Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Floor recognition method based on improved hidden Markov model

A recognition method and floor technology, which is applied in character and pattern recognition, transmission monitoring, instruments, etc., can solve the problems of less probability of people going, many people going, and the probability factors of people going to different floors are not taken into account, so as to achieve accurate The effect of improved efficiency, strong robustness, and high algorithm and model complexity

Active Publication Date: 2019-11-05
CHINA UNIV OF MINING & TECH
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, most current floor positioning methods only use barometer sensors or wireless signals such as WiFi and Bluetooth to realize floor positioning, and do not take into account the probability factors of people going to different floors in real scenes. For example, some floors are office areas, and people who go there Many, some floors are warehouses, less likely to be visited by people

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Floor recognition method based on improved hidden Markov model
  • Floor recognition method based on improved hidden Markov model
  • Floor recognition method based on improved hidden Markov model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0087] In a preferred example of the present invention, in Image 6 The experiment is carried out in the indoor positioning scene shown in the figure. This scene has 3 floors in total, mainly including offices, meeting rooms, toilets, and stairs. The wireless access points have two frequency bands of 2.4G and 5G respectively. The layout positions are as follows Figure 7 shown. The number of visible APs on the first, second, and third floors were 7, 12, and 7 respectively, and a total of 955 reference points were collected, of which the numbers of reference points on the first, second, and third floors were 285, 340, and 330, respectively, and the distance between reference points was 1.2m.

[0088] Use the Huawei P20 smartphone to collect fingerprints at the reference points on each floor, and the collection software is independently developed. Collect RSSI values ​​from only visible APs on this floor, with a sampling period of 15, and collect 60 sets of RSSI values ​​and MA...

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

No PUM Login to View More

Abstract

The invention discloses a floor recognition method based on an improved hidden Markov model. The method comprises the steps of establishing a signal fingerprint database used for initializing the improved hidden Markov model; establishing a personnel flow database for initializing the improved hidden Markov model; clustering the signal fingerprint database; constructing an improved hidden Markov model for floor recognition; establishing a training set for adjusting parameters of the improved hidden Markov model; adjusting an improved hidden Markov model for floor recognition; and predicting the floor by using the wireless signals acquired in real time and the improved hidden Markov model. Parameters are initialized according to the scene pedestrian flow change trend and the clustering result of the signal fingerprint, then the in-building activities of the user are sampled, and the model parameters are adjusted, so that the model is more stable and reliable. According to the method, people flow information data are mined and utilized, probability factors of people going to different floors in a real scene are considered, and accurate positioning of the floors in different buildingsis realized.

Description

technical field [0001] The invention relates to a floor recognition method based on an improved hidden Markov model, belonging to the technical field of indoor positioning. Background technique [0002] With the rapid development of science and technology, especially the development of computer and communication fields, location-based services (Location-Based Service, LBS) have become inseparable from people's daily life. In recent years, scholars at home and abroad have developed many technologies based on ZigBee, ultrasonic, infrared, radio frequency identification (RFID), Bluetooth, wireless local area network, ultra-wideband (UWB), visible light communication, computer vision, geomagnetism, etc. However, most of these positioning algorithms focus on the positioning of two-dimensional planes, and relatively little attention is paid to three-dimensional floor recognition, which cannot meet the needs of indoor positioning in the current complex building environment, especia...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/2458G06K9/62H04B17/318H04W64/00
CPCG06F16/2465G06F16/2462H04W64/006H04B17/318G06F18/23G06F18/295Y02D30/70
Inventor 司明豪汪云甲徐生磊孙猛
Owner CHINA UNIV OF MINING & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products