Wearable Movement Profiling for Atypical Motion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wearable sensor technologies fail to effectively track the quality of user movements, particularly in classification subspaces over time, and do not adequately integrate individual movement segments or combine within-subject deviations with subgrouping between individuals, limiting their application outside the lab.
Innovation Solution
A device utilizing computer processors and memory to analyze individualized movement profiles from wearable sensors, employing supervised and unsupervised machine learning to identify typical and atypical movements, and subgroup analyses to provide real-time feedback on deviations from predefined patterns, considering external factors like terrain and weather.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If wearable sensors are used to track movement quantity, then basic fitness tracking is achieved, but movement quality assessment is insufficient
Solution Approach 1:
The patent combines multiple motion sensors (accelerometers, gyroscopes, magnetometers) into an integrated wearable device that simultaneously captures linear acceleration, angular velocity, and magnetic field data. This merging of sensing capabilities enables comprehensive movement quality assessment without requiring multiple separate devices, thus improving measurement precision while managing device complexity.
Solution Approach 2:
The patent introduces machine learning algorithms as an intermediary between raw sensor data and movement quality assessment. These algorithms process and interpret the complex sensor signals to extract meaningful movement patterns and quality metrics, bridging the gap between basic motion detection and sophisticated movement analysis.
2Measurement precision
If existing approaches examine gait patterns on average, then population-level trends are identified, but individual movement segments are not considered
Solution Approach 1:
The patent segments continuous gait data into discrete movement cycles (e.g., individual steps or strides) and analyzes each segment separately. This segmentation enables precise assessment of individual movement patterns while maintaining the ability to aggregate results for population-level analysis, thus improving individual movement analysis without overwhelming data processing requirements.
Solution Approach 2:
The patent applies machine learning models selectively to identify and analyze only the most relevant movement segments that deviate from normal patterns. Rather than processing every single data point equally, the system focuses computational resources on significant deviations, achieving high measurement precision with reduced data processing volume.
3Measurement precision
If single motion sensing devices are used, then device simplicity is maintained, but detection accuracy is limited
Solution Approach 1:
The patent merges multiple types of motion sensors (accelerometers for linear motion, gyroscopes for rotational motion, magnetometers for orientation) into a unified sensing system. This combination enables comprehensive three-dimensional movement tracking and significantly improves detection accuracy compared to single-sensor devices, while the sensors are integrated into a single wearable unit to manage complexity.
4Ease of operation
If existing approaches are used outside the lab, then portability is achieved, but measurement reliability deteriorates
Solution Approach 1:
The patent implements feedback mechanisms where the wearable device continuously monitors movement patterns and provides real-time or near-real-time assessment results to users. This feedback loop enables the system to adapt to individual user characteristics and environmental conditions, maintaining measurement reliability in diverse real-world settings while preserving portability.
Solution Approach 2:
The patent employs machine learning models that are pre-trained and embedded within the wearable device, enabling it to perform autonomous movement analysis without requiring lab-based equipment or expert intervention. The device self-calibrates and self-analyzes movement patterns, ensuring reliable assessment in portable, real-world applications.
Data Source
AI summary
Methods, systems and devices are provided for utilizing user movement data obtained from one or more wearable sensors during physical activity to compare individualized changes overtime, for example typical versus atypical movement patterns, with subgroup analyses for assessing changes between other users in order to develop an assessment of movement for, for example, tracking injury risk, performance, and/or rehabilitation. The movement information may comprise multi-sensor, high dimensional datasets. Techniques are provided for integrating human movement data from one or more wearable sensor with one or more additional data sources to define an individualized movement profile of a user's movements. The user or another individual may be notified when the user's movements deviate from this individualized movement profile.