This paper presents simulated hybridized solar-wind generation as an alternative for rural dwellers that do not have access to a conventional grid connection. Solar and wind were used as the main sources of energy with battery storage. Each power source has a DC-DC converter to control the power flow. An axial flux permanent magnet generator, which is suitable for a location with a low wind speed, was driven by the wind turbine. By using this generator, the efficiency of the system increased since certain losses were removed. The perturbation and observation method of MPPT is used to achieve maximum power extraction from the solar panel. The hybrid system was modelled in Matlab/Simulink software. A squirrel cage induction motor was used as the electrical load to the system load. The results obtained for the proposed hybrid system indicates that it can be used as an isolated power supply. By doing so, it improves the standard of living and hence, increasing total number of citizens using energy in the country.

Feature selection improves the classification performance of machine learning models. It also identifies the important features and eliminates those with little significance. Furthermore, feature selection reduces the dimensionality of training and testing data points. This study proposes a feature selection method that uses a multivariate sample similarity measure. The method selects features with significant contributions using a machine-learning model. The multivariate sample similarity measure is evaluated using the University of California, Irvine heart disease dataset and compared with existing feature selection methods. The multivariate sample similarity measure is evaluated with metrics such as minimum subset selected, accuracy, F1-score, and area under the curve (AUC). The results show that the proposed method is able to diagnose chest pain, thallium scan, and major vessels scanned using X-rays with a high capability to distinguish between healthy and heart disease patients with a 99.6% accuracy.

This paper presents a comprehensive mathematical modelling of a DC to DC Buck-Boost converter. The different power losses associated with the Buck-Boost circuit are also presented. Analysis of the converter power loss is graphically represented at varied duty cycles and load resistance values. A low frequency pulse width modulated inverter is interfaced with the Buck-Boost converter using MATLAB/SIMULINK. For an efficient performance and attenuation of low order harmonics, the low frequency pulse width modulated inverter is substituted with a high frequency pulse width modulated voltage source inverter. A comparison is therefore drawn to show the significant change in the percentage harmonic reduction of the two different frequency modulations. All simulation results are achieved using MATLAB 7.14 version. The simulation results however show that Mosfet switching loss decreases with an increase in the duty cycle whereas Diode and Inductor conduction losses increase with an increase in the duty cycle values.Contribution/ Originality: This study contributes in the existing literature by showing that at a reduced duty cycle and varied resistance values of a dc-dc buck boost converter, the Mosfet switching loss is increased whereas the Diode and Inductor conduction losses decrease correspondingly with the decrease in the duty cycle.

Electrical power generated and transmitted at a long distance away from the power stations is usually affected by inherent transmission line losses. The Ohmic and Corona losses which are predominantly common in power transmission lines are considered in this paper. These two losses are mathematically modeled with and without embedded bundled conductors. The resultant model which is a non-linear multivariable unconstrained optimized equation is minimized using the Hessian matrix determinant method for stability test purposes. The results obtained show that corona losses are minimized with embedded bundled conductors at a very low current value with large spacing distance between the bundled conductors. The decrease in the corona loss which is a consequence of spacing adjustment of the 2, 3, and 4 strands of bundled conductors was plotted using MATLAB 7.14. The plots obtained are in conformity with the inverse relation between corona loss and conductor spacing.

Chronic kidney disease is one of the leading causes of death around the world. Early detection of chronic kidney disease is crucial to the reduction of mortality caused as a result of the disease. Machine learning methods are recently becoming popular for the detection of chronic kidney disease. This study investigates the influence of resampling for chronic kidney disease detection using an imbalanced chronic kidney disease dataset. Choosing an optimal feature subset for medical datasets is important for improving the performance of data-driven predictive models. The influence of imbalanced class distribution on predictive models has become an increasingly important topic due to the recent advances in automatic decision-making processes and the continuous expansion in the volume of the data collected by medical institutions. To address the identified research gap, an experimental evaluation of synthetic minority oversampling and near miss undersampling technique was performed on a real-world chronic kidney disease dataset using several classification methods such as decision tree, random forest, K-nearest neighbor, adaptive boosting, and support vector machine. The results demonstrate that a number of variables, including performance metrics, classification algorithm, and dataset characteristics, influence the best class distribution.The study also offers useful information about resampling methods for an imbalanced classification problem which will help improve classification accuracy.