Dispersive Flies Optimisation

Abstract

Abstract-One of the main sources of inspiration for techniques applicable to complex search space and optimisation problems is nature. This paper proposes a new metaheuristic -Dispersive Flies Optimisation or DFO -whose inspiration is beckoned from the swarming behaviour of flies over food sources in nature. The simplicity of the algorithm, which is the implementation of one such paradigm for continuous optimisation, facilitates the analysis of its behaviour. A series of experimental trials confirms the promising performance of the optimiser over a set of benchmarks, as well as its competitiveness when compared against three other well-known population based algorithms (Particle Swarm Optimisation, Differential Evolution algorithm and Genetic Algorithm). The convergence-independent diversity of DFO algorithm makes it a potentially suitable candidate for dynamically changing environment. In addition to diversity, the performance of the newly introduced algorithm is investigated using the three performance measures of accuracy, efficiency and reliability and its outperformance is demonstrated in the paper.

Optimising SVM to classify imbalanced data using dispersive flies optimisation

“…Despite the rapid development in using swarm intelligence techniques to solve the class imbalance problem at the algorithmic level by optimising the kernel's parameters, these techniques face the challenge of the slow convergence rate, the trap to local optima and the number of tunable parameters. Al-Rifaie (2014) proposed a new meta heuristic, Dispersive Flies Optimisation, derived from the swarming behaviour of flies, which they use to locate the food source and the way it is communicated to other flies so that they can access the food source with minimal attempt to locate it [5]. In this paper, DFO will be used to perform SVM cost sensitive learning on various benchmarks data and compare the proposed method with both evolutionary and non evolutionary search based techniques from the literature on the same datasets.…”

“…DFO, first introduced in [5], is an algorithm inspired by the swarming behaviour of flies hovering over food sources. The swarming behaviour of flies is determined by several factors including the presence of threat which disturbs their convergence on the marker (or the optimum value).…”

“…The simplicity of the algorithm has been compared against several other swarm and evolutionary computation techniques in [6] where the elegance of the algorithm in having only one tunable parameter (the disturbance threshold), is explored. It has also been shown that DFO outperforms the standard versions of the well-known Particle Swarm Optimisation, Genetic Algorithm (GA) as well as Differential Evolution (DE) algorithms on an extended set of benchmarks over three performance measures of error, efficiency and reliability [5]. It is demonstrated that DFO is more efficient in 84.62% and more reliable in 90% of the 28 standard optimisation benchmarks used; furthermore, when there exists a statistically significant difference, DFO converges to better solutions in 71.05% of problem sets.…”

Nature-Inspired Algorithms in Real-World Optimization Problems

“…Dispersive flies optimization algorithm (DFO ) was proposed in 2014 [12], the only control parameter called disturbance threshold, is set to dt = 1 × 10 −3 .…”

Dispersive Flies Optimisation and Medical Imaging

“…Furthermore CAD is a promising learning tool for both medical students and junior doctors to develop basic diagnostic skills. This paper presents a new CAD approach in which a recently developed swarm intelligence algorithm -Dispersive Flies Optimisation [10] -is applied to a medical imaging modality where the potential areas of microcalcifications on the x-ray mammography are detected.…”