Browsing by Author "Shafie, A. A."
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Application of modeling techniques to diabetes diagnosis(IEEE, 2010-11-30) Aibinu, A. M.; Salami, Momoh-Jimoh E.; Shafie, A. A.In recent times, the introduction of complex-valued neural networks (CVNN) has widened the scope and applications of real-valued neural network (RVNN) and parametric modeling techniques. In this paper, new expert systems for automatic diagnosis and classification of diabetes using CVNN and RVNN based parametric modeling approaches have been suggested. Application of complex data normalization technique converts the real valued input data to complex valued data (CVD) by the process of phase encoding over unity magnitude. CVNN learn the relationship between the input and output phase encoded data during training and the coefficients of Complex-valued autoregressive (CAR) model can be extracted from the complex-valued weights and coefficients of the trained network. Classification of the obtained CAR or RVAR model coefficients results in required distinct classes for diagnosis purpose. Similar operations can be performed for real-valued autoregressive technique except for CVD normalization. The effect of data normalization techniques, activation functions, learning rate, number of neurons in the hidden layer and the number of epoch using the suggested techniques on PIMA INDIA diabetes dataset have been evaluated in this paper. Results obtained compares favorably with earlier reported results.Item Development of a new method of crack modeling and prediction algorithm(Proceedings of the 3rd International Conference on Mechatronics (ICOM’08), 2008) Aibinu, M.; Shafie, A. A.; Salami, Momoh-Jimoh E.; Lawal, W. A.In this report, the well known parametric method of signals and systems representation is extended to modeling and prediction of cracks on building and road surfaces. Also, a new algorithm based on complex value autoregressive neural network with split linear activation function for the determination of Complex-Value Autoregressive Moving average (CARMA) coefficients is also proposed in this report. Furthermore, mathematical derivation and detail analysis of the proposed CARMA based Complex-Value Neural Network (CVNN) algorithm is also discussed in this work.Item Optimization of CO2 production rate for firefighting robot applications using response surface methodology(Cogent, 2018-01-01) Ajala, M. T.; Khan, R.; Shafie, A. A.; Salami, Momoh-Jimoh E.; Nor, Mohamad; Oladokun, M. O.A carbon dioxide gas-powered pneumatic actuation has been proposed as a suitable power source for an autonomous firefighting robot (CAFFR), which is designed to operate in an indoor fire environment in our earlier study. Considering the consumption rate of the pneumatic motor, the gas-powered actuation that is based on the theory of phase change material requires optimal determination of not only the sublimation rate of carbon dioxide but also the sizing of dry ice granules. Previous studies that have used the same theory are limited to generating a high volume of carbon dioxide without reference to neither the production rate of the gas nor the size of the granules of the dry ice. However, such consideration remains a design requirement for efficient driving of a carbon dioxide-powered firefighting robot. This paper investigates the effects of influencing design parameters on the sublimation rate of dry ice for powering a pneumatic motor. The optimal settings of these parameters that maximize the sublimation rate at the minimal time and dry ice mass are presented. In the experimental design and analysis, we employed full-factorial design and response surface methodology to fit an acceptable model for the relationship between the design factors and the response variables. Predictive models of the sublimation rate were examined viaANOVA, and the suitability of the linear model is confirmed. Further, an optimal sublimation rate value of 0.1025 g/s is obtained at a temperature of 80°C, the mass of 16.1683 g, and sublimation time of 159.375 s.Item Prediction of dry ice mass for firefighting robot actuation(IOP Publishing, 2017-11) Ajala, M. T.; Khan, R.; Shafie, A. A.; Salami, Momoh-Jimoh E.; Nor, MohamadThe limitation in the performance of electric actuated firefighting robots in hightemperature fire environment has led to research on the alternative propulsion system for the mobility of firefighting robots in such environment. Capitalizing on the limitations of these electric actuators we suggested a gas-actuated propulsion system in our earlier study. The propulsion system is made up of a pneumatic motor as the actuator (for the robot) and carbon dioxide gas (self-generated from dry ice) as the power source. To satisfy the consumption requirement (9cfm) of the motor for efficient actuation of the robot in the fire environment, the volume of carbon dioxide gas, as well as the corresponding mass of the dry ice that will produce the required volume for powering and actuation of the robot, must be determined. This article, therefore, presents the computational analysis to predict the volumetric requirement and the dry ice mass sufficient to power a carbon dioxide gas propelled autonomous firefighting robot in a high-temperature environment. The governing equation of the sublimation of dry ice to carbon dioxide is established. An operating time of 2105.53s and operating pressure ranges from 137.9kPa to 482.65kPa were achieved following the consumption rate of the motor. Thus, 8.85m3 is computed as the volume requirement of the CAFFR while the corresponding dry ice mass for the CAFFR actuation ranges from 21.67kg to 75.83kg depending on the operating pressure.Item Retina fundus image mask generation using pseudo parametric modeling technique(IIUM Engineering Journal, 2010-11) Aibinu, Musa A.; Salami, Momoh-Jimoh E.; Shafie, A. A.ABSTRACT (abstract): The use of vascular intersection as one of the symptoms for monitoring and diagnosis of diabetic retinopathy from Fundus images have been widely reported in literatures. In this work, a new hybrid approach that makes use of three different methods of vascular intersection detection namely Modified Cross-Point Number (MCN), Combine Cross-Points Number (CCN) and Artificial Neural Network (ANN) technique is hereby proposed. Result obtained from the application of this technique to both simulated and experimental shows a very high accuracy and precision value in detecting both bifurcation and cross over points. Thus an improvement in bifurcation and vascular point detection and a good tool in the monitoring and diagnosis of diabetic retinopathy