Highly sensitive lab-on-chip with deep learning AI for detection of bacteria in water

Artificial Intelligence (AI) has provided a new insight on how to make better predictions in water quality. AI uses convolutional neural networks (CNN) modeled after the human brain. In this work we have started implementing deep learning techniques to predict level of bacterial contaminants in water. A look-up table is used to classify the level of sensing parameters based on signature of the bacteria. AI will be very helpful for accurate prediction based on signature as identified by the sensor. We have simulated an AI-based lab-on-chip application platform that can detect the contamination using the output from Photonic Crystal based optical biosensor. The presence of bacteria in water changes the output spectral behavior. By training with the different samples, design of input layer was optimized for bacteria in water. Optical biosensors are generally light weight, small and portable and less noisy system and works without electric power. The AI technique helped to distinctly predict the presence of Escherichia coli bacteria. Research concludes with the probability of accuracy of 95% detection based on output spectrum and identified training data.