Slight delay as the project officially ended, formally at least, though there’s a little ‘tidying up’ to perform and further data to be collected then analysed to (hopefully) once and for all either prove or refute the central hypothesis! That is, that swarm based solutions are appropriate for the kind of detection problems alluded to…As of this time the aforementioned human-in-the-loop was evidenced to be the best approach yet, again, slight improvements have been identified that may obviate the human altogether. As to whether that’s a good or bad thing is another (largely ethical) question altogether. Which leads on nicely to potential future developments presently under discussion! 😁