Improved Algorithm Enhances Precision of Pressure Sensors for Wild Bird Tracking
Oct 31, 2023
Researchers from the State Key Laboratory of Transducer Technology with the Aerospace Information Research Institute (AIR), Chinese Academy of Sciences (CAS) have proposed an improved algorithm called Dynamic Quantum Particle Swarm Optimization (DQPSO) to improve the accuracy and reliability of pressure sensors used in tracking and monitoring wild migratory birds. This algorithm optimizes the performance of a Radial Basis Function (RBF) neural network, specifically designed for temperature compensation.
The study was published in Electronics on Oct.22.
The DQPSO algorithm takes a holistic approach to address the challenge of sensor accuracy in the face of fluctuating temperatures. It incorporates a temperature-pressure fitting model, which includes critical parameters such as the rate of temperature change and gradient reference terms. This model ensures that the pressure sensors can effectively adapt to varying environmental conditions, a crucial requirement when monitoring the movements of wild migratory birds.
One of the distinguishing features of the DQPSO algorithm is its innovative loss function, which considers both fitting accuracy and complexity. This approach significantly enhances the robustness of pressure sensors, making them capable of delivering reliable data in the presence of complex temperature variations.
Calibration experiments conducted to validate the algorithm's effectiveness demonstrated remarkable results. Prior to implementation, the pressure sensors exhibited an average absolute error of 145.3 Pascals during dynamic temperature changes, as determined by commonly used commercial sensor algorithms. However, with the DQPSO algorithm in place, this error was drastically reduced to just 20.2 Pascals. This impressive reduction represents an astonishing 86% improvement over the conventional polynomial compensation method, indicating the significant leap in accuracy and precision achieved by the DQPSO approach.
Furthermore, the DQPSO algorithm outperformed traditional feedforward network models, providing an excellent solution for the challenging task of temperature compensation in pressure sensors.
The algorithm has been deployed and verified in an embedded environment, ensuring low-power, high-precision, real-time pressure compensation during the tracking and monitoring of wild migratory birds. This development holds immense promise for researchers and conservationists seeking to gain deeper insights into the behaviors and movements of these avian travelers.
With its ability to substantially reduce errors in pressure sensor readings under dynamic temperature conditions, this DQPSO algorithm opens new doors for understanding and safeguarding the journeys of wild migratory birds.