Wearable Sensor Hyperactivity Scoring With Context Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for measuring hyperactivity in children rely heavily on subjective reports from parents or teachers, which are prone to bias.
Innovation Solution
A system and method using a wearable device to collect sensor data, apply machine-learning models for activity labeling and context filtering, and generate objective hyperactivity risk scores based on motion, location, and heart rate data, with graphical user interfaces for visualization and intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If subjective reports from parents or teachers are used to measure hyperactivity, then the measurement process is simple and easy to implement, but the measurement precision and objectivity deteriorate due to subjectivity and bias
Solution Approach 1:
The patent replaces the manual, subjective reporting system with an automated sensor-based measurement system. Wearable devices with accelerometers, gyroscopes, and other sensors continuously collect objective physiological and behavioral data, eliminating human subjectivity while providing precise, quantifiable hyperactivity measurements through algorithmic analysis of motion patterns, heart rate, and other biomarkers
Solution Approach 2:
The patent introduces wearable sensors and machine learning algorithms as intermediaries between the subject's behavior and the measurement outcome. These intermediaries objectively capture and interpret hyperactivity signals, translating complex physiological data into standardized hyperactivity scores that are free from parental or teacher bias while maintaining measurement accuracy
2Measurement precision
If continuous sensor data collection is implemented to improve measurement precision, then objectivity and granularity of hyperactivity assessment improve, but the quantity of data and processing requirements increase
Solution Approach 1:
The patent extracts only the most relevant features from the continuous sensor data stream for hyperactivity analysis. Instead of processing all raw sensor data, the system identifies and extracts key motion patterns, activity intensity metrics, and temporal characteristics that specifically indicatehyperactivity, discarding redundant information while maintaining measurement precision
Solution Approach 2:
The patent segments the continuous sensor data into meaningful time windows and activity contexts for analysis. By dividing the data stream into discrete segments and analyzing hyperactivity patterns within each segment, the system manages data volume while maintaining granular assessment capability, allowing detailed temporal analysis without overwhelming processing requirements
3Measurement precision
If context filtering is applied to improve measurement precision by considering activity labels, then the accuracy ofhyperactivity detection improves, but the device complexity and processing requirements increase
Solution Approach 1:
The patent applies preliminary context filtering by pre-defining activity contexts and labels that are used to filter and interpret sensor data. Activity recognition algorithms pre-identify contexts such as sleeping, exercising, or sedentary periods, and thehyperactivity measurement system uses these pre-established contexts to filter relevant data, improving accuracy without requiring complex real-time processing of all possible activity scenarios
Data Source
AI summary
Provided is a system, method, and device for determining hyperactivity based on sensor data. The system includes at least one processor configured to collect sensor data from a wearable device worn by a subject user over a time period, the sensor data comprising at least motion data for the subject user, extract features from the sensor data, automatically assign at least one activity label of a plurality of activity labels to each feature based on at least one classification model, apply context filtering to the features based on the plurality of activity labels resulting in filtered feature data, and generate a hyperactivity risk score for the subject user based on at least one machine-learning model and the filtered feature data.