Engineering
Permanent URI for this community
These are the scholarly outputs of the Faculty of Engineering
Browse
Browsing Engineering by Subject "Abstracts"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Classification of Retinal Images Based on Statistical Moments and Principal Component Analysis(IEEE, 2014-09-23) Salami, Momoh-Jimoh E.; Khorshidtalab, A.; Baali, A.; Aibinu, A. M.Early diagnosis of Diabetic Retinopathy (DR) has been suggested as a good measure of preventing blindness associated with Diabetes. Some of the reported methodologies of Retinal Images (RI) classification for early diagnosis of DR have been shown to involve several steps and approaches for effective and accurate diagnosis. Thus, this paper investigates the classification of RI using a two-stage procedure. The first stage includes the extraction of blood vessels from RI belonging to healthy and diabetes retinal images using a modified local entropy thresholding algorithm. In the second stage, different features are extracted including statistical moments and principal components. The set of extracted features is combined into one feature vector and fed into a Sequential Minimal Optimization (SMO) classifier. The obtained result is encouraging with an average accuracy of 68.33 %.Item Hardware Implementation of ANFIS Controller for Gas-Particle Separations in Wet Scrubber System(IEEE, 2014-09-23) Hawari, Yasser; Salami, Momoh-Jimoh E.; Aburas, Abdurazzag A.Wet scrubber system has been used for the control of gas and particulate matter (PM) emissions from production industries. Due to non-linear characteristics, wet scrubbers are limited to the control of PM that is less than 5μm. In this study, an intelligent control technique based on Adaptive Neuro-Fuzzy Inference System (ANFIS) has been designed using MATLAB software. The ANFIS Controller has the advantage of solving nonlinearities in the proposed wet scrubber system by manipulating the scrubbing liquid droplet size for the effective control of particulate matter that is less than 5μm. From the simulation results, the controller was able to set PM concentration below the setpoint and provides smooth control response within short settling time. Hardware implementation of the ANFIS controller was performed using prototype wet scrubber system by considering Arduino Duemilanove microcontroller and MATLAB interface. The results show that the intelligent controller has achieved the desired objectives of controlling the PM concentration effectively by setting the value below the set point (20μg/m 3) which is the allowable PM concentration standard recommended by World Health Organization.Item Singular Value Decomposition (SVD) Based Orthogonal Transform Approach for Earth's Electric Field Signal Processing(IEEE, 2014-09-23) Astuti, W.; Salami, Momoh-Jimoh E.; Akmeliawati, R.; Sediono, W.The Earth's electric field signal is generated from the released energy through a sudden dislocation of the segment in the earth's crust. Many researchers have reported the use of parametric modeling technique for earth's electric field signal processing. The existing earth's electric signal processing based on parametric modeling technique has suffered from the noise. Therefore, the effective earth's electric field signal processing is necessary in order to process the signal with better performance for the identification. Singular value decomposition (SVD) based parametric modeling technique is applied as feature extraction technique to the Earth's electric field signal. The projection of excitation signal on the right eigenvector of the LPC filter impulse response matrix is involved in this technique. The combination of SVD-based parametric modeling technique has perfectly classified the significant Earth's electric field data prior to the earthquake and the Earth's electric field data on the normal condition after the polynomial kernel function is applied.