Abstract
Birth-cry, birth-weight, mother’s distress during pregnancy , baby’s health condition soon after birth, are some symptoms that might have some relationship with disability in a child. Influence factors are determined and multiple linear regression and backpropagation artificial neural network (ANN) are applied for modeling the occurrence of disability in a child. Results of multiple regression show that the factors considered have significant effects on the occurrence of disability. Also, the largest beta value (regression coefficient) corresponds to the birth-cry factor of a newborn. It implies the strongest and unique contribution of this variable to explain the dependent variable, which in this case is the proportion of disabled children. An ANN in feedforward form is also configured to perform identical regression for the purpose. Experimental results show that the ANN is a suitable technique for the study of such cases.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Standard coefficients are used to compare the different variables. These values for each of the different variables have been converted to the same scale. Unstandardized coefficient values are used in construction of regression equation. Tolerance is calculated by 1-R2 for each variable. A very lower tolerance value (near 0) indicates the possibility of multicollinearity.
References
Haykin S (2006) Neural networks, 2nd edn. Dorling Kindersley, India
Moradzadehfard M, Motlagh PA, Fathi MR (2011) Comparing neural network and multiple regression models to estimate dividend payout ratio. Mid East J Secur. Resolut 10(3):302–309 (IDOSI Publications)
Nguyen N, Cripps A (2001) Predicting housing value: a comparison of multiple regression analysis and artificial neural networks. JRER 22(3):313–336
Kim JY, Cho BH, Im SM, Jeon MJ, Kim IY, Kim SI (2005) Comparative study on artificial neural network with multiple regressions for continuous estimation of blood pressure. In: Proceedings IEEE 27th annual conference engineering in medicine and biology. Shanghai, China, pp 1–4
Pugh, WM, Ryman DH (1992) A comparison of multiple regression and a neural network for predicting a medical diagnosis. In: Interim report, Jul–Sep 91, Naval Health Research Center, San Diego, CA
Subramanian N, Yajnik A, Murthy RSR (2004) Artificial neural network as an alternative to multiple regression analysis in optimizing formulation parameters of cytarabine liposomes. AAPS PharmSciTech 5(1). http://www.aapspharmscitech.org
Pao HT (2008) A comparison of neural network and multiple regression analysis in modeling capital structure. Expert Syst Appl Elsevier 35:720–727
Chi TH, Wang YM (2011) Using multiple regression and artificial neural network approach for modeling airport visibility. In: Proceedings of international conference on agriculture and biosystems engineering. Adv Biomed Eng 1–2:428–431
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer India
About this chapter
Cite this chapter
Kalita, J., Sarma, K.K., Sarmah, P. (2015). Role of Baby’s Birth Symptoms and Mother’s Pregnancy Conditions on Children’s Disability Determined Using Multiple Regression and ANN. In: Sarma, K., Sarma, M., Sarma, M. (eds) Recent Trends in Intelligent and Emerging Systems. Signals and Communication Technology. Springer, New Delhi. https://doi.org/10.1007/978-81-322-2407-5_6
Download citation
DOI: https://doi.org/10.1007/978-81-322-2407-5_6
Published:
Publisher Name: Springer, New Delhi
Print ISBN: 978-81-322-2406-8
Online ISBN: 978-81-322-2407-5
eBook Packages: EngineeringEngineering (R0)