Development and Evaluation of a Probabilistic Local Search Algorithm for Complex Dynamic Indoor Construction Sites

Abstract

The nature of an indoor construction site is dynamic and complex. This characteristic becomes even more evident when a multitude of interactions among workers, equipment, and materials exists. To assist various operations of construction, which are dynamic and complex in nature, previous research explored sensing technologies to discover advanced approaches to supporting construction operations. In particular, many researchers have focused on investigating the tracking of construction resources over the past several years. Despite the previous research efforts in radio-signal-strength-indication (RSSI)–based tracking systems, signal interference such as signal degradations, occlusions, obstructions, and multipath effects created by a complex and dynamic construction environment has not been clearly discussed. Furthermore, fundamental understanding of issues associated with signal interference is limited. This research aims to reduce the gap in knowledge of the RSSI-based tracking system when it is used in a highly noisy environment like a dynamic, complex, and large indoor construction site. This paper presents the development of a new probabilistic local search (PLS) algorithm using Bluetooth low energy network technology. The PLS is assessed with respect to accuracy, reliability, and robustness. Two conventional positioning methods are subjected to the same tests as a benchmark for comparison. The results indicate that PLS outperforms the other conventional methods when the signal interference is high and performs comparably when the signal interference is minimal.