Multi-classifier global dynamic fusion positioning method based on WiFi and geomagnetic fingerprint
A fusion positioning and multi-classifier technology, which is applied in positioning, instruments, ground navigation, etc., can solve the problems that the local dynamic fusion method of classifiers cannot maximize the classification complementary characteristics, and the positioning accuracy is not high, so as to achieve good real-time positioning and high accuracy. High, the effect of improving accuracy and robustness
Active Publication Date: 2018-12-18
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 9 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is: to solve the problem that the partial dynamic fusion method of the classifier cannot maximize the complementary characteristics of each classification, and at the same time, to solve the problem that only relying on WiFi fingerprints cannot maximize the information acquisition function of the rich sensors at the mobile terminal, resulting in low positioning accuracy problem, the present invention provides a multi-classifier global dynamic fusion positioning method based on WiFi and geomagnetic fingerprints
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0037] In order to solve the problem that the local dynamic fusion method of the classifier cannot maximize the complementary characteristics of each classification, and at the same time, in order to solve the problem that the information acquisition function of the rich sensors on the mobile terminal cannot be maximized by only relying on WiFi, resulting in low positioning accuracy, the present invention provides a A multi-classifier global dynamic fusion positioning method based on WiFi and geomagnetic fingerprints. The method of the present invention uses a mobile terminal to quickly obtain geomagnetic fingerprints and indoor WiFi signal strengths, construct a WiFi signal strength and geomagnetic mixed fingerprint library, and use the mixed fingerprint library to perform Multi-classifier training, global dynamic fusion of the prediction results of multiple classifiers to obtain the final position estimation during actual measurement. This method can fully tap the complementa...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a multi-classifier global dynamic fusion positioning method based on WiFi and a geomagnetic fingerprint, and relates to the technical field of indoor fusion positioning. The method comprises an offline stage: building a WiFi and geomagnetic hybrid fingerprint database, and dividing the WiFi and geomagnetic hybrid fingerprint database into two parts, wherein one part is usedfor classifier training, and the other part is used for training the weight of each classifier at each grid point to obtain a weight matrix; and an online positioning stage: preprocessing online data,inputting into each classifier to obtain classification results, indexing the weight matrix by using the online data and an offline fingerprint matching result to obtain a fusion weight, and weighting and fusing the classification results of the classifiers to obtain final position estimation. Through adoption of the method, the problem that a classifier local dynamic fusion method cannot maximize the complementary characteristics of the classifiers is solved, the positioning accuracy is effectively improved through combined use of WiFi and the geomagnetic fingerprint.
Description
technical field [0001] The invention relates to the technical field of indoor fusion positioning, in particular to a multi-classifier global dynamic fusion positioning method based on WiFi and geomagnetic fingerprints. Background technique [0002] In recent years, with the rapid development of Internet of Things technology, indoor positioning technology has gained a lot of attention in military and civilian fields. Due to the complexity of the indoor environment, positioning systems such as WiFi signal strength, geomagnetism, Bluetooth, and inertial navigation information cannot effectively combat multipath propagation in complex indoor environments. Combined use of the above positioning information for positioning in complex indoor environments is an important development direction in the field of indoor positioning. In comparison, there is no need to deploy additional positioning equipment to obtain WiFi and geomagnetic information. WiFi signals have high discrimination ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G01C21/08G01C21/20G01S5/02
CPCG01C21/08G01C21/206G01S5/0252G01S5/0257
Inventor 郭贤生徐峰李林段林甫万群李会勇沈晓峰
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA