Efficient Dataset Creation for MEMS-Based Magnetic Sensor Systems in Intelligent Transportation Applications.

Area of Science:

• Engineering
• Computer Science
• Transportation Technology

Background:

• Intelligent transportation systems rely on accurate data from Micro-Electro-Mechanical Systems (MEMS) sensors.
• Developing high-quality datasets for MEMS sensor applications is time-consuming and labor-intensive.
• Optimizing data annotation is crucial for enhancing the performance and reliability of MEMS-based applications.

Purpose of the Study:

• To introduce and evaluate an advanced annotation tool for MEMS sensor datasets in intelligent transportation.
• To demonstrate the tool's capability in improving the efficiency and accuracy of dataset creation.
• To showcase the practical application of the tool using magnetometer data for traffic flow monitoring.

Main Methods:

• Development of a specialized annotation tool for MEMS sensor data.
• Integration of the tool into existing data processing workflows.
• Testing the tool with a magnetometer-based sensor system for traffic flow monitoring.

Main Results:

• Significant reduction in annotation time per event compared to manual labeling.
• Increased throughput of events processed without compromising label consistency.
• Demonstrated practical effectiveness and real-world applicability in traffic monitoring scenarios.

Conclusions:

• The advanced annotation tool offers a substantial improvement for MEMS sensor dataset development.
• The tool enhances efficiency and accuracy, benefiting engineers and researchers in sensor technology.
• This innovation supports the advancement of MEMS applications in intelligent transportation systems.