Artificial Neural Network and Savitzky Golay Derivative in Predicting Blood Hemoglobin Using Near-Infrared Spectrum

  • Mohd Nazrul Effendy Mohd Idrus Batu Pahat Community College
  • Kim Seng Chia Universiti Tun Hussein Onn Malaysia http://orcid.org/0000-0003-0854-8954
  • Hiew Moi Sim Southern University College
  • Hasan Ali Gamal Al-kaf Universiti Tun Hussein Onn Malaysia
Keywords: Blood hemoglobin prediction, Savitzky Golay pre-processing, Artificial neural network, Near-infrared

Abstract

Monitoring blood hemoglobin level is essential to diagnose anaemia disease. This study aims to evaluate the capability of an artificial neural network (ANN) and Savitzky Golay (SG) pre-processing in predicting the blood hemoglobin level based on the near-infrared spectrum. The effects of the hidden neuron number and different SG pre-processing strategies were examined and discussed. ANN coupled with first order SG derivative and five hidden neurons achieved better prediction performance with root mean square error of prediction of 0.3517 g/dL and Rp2 of 0.9849 compared to the previous studies. Results depict that ANN that coupled with first order SG derivative could improve near-infrared spectroscopic analysis in predicting blood hemoglobin level, and the proposed nonlinear model outperforms linear models without variable selections. This finding suggests that the modelling strategy is promising in establishing a better relationship between the blood hemoglobin and near-infrared spectral data.

Author Biography

Kim Seng Chia, Universiti Tun Hussein Onn Malaysia
Kim Seng Chia completed his Bachelor Degree in Electrical Engineering (First Class Honours) at Universiti Teknologi Malaysia in 2010. He received his doctorate at Universiti Teknologi Malaysia in 2014. His PhD research focused on developing predictive models that are capable of predicting the soluble solids content of a pineapple non-destructively by means of near infrared spectroscopy. He served Southern University College, Malaysia from Mac 2014 to August 2014 as an assistant professor. He is currently serving Universiti Tun Hussein Onn Malaysia in Faculty of Electronic and Electrical Engineering as an academic staff.
Published
2018-12-31
How to Cite
Mohd Idrus, M. N. E., Chia, K. S., Sim, H. M., & Gamal Al-kaf, H. A. (2018). Artificial Neural Network and Savitzky Golay Derivative in Predicting Blood Hemoglobin Using Near-Infrared Spectrum. International Journal of Integrated Engineering, 10(8). Retrieved from https://publisher.uthm.edu.my/ojs/index.php/ijie/article/view/2302
Section
Articles