We are happy to announce the release of Wallacei X, a new component within the Wallacei platform.
Wallacei X is an evolutionary engine that allows users to run evolutionary simulations in Grasshopper 3D through utilising highly detailed analytic tools coupled with various comprehensive selection methods, including algorithmic clustering, to assist users to better understand their evolutionary runs, and make more informed decisions at all stages of their evolutionary simulations; including setting up the design problem, running the evolutionary algorithm, analysing the outputted results and selecting the desired solution or solutions for the final output. Wallacei also provides users with the ability to select, reconstruct and output any phenotype from the population after completing their simulation!
The free plugin is streamlined to give users efficient access to the data outputted by their evolutionary simulations, and enable clear and efficient methods for analysis and selection – The aim is for users (of all degrees of expertise) to better understand their evolutionary simulations, gain a thorough understanding of the outputted numeric values, and seamlessly extract the optimised data; all within one user interface.
One of the challenges of the multi-objective optimization processes is how to select a solution or a set of candidate solutions from the population of generated options. Complex problems that comprise multiple (conflicting) objectives do not normally have a single solution as the final definitive outcome that can address all objectives as the objectives are usually in conflict with one another. This is one of the main differences between single objective optimization and multi-objective optimization problems. When it comes to the selection procedures, one can choose from Pareto Front solutions, or selecting from a set of individuals that address one objective better/worse than others etc. In Wallacei we have an extensive collection of toolsets, all embedded in the UI ( Tab 2 and Tab 3) that help users to make an informed decision and select the solution or a set of candidate solutions by providing the entire history of the evolution. I suggest you watch the video below where it briefly explains these procedures. In general WallaceiX playlist in our YouTube channel is a good resource to jump-start into the subject.
Thanks , i watch some videos and read the pdf but don’t understand how wallacei know if the objective is minimum or maximum or equal like in galapagos.
In the example above i plug the 3 sliders to genes , v to objective; now how to add the constraint equal to 300?
Wallacei always minimises. These two following videos will help you to understand how to minimise/maximise or constrain a fitness objective around a constant variable or within a domain.
In general, It is highly recommended to minimise Rhino when the simulation is running, especially for the heavy design problems. Rendering meshes and geometries iteratively will slow down the simulation.
I need to see your GH file to better understand what the problem is tho.
The reason is that all the individuals in those generations are exactly the same (see the image). So anything more than one cluster (like two clusters) do not make any sense. However Wallacei should not stop working, it should give you a message about this error ( if you choose hierarchical clustering it gives a message). I make sure this is fixed for kmeans as well in the next release.
FYI this is not a good example to do the clustering.