KNN indoor target positioning method based on adjacent weighted adaptive k value

Abstract

The invention provides a KNN indoor target positioning method based on an adjacent weighted adaptive k value, and the method comprises the following steps: 1, constructing a position fingerprint database which comprises a position set P and a signal intensity value R through the RSS data, collected by RFID equipment, of each indoor position; and 2, acquiring a corresponding signal intensity valueof a to-be-positioned target by using a RFID card reading antenna, matching the signal intensity value with the position fingerprint database by using a KNN improved algorithm to obtain a fingerprintwith the highest matching degree, and taking the fingerprint mapping position as the current position of the to-be-positioned target. According to the KNN improved algorithm, the optimal k value corresponding to the fingerprint information of the to-be-positioned target is obtained by calculating the correlation between the RSS data set measured on line and the fingerprint data set in the positionfingerprint database, and the matching error probability is reduced as much as possible by using an adjacent weighting method. Simulation results show that compared with KNN and WKNN, the matching precision of the improved algorithm is improved by at least 7.1 times.

Description

technical field [0001] The invention relates to position fingerprint positioning technology, in particular to a KNN indoor target positioning method based on adjacent weighted self-adaptive k value. Background technique [0002] With the maturity of the mobile Internet, location-based mobile application services are becoming more and more common in people's daily lives. In the outdoor environment, applications such as Internet of Vehicles, shared bicycles, and smart logistics are all based on location positioning to provide services for people. In the indoor environment, services such as indoor navigation, elderly care and personnel care have greatly facilitated people's daily necessities of life. At the same time, relevant literature shows that people spend more than 80% of their time indoors, which makes people's demand for indoor positioning services higher and higher. Therefore, indoor wireless positioning service has become a hotspot of extensive research at present. ...

AI Technical Summary

Problems solved by technology

The trilateration positioning method has low complexity and low calculation amount, but it is limited by the performance of the RFID itself, and the positioning accuracy is not high

The k-nearest neighbor algorithm is generally used as the matching algorithm in the position fingerprint positioning method, but in the actual application process, the algorithm has the problem of being unable to adapt to the characteristics of the data sample due to factors such as the fixed value of k and the choice of distance measurement.

Images