Artificial neural network implementation in single low-cost chip for the detection of insecticides by modeling of screen-printed enzymatic sensors response

This work presents a hardware implementation of artificial neural networks (ANNs) using a dsPIC® microcontroller to resolve mixtures of pesticides measured by amperometric acetylcholinesterase (AChE) biosensors. The response of three biosensors with different concentrations of Chlorpyrifos Oxon (CPO) and Chlorfenvinfos (CFV) was modeled by two ANNs, which were implemented on the dsPIC®. The performance of the ANNs was good, the prediction ability was better than 0.986 when the obtained values were compared with those expected for a set of eight external test samples, which were not used for training. This implementation is proposed to develop low-cost analytical chemical specialized tools.

Research highlights▶ Detection of Chlorpyrifos Oxon (CPO) and Chlorfenvinfos (CFV) insecticides. ▶ Acetylcholinesterase (AChE) biosensors with high sensitivity. ▶ Artificial neural networks implementations are developed for specific applications.▶ dsPIC microcontrollers are low-cost chips of general purposes.