multi-objective optimization

The Pareto optimal solution is unique in single objective Particle Swarm Optimization (SO-PSO) problems as the emphasis is on the variable space of the decision. A multi-objective-based optimization technique called Multi-Objective Particle Swarm Optimization (MO-PSO) is introduced in this paper for image segmentation. The multi-objective Particle Swarm Optimization (MO-PSO) technique extends the principle of optimization by facilitating simultaneous optimization of single objectives. It is used in solving various image processing problems like image segmentation, image enhancement, etc. This technique is used to detect the tumour of the human brain on MR images. To get the threshold, the suggested algorithm uses two fitness(objective) functions- Image entropy and Image variance. These two objective functions are distinct from each other and are simultaneously optimized to create a sequence of pareto-optimal solutions. The global best (Gbest) obtained from MO-PSO is treated as threshold. The MO-PSO technique tested on various MRI images provides its efficiency with experimental findings. In terms of “best, worst, mean, median, standard deviation” parameters, the MO-PSO technique is also contrasted with the existing Single-objective PSO (SO-PSO) technique. Experimental results show that Multi Objective-PSO is 28% advanced than SO-PSO for „best‟ parameter with reference to image entropy function and 92% accuracy than Single Objective-PSO with reference to image variance function.

In addition to the improved calculation of the parameter values, a high yield estimation is necessary for designing analog integrated circuits. Although Monte-Carlo (MC) simulation is popular and precise for yield estimation; however, its efficiency is not high enough and it requires too many costly transistor-level simulations. Therefore, some accelerated methods are needed for MC simulations. This paper presents a novel approach for improving automated analog yield optimization using a three-stage strategy. Firstly, critical solutions are recognized using Critical Analysis (CA) and Multi-objective Optimal Computing Budget Allocation (MOCBA). Then they are separated from non-critical answers. It's so helpful to avoid repeating the Monte Carlo (MC) simulations of non-critical solutions. Due to the existence of several objective functions (typically more than one) in the yield optimization problem, by using the Multi-Objective Optimization (MOO) in the second stage, more precise answers can be found. Finally, MC simulations are performed to explore the proposed algorithm performance. Simulation results show that our approach locates higher quality in terms of yield rate within less run time and without affecting the accuracy.

This study proposes, a novel approach for optimal energy management’s problem and capacitor switching in the distribution network at the presence of distributed generators, energy storage units and solar photovoltaic arrays. Modern distribution networks, in addition to the importance of economic issues, must operate at an acceptable level of system reliability, Failure to pay attention to the reliability importance can lead to irreparable damages in the distribution network. Toward this end, energy not supplied as a reliability index along with operation cost are considered as objective functions. Also, the effect of uncertainty resources related to solar photovoltaic arrays power generation and electricity price are considered in the optimization problem evaluations. Considering the effects of distributed generators and energy storage units causes the proposed problem more be complicated, for this reason, an improved particle swarm optimization algorithm is provided to deal the complexity of the problem. The proposed algorithm is tested in the IEEE 33-node test system, and its superiorities are shown through comparison with other evolutionary algorithms.

A multi-periodic, multi-echelon green supply chain network consisting of manufacturing plants, potential distribution centers, and customers is developed. The manufacturing plants can provide the products in three modes including production in regular time, production in over time, or by subcontracting. The problem has three objectives including minimization of the total costs of the green supply chain network, maximization of the average safe inventory levels of the manufacturing plants and the distribution centers and minimization of the environmental impacts of the manufacturing plants in producing, holding and dispatching the products and also the environmental impacts of the distribution centers in holding and dispatching the products. The problem is first formulated as a mixed-integer mathematical model. Then, in order to solve the model, the augmented weighted Tchebycheff method is employed and its performance in producing the Pareto optimal solutions is compared with the goal attainment method.

Fuzzy clustering methods are conveniently employed in constructing a fuzzy model of a system, but they need to tune some parameters. In this research, FCM is chosen for fuzzy clustering. Parameters such as the number of clusters and the value of fuzzifier significantly influence the extent of generalization of the fuzzy model. These two parameters require tuning to reduce the overfitting in the fuzzy model. Two new cost functions are developed to set the parameters of FCM algorithm properly and the two evolutionary optimization algorithms, i.e. the multi-objective simulated annealing and the multi-objective imperialist competitive algorithm, are employed to optimize the parameters of FCM according to the proposed cost functions. The multi-objective imperialist competitive algorithm is the proposed algorithm.