Applying Movement Constraints to BLE RSSI-Based Indoor Positioning for Extracting Valid Semantic Trajectories.

Area of Science:

• Computer Science
• Electrical Engineering
• Ubiquitous Computing

Background:

• Indoor positioning systems often rely on Received Signal Strength Indicator (RSSI) for trajectory-based services like user analytics.
• Obstacles in indoor environments frequently disturb RSSI signals, leading to inaccurate positioning data.
• Existing techniques can generate invalid trajectories with improbable consecutive positions, limiting practical applications.

Purpose of the Study:

• To enhance indoor positioning techniques by incorporating movement constraints.
• To prevent the extraction of invalid semantic indoor trajectories from disturbed RSSI data.
• To develop a method that can be extended to various indoor positioning techniques.

Main Methods:

• Implemented movement constraints on Bluetooth Low Energy (BLE) RSSI data.
• Ensured that predicted semantic positions remain logically close to previous positions.
• Applied the enhanced method to real-world BLE RSSI datasets across diverse indoor scenarios.

Main Results:

• The proposed approach successfully prevented invalid semantic indoor trajectories.
• Experimental results demonstrated the effectiveness of movement constraints in improving trajectory accuracy.
• The method proved robust across various indoor environment configurations.

Conclusions:

• Movement constraints are effective in refining indoor positioning accuracy using BLE RSSI data.
• The developed technique enhances the reliability of trajectory-based services in indoor environments.
• This approach offers a versatile extension for existing indoor positioning systems.