Fish-Inspired Heuristics: A Survey of the State-of-the-Art Methods

Abstract

The collective behaviour of fish schools, shoals and other swarms in nature has long inspired researchers to develop solutions for optimization problems. Instinct influences the behaviour of fish to group into schools to increase safety, enhance foraging success, and promote breeding. According to these instinctive behaviours, several fish-inspired algorithms have been introduced to solve hard problems. This paper presents a comprehensive survey of fish-inspired heuristics, exploring their evolution within the context of general optimization problems. To our knowledge, this survey is the first to cover both main fish-inspired heuristics in the literature, namely, the artificial fish swarm algorithm (AFSA) and Fish school search (FSS), in addition to other algorithms inspired by specific fish species. The review covers more than 50 papers published in the Web of Science and IEEE databases since 2000. We first review the basic fish heuristics, highlighting their advantages and drawbacks, and then detail attempts in the literature to improve their behaviour to solve complex, multi-objective and high-dimensional problems in several domains. Our work is intended to provide guidance for researchers and practitioners for the purpose of further advancing research in the area of fish-inspired heuristics. We aspire to encourage their utilization in various fields for global optimization and in real-life applications. The survey findings indicate that fish-inspired heuristics are very alive in recent literature and still have great potential. Several challenges and future research directions are also identified among the findings of this survey, which can help to enhance this vibrant line of research.

Surface Deformation Prediction Model of High and Steep Open-Pit Slope Based on APSO and TWSVM

“…Compared to the support vector machine model, it not only has higher training speed, but also has better generalisation ability [11]. Since the TWSVM model is affected by parameters, the parameters must be optimised by combining the genetic algorithm [12], the particle swarm algorithm [13], the artificial fish swarm algorithm [14], and other search algorithms to improve the convergence speed and recognition accuracy of the model algorithm. Therefore, it is necessary to establish the combination prediction model strategy and make full use of the advantages of various models to improve the slope prediction accuracy.…”