No abstract

Many complex real-world problems such as bin-packing are optimised using evolutionary computation (EC) techniques. Involving a human user during this process can avoid producing theoretically sound solutions that do not translate to the real world but slows down the process and introduces the problem of user fatigue. Gamification can alleviate user boredom, concentrate user attention, or make a complex problem easier to understand. This paper explores the use of gamification as a mechanism to extract problem-solving behaviour from human subjects through interaction with a gamified version of the bin-packing problem, with heuristics extracted by machine learning. The heuristics are then embedded into an evolutionary algorithm through the mutation operator to create a human-guided algorithm. Experimentation demonstrates that good human performers augment EA performance, but that poorer performers can be detrimental to it in certain circumstances. Overall, the introduction of human expertise is seen to benefit the algorithm. CCS CONCEPTSComputing methodologies → Machine learning → Machine learning approaches → Bio-inspired approaches → Genetic algorithms;Applied computing → Operations research → Decision analysis → Multi-criterion optimization and decision-making

Evolutionary Algorithms (EAs) have been employed for the optimisation of both theoretical and real-world problems for decades. These methods although capable of producing nearoptimal solutions, often fail to meet real-world application requirements due to considerations which are hard to define in an objective function. One solution is to employ an Interactive Evolutionary Algorithm (IEA), involving an expert human practitioner in the optimisation process to help guide the algorithm to a solution more suited to real-world implementation. This approach requires the practitioner to make thousands of decisions during an optimisation, potentially leading to user fatigue and diminishing the algorithm's search ability. This work proposes a method for capturing engineering expertise through machine learning techniques and integrating the resultant heuristic into an EA through its mutation operator. The human-derived heuristic based mutation is assessed on a range of water distribution network design problems from the literature and shown to often outperform traditional EA approaches. These developments open up the potential for more effective interaction between human expert and evolutionary techniques and with potential application to a much larger and diverse set of problems beyond the field of water systems engineering.