Brainwave Signal Compression via Feature Tag Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for transmitting brainwave physiological signals are inefficient, as they require users to wait several hours to several days for data interpretation, and real-time comparison with databases is challenging due to the large amount of data involved in displaying brainwave waveforms.
Innovation Solution
A method that compresses brainwave signals using static and dynamic feature tags, allowing for real-time transmission of these signals to a remote cloud system, enabling immediate feedback and adjustment through visual or auditory means.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If brainwave physiological signals are transmitted in original waveform format with many sampling points, then measurement precision is maintained, but transmission time and data processing time increase significantly
Solution Approach 1:
The patent extracts key characteristic points (peak points, valley points, inflection points) from the continuous brainwave signal and transmits only these extracted features along with their temporal and amplitude relationships. This extraction approach maintains the essential information needed for accurate waveform reconstruction while dramatically reducing the data volume and transmission time compared to transmitting all sampling points.
Solution Approach 2:
The patent creates a simplified representation (copy) of the original brainwave signal by using discrete characteristic points that capture the essential waveform features. This copy contains sufficient information to reconstruct the original signal accurately but requires far less transmission bandwidth and processing time than the full high-resolution waveform data.
2Measurement precision
If sampling frequency is increased to capture more brainwave details, then measurement precision improves, but data quantity and transmission complexity increase
Solution Approach 1:
Instead of transmitting all high-frequency sampling points, the patent extracts only the critical characteristic points (peaks, valleys, inflection points) that define the brainwave morphology. This extraction reduces the data complexity from thousands of points per second to a manageable set of key features while preserving the essential diagnostic information.
Solution Approach 2:
The patent transforms the continuous analog brainwave signal into discrete digital parameters representing characteristic points with specific attributes (amplitude, time position, point type). This parameter transformation simplifies the data structure and reduces transmission complexity while maintaining measurement precision through the preservation of key waveform features.
3Measurement precision
If all brainwave data is transmitted to cloud platform for analysis, then analysis accuracy is improved, but transmission time and user waiting time increase
Solution Approach 1:
The patent extracts and transmits only the essential characteristic points needed for accurate brainwave analysis rather than all raw sampling data. This extraction enables the cloud platform to perform accurate analysis on reduced data, achieving both high analysis accuracy and fast processing speed, thereby enabling real-time feedback applications.
Solution Approach 2:
The patent performs preliminary processing at the data acquisition end by identifying and extracting characteristic points before transmission. This preliminary action reduces the data burden on the cloud platform, allowing faster analysis and enabling real-time feedback without sacrificing analysis accuracy.
Data Source
AI summary
A method for transmitting compressed brainwave physiological signals is provided and including detecting a plurality of brainwave physiological signals of a subject, and generating an electroencephalography based on a time sequence of the plurality of brainwave physiological signals; splitting the electroencephalography into a plurality of sub-images based on the time sequence; using a plurality of static feature tags and a plurality of dynamic displacement tags stored in a brainwave database to identify at least one static feature tag and a plurality of associated dynamic displacement tags based on the time sequence according to the plurality of sub-images; generating at least one superimposed group tag, the superposed group tag is used to integrate the identified static feature tag and the associated dynamic displacement tag according to the time sequence; and transmitting the identified static feature tag, the associated dynamic displacement tag, and the superimposed group tag to a remote cloud system according to the time sequence.