@techreport{oai:ipsj.ixsq.nii.ac.jp:00211457,
 author = {Yang, Zhen and Masato, Sugasaki and Yoshihiro, Kawahara and Kota, Tsubouchi and Masamichi, Shimosaka and Yang, Zhen and Masato, Sugasaki and Yoshihiro, Kawahara and Kota, Tsubouchi and Masamichi, Shimosaka},
 issue = {11},
 month = {May},
 note = {With the pandemic of COVID-19, indoor crowd density monitoring is on-demand by public service providers. Due to the fact that its performance on crowd density monitoring highly depends on how BLE beacons are allocated, BLE beacon placement optimization has been tackled as fundamental research work in the ubiquitous computing community. However, the previous researches focus on the batch optimization and ignore the actual workload to obtain the optimal placement result. In this research, we propose a novel approach to incrementally optimize the beacon placement by detecting the optimal placement of BLE sensors in favor of Bayesian optimization and determining the optimal location to place the beacon. Our proposed method can optimize the beacon placement effectively to improve the signal coverage quality in the given environment and also minimize the human workload. The experiment results on actual BLE sensing results show that our proposed method can provide over 13% area coverage than the average placement while reducing 67% optimization time., With the pandemic of COVID-19, indoor crowd density monitoring is on-demand by public service providers. Due to the fact that its performance on crowd density monitoring highly depends on how BLE beacons are allocated, BLE beacon placement optimization has been tackled as fundamental research work in the ubiquitous computing community. However, the previous researches focus on the batch optimization and ignore the actual workload to obtain the optimal placement result. In this research, we propose a novel approach to incrementally optimize the beacon placement by detecting the optimal placement of BLE sensors in favor of Bayesian optimization and determining the optimal location to place the beacon. Our proposed method can optimize the beacon placement effectively to improve the signal coverage quality in the given environment and also minimize the human workload. The experiment results on actual BLE sensing results show that our proposed method can provide over 13% area coverage than the average placement while reducing 67% optimization time.},
 title = {Incremental BLE beacon placement optimization for crowd density monitoring applications},
 year = {2021}
}