Wearable Transducer with MSH Model for Movement Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wearable monitoring devices are unable to provide detailed, real-time feedback on the correctness of physical movements during exercise routines without user intervention, relying on observers for assessment and feedback.
Innovation Solution
A system incorporating wearable transducers with MEMS sensors and a multilayer perceptron/support vector machine/hidden Markov (MSH) model that generates physiologic data, analyzes it, and provides feedback on movement correctness by comparing it to stored exercise models, allowing for context-aware monitoring and real-time feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If wearable transducers with MEMS sensors and MSH model are used to analyze physiologic data and provide real-time feedback on movement correctness, then measurement precision and feedback accuracy are improved, but device complexity increases
Solution Approach 1:
The system segments the complex monitoring task into multiple components: wearable transducers capture physiologic data, MEMS sensors process movement information, and the MSH model analyzes patterns. This segmentation allows each component to specialize in specific functions, improving overall measurement precision while distributing complexity across modular elements that can be independently optimized.
Solution Approach 2:
The patent introduces an intermediary processing layer (the MSH model and associated algorithms) that mediates between raw sensor data and final feedback output. This intermediary layer transforms complex raw data into meaningful movement correctness assessments, thereby improving measurement precision without requiring the wearable device itself to become overly complex.
2Productivity
If automated analysis with MSH model is implemented to provide feedback without observer intervention, then productivity and ease of operation are improved, but device complexity increases
Solution Approach 1:
The system implements self-service capability through the MSH model, which automatically analyzes physiologic data and generates feedback without requiring external observers or manual intervention. The wearable device with integrated sensors and processing algorithms serves itself to provide continuous monitoring and assessment, thereby improving productivity and ease of operation.
Solution Approach 2:
The patent establishes a closed-loop feedback system where the MSH model continuously analyzes sensor data and provides real-time feedback on movement correctness. This automated feedback mechanism eliminates the need for manual observer intervention, significantly improving productivity while the modular architecture manages the associated complexity.
3Measurement precision
If multiple sensors and processing algorithms are integrated into wearable device to enable context-aware monitoring, then measurement precision is improved, but use of energy increases
Solution Approach 1:
The system applies partial action by activating the full processing power of the MSH model and multiple sensors only when needed for specific analysis tasks. During normal operation, the device uses lower-power modes with selective sensor activation, thereby maintaining measurement precision when required while reducing overall energy consumption during continuous wear.
Data Source
AI summary
An exercise monitoring method and system in one embodiment includes a communications network, a wearable transducer configured to generate physiologic data associated with movement of a wearer, and to form a communication link with the communications network, a system memory in which command instructions are stored, a user interface operably connected to the computer, and a system processor configured to execute the command instructions to receive the generated physiologic data, analyze the received physiologic data with a multilayer perceptron/support vector machine/hidden Markov (MSH) model, model the analyzed physiologic data, and generate feedback based on a comparison of the model and a stored exercise object.