Sains Malaysia 34(1): 81-85 (2005)

Penggunaan Jaringan Neural Tiruan bagi menentukan Kekeruhan

air berdasarkan Pencaman Corak Spektrum Pantulan

(The use of Artificial Neural Network for Determination of Water Turbidity

based on Pattern Recognition of the Reflectance Spectrum)

Mohd. Azwani Shah Mat Lazim, Musa Ahmad, Zuriati Zakaria

Pusal Pengajian Sains Kimia & Teknologi Makanan

Fakulti Sains dan Teknologi

Universiti Kebangsaan Malaysia

43600 UKM Bangi. Selangor. D.E.

Mohd. Nasir Taib

Fakulti Kejuruteraan Elektrik

Universiti Teknologi MARA

40450 Shah Alam. Selangor. D.E. Malaysia

ABSTRAK

Jaringan neural tiruan (ANN) dengan lagoritma perambatan balik (BP) telah digunakan dalam kajian ini untuk menentukan kekeruhan air. Tiga panjang gelombang yang mewakili serapan bagi lapan sampel telah dipilih sebagai imput latihan. Hasil kajian menunjukkan bagi  jaringan terlatih dengan bilangan ulangan latihan 250,000 dan kadar pembelajaran 0.001 telah memberikan nilai SSE yang terendah iaitu 0.04. Dalam kajian ini jaringan ANN didapati boleh menentu dan meramalkan nilai kekeruhan sample air berdasarkan corak serapan pantulan. Arkitektur yang sesuai bagi kajian ini adalah 3:25:1. Purata ralat ramalan adalah 0.02.

Kata kunci: Jaringan neural tiruan algoritma perambatan balik, kekeruhan

ABSTRACT

Artificial neural network (ANN) was used in this study to determine water turbidity by using back propagation algorithm. Three wavelengths which represent reflectance intensity for eight standard samples were used as training input. The finding from the study shows that the trained network with number of epochs of 250,000 and learning rate of 0.001 gave the lowest sum of squared error (SSE) of 0.04. ANN was able to predict the turbidity of water based on the pattern recognition of the reflectance spectrum. The architecture of optimized ANN used in this study was 3:25:1. The average prediction error was 0.02.

Keywords: Artificial neural network, back propagation algorithm, turbidity

RUJUKAN/REFERENCES

Abdul Latif, A. Suzylawaty, I. & Subash, B. 2003. Water recycling from palm oil mill effluent using membrane technology. Desalination. 157: 87-95.

Bos, M. Bos, A. & Van de Linden, W.E. 1993. Data processing by neural networks in quatitative chemical analysis, Analyst, 118: 323-328.

Despagne, F. & Massart, D.L. 1998. Neural network in multivariate calibration. Analyst. 123: 157-163.

Dickinson, E. 1992.  An Introduction to Food Colloids. Oxford: Oxford University Press.

Dickinson, E. 1994. Colloidal aspects of beverages. Food Chemistry 51: 343-347.

Faiz Bukhari M.S. Musa A., Mohd. Nasir T. (2003). Oprimisation of the range of an optical fibre pH sensor using feed-forward ANN. Sensors Actuators B. 90: 175-181.

Farinato, R.S. & Rowell. R.L. 1983. Optical Properties of Emulsion. Encyclopedia of Emulsion. New York: Marcel Dekker.

Gasteiger. J & Zupan, 1. 1993. Neural networks in chemistry. Angew: Int. Ed. Eng. 32: 503-527.

March. J.G., Simonet. B.M. & Grases. F. 1999. Determination of phytic acid by catalytic f1uorimetric. Analyst. 124: 897-­900.

Mashudi, M.R. 2001. Forecasting water demand using back propagation networks in the operation of reservoirs in the Citarum Cascade, West Java, Indonesia. ASEAN Journal on Science and Tech. for Development. 18(2): 71-82.

Taib.M.N & Narayanaswamy. R. 1996. Multichannel calibration technique for optical fibre chemical sensor using ANN. Sens. Actuators. B. 365: 38-39:

Taib.M. N. & Nrayanaswamy. R. 1997. Multichannel calibration technique for optical fibre chemical sensor using artificial neural network Sens. Actuators. B. 38-39: 365.

Wasserman, P.D. 1989.  Neural Computing: Theory and Practise. New York: Van Nostrand Reinhold.