Therefore, it is usually in the form of combining multiple sensors, e.g., the fusion of WiFi and IMU, the hybrid of Bluetooth and IMU, the integration of WiFi, geomagnetic field, and IMU. Complex and changeable indoor environments, various indoor structures and layouts, and moving pedestrians make it extremely difficult and challenging for any technology to realize universal high-precision indoor positioning (Cheema, 2018, Hancke and Silva, 2021, Nguyen et al., 2021). IMU is often utilized with other sensors because it is not susceptible to interference from the external environment. But methods using IMU alone can only output relative positioning results. The geomagnetic field positioning approach could get absolute meter-level results using fingerprints. With densely deployed WiFi, Bluetooth, UWB, light, or ultrasonic stations, these methods can quickly obtain the absolute location based on ranges, angles, or fingerprints. Other positioning methods can achieve positioning accuracy from the sub-meter to the meter level. The high-precision positioning of pseudo-satellite requires specific devices. For example, computer vision is sensitive to light and tends to fail in less differentiated scenes. But they are limited to experimental scenes or equipment. Technologies using computer vision or pseudo-satellite could achieve millimeter-level positioning accuracy. Yu et al., 2021), and inertial measurement unit (IMU)(Feng et al., 2020, Wen et al., 2020, Wong et al., 2022). Li, Zhao, & Sandoval, 2020), ultrasonic (Carotenuto et al., 2020, Chen et al., 2021), computer vision (Jeong et al., 2021, Jin et al., 2018), visible light (Bai et al., 2021, Bakar et al., 2021), pseudo-satellite (Y. Sun et al., 2022), ultra-wideband (UWB) (Ardiansyah, Nugraha, Han, Deokjai, & Kim, 2019 B. Zhou, Yuan, Liu, & Qiu, 2017a), geomagnetic field (Shi, He, & Feng, 2021 M. There are a lot of indoor positioning technologies, such as wireless fidelity (WiFi) (Ashraf et al., 2019, Liu et al., 2019, Seong and Seo, 2018), Bluetooth (Puckdeevongs et al., 2020 C. The needs for high-precision indoor positioning services are necessary and urgent. Indoor positioning plays a critical role in the fields of indoor navigation, emergency rescue, automatic driving, intelligent warehousing, smart campus, and smart home (B. The PSOSVRPos algorithm could achieve positioning accuracy with a mean absolute error of 1.040 m, a root mean square error (RMSE) of 0.863 m and errors within 1 m of 59.8%.Įxperimental results indicate that the PSOSVRPos algorithm is a precise approach for WiFi indoor positioning as it reduces the RMSE (35%) and errors within 1 m (14%) compared with state-of-the-art algorithms such as convolutional neural network (CNN) based methods. The positioning experiment is conducted on an open dataset (1511 samples, 154 features). PSO algorithm concentrates on the global-optimal parameter estimation of the SVR model. SVR algorithm devotes itself to solving localization as a regression problem by building the mapping between signal features and spatial coordinates in high dimensional space. To improve the accuracy, we propose a WiFi indoor positioning algorithm based on support vector regression (SVR) optimized by particle swarm optimization (PSO), termed PSOSVRPos. It faces many challenges, and the primary problem is the low positioning accuracy, which hinders its widespread applications. Wireless fidelity (WiFi) indoor positioning has attracted the attention of thousands of researchers.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |