Multi-Sensor Multi-Model Data Fusion for Biomedical Sensors
Biomedical sensors play a crucial role in monitoring and diagnosing various health conditions. However, the accuracy and reliability of these sensors can be enhanced by integrating multiple sensor modalities and employing advanced data fusion techniques. Data fusion, which is the act of merging data from diverse sources to produce a more comprehensive picture of what’s occurring, appears since there is a requirement to expand above individual observations and adopt a holistic approach to monitoring. The utilization of data fusion could improve accuracy, reliability, and overall performance.
Objectives: Wearable sensors will become more compact, more effective, and more useful as technology develops, allowing them to gather many health parameters that are not now conceivable. As a result, fusion will become increasingly crucial in merging the results of wearable biosensors. The primary objective of this research is to explore various data fusion techniques suitable for multi-sensor multi-model integration. Moreover, a framework for data fusion will be developed and the performance of the proposed framework will be evaluated through experimental studies. The main outcome of this research is to enhance the accuracy. The integration of multiple sensor modalities through data fusion will enhance accuracy by reducing measurement errors and compensating for limitations inherent in individual sensors. By combining information from multiple sensors, the proposed framework will improve the reliability of biomedical sensor measurements.