Support vector regression (SVR) models have been designed to predict the concentration of chemical oxygen demand in sequential batch reactors under high temperatures. The complex internal interaction between the sludge characteristics and their influent were used to develop the models. The prediction becomes harder when dealing with a limited dataset due to the limitation of the experimental works. A radial basis function algorithm with selected kernel parameters of cost and gamma was used to developed SVR models. The kernel parameters were selected by using a grid search method and were further optimized by using particle swarm optimization and genetic algorithm. The SVR models were then compared with an artificial neural network. The prediction results R² were within >90% for all predicted concentration of COD. The results showed the potential of SVR for simulating the complex aerobic granulation process and providing an excellent tool to help predict the behaviour in aerobic granular reactors of wastewater treatment.

The water supply system has a high operational cost associated with its operations. This is characteristically due to the operations of the pumps that consume significantly high amount of electric energy. In order to minimize the electric energy consumption and reduce the maintenance cost of the system, this paper proposes the use of an Adaptive Weighted sum Genetic Algorithm (AWGA) in creating an optimal pump schedule, which can minimize the cost of electricity and satisfy the constraint of the maximum and minimum levels of water in the reservoir as well. The Adaptive weighted sum GA is based on popular weighted sum approach GA for multi-objective optimization problem wherein the weights multipliers of the individual fitness functions are adaptively selected. The algorithm has been tested using a hypothetical case study and promising results have been obtained and presented.

Heat sink is the most popular device used for electronic cooling. A continuing in increasing of power density in CPU processor, by reducing the size of electronic products has led to the importance of thermal management issue in this industry. This issue will reduce the performance of the CPU processor and indirectly affects the lifetime of the electronics package. In order to avoid these consequences, therefore, heat sink with high heat transfer rate is need. The selection of suitable heat sink geometries requires a compromise among the availability of space, weight, and cost as well as the heat transfer characteristics of the heat sink model surface. This study aims to provide the optimal arrangement of heat sink by using random approach that randomly generated the position of pin by visualized the thermal profile using COMSOL Multiphysics software. The finding of this study propose a new arrangement (optimal) of the pin fin that be able to give better thermal performance which are 2.84 percent and 0.63 percent compared to the conventional design, which is inline and staggered arrangement. To develop a simple and effective random approach arrangement can significantly contribute to the advancement of thermal performance solution and catering the industrial needs.

This paper presents an algorithm for thermal optimization formulation strategies for multi-heat generation of integrated circuit (IC) on printed circuit board (PCB). Weighted-sum approach for multi-objective genetic algorithm (WMOGA) with formulated initial placement and multi-constraints parameters (FIPMCP) are presented. FIPMCP is used for the components selection and components to PCB placement mapping procedures for random initial population. The objectives are to optimize thermal distribution f(T) of electronic components on PCB and the PCB area f(A) needed simultaneously. For multi-objective optimization process, non-dominated optimal solutions and the best fitness WMOGA over iterations are plotted for both cases in order to obtain the best PCB optimal design solution. The results show that the best solution of f(T), f(A) and F(T, A) are minimized by 1.80%, 8.54% and 4.97% respectively.