The Use of Artificial Neural Networks as a Component of a Cell-based Biosensor Device for the Detection of Pesticides

• Published in: Procedia engineering Vol. 47; pp. 989 - 992
• Main Authors: Ferentinos, K.P., Yialouris, C.P., Blouchos, P., Moschopoulou, G., Tsourou, V., Kintzios, S.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 2012
• Subjects: Artificial neural networks; Cell-based biosensor; Pesticides; Cell-based biosensor; Artificial neural networks; Pesticides
• ISSN: 1877-7058; 1877-7058
• DOI: 10.1016/j.proeng.2012.09.313

The present study describes an artificial neural network (ANN) system that uses a cell-based biosensor based on the Bioelectric Recognition Assay (BERA) methodology, for the detection and classification of pesticide residues in food commodities. The insecticidal compounds carbaryl and chlorpyrifos as well as the pyrethroid group were used as models for the training of the ANN. The biosensor was based on neuroblastoma N2a cells, which are targets of the pesticides due to the inhibition of the enzyme acetylcholine esterase by them. The response of the biosensor to different concentrations (samples) of either pesticide was recorded as a time-series of potentiometric measurements (in Volts). The feedforward methodology was used for the development of the ANN, which was trained with the backpropagation training algorithm. The results of the application of the developed system indicate that the novel classification methodology exhibits promising performance as a central component of a rapid, high throughput screening system for pesticide residues.