AI Position Inference Training with Obstacle-Filtered Signals and GPR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for inferring position information using wireless fidelity (wi-fi) and Bluetooth signals are hindered by obstacles such as pedestrians, which affect signal strength and quality, leading to low-quality training data and inaccurate position predictions.
Innovation Solution
A method and electronic device for training an artificial intelligence model that filters out low-quality signal data based on obstacle data and generates augmented data using algorithms like Gaussian Process Regression (GPR) to improve position inference accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If signal data is collected in environments with obstacles (pedestrians, walls), then more training data is available, but the position inference accuracy deteriorates due to signal interference
Solution Approach 1:
The patent extracts and removes low-quality signal data points that are affected by obstacles from the training dataset. By identifying and excluding data collected in environments with pedestrians or walls, the system retains only high-quality signal data for training, thereby maintaining position inference accuracy while still utilizing available training data.
2Measurement precision
If obstacle data is used to filter signal data, then position inference accuracy improves, but device complexity increases due to additional processing requirements
Solution Approach 1:
The patent applies preliminary action by pre-filtering signal data during the training phase using obstacle information. The system预先 identifies and removes low-quality data points before model training, so that the position inference model only needs to process high-quality data during deployment, reducing real-time computational complexity while maintaining high accuracy.
3Measurement precision
If augmented data is generated using GPR algorithm, then position inference accuracy improves, but loss of time increases due to additional data generation processing
Solution Approach 1:
The patent uses copying by generating augmented training data through Gaussian Process Regression (GPR) algorithm. The GPR algorithm creates synthetic signal data that mimics real-world conditions, allowing the model to be trained on diverse scenarios without requiring additional physical data collection, thus improving accuracy while avoiding the time cost of extensive field data gathering.
Data Source
AI summary
A method of training an artificial intelligence model for inferring position information is provided. The method includes identifying a first data set including first signal data for a signal device collected at a first position by a user terminal, data for an obstacle located within a certain distance from the user terminal when collecting the first signal data, and second signal data for the signal device collected at a second position, generating a second data set by filtering out the first signal data from the first data set, based on the data for the obstacle, generating a third data set by generating augmented data for the first position and the signal device, based on the second signal data, and training an artificial intelligence model for inferring position information by using the third data set.