SmartSPR sensor: Machine learning approaches to create intelligent surface plasmon based sensors

Abstract Surface plasmon resonance (SPR) based sensors allow to evaluate liquid and gases solutions from real-time measurements of molecular interactions. The reliability of the response generated by a SPR sensor must be guaranteed, especially in substance detection, diagnoses and others routine application, since poorly handled samples, instrumentation noise features or even molecular tampering manipulations can lead to wrong interpretations. This work investigates the use of different machine learning techniques to deal with such issues, and aim to improve and attest the quality of the real-time SPR responses so-called sensorgrams. A new strategy to describe a SPR-sensorgram is show. The results of the proposed approach of using machine learning allows to create the intelligent SPR-sensor which is able to classify sensorgramas and identify the substances presents in it. Also made it possible to order and analyze interest areas of a sensorgrams, standardizing data and supporting eventual official audit. With those embedded intelligence features, the new generation of SPR-intelligent biosensors are qualify to perform automated testing. A properly protocol for Leishmaniasis diagnosis with SPR was used to verify these new feature.