PENENTUAN KUALITAS AIR MINUM KEMASAN MENGGUNAKAN JARINGAN SYARAF TIRUAN (STUDI KASUS : AIR KEMASAN GALON �QANNAT� YOGYAKARTA)

• Main Authors: , Erfanti Fatkhiyah, , Prof. Drs. Subanar, Ph.D.
• Format: Theses and Dissertations NonPeerReviewed
• Published: [Yogyakarta] : Universitas Gadjah Mada 2011
• Subjects: ETD
• Online Access: https://repository.ugm.ac.id/89419/; http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=52046
• Institution: Universitas Gadjah Mada

Artificial neural network (ANN) is a clone of the human brain way of thinking. Neural network is implemented by using a computer program that can solve a number of calculations during the learning process. One of the kinds of neural networks is a single-layer perceptron feedfoward. The quality of bottled water is determined by the elements contained in the water with a predetermined standard. By using a single-layer perceptron neural network feedfoward, quality drinking water to be packaged can be determined, so that bottled water is consumable. This research tries to build an artificial neural network system which can identify that bottled water is not feasible or appropriate to be packed with the input data elements contained in water. Every element of water is then normalized through the process of training and testing. The process of training and testing conducted by the various values α and θ. All of the training and testing process, produce average of network performance with 87,269% accuracy, so that a single-layer perceptron feedfoward method can be used to determine the quality of bottled water that suitable with drinking water quality standard.