关键词：光机电；传感器；硝酸；温度检测
摘 要：In this paper, the output parameters of the planar electromagnetic sensor have observed with different kind of water samples at different concentrations. The output parameters have been derived and tested to be incorporated with independent component analysis (ICA) and as inputs for an analysis model. The analysis model targeted to estimate the amount of nitrate contamination in water samples with the assistance of ICA based on FastICA fixed point algorithm under the contrast functions of pow3 and tanh. Nitrates sample in the form of ammonium nitrates (NH_4NO_3), each of different concentration between 5 mg and 20 mg dissolved in 1 litre of deionized water (mili-q) was used as one of the main references. A model based on independent component analysis was developed to estimate nitrate contamination in natural water source. The model was tested with two sets of mixed NH_4NO_3 and (NH_4)_2HPO_4 water samples based on Manawatu river water. From the results, the model can acceptably detect the presence of nitrate in Manawatu River and capable of distinguishing the concentration level in the presence of other type of contamination. Furthermore, the effect of temperature change was also observed in this study. The system and approach presented in this paper has the potential to be used as a useful tool for water sources monitoring.