Implementation Analog Neural Network for Electronic Nose using Field Programable Analog Arrays (FPAA)

Artificial Neural Network (ANN) is computation method based on mathematic model which have neuron structure and have process like human brain. Neural Network (NN) consists of simple element that works in parallel. NN decided by connection between elements which will be adjusted or trained so some input be able to appointed to some output. NN computation algorithm usually use computer to finish it. Computer has good ability in computation, but have disadvantage in flexibility because of size and need large power. Field Programmable Analogue Array (FPAA) gives opportunity to design and implemented NN by analogue. First benefit using NN analogue is the input sensor can directly process by FPAA without need to convert into digital. Therefore, error because of conversion can be minimize and increase the computation. Second gain is FPAA has small size and low consumption of power. Furthermore, FPAA can suitable in implementation electronic nose robot.