Information Literacy Assessment with a Modified Hybrid Differential Evolution with Model-Based Reinitialization

Information literacy assessment is extremely important for the evaluation of the information literacy skills of college students. Intelligent optimization technique is an effective strategy to optimize the weight parameters of the information literacy assessment index system (ILAIS). In this paper, a new version of differential evolution algorithm (DE), named hybrid differential evolution with model-based reinitialization (HDEMR), is proposed to accurately fit the weight parameters of ILAIS. The main contributions of this paper are as follows: firstly, an improved contraction criterion which is based on the population entropy in objective space and the maximum distance in decision space is employed to decide when the local search starts. Secondly, a modified model-based population reinitialization strategy is designed to enhance the global search ability of HDEMR to handle complex problems. Two types of experiments are designed to assess the performance of HDEMR. In the first type of experiments, HDEMR is tested and compared with seven well-known DE variants on CEC2005 and CEC2014 benchmark functions. In the second type of experiments, HDEMR is compared with the well-known and widely used deterministic algorithm DIRECT on GKLS test classes. The experimental results demonstrate the effectiveness of HDEMR for global numerical optimization and show better performance. Furthermore, HDEMR is applied to optimize the weight parameters of ILAIS at China University of Geosciences (CUG), and satisfactory results are obtained.

Drivers of diversity in individual life courses: Sensitivity of the population entropy of a Markov chain

Individuals differ in their life courses, but how this diversity is generated, how it has evolved and how maintained is less understood. However, this understanding is crucial to comprehend evolutionary and ecological population dynamics. In structured populations, individual life courses represent sequences of stages that end in death. These sequences can be described by a Markov chain and individuals diversify over the course of their lives by transitioning through diverse discrete stages. The rate at which stage sequences diversify with age can be quantified by the population entropy of a Markov chain. Here, we derive sensitivities of the population entropy of a Markov chain to identify which stage transitions generate—or contribute—most to diversification in stage sequences, i.e. life courses. We then use these sensitivities to reveal potential selective forces on the dynamics of life courses. To do so we correlated the sensitivity of each matrix element (stage transition) with respect to the population entropy, to its sensitivity with respect to fitness λ, the population growth rate. Positive correlation between the two sensitivities would suggest that the stage transitions that selection has acted most strongly on (sensitivities with respect to λ) are also those that contributed most to the diversification of life courses. Using an illustrative example on a seabird population, the Thick-billed Murres on Coats Island, that is structured by reproductive stages, we show that the most influential stage transitions for diversification of life courses are not correlated with the most influential transitions for population growth. Our finding suggests that observed diversification in life courses is neutral rather than adaptive. We are at an early stage of understanding how individual level dynamics shape ecological and evolutionary dynamics, and many discoveries await.

Drivers of diversification in individual life courses

ABSTRACTHeterogeneity in life courses among individuals of a population influences the speed of adaptive evolutionary processes, but it is less clear how biotic and abiotic environmental fluctuations influence such heterogeneity. We investigate principal drivers of variability in sequence of stages during an individual’s life in a stage-structured population. We quantify heterogeneity by measuring population entropy, which computes the rate of diversification of individual life courses of a Markov chain. Using individual data of a primate population, we show that density regulates the stage composition of the population, but its entropy and the generating moments of heterogeneity are independent of density. This lack of influence of density on heterogeneity is neither due to low year-to-year variation in entropy nor due to differences in survival among stages, but due to differences in stage transitions. Our analysis thus shows that well-known classical ecological selective forces, such as density regulation, are not linked to potential selective forces governing heterogeneity through underlying stage dynamics. Despite evolution acting heavily on individual variability in fitness components, our understanding is poor whether observed heterogeneity is adaptive and how it evolves and is maintained. Our analysis illustrates how entropy represents a more integrated measure of diversity compared to the population structural composition, giving us new insights about the underlying drivers of individual heterogeneity within populations and potential evolutionary mechanisms.

From Typical Sequences to Typical Genotypes

We demonstrate an application of a core notion of information theory, that of typical sequences and their related properties, to analysis of population genetic data. Based on the asymptotic equipartition property (AEP) for non-stationary discrete-time sources producing independent symbols, we introduce the concepts of typical genotypes and population entropy rate and cross entropy rate. We analyze three perspectives on typical genotypes: a set perspective on the interplay of typical sets of genotypes from two populations, a geometric perspective on their structure in high dimensional space, and a statistical learning perspective on the prospects of constructing typical-set based classifiers. In particular, we show that such classifiers have a surprising resilience to noise originating from small population samples, and highlight the potential for further links between inference and communication.

Analysis of Population Diversity of Dynamic Probabilistic Particle Swarm Optimization Algorithms

In evolutionary algorithm, population diversity is an important factor for solving performance. In this paper, combined with some population diversity analysis methods in other evolutionary algorithms, three indicators are introduced to be measures of population diversity in PSO algorithms, which are standard deviation of population fitness values, population entropy, and Manhattan norm of standard deviation in population positions. The three measures are used to analyze the population diversity in a relatively new PSO variant—Dynamic Probabilistic Particle Swarm Optimization (DPPSO). The results show that the three measure methods can fully reflect the evolution of population diversity in DPPSO algorithms from different angles, and we also discuss the impact of population diversity on the DPPSO variants. The relevant conclusions of the population diversity on DPPSO can be used to analyze, design, and improve the DPPSO algorithms, thus improving optimization performance, which could also be beneficial to understand the working mechanism of DPPSO theoretically.