Extracting Preference Rules Using <i>Kansei</i> Retrieval Agents with Fuzzy Inference

This study examines a Kansei retrieval agent (KaRA) model based on fuzzy reasoning in terms of optimizing rules. The KaRA learns the user’s preferences sensory evaluation, and retrieves what user wants from large amount data. has information membership functions Previous studies have demonstrated effectiveness learning evaluation criteria by function using numerical simulation. However, rules not been optimized. By rules, can acquire sensibility linguistic expressions (fuzzy rules). Therefore, we confirmed rule optimization model. We conducted simulations pseudo-users experiments with real users. Consequently, examined