Graph-Based Bio-Signal Event Sensing for Wearable Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wearable devices face challenges in continuous monitoring due to limited battery capacity and computational power, making it difficult to handle complex and computationally expensive data analyses, such as detecting brain order-disorder transitions, which require better compressive sensing capabilities to capture the structure of events.
Innovation Solution
The implementation of graph-based computation for bio-signal event sensing, which involves converting raw signals into graph structures to reduce computational and communication costs, exploring temporal and spatial relations, and matching graph structures to identify potential medical conditions, thereby reducing the burden on wearable devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex data analysis methods are used to detect brain order-disorder transitions, then measurement precision is improved, but device complexity increases and computational power requirements exceed wearable device capabilities
Solution Approach 1:
The patent introduces graph structures as an intermediary representation between raw bio-signals and analysis results. The graph-based computation framework transforms complex signal processing into graph operations, reducing computational complexity while maintaining detection precision for brain order-disorder transitions
Solution Approach 2:
The patent changes the parameter representation from continuous time-series signals to discrete graph structures with nodes and edges. This parameter transformation enables efficient computation of correlation between bio-signals and detection of transitional patterns, resolving the contradiction between precision and computational complexity
2Reliability
If continuous monitoring is performed to capture health events, then reliability is improved, but energy consumption increases and battery life decreases
Solution Approach 1:
The patent implements periodic graph-based analysis at specific time windows instead of continuous processing. The system continuously monitors bio-signals but performs computationally intensive graph operations periodically or event-triggered, maintaining monitoring reliability while significantly reducing energy consumption on wearable devices
Solution Approach 2:
The patent extracts only the essential features and transitional patterns from continuous bio-signals by converting them to graph structures. This extraction process removes redundant data while preserving critical health event information, enabling reliable monitoring with reduced computational and energy requirements
Data Source
AI summary
One or more biological signals are obtained. The one or more biological signals are converted to one or more graph structures. Correlation between two or more of the biological signals are determined using the one or more graph structures. One or more changes in the one or more graph structures within a time window are recorded. A signal graph model is generated based on the recorded changes.