P-02 A Three-Dimensional Convolutional Neural Network for ECL Sensor Analysis
Department
Computing
Abstract
Sensor technology has the potential to revolutionize fields ranging from biofuel manufacturing to Healthcare. One major innovation in the sensor field is Electrochemiluminescent (ECL) sensors, which have low background noise, allowing for ultra-sensitivity. ECL sensors are also cost-effective as they require less instrumentation for voltage delivery and provide measurements in a matter of seconds. Traditionally, calibration curves with a predetermined feature are used for some sensors to infer the concentration based on the reading. However, this method leads to variations between sensors that would require recalibration. This project seeks to use Machine Learning to interpret the sensor data, allowing generalization across sensor differences.
Location
Buller Hall, Student Lounge
Start Date
3-11-2022 1:30 PM
End Date
3-11-2022 3:30 PM
P-02 A Three-Dimensional Convolutional Neural Network for ECL Sensor Analysis
Buller Hall, Student Lounge
Sensor technology has the potential to revolutionize fields ranging from biofuel manufacturing to Healthcare. One major innovation in the sensor field is Electrochemiluminescent (ECL) sensors, which have low background noise, allowing for ultra-sensitivity. ECL sensors are also cost-effective as they require less instrumentation for voltage delivery and provide measurements in a matter of seconds. Traditionally, calibration curves with a predetermined feature are used for some sensors to infer the concentration based on the reading. However, this method leads to variations between sensors that would require recalibration. This project seeks to use Machine Learning to interpret the sensor data, allowing generalization across sensor differences.
Acknowledgments
Advisors: Rodney Summerscales, Computing and Hyun Kwon, Engineering