Inertial Sensor Activity Identification via Signal Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing step counting devices are unable to detect or count motions other than steps and cannot differentiate between various user activities without external sensors, limiting their functionality in monitoring human activity.
Innovation Solution
A system utilizing inertial sensors in portable electronic devices to identify user activities and count periodic human motions by processing acceleration data, including the use of activity identification engines and motion processors to differentiate between activities such as walking, biking, and skiing, regardless of device orientation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If step counting devices use only basic acceleration sensors, then device complexity is reduced and manufacturing cost decreases, but the ability to detect and differentiate various human activities is limited
Solution Approach 1:
The patent applies multi-functionality by enabling a single acceleration sensor to perform multiple detection functions through sophisticated signal processing. The system processes acceleration data to detect various activities including walking, running, cycling, and swimming by analyzing different motion patterns, thereby eliminating the need for separate sensors for each activity type while maintaining high adaptability
Solution Approach 2:
The patent replaces mechanical sensor differentiation (using multiple physical sensors for different activities) with computational differentiation (using signal processing algorithms to distinguish activities). The activity identification engine uses pattern recognition and machine learning to differentiate between various human activities based solely on acceleration data, substituting mechanical complexity with computational intelligence
2Adaptability or versatility
If external sensors are added to detect non-step motions, then activity detection capability improves, but device complexity and dependency on external components increases
Solution Approach 1:
The patent applies self-service by enabling the acceleration sensor to independently detect and differentiate all types of human activities without requiring external sensors. The integrated activity identification engine processes raw acceleration data to identify walking, running, cycling, swimming, and other activities, making the system self-sufficient and eliminating dependency on external components
Solution Approach 2:
The patent merges the functions of multiple specialized sensors into a single acceleration sensor system. By combining activity detection, motion recognition, and classification functions into one integrated system with unified signal processing, the patent reduces system complexity while maintaining comprehensive activity monitoring capabilities
3Measurement precision
If activity identification algorithms are enhanced to differentiate between activities, then measurement precision improves, but processing time and computational energy consumption increase
Solution Approach 1:
The patent applies partial action by implementing a hierarchical processing approach where the system first performs basic motion detection and then applies more sophisticated classification algorithms only when needed. The activity identification engine uses simplified heuristics for common activities and reserves complex pattern recognition for ambiguous cases, thereby reducing overall computational energy consumption while maintaining high classification accuracy
Solution Approach 2:
The patent changes processing parameters dynamically based on detected activity patterns. The system adjusts sampling rates, processing intensity, and algorithm selection according to the detected motion characteristics, reducing computational energy consumption during routine activities while maintaining high precision during complex or ambiguous activity classification
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate monitoring and counting of various human activities without external sensors, providing users with comprehensive data on their activity levels and specific activity performance, regardless of device placement or orientation.
Implementation Method 1
The development of Micro-Electro-Mechanical Systems (MEMS) technology has enabled manufacturers to produce inertial sensors (e.g., accelerometers) of sufficiently small size, cost, and power consumption to fit into portable electronic devices. Such inertial sensors can be found in a limited number of commercial electronic devices such as cellular phones, portable music players, pedometers, game controllers, and portable computers.
Data Source
AI summary
A method for monitoring human activity using an inertial sensor includes monitoring accelerations, identifying a current user activity from a plurality of user activities based on the accelerations, and counting periodic human motions appropriate to the current user activity.