Unlock instant, AI-driven research and patent intelligence for your innovation.

An Indoor Room-Level Localization Method Based on Wi-Fi Fingerprint Database Text Classification

A technology of text classification and positioning method, applied in text database clustering/classification, unstructured text data retrieval, transmission monitoring and other directions, can solve the problem that Wi-Fi signals are easily affected by environmental factors, and reduce the data dimension. , high efficiency, and the effect of improving positioning accuracy

Active Publication Date: 2022-04-19
ZHEJIANG UNIV CITY COLLEGE
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But Wi-Fi signal is easily affected by environmental factors such as walls, doors, furniture and even 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
  • An Indoor Room-Level Localization Method Based on Wi-Fi Fingerprint Database Text Classification
  • An Indoor Room-Level Localization Method Based on Wi-Fi Fingerprint Database Text Classification
  • An Indoor Room-Level Localization Method Based on Wi-Fi Fingerprint Database Text Classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0084] In order to verify the positioning effect of this method, the present invention uses the 2017 Tianchi competition shop positioning data set, and uses the Wi-Fi data merged by 4 shops (m_615, m_622, m_623, m_625) to verify the present invention. Firstly, mobile hotspots and communication provider hotspots are eliminated from the data of the 4 shops, and a Wi-Fi signal strength fingerprint library is constructed, and according to figure 2 In the manner shown, the signal strength and the number of APs are combined to form words of the short text. The short text data consists of the name of the store as a label, and a short sentence composed of multiple words as a feature.

[0085] By dividing the short text data, the training set and test set are experimented according to the ratio of (50%, 60%, 70%, 80%, 90%), and input into the text classifier to calculate the classification accuracy. Such as image 3 As shown, in this shop data set, it is compared with KNN, Naive Ba...

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 relates to an indoor room-level positioning method based on Wi-Fi fingerprint library text classification, comprising the steps of: first collecting Wi-Fi signal strength and basic service set identifiers in the indoor environment of shopping malls; converting the Wi-Fi fingerprint library into Short text data; perform feature selection and word weight calculations; use Crammer‑Singer support vector classifier; calculate classification accuracy. The beneficial effects of the present invention are: the present invention converts the signal strength of Wi-Fi into short text words, ignoring the influence of its signal strength directly, no longer considering the characteristics of its signal strength, and reducing the Wi-Fi fingerprint database; The invention converts the Wi-Fi fingerprint database into a short text data set, which reduces the data dimension. At the same time, the text classifier is based on a linear kernel SVM classifier, which is highly efficient in training and testing, and can greatly reduce positioning time and improve positioning accuracy.

Description

technical field [0001] The invention relates to an indoor room-level positioning method based on the text classification of a Wi-Fi fingerprint database, mainly using the text classification method to perform indoor room-level positioning on the Wi-Fi fingerprint database. Background technique [0002] With the rapid development of mobile communication and pervasive computing technology, various applications are widely trying various technologies for indoor positioning. [0003] Current technologies such as outdoor positioning based on GPS, indoor positioning technology based on geomagnetism, RFID, ZigBee network, Bluetooth, etc. Wi-Fi based positioning is mainly divided into two categories: methods based on location fingerprints and methods based on signal propagation models. Among them, the fingerprint-based indoor positioning system uses Wi-Fi fingerprints composed of multiple access points (APs) and their signal strength (RSSI). But Wi-Fi signals are easily affected by...

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 Patents(China)
IPC IPC(8): G06F16/35G06F40/216G06F40/151H04B17/318H04W64/00
CPCG06F16/355H04B17/318H04W64/006
Inventor 郑增威汪振陈垣毅陈丹
Owner ZHEJIANG UNIV CITY COLLEGE