Sains Malaysiana 37(1): 51-57(2008)

Penggunaan Jaringan Neural Tiruan untuk Analisis Kuantitatif

Ion Al(III) Berasaskan Pengecaman Corak Spektrum Serapan

(Quantitative Analysis of Al(III) Ion Using Artificial Neural

Network Based on Pattern Recognition)

BabTan Ling Ling & Musa Ahmad

Pusat Pengajian Sains Kimia & Teknologi Makanan

Fakulti Sains & Teknologi, Universiti Kebangsaan Malaysia

43600 Bangi, Selangor D.E., Malaysia

Diserahkan: 15 Februari 2007 / Diterima : 16 April 2007 

ABSTRAK  

Analisis kuantitatif telah dilakukan untuk menentukan kepekatan ion aluminium (Al³⁺) dalam larutan dengan menggunakan kaedah spektrofotometri UL-Nampak dan jaringan neural tiruan (ANN). Reagen morin telah digunakan untuk membentuk kompleks morin-Al(III). Pencirian terhadap reagen dalam larutan termasuk analisis kestabilan foto reagen, kesan pH, kesan kepekatan, masa rangsangan, julat kepekatan dinamik dan kebolehulangan telah dilakukan. Penggunaan ANN telah berupaya memanjangkan julat kepekatan dinamik ion Al³⁺ sehingga julat kepekatan 1-13 ppm. 

Kata kunci: Aluminium; jaringan neural tiruan; morin 

ABSTRACT 

A quantitative analysis has been conducted to determine the concentrations of aluminium ion (Al³⁺) in solution by using UV-Visible spectrophotometry method and artificial neural network (ANN). Morin reagent was used to form morin-Al(III) complex. The characterisations of reagent in solution such as photostability, pH effect, reagent concentration, response time, dynamic ranges and repeatability were conducted. The use of ANN was able to extend the dynamic concentration range of Al³⁺ ion to 1 – 13 ppm.

Keywords: Aluminium; artificial neural network; morin

RUJUKAN/REFERENCES

Bhagat, P. 1990. An introduction to neural networks. Chem, Eng. Prog. 86(8): 55.

Bos, A., Bos, M. & van der Linder, W.E. 1992. Artificial neural networks as a tool for soft-modelling in quantitative analytical chemistry : the prediction of the water content of cheese. Anal. Chem. Acta. 256: 133-144

Cirovic, D.A. 1997. Feed-forward artificial neural networks: applications to spectroscopy. Trends in Analytical Chemistry. 16(3): 148-155.

Faiz Bukhari Mohd Suah, Musa Ahmad & Mohd Nasir Taib. 2003. Applications of artificial neural network on signal processing of optical fibre pH sensor based on bromophenol blue doped with sol-gel film. Sensors and Actuators B. 90:182-188.

Hagan, M.T., Demuth, H.B. & Beale, M. 1996. Neural network design. Boston : PWS Publishing Company.

Handbook of Chemistry and Physics. 1972. Ed. Ke-53. USA: CRC Press.

Hanson, N.W. 1973. Official, standardized and recommended methods of analysis. Ed. ke-2. London: The Society For Analytical Chemistry.

Onishi, H. 1986. Photometric determination of traces of metals. Ed. Ke-4. New York: John Wiley & Sons.

Pinta, M. 1966. Detection and determination of trace elements. Jerusalem: Israel Program for Scientific Translations.

Sandell, E.B. 1959. Colorimetric determination of traces of metals. Ed. ke-3. New York: Interscience Publishers, Inc.

Sandell, E.B. & Onishi, H. 1978. Photometric determination of traces of metals. Ed. Ke-4. New York: John Wiley & Sons, Inc.

Senthilkumar, M. & Selvakumar, N. 2005. Achieving expected depth of shade in reactive dye application using artificial neural network technique. Dyes and Pigments. 68:89-94.

Victor, A.V. & Alfred, H. 1997. An aluminium-morin fluorescence assay for the visualization and determination of aluminium in cultured cells of Nicotiana tabacum L. cv. BY-2. Ed. ke-12. USA: Plant Science. 122 : 35-42.

Welcher, F.J. 1963. Standard methods of chemical analysis. Ed. ke-6. New York: Van Norstrand Reinhold Company.

Wikipedia. 2005. Toxic heavy metals sources and effect. (1-800-800-1285) http:/en.wikipedia.org/wiki/Heavy_metals (31 July 2005).