Indoor Outdoor Detection Model Selection for Mobile Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for indoor/outdoor detection in mobile devices are inaccurate and power-intensive, and fail to provide reliable high-performance applications due to insufficient data from cost-effective mobile devices, which are limited by light-based systems, magnetometer-based systems, and wireless-signal-strength-based systems.
Innovation Solution
A method and system that utilize a mobile device's sensors to obtain readings and contemporaneous local condition information, selecting and applying trained models to determine the likelihood of being indoors or outdoors, combining data from various sensors and external sources to improve accuracy and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sensor-based methods are used for indoor/outdoor detection, then the device can determine location state, but the accuracy is insufficient and power consumption is high
Solution Approach 1:
The system dynamically selects between multiple detection models (light-based, magnetometer-based, wireless-signal-strength-based) based on current environmental conditions and device state. This dynamic selection allows the system to use the most energy-efficient model appropriate for the current situation while maintaining detection accuracy.
Solution Approach 2:
The system changes operational parameters by switching between different detection algorithms and models based on contextual information. By adjusting which model is active based on environmental parameters (light availability, motion state, transition phase), the system optimizes both accuracy and power consumption.
2Ease of operation
If light-based systems are used for detection, then detection can be performed, but accuracy is limited to daytime, non-concealed device, and clear sky conditions
Solution Approach 1:
The system implements multiple detection models that can function under different environmental conditions. The light-based model operates during daytime, the magnetometer-based model operates during movement, and the wireless-signal-strength model operates during transitions. This multi-functionality ensures detection availability across all conditions while maintaining reliability through appropriate model selection.
Solution Approach 2:
The system dynamically switches between detection models based on environmental conditions. When light conditions are unsuitable (nighttime, cloudy), the system transitions to alternative models, maintaining both ease of operation and detection reliability across varying conditions.
3Ease of operation
If magnetometer-based systems are used for detection, then detection can be performed, but accuracy is limited to when user is moving
Solution Approach 1:
The system provides multiple detection models with different operational characteristics. The magnetometer-based model serves as one option that excels during movement, while other models cover stationary scenarios. This universality ensures the system can operate under various user states while maintaining accuracy through appropriate model selection.
4Ease of operation
If wireless-signal-strength-based systems are used for detection, then detection can be performed, but operation is limited to indoor/outdoor transitions
Solution Approach 1:
The system implements multiple detection models where the wireless-signal-strength-based model specifically handles transition scenarios, while other models handle stable indoor and outdoor scenarios. This multi-functionality ensures comprehensive coverage across all operational phases with appropriate model selection for each phase.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods, systems, computer-readable media, and apparatuses for determining indoor/outdoor state of a mobile device are presented. In some embodiments, a sensor reading is obtained from a sensor accessible by the mobile device. Contemporaneous information related to a local condition associated with an area where the mobile device is located is obtained. The sensor reading is provided as input to an indoor/outdoor detection model selected from a plurality of trained models, selected on the basis of the information related to the local condition. Based on the output of the model, the mobile device is classified as indoors or outdoors.