Abstract
Currently most of the existing indoor fingerprint positioning algorithms are based on fingerprint database. The accuracy of the fingerprint database will directly affect the final positioning accuracy. Therefore, through the research of fingerprint data, a method based on skewness-kurtosis normality test and Kalman filter fusion is proposed. In the training phase, the RSSI (Received Signal Strength Indication) samples received on each fingerprint point are tested based on the skewness-kurtosis normality. If the normal distribution model is met, the normal distribution function is used to estimate the probability density of the samples. If not the kernel function will be used. And then the value of the large probability density is taken for Kalman filtering, and finally, the averaged value after filtering is used to establish a high-precision fingerprint database. In the online positioning stage, the weighted KNN (K-Nearest Neighbor) is used to estimate the position, and finally, the positioning point is corrected by the fusion of the Levenberg-Marquardt method and the Kalman filter. The optimization of the three stages can improve the positioning accuracy. The simulation results show that the indoor positioning method proposed in this paper has the least number of iterations and the positioning accuracy is improved by 60% compared with the traditional Kalman filtering method.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
