D0L-System Inference from a Single Sequence with a Genetic Algorithm

Round 1

Reviewer 1 Report

Could fitness computational effort be reduced by using a surrogate fitness function based on similarity with previously explored individuals, which will estimate the fitness accurately for individuals that are similar to others seen before?

Could the authors compare the performance of a generational GA with that of a steady state GA?

This paper seems to restrict crossover to individuals of the same rule-count.  But crossover operators have been devised in the literature for individuals of unequal length, e.g., sets of different sizes.  For instance, each element of each parent could be chosen for the offspring with some probability such as 0.5.  Could those be used?

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 2 Report

The paper entitled 'D0L-system Inference from a Single Sequence with a Genetic Algorithm' is an interesting manuscript that proposes a new approach to the image-based grammatical inference. I believe the work has some potential, however:

1. In my opinion, it is worth extending the introduction, for example, by arguing the choice of a genetic algorithm (many different metaheuristics are known) and emphasizing the necessity of using metaheuristics.

2. I think it's worth adding the pseudocode of the genetic algorithm used.

3. I don't see a reference to Algorithm 1 and Table 1 in the text.

4. It is also worth including the standard deviation in Table 1.

5. There is no information on how the parameter values for the genetic algorithm were selected. Have empirical studies been conducted to determine them? If so, it's worth posting them.

6. You provide the execution time, so it is worth providing the parameters of the computer on which the tests were performed.

The paper was written correctly, but I suggest introducing abbreviations (e.g. for genetic algorithm) and using them in the text.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

The authors took into account my comments, therefore I recommend accepting the work.