Conditional Signal Storage for Bio-Signal Memory Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high memory requirements and cost associated with continuously monitoring and storing bio-signals at high resolution over extended periods pose significant challenges due to the large amount of data needed to accurately record signals with high-frequency components.
Innovation Solution
A personal computer device equipped with sensors and processors that classify bio-signals as anomalous or non-anomalous, saving them at higher resolution only when anomalies are detected, thereby reducing memory usage and storage costs by storing non-anomalous signals at lower resolution or omitting them altogether.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If continuous high-resolution monitoring of bio-signals is performed, then measurement precision is improved, but memory requirements increase
Solution Approach 1:
The patent applies local quality by storing different portions of the signal at different resolutions. Specifically, portions containing anomalies are stored at high resolution while normal portions are stored at low resolution or not stored at all. This resolves the contradiction by making the storage quality local to the signal content rather than uniformly high across all data.
Solution Approach 2:
The patent changes the resolution parameter dynamically based on signal characteristics. The system adjusts the storage resolution from high to low or zero based on whether anomalies are detected in the signal portions, thereby reducing overall memory requirements while maintaining measurement precision where needed.
2Reliability
If high-resolution data is stored for extended periods, then reliability is improved, but loss of substance increases
Solution Approach 1:
The patent ensures reliability is maintained for anomaly detection by storing high-resolution data locally at anomaly points, while reducing storage elsewhere. This selective approach maintains the necessary data quality for reliable anomaly detection without the prohibitive cost of storing all data at high resolution continuously.
Solution Approach 2:
The system dynamically changes the storage resolution parameter based on anomaly detection results, storing high-resolution data only when anomalies are present and low-resolution or no data when signals are normal, thereby reducing overall storage cost while maintaining detection reliability.
3Measurement precision
If continuous monitoring at high data rate is performed, then measurement precision is improved, but use of energy increases
Solution Approach 1:
The patent reduces processing energy by applying high measurement precision only locally to portions of the signal containing anomalies. Normal signal portions are processed at lower precision or not processed at all, significantly reducing the overall energy consumption while maintaining accuracy where anomalies occur.
Solution Approach 2:
The system dynamically changes the processing precision parameter based on anomaly detection, using high precision processing only when anomalies are detected and low precision processing during normal conditions, thereby reducing energy consumption while maintaining measurement accuracy when needed.
Data Source
Figure 1~2E
Figure 3~5
Figure 6~7
AI summary
An apparatus comprising: circuitry configured to classify a signal; and circuitry configured to control saving of the signal to a memory with a conditional resolution, wherein a signal that is classified as anomalous is saved at higher resolution as a higher resolution signal and a signal that is not classified as anomalous is saved at lower resolution as a lower resolution signal or is not saved.