Gas Detection and Classification Using Neural Network Based Gas Sensors

Alcoholic beverages, apart from being haram, also cause loss of consciousness. The influence alcohol while driving is very dangerous and can result in an accident. For this reason, it necessary to detect the content beverages so that their halal status known avoid dangers consuming alcohol. This research aroma using MQ-3 gas sensor, which consists sensor general with Artificial Neuron Network (ANN), such as number neurons, layers, epoch. Most learning schemes require testing optimize model structure. experiment, ANN used a liquid classification grouping alcoholic non-alcoholic liquids. successfully reads vapor levels 30%, 50%, 70%, other water-based An artificial neural network 2 hidden 10 1000 iterations sigmoid activation function approach regression score 1.1545 sq error 0.5781.