Indoor Positioning Grid Clustering for RSSI Noise
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Indoor positioning systems face challenges due to noise in radio frequency signals and environmental changes, leading to inaccuracies in positioning estimation, which existing methods struggle to overcome effectively.
Innovation Solution
A method combining two approaches for indoor positioning, using a grid pattern with anchor points and unsupervised learning to update positioning parameters based on RSSI measurements, which iteratively improves path-loss parameters and adapts to environmental changes, enhancing accuracy and robustness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional RSSI-based positioning methods are used in indoor environments, then positioning can be implemented, but noise in transmitted or received signals and changing environment cause inaccuracies in positioning estimation
Solution Approach 1:
The system performs preliminary clustering of RSSI measurements into subsets associated with different grids before positioning estimation. This pre-processing organizes the noisy data into structured groups, enabling more accurate parameter extraction and reducing the impact of random noise on final positioning accuracy.
Solution Approach 2:
The system iteratively updates path-loss parameters for each grid by comparing clustered RSSI measurements with expected values. This feedback mechanism continuously refines the positioning model by adjusting parameters based on observed measurements, thereby improving accuracy while adapting to environmental changes.
2Measurement precision
If path-loss parameters are updated iteratively using clustered RSSI measurements, then positioning accuracy improves, but computational complexity increases
Solution Approach 1:
The indoor space is divided into multiple grids, and RSSI measurements are clustered into subsets corresponding to each grid. This segmentation allows the system to process measurements locally for each grid rather than handling all measurements globally, reducing computational complexity while maintaining positioning accuracy through localized parameter updates.
Data Source
AI summary
A method for evaluating positioning parameters in a defined area, wherein the defined area is affected by at least three stationary access beam points and over which a grid pattern is laid with at least two grids, each grid having an anchor. An initial vector of positioning parameters is assigned to each anchor and a plurality of RSSI measurements are captured within the defined area by receiving signals from the at least three stationary access beam points. The plurality of RSSI measurement are clustered in a plurality of subsets, wherein the number of subsets corresponds to the number of the at least two grids. Finally, each subset of the plurality of subsets is associated with a respective one of the at least two grids and the initial vector is updated based on the subset of the plurality of subsets associated with the respective one of the at least two grids.