Hierarchical Sensor Context Detection for Mobile Energy Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting a mobile device's context, such as being in a moving vehicle, face challenges including high energy consumption, delayed detection, and frequent false classifications, often requiring multiple sensors and user feedback for adaptation, which can lead to inefficient battery usage and unsatisfactory classification results.
Innovation Solution
A method involving a context detection module that hierarchically organizes sensors into groups, using a classifier to determine context based on sensor readings, where sensors are powered on minimally and adaptively configured based on higher-level classification results, reducing energy consumption and improving detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensors are used to detect context, then classification accuracy is improved, but energy consumption increases
Solution Approach 1:
The patent segments sensors into hierarchical groups (first group with lower-power sensors like accelerometers, second group with higher-power sensors like GPS receivers). The system activates only the necessary group based on detection needs, avoiding continuous operation of all sensors. This segmentation allows the device to achieve accurate context detection while minimizing energy consumption by not running all sensors simultaneously.
Solution Approach 2:
The patent implements dynamic sensor activation where the system adapts which sensors are active based on current context detection requirements. The context detection module dynamically switches between using only first-group sensors, only second-group sensors, or both groups together. This dynamic approach optimizes the balance between classification accuracy and energy consumption in real-time.
2Loss of time
If sensors are activated frequently to improve detection speed, then detection delay is reduced, but energy consumption increases
Solution Approach 1:
The patent implements periodic activation of sensors rather than continuous operation. The context detection module periodically checks context using first-group sensors, and only activates second-group sensors when needed based on detected patterns. This periodic action reduces energy consumption while maintaining acceptable detection response times by strategically timing sensor activation.
Solution Approach 2:
The patent uses preliminary detection with first-group sensors to identify situations that warrant activation of second-group sensors. By performing preliminary context assessment with low-power sensors, the system can anticipate when higher-power sensors will be needed, reducing overall detection delay while avoiding unnecessary activation of energy-intensive sensors.
3Use of energy by moving object
If hierarchical sensor groups are used with adaptive configuration, then energy consumption is reduced, but device complexity increases
Solution Approach 1:
The patent implements self-service through automatic context-based sensor activation. The context detection module autonomously determines which sensor groups to activate based on detected context patterns, without requiring manual user configuration. The system adapts its sensor usage automatically, reducing the perceived complexity for users while maintaining sophisticated sensor management internally.
Solution Approach 2:
The patent uses feedback mechanisms where the context detection module continuously monitors sensor data and adjusts sensor activation patterns based on detected context. The system learns from contextual patterns and adapts which sensors to activate, creating a feedback loop that optimizes energy consumption. This automated feedback-based adaptation manages device complexity by embedding the complexity in the control logic rather than requiring complex hardware architecture.
Data Source
AI summary
A method for detecting a context of a mobile device equipped with sensors and a context detection module in which the sensors are assigned to at least two groups, each of which comprises at least one sensor, and each group is allocated a group classifier adapted to detect, in a form of a classification result, currently identified, by means of a given classifier, context of the device based on indications of the sensors belonging to the given group, characterized in that with a use of the context detection module, whereas the groups of sensors are ordered hierarchically, and the device context is detected by reading a classification result indicated by the classifier of the currently active group, wherein in case of detection of an identified context in the active group, switching on power supply of the sensors and activating classification in a group with a level higher by one level and reading the context indicated by said group's classifier, wherein based on the results of the classification indicated by the higher groups' classifiers, executing adaptation of the configuration of lower groups' classifiers.