Indoor positioning method based on spectrum regression kernel discriminant analysis for terminal building
A discriminant analysis and indoor positioning technology, applied in the aviation field, can solve the problems of low positioning efficiency, no consideration of RSS data interference, and increased positioning errors
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0040] In order to verify the effect of the present invention, experimental verification is carried out according to the steps mentioned above. Experimental verification results such as Figure 2-4 shown.
[0041] Step 1: Offline data collection. The data collection experiment was carried out at the departure floor of Terminal T2 of Tianjin Binhai International Airport. Taking many factors into consideration, a rest area on the departure floor of the terminal building was selected as the experimental area. Judging from the collected data, in this rest area, multiple data collections at the same location fluctuate greatly due to the impact of people walking. The received signal strength data collected in this environment can effectively illustrate the advantages of the algorithm in this paper. Compared with most current indoor positioning, it is more practical. Take a reference node every 1m, a total of 10 reference nodes, as RP; Also select 10 locations in the experimental...
Embodiment 2
[0047] like Figure 5 As shown, this embodiment is to verify the impact of the number of offline samples on the data processing time, and its main implementation process includes:
[0048] In this embodiment, the King data set is used for verification. This data set is a relatively authoritative data set. Experiments on this data set can better explain the advantages and disadvantages of the algorithm. At the same time, the data set is also collected in a real environment, so the data is more descriptive. The data set includes 14,300 training sets and 5,060 test sets. Using the SRKDA algorithm on this data set can better reflect its computational superiority and greatly save calculation time.
[0049] This embodiment mainly focuses on the impact of different offline sample sizes on data processing time. In the process of offline sample processing, by controlling the number of offline samples from 1100 to 14300, other variables are kept constant.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


