Indoor Positioning Model Based on Support Vector Regression Optimized by the Sparrow Search Algorithm

With the popularity and development of mobile smart terminals and wireless LANs, the demand for instant information data is increasing, thus indoor positioning is particularly significant. WiFi positioning technology is widely used for indoor positioning due to its low cost, easy implementation, wide coverage, and strong communication capability. Location fingerprint method is a location algorithm in WiFi positioning technology, which does not have high requirements for an indoor network environment. The positioning results of indoor positioning are susceptible to interference from external factors such as the positioning environment. In order to improve the accuracy and stability of localization, the population initialization process of the sparrow search algorithm (SSA) is optimized using logistic chaos mapping, and the support vector regression (SVR) machine is optimized with an improved sparrow search algorithm to obtain an indoor positioning prediction model. The model is compared and analyzed with GA-SVR and PSO-SVR through simulation experiments to show the superiority of the model.