Method of Multi-sensor Fusion

Citation

Rigelsford, J. (2002), "Method of Multi-sensor Fusion", Sensor Review, Vol. 22 No. 4. https://doi.org/10.1108/sr.2002.08722dad.012

Method of Multi-sensor Fusion

Method of Multi-sensor Fusion

Applicant: SpaceLabs Medical, Inc., USAPatent number: US5,626,140Publication date: 6 May 1997Title: System and method of multi-sensor fusion of physiological measurementsKeywords: Sensor fusion, Patents

This patent presents a system and method for sensor fusion using multiple physiological sensors. The system comprises a plurality of sensors which are coupled to the subject, with each of the sensors providing a physiological signal capable of producing a heart rate measurement.

A statistical model affecting the fusion of the sensor measurements is used by a Kalman filter circuit to produce a parameter estimate for each possible combination of the sensor measurements. The heart rate measurements of each combination can be considered to be acceptable or unacceptable. The Kalman filter utilises probability density functions, a prediction error model, and past estimates of the physiological parameter to produce the Kalman filter outputs.

A confidence calculator uses Bayesian statistical analysis to determine a confidence level for each of the Kalman filter outputs and selects a fused estimate for the physiological parameter based on the confidence level. The fused estimate and the confidence level are used to dynamically update the nominal error contamination model and prediction error model to create an adaptive measurement system. The confidence calculator also compensates for error contamination in any or all of the sensor measurements. The system assumes a worst case analysis of the sensor combination and therefore produces a robust model which is able to adapt to varying errors.