Preferential Bayesian optimization (PBO) is a variant of Bayesian optimization that observes relative preferences (e.g., pairwise comparisons) instead of direct objective values, making it especially suitable for human-in-the-loop scenarios. However, real-world optimization tasks often involve inequality constraints, which existing PBO methods have not yet addressed. To fill this gap, we propose constrained preferential Bayesian optimization (CPBO), an extension of PBO that incorporates inequality constraints for the first time. Specifically, we present a novel acquisition function for this purpose. Our technical evaluation shows that our CPBO method successfully identifies optimal solutions by focusing on exploring feasible regions. As a practical application, we also present a designer-in-the-loop system for banner ad design using CPBO, where the objective is the designer's subjective preference, and the constraint ensures a target predicted click-through rate. We conducted a user study with professional ad designers, demonstrating the potential benefits of our approach in guiding creative design under real-world constraints.

Wireless Local Area Networks (WLANs) have been deployed more densely according to high wireless demands. In a dense environment where a lot of stations (STAs) located closely, co-channel interference decreases system performance seriously. IEEE 802.11ax Task Group focuses on spatial reuse that utilizes finite frequency resources to address this problem. Although existing studies about spatial reuse have been discussed so far, interference from other basic service sets (BSSs) and cooperation with each access point (AP) have not been considered fully. To enhance communication fairness, we propose fair Dynamic Sensitivity and Transmission Power Control (fairDSTPC) that adjusts CCAT and transmission power based on AP cooperation. We improve communication environment of BSS which results in the worst throughput by exchanging information, such as throughput and number of sent data frames, between APs. Simulation results showed that our method achieved effectiveness compared with existing method and legacy system. In an open space scenario, our method reached approximately two times higher 5% ile downlink throughput than an existing method while maintaining 5% ile uplink throughput and aggregate throughput.