respect to LS.