Indoor position Backpropagation neural network probability density prediction method
A back-propagation and probability density technology, applied in neural learning methods, biological neural network models, and location-based services, etc., can solve problems such as poor distribution simulation and large probability calculation errors.
Active Publication Date: 2021-12-21
XIAN UNIV OF TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide a method for predicting the probability density of indoor location by backpropagation neural network, which solves the problems of poor simulation of the distribution of indoor location data in different environments and large error in probability calculation, and improves indoor positioning. precision
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
[0036] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0037] Due to the wide application of current indoor positioning technology and the high requirement of positioning accuracy, the present invention proposes a way to make the excitation of neurons in the same layer The functions are different, and finally improve the accuracy of the neural network model to predict the location and apply it to the field of indoor positioning.
[0038] A kind of backpropagation neural network probability density prediction method of indoor position of the present invention is specifically implemented according to the following steps:
[0039] Step 1, select the square test area of multi-layer indoor structure (such as the first floor in the library) as the test site such as figure 1 As shown, select n*n (example 8*8=64) standard reference points altogether with the form of rectangular grid, each standard ref...
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 discloses an indoor position back propagation neural network probability density prediction method. The method comprises the following steps: firstly, selecting a square test area of a multi-layer indoor structure as a test site; totally selecting n * n standard reference points in a rectangular grid form; setting RSSI signal transmitters respectively at four corners of the test site; summarizing two types of data of the RSSI value and the angle value measured by the selected standard reference point into the same standard data set; carrying out normalization processing on the measured standard data set; dividing the processed standard data set into a training set and a test set according to the ratio of 7: 3; improving a traditional back propagation neural network model and analyzing same, and finally obtaining an improved BPNN model; and finally, obtaining an accumulative error distribution function and a probability density function of the reference standard point. According to the invention, the problems of poor distribution condition simulation and large probability calculation error of indoor position data in different environments are solved, and the indoor positioning precision is improved.
Description
technical field [0001] The invention belongs to the technical field of indoor positioning, and in particular relates to a method for predicting the probability density of an indoor position by a backpropagation neural network. Background technique [0002] In recent years, the number of positioning technology applied to new mobile devices such as mobile phones, tablet computers and portable devices has been increasing, and with the rapid growth of network equipment functions, indoor positioning technology has also played an increasingly important role in the expansion of location-aware related applications. role. In the indoor environment, due to the complex obstacle environment outdoors, accurate GPS signals cannot be received indoors or there are large errors in the received signals, which cannot be accurately applied to indoor positioning. Therefore, positioning services based on indoor information have great potential. research and commercial value. Indoor positioning ...
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): G06N3/04G06N3/06G06N3/08G06Q10/04H04W4/029H04W4/33
CPCG06N3/04G06N3/084G06N3/061G06Q10/04H04W4/029H04W4/33
Inventor 费蓉郭与番李军怀李爱民张宽杨璐
Owner XIAN UNIV OF TECH