Performance Evaluation of Three-Dimensional UWB Real-Time Locating Auto-Positioning System for Fire Rescue

Yang, Hang; Li, Xunbo; Pedrycz, Witold

doi:10.32604/iasc.2023.040412

Cited by 1 publication

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, UWB positioning technology is commonly utilized in indoor positioning because of its high accuracy, low power consumption, and anti-interference characteristics 10 . Many UWB positioning algorithms have been proposed, such as TOA positioning and TDOA positioning, which rely on UWB equipment for ranging and finding the tag position based on related algorithms 11,12 , wireless signal arrival angle AOA (Angle of Arrival) positioning 13 and fingerprint matching positioning based on signal strength RSSI (Received Signal Strength Indication) 14 . However, due to the high complexity of the indoor environment, the signal will be affected by factors such as multipath, occlusion, noise interference, and signal attenuation in the transmission process, which increases the error of UWB indoor positioning, making positioning results fail to meet the requirements 15 .…”

Section: Introductionmentioning

confidence: 99%

Application of a long short-term memory neural network algorithm fused with Kalman filter in UWB indoor positioning

Tian,

Lian,

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Ultra-wideband technology has good anti-interference capabilities and development prospects in indoor positioning. Since ultra-wideband will be affected by random errors in indoor positioning, to exploit the advantages of the Kalman filter and the LSTM network, this paper proposes a long short-term memory neural network algorithm fused with the Kalman filter (KF-LSTM) to improve UWB positioning. First, the ultra-wideband data is processed through Kalman filtering to weaken the noise in the data, and then the data is fed into the LSTM network for training, and the capability of the LSTM network to process time series features is employed to obtain more accurate label positions. Finally, simulation and measurement results show that the KF-LSTM algorithm achieves 71.31%, 37.28%, and 49.31% higher average positioning accuracy than the BP, KF-BP, and LSTM network algorithms, respectively, and the KF-LSTM algorithm performs more stably. Meanwhile, the more noise the data contains, the more obvious the stability contrast between the four algorithms.

show abstract