IoT-driven smart furniture system design and user experience optimization

Abstract In the age of intelligent living, it is increasingly important to maximise human engagement and design efficiency in smart furniture systems. In order to improve the design and user experience of smart furniture systems, this study suggests a novel IoT-driven framework that makes use of the Reformed Bat Optimisation Algorithm with K-means Clustering (RBOA-K-means). MIT Indoor Scenes, SUN RGB-D, and WikiArt are just a few of the multi-source datasets that our model integrates to accomplish intelligent segmentation, depth-aware personalisation, and style-aware adaption of interior settings. According on experimental data, the suggested RBOA-K-means method performs noticeably better in terms of clustering quality and usability than both regular K-means and PSO-K-means. It obtained an F1 score of 90.1%, recall of 90.8%, accuracy of 91.2%, and precision of 89.5%. User-centric assessment also revealed significant gains in interaction performance, with a SUS score of 89.3/100 indicating excellent user satisfaction and system intuitiveness, a 47.6% reduced mistake rate, and a 52% decrease in work time. These results demonstrate how well RBOA-K-means works to convert IoT-driven smart furniture into surroundings that are flexible, effective, and easy to use.