Optofluidic microdevice for algae classification: a comparison of results from discriminant analysis and neural network pattern recognition
The early detection of changes in the level and composition of algae is essential for tracking water quality and environmental changes. Current approaches require the collection of a specimen which is later analyzed in a laboratory: this slow and expensive approach prevents the rapid identification of changes in algae species dynamics and hinders a quick response to potential outbreaks. In a recent work, we presented a microfluidic chip for classifying and quantifying algae species in water. Here, we study the device performance and specifically compare the difference in results obtained by using a discriminant analysis classification approach and a neural network pattern recognition approach. Using both of these methods, we demonstrate the classification of algae by species, of microspheres by size, and of a detritus/cyanobacteria mixture by type. In each of the demonstrations here, the neural network outperforms the discriminant analysis method.