Likelihood Threshold Filtering for ML Data in Mobile Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In mobile communication systems, the use of unique data for machine learning processing can lead to lower learning accuracy and inappropriate processing outcomes.
Innovation Solution
A communication method that involves deriving a trained model for a predetermined block based on signals received from a data reception entity, calculating output data using either the predetermined block or the trained model, and performing predetermined processing when the likelihood of the input or output data is equal to or less than a threshold value.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If machine learning processing uses unique data, then processing can be performed, but learning accuracy deteriorates
Solution Approach 1:
The patent implements a feedback mechanism where the data reception entity calculates likelihood values for received data and returns this information to the data transmission entity. The data transmission entity then uses this feedback to filter out data with likelihood values below a threshold before using it for machine learning training, thereby improving learning accuracy by preventing inappropriate data from degrading model performance
Solution Approach 2:
The patent introduces a likelihood threshold parameter that changes the data selection criterion from accepting all unique data to selectively accepting only data exceeding a likelihood threshold. This parameter change enables the system to maintain machine learning processing while filtering out data that would degrade learning accuracy, thus resolving the contradiction between processing capability and learning quality
2Reliability
If data transmission entity transmits all data to data reception entity, then data utilization is maximized, but learning accuracy deteriorates due to inclusion of inappropriate data
Solution Approach 1:
The data reception entity calculates likelihood values for received data and feeds this information back to the data transmission entity. This feedback loop enables the data transmission entity to selectively transmit only data exceeding the likelihood threshold, maximizing data utilization for machine learning while preventing inappropriate data from reducing learning accuracy
Solution Approach 2:
The introduction of the likelihood threshold parameter transforms the data transmission strategy from transmitting all data to transmitting only data meeting the threshold criterion. This parameter-based filtering maintains high data utilization for training purposes while ensuring that only appropriate data is used, thereby preserving learning accuracy
Data Source
AI summary
In an aspect, a communication method is a communication method in a mobile communication system. The communication method includes deriving, by a data transmission entity, a trained model for a predetermined block based on a signal received from a data reception entity. The communication method includes calculating, by the data transmission entity, output data corresponding to input data by using one of the predetermined block or the trained model. The communication method includes performing, by the data transmission entity, predetermined processing when a likelihood of the input data and/or a likelihood of the output data is equal to or less than a threshold value.