Wi-Fi positioning system and method based on probability and support vector machine calculation

Abstract

The invention discloses a WiFi positioning system based on probability and support vector machine computation and a method thereof. Multiple APs are randomly deployed in a positioning space so that the positioning space is divided into multiple positioning areas. The system comprises a data acquisition module, a data processing module and an SVM training module. The data acquisition module acquires positioning area data including positioning area identification, AP unique identification and signal intensity and acquires data to be positioned including AP unique identification and signal intensity. The data processing module processes the positioning area data so that a standard data table is generated. The SVM training module performs training processing with the data in the standard data table acting as an input source, and an SVM training result module is acquired after processing. The data to be positioned are processed by the SVM training result module so that a positioning result is acquired. The APs can be randomly deployed without limitation of aspects of position, number, clock or cost so that applicable occasions are wide.

Description

technical field [0001] The invention relates to a WiFi positioning system and method based on probability and support vector machine calculation, belonging to the technical field of wireless communication. Background technique [0002] As a supplement to GPS positioning technology, WiFi (wireless fidelity) positioning technology has been widely used due to its advantages of fast positioning speed and high precision. Deploying WiFi networks in buildings and densely populated areas, especially indoor spaces, can get good positioning and Network connection effects. [0003] The existing WiFi positioning methods mainly include the following three types: [0004] First, positioning is based on the triangular positional relationship between the mobile terminal and the AP and the detected signal strength. Since the signal strength of the wireless signal attenuates with the increase of the transmission distance, the mobile terminal can estimate the distance between the communicati...

AI Technical Summary

Problems solved by technology

[0010] The conditions for the use of this method are that the WiFi tag device needs to be customized to ensure isomorphism and uniform coverage in the positioning space, and the WiFi tag device maintains a network connection with the server; the disadvantage of this method is that a large-scale deployment of customized WiFi tag devices is required , high cost, only suitable for large spaces but not for small spaces

[0011] It can be seen that the existing WiFi positioning methods have certain requirements for the deployment location, quantity, clock, and equipment cost of APs, and the application occasions are limited.

Images