Search

Expensive optimization problems arise in diverse fields, and the expensive computation in terms of function evaluation poses a serious challenge to global optimization algorithms. In this article, a simple yet effective optimization algorithm for computationally expensive optimization problems is proposed, which is called the neighborhood regression optimization algorithm. For a minimization problem, the proposed algorithm incorporates the regression technique based on a neighborhood structure to predict a descent direction. The descent direction is then adopted to generate new potential offspring around the best solution obtained so far. The proposed algorithm is compared with 12 popular algorithms on two benchmark suites with up to 30 decision variables. Empirical results demonstrate that the proposed algorithm shows clear advantages when dealing with unimodal and smooth problems, and is better than or competitive with other peer algorithms in terms of the overall performance. In addition, the proposed algorithm is efficient and keeps a good tradeoff between solution quality and running time. [ABSTRACT FROM AUTHOR]

The lower luminous efficiency is a critical issue for ultraviolet light-emitting diodes (UV-LEDs) owing to the poor carrier injection efficiency and high dislocation density. Here, we can improve the luminous efficiency in two avenues by adjusting the Al composition of the InGaN/AlxGa1-xN pre-well superlattice. First, due to the strain-induced piezoelectric and intrinsic spontaneous polarization, a large number of electrons gather at the InGaN/AlxGa1-xN interface, which improves the electron concentration of the pre-well superlattice and lowers the conduction band energy of the first quantum barrier layer (FQB), thus enhancing the electron injection efficiency. Second, the pre-well superlattice can act as a hole blocking layer to prevent holes from leaking into the n-type layer and confine them in the quantum well layer. As the Al composition increases, the hole blocking effect of the pre-well superlattice is strengthened. However, higher Al composition decreases the lattice quality, which makes it possible for carrier loss through defect-related non-radiative recombination. Finally, the output power of the samples with 5% Al composition in the pre-well superlattice is 5.9% and 102.5% higher than that of the samples with 3% and 7% Al composition, respectively. [ABSTRACT FROM AUTHOR]