Modelling of Shre Drag Tilt Velocimeter (DTV) with Curvilinear, Gompertz and Artificial Neural Network Method


  • I.A. M Muharram Department of Control and Mechatronics Engineering, Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia.
  • Z.H. Ismail Centre of Artificial Intelligence and Robotic, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, Kuala Lumpur, Malaysia.


Drag Tilt, Modelling, Velocimeter


Different method of modelling presented in this paper on Shre Drag Tilt Velocimeter non-linear data. The idea of different non-linear modelling method is to know which makes more possible to describe more accurate on interacting effects between velocities and tilt angle when compared among modellers. The models, which were used are static analytic approximation model, curvilinear bivariate regression model, Gompertz the classical growth model and Artificial Neural Network (ANN) model. Accuracy of the models was determined by mean square error (MSE), mean absolute deviation (MAD), bias and R Square. The datasets gathered from an experiment of Shre DTV at flume were divided into training data and testing data for the purpose of developing and validating all type of models. The difference between the model and the observed value become the forecasting error measurements. For the training data, the lowest MSE, RMSE and better R Square were noted for the Gompertz model. But ANN generalized better on testing data by obtaining lowest MSE, RMSE and higher R Square among others. ANN generalization result is 88.60%, Gompertz is 54.89%, curvilinear is 69.28% and static analytic is -1.29%. Lower bias was also for the neural network test data. As demonstrated by the bias values, only curvilinear model presenting overestimation model while other models produce little or no overestimation of the observed tilt response. Interpretations of the parameters estimation on Gompertz model have been attempted previously. However, focusing on the ability of Shre DTV to predict responses may be more practical than the relevance of parameter estimates.


R. Marchant, S. Member, T. Stevens, S. Choukroun, G. Coombes, M. Santarossa, J. Whinney, and P. Ridd, “A Buoyant Tethered Sphere for Marine Current Estimation,” IEEE J. Ocean. Eng., vol. 39, no. 1, pp. 2–9, 2014.

JKR Malaysia and UNIMAS, “Energy Mapping Study at Schools along Sungai Balleh, Kapit, Sarawak.,” 2010.

P. E. Wellstead, Introduction to Physical System Modelling, 1979th ed. Kent, Great Britain: Control Systems Principles, (, 1979.

M. M. Rosli, E. Tempero, and A. Luxton-reilly, “Can We Trust Our Results ? A Mapping Study on Data Quality,” in 20th Asia-Pacific Software Engineering Conference, 2013, pp. 116–23.

Y. I. Shtern, Y. S. Kozhevnikov, V. M. Rykov, and R. E. Mironov, “Mathematical Models and Hardware & Software for Highly Accurate Electronic Temperature Meters,” Russ. Microelectron., vol. Volume 42, no. 7, pp. 384–388, 2013.

H. Cheng, Y. Zhao, Z. Qian, and B. Li, “Research on Performance Analyzing and Modeling of Quartzose Flexible Accelerometer,” in The Ninth International Conference on Electronic Measurement & Instruments (ICEMI 2009), 2009, pp. 412–415.

S. L. B. W.B. Roush, W.A. Dozier III, “Comparison of gompertz and neural network models of broiler chickens,” Poult. Sci., vol. 85, pp. 794–797, 2006.

M. Xiao, P. Huang, P. Lin, and S. Yan, “Broiler Growth Performance Analysis :from Correlation Analysis , Multiple Linear Regression , to Neural Network,” no. 2007, pp. 25–28, 2010.

B. Kjerfve, “Calibration of estuarine current crosses,” Estuar. Coast. Shelf Sci., vol. 15, no. 5, pp. 553–559, 1982.

Z. H. Ismail and I. A. M. Muharram, “Design Consideration of Drag Tilt Velocimeter for River Flow Studies,” in The 3rd International Conference on Water Resources ICWR-2015, 2015, no. 2015, pp. 1–10.

Z. H. Ismail and I. A. M. Muharram, “Calibration of a Drag Tilt Current Velocimeter for an Open Channel Application,” J. Teknol. UTM, vol. 78, no. 6–13, pp. 89–94, 2016.

M. Azarkhail, “Model for Treatment of Incomplete Records in Preventive Maintenance,” in IEEE Conference Publication- Reliability and Maintainability Symposium (RAMS), 2013 Proceedings, 2013, pp. 1–7.

B. J. Baliga, “Analytical Modeling of IGBTs : Challenges and Solutions,” IEEE Trans. Electron Devices, vol. 60, no. 2, pp. 535–543, 2013.

R. G. L. Randall E. Schumacker, A Beginner’s Guide to Structural Equation Modeling, 2nd Editio. Lawrence Erlbaum Associates, Inc, 2005.

C. P. Winsor, “The Gompertz Curve as a Growth Curve.,” Proc Natl Acad Sci U S A, vol. 18, no. 1, pp. 1–8, 1932.

M. Pitchaimani and T. Eakin, “Unique estimation of Gompertz parameters with mortality deceleration rate,” vol. 47, pp. 104–114, 2008.

C. F. Ã. Lo, “Stochastic Gompertz Model of Tumour Cell Growth,” J. Theor. Biol., vol. 248, pp. 317–321, 2007.

X. Li and E. Wang, “Prediction of Electric Vehicle Ownership Based on Gompertz Model *,” in Proceeding of the IEEE International Conference on Information and Automation, 2014, no. July, pp. 87–91.

S. Haykin, Neural Networks: A Comprehensive Foundation. MacMillan Publishing Company, 1994.

Q. Dai, S. Xu, and X. Li, “Parallel Process Neural Networks and its Application in the Predication of Sunspot Number Series,” in 2009 Fifth International Conference on Natural Computation, 2009, pp. 237–241.

L. Yu, S. Wang, and K. K. Lai, “An Integrated Data Preparation Scheme for Neural Network Data Analysis,” IEEE Trans. Knowl. Data Eng., vol. 18, no. 2, pp. 1–14, 2006.

N. Clarence and W. Tan, An Artificial Neural Networks Primer with Financial Applications Examples in Financial Distress Predictions and Foreign Exchange Hybrid Trading System ’ by. School of Information Technology, Bond University, Gold Coast, QLD 4229, Australia, 1999.

Oberstone, Management Science – Concepts, Insights, and Applications. West Publication Co. New York, 1990.

J. R. Taylor, An Introduction to Error Analysis-The Study of Uncertainties in Physical Measurement. University Science Books, 1982.




How to Cite

M Muharram, I., & Ismail, Z. (2016). Modelling of Shre Drag Tilt Velocimeter (DTV) with Curvilinear, Gompertz and Artificial Neural Network Method. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 8(11), 1–6. Retrieved from