An ontology-based model of artificial bee colony (ABC) algorithm and its future directions

Abstract

This article repositions the Artificial Bee Colony (ABC) algorithm beyond its conventional treatment as a metaheuristic optimization technique by framing it along a three-layer axis of conceptual and methodological maturity. At the first level, ABC is analyzed as an ontology-driven and cognitively inspired model rooted in its biological foundations, specifically the foraging and dance behaviors of honey bee colonies. Intra-colony interactions-such as decision-making, communication, and information sharing-are interpreted through the perspectives of swarm intelligence and preference-vector-based cognitive orientation, explaining the emergence of collective optimization behavior. At the second level, the algorithm gains mathematical rigor through the integration of time-dependent stochastic processes, Markov chains, transition probabilities, entropy, and diversity measures within an information theory based framework. From this standpoint, ABC is no longer viewed only as a search procedure ensuring convergence, but as a formal structure capable of modeling information flow, uncertainty reduction, and collective learning in the solution space. The third level extends the scope of ABC beyond classical engineering optimization problems. The algorithm is situated within a broader valueoriented framework that includes advanced distributed and cognitive systems such as quantum computing, blockchain-based security architectures, cyber defense ecosystems, secure artificial intelligence (AI), AI safety, and the Internet of Minds (IoM). Within this vision, ABC functions not only as a mathematical tool but also as a conceptual metaphor for fair optimization, distributed decision-making, and cognitive societies. By revisiting the algorithm's twenty-year evolution, the study offers a conceptual contribution by redefining ABC as an ontologybased decision-making structure composed of roles, states, and relational dynamics. The proposed perspective suggests that the historical evolution of ABC reflects not only improvements in optimization performance but also a progressive expansion of the classes of problems that can be effectively addressed.