An Adaptive Island Model of Population for Neuroevolutionary Ship Handling

This study presents a method for the dynamic value assignment of evolutionary parameters to accelerate, automate and generalise the neuroevolutionary method of ship handling for different navigational tasks and in different environmental conditions. The island model of population is used in the modified neuroevolutionary method to achieve this goal. Three different navigational situations are considered in the simulation, namely, passing through restricted waters, crossing with another vessel and overtaking in the open sea. The results of the simulation examples show that the island model performs better than a single non-divided population and may accelerate some complex and dynamic navigational tasks. This adaptive island-based neuroevolutionary system used for the COLREG manoeuvres and for the finding safe ship’s route to a given destination in restricted waters increases the accuracy and flexibility of the simulation process. The time statistics show that the time of simulation of island NEAT was shortened by 6.8% to 27.1% in comparison to modified NEAT method.

Island-based Cuckoo Search with Elite Opposition-based Learning and Multiple Mutation Methods for Solving Discrete and Continuous Optimization Problems

The Island Cuckoo Search ( i CSPM) algorithm is a new variation of Cuckoo Search (CS) that uses the island model and the Highly Disruptive Polynomial (HDP) mutation for solving a broad range of optimization problems. This article introduces an improved i CSPM algorithm called i CSPM with elite opposition-based learning and multiple mutation methods ( i CSPM2). i CSPM2 has three main characteristics. Firstly, it separates candidate solutions into a number of islands (sub-populations) and then divides the islands equally among four improved versions of CS: CS via Le'vy fights (CS1) [1], CS with HDPM mutation (CS10) [2], CS with Jaya mutation (CSJ) and CS with pitch adjustment mutation (CS11) [2]. Secondly, it uses Elite Opposition-based Learning (EOBL) to improve its convergence rate and exploration ability. Finally, it uses the Smallest Position Value (SPV) with scheduling problems to convert continuous candidate solutions into discrete ones. A set of 15 popular benchmark functions was used to compare the performance of iCSPM2 to the performance of the original i CSPM algorithm based on different experimental scenarios. Results indicate that i CSPM2 exhibits improved performance over i CSPM. However, the sensitivity analysis of i CSPM and i CSPM2 to their parameters indicates that their convergence behavior is sensitive to the island model parameters. Further, the single-objective IEEE CEC 2014 functions were used to evaluate and compare the performance of iCSPM2 to four well-known swarm optimization algorithms: DGWO [3], L-SHADE [4], MHDA [5] and FWA-DM [6]. The overall experimental and statistical results suggest that i CSPM2 has better performance than the four well-known swarm optimization algorithms. i CSPM2's performance was also compared to two powerful discrete optimization algorithms (GAIbH [7] and MASC [8]) using a set of Taillard's benchmark instances for the permutation flow shop scheduling problem. The results indicate that i CSPM2 performs better than GAIbH and MASC. The source code of i CSPM2 is publicly available at https://github.com/bilalh2021/iCSPM2

Mathematical constraints on FST: multiallelic markers in arbitrarily many populations

Interpretations of values of the FST measure of genetic differentiation rely on an understanding of its mathematical constraints. Previously, it has been shown that FST values computed from a biallelic locus in a set of multiple populations and FST values computed from a multiallelic locus in a pair of populations are mathematically constrained by the frequency of the allele that is most frequent across populations. We report here the mathematical constraint on FST given the frequency M of the most frequent allele at a multiallelic locus in a set of multiple populations, providing the most general description to date of mathematical constraints on FST in terms of M. Using coalescent simulations of an island model of migration with an infinitely-many-alleles mutation model, we argue that the joint distribution of FST and M helps in disentangling the separate influences of mutation and migration on FST. Finally, we show that our results explain puzzling patterns of microsatellite differentiation, such as the lower FST values in interspecific comparisons between humans and chimpanzees than in the intraspecific comparison of chimpanzee populations. We discuss the implications of our results for the use of FST.

Migration pulsedness alters patterns of allele fixation and local adaptation in a mainland-island model

Gene flow, through allele migration and spread, is critical in determining patterns of population genetic structure, divergence and local adaptation. While evolutionary theory has typically envisioned gene flow as a continuous connection among populations, many processes can render it fluctuating and intermittent. We analyze mathematically a stochastic mainland-island model in continuous time, in which migration occur as recurrent ''pulses''. We derive simple analytical approximations regarding how migration pulsedness affects the effective migration rates across a range of selection and dominance scenarios. Predictions are validated with stochastic simulations and summarized with graphical interpretations in terms of fixation probabilities. We show that migration pulsedness can decrease or increase gene flow, respectively above or below a selection threshold that is s~-1/N for additive alleles and lower for recessive deleterious alleles. We propose that pulsedness may leave a genomic detectable signature, by differentially affecting the fixation rates of loci subjected to different selection regimes. The additional migration created by pulsedness is called a ''pulsedness'' load. Our results indicate that migration pulsedness, and more broadly temporally variable migration, is important to consider for evolutionary and population genetics predictions. Specifically, it would overall be detrimental to the local adaptation and persistence of small peripheral populations.