Metaheuristic Optimisation Algorithms for Tuning a Bioinspired Retinal Model

Abstract

A significant challenge in neuroscience is understanding how visual information is encoded in the retina. Such knowledge is extremely important for the purpose of designing bioinspired sensors and artificial retinal systems that will, in so far as may be possible, be capable of mimicking vertebrate retinal behaviour. In this study, we report the tuning of a reliable computational bioinspired retinal model with various algorithms to improve the mimicry of the model. Its main contribution is two-fold. First, given the multi-objective nature of the problem, an automatic multi-objective optimisation strategy is proposed through the use of four biological-based metrics, which are used to adjust the retinal model for accurate prediction of retinal ganglion cell responses. Second, a subset of population-based search heuristics—genetic algorithms (SPEA2, NSGA-II and NSGA-III), particle swarm optimisation (PSO) and differential evolution (DE)—are explored to identify the best algorithm for fine-tuning the retinal model, by comparing performance across a hypervolume metric. Nonparametric statistical tests are used to perform a rigorous comparison between all the metaheuristics. The best results were achieved with the PSO algorithm on the basis of the largest hypervolume that was achieved, well-distributed elements and high numbers on the Pareto front.

Autofocus Entropy Repositioning Method Bioinspired in the Magnetic Field Memory of the Bees Applied to Pollination

“…The barycenter of the objects is employed as central points for sampling the regions of interest, with a later transformation to gray-scale and the Laplacian operator for the extraction around the edges [ 13 , 14 , 15 ]. The matrixes resulting from the convolution process are vectored, stored, and used to calculate the variances, probability distributions, and entropies.…”

“…Control of the omni-wheels robots using an algorithm bioinspired in the brain limbic system was developed in [ 13 ]. Algorithms of bioinspired optimizations, using particle swarm optimization and genetic algorithm, were used on the tune retinal models for hierarchical feature extraction of images [ 14 ]. In [ 15 ], a denoising algorithm was developed, bioinspired on bees for dim luminous conditions were used in the night vision algorithm to mimic the amplification of the transduction process in photoreceptors of Megalopta genalis.…”

Combinatorial Optimization Problems and Metaheuristics: Review, Challenges, Design, and Development

“…In the past few decades, the creation of metaheuristics algorithms was intense [6,12,15,[69][70][71][72] due to its success in solving hard problems. These algorithms usually obtain their inspiration from some characteristics found in nature [13,70,[73][74][75][76][77][78][79]. Nevertheless, some researchers have criticized the excess of new metaheuristics more focused on its metaphor than their quality as optimization methods [12,15,80].…”

E3H2O-LE-TDR Algorithm for Optimizing Solar PV Cell Models and Solving Real-World Engineering Problems

“…For mathematical optimization problems with more than one objective for which no single solution exists, multiobjective optimization is used. Stochastic optimization methods, such as metaheuristics, use mechanisms inspired by nature to solve optimization problems [13]. Metaheuristic algorithms are very well optimization techniques that have been utilized to solve a wide variety of optimization issues [14].…”

“…In most situations, complexity analysis, performance assessment, and metaheuristic parameter adjustment were ignored when metaheuristics were used to address optimization problems [16]. Single-solution metaheuristics focus on a single starting solution, whereas population-based metaheuristics focus on a large number of possible solutions [13]. It is generally more effective to use standard metaheuristics when dealing with typical research challenges [17].…”