Performance Comparison of Hybrid Electromagnetism-Like Mechanism Algorithms with Descent Method

Abstract

Electromagnetism-like Mechanism (EM) method is known as one of metaheuristics. The basic idea is one that a set of parameters is regarded as charged particles and the strength of particles is corresponding to the value of the objective function for the optimization problem. Starting from any set of initial assignment of parameters, the parameters converge to a value including the optimal or semi-optimal parameter based on EM method. One of its drawbacks is that it takes too much time to the convergence of the parameters like other meta-heuristics. In this paper, we introduce hybrid methods combining EM and the descent method such as BP, k-means and FIS and show the performance comparison among some hybrid methods. As a result, it is shown that the hybrid EM method is superior in learning speed and accuracy to the conventional methods.

Naturally Inspired Firefly Controller For Stabilization Of Double Inverted Pendulum

“…With the help of Pade approximation, the shift operator can be approximated by a rational transfer function of first order as The firefly algorithm is an algorithm where the natural life cycle of fireflies is imitated for obtaining the fitness of a function. The algorithm is better than the conventional gradient descent method [18] applied to systems in terms of energy as fireflies use optimized energy whereas gradient descent does not use specifications like intensity of light. The species of fireflies are a vivid variety which have distinct mechanism of communicating with one another and which observes certain patterns as they mutate based on how they respond to the individual patterns.…”

Emotion-Aware Brainstorm Optimization

“…Comparisons with conventional algorithms have proven that hybrid EMO approaches, combining EMO with other evolutionary algorithms, can be both efficient and effective [31]. Recent examples include the hybridization of EMO with firefly algorithm (FA) [32], where the interactive forces of EMO among individuals are used to improve the bi-directional local search ability of FA; EMO with collective animal behavior to retain more than one optimal solutions per iteration [33]; and EMO with tabu search algorithm for improving the local search and trading-off between intensification and diversification strategies [34].…”

New privacy preserving clustering methods for secure multiparty computation

“…Input vector x(t) is the vector randomly selected from X at step t. Figure 4 shows the algorithm of k-means method. [22,23] The second method, NG method, is known as a novel VQ method. The feature of NG method is that all the weights are updated based on the rank of distance between input and reference vectors.…”