Fuzzy dynamic parameter adaptation in the bird swarm algorithm for neural network optimization

Abstract

Fuzzy dynamic parameter adaptation has proven to be of great help when it is implemented in bio-inspired algorithms for optimization in different application areas, such as control, mathematical functions, classification, among others. One of the main contributions of this work is the proposed improvement of the Bird Swarm algorithm using a Fuzzy System approach, and we called this improvement the Fuzzy Bird Swarm Algorithm. Furthermore, we use a set of complex Benchmark Functions of the Congress on Evolutionary Computation Competition 2017 to compare the results between the original algorithm and the proposed improvement of the algorithm. The fuzzy system is utilized for the dynamic parameter adaptation of the C1 and C2 parameters of the Bird Swarm Algorithm. As a result, the Fuzzy Bird Swarm Algorithm has enhanced exploration and exploitation abilities that help in achieving better results than the Bird Swarm Algorithm. We additionally test the algorithm’s performance in a real problem in the medical area, using the optimization of a neural network to obtain the risk of developing hypertension. This neural network uses information, such as age, gender, body mass index, systolic pressure, diastolic pressure, if the patient smokes and if the patient has parents with hypertension. Hypertension is one of the leading causes of heart problems, which in turn are also one of the top causes of death. Moreover, these days it causes more complications and deaths in people infected with COVID-19, the virus of the ongoing pandemic. Based on the results obtained through the 30 experiments carried out in three different study cases, and the results obtained from the statistical tests, it can be concluded that the proposed method provides better performance when compared with the original method.

An Experimental Study of a Fuzzy Adaptive Emperor Penguin Optimizer for Global Optimization Problem

“…Liu et al [69] and Qi and Chunming [70] tuned the same parameters (i.e., mutation and crossover) to improve the performance of the Genetic Algorithm (GA). In [71], [74], [75], [77], [79], [81], the iterations are considered as fuzzy input to tune the corresponding parameters for Gravitational Search Algorithm (GSA), Harmony Search Algorithm (HSO), Flower Pollination Algorithm (FPA), Bee Colony Optimization (BCO), and Bird Swarm Algorithm (BSA). Neyoy et al [72] tuned the alpha parameter using the errors and the changes in the errors to improve Ant Colony Optimization (ACO).…”

Fuzzy Optimal Control of Radon Exhalation in Uranium Tailings under Double-Layer Coverage

“…Alfi and Fateh [36] used a fuzzy inertia weight to balance the global and local exploitation abilities rationally. By using membership functions and swarm intelligence algorithms, these studies enabled the construction of fuzzy constraint equations and fuzzy targets for radon exhalation [37][38][39][40]. Additionally, integration functions with varying probability levels and degrees of importance, along with an optimal decision-making database, can be obtained through this approach.…”

Enhancing Dynamic Parameter Adaptation in the Bird Swarm Algorithm Using General Type-2 Fuzzy Analysis and Mathematical Functions

“…In this research, we focus on the Bird Swarm Algorithm (BSA), which is inspired by how birds search for food, performing a dynamic parameter adaptation. Previous works [26,27] honed BSA performance through the application of Type-1 and Interval Type-2 fuzzy systems to address a variety of issues; tests were carried out using both classic and CEC2017 suite benchmark functions. The results demonstrated significant improvements compared to the original approach and other methods previously documented in the literature.…”