Abstract: Nature-inspired optimization algorithms refer to techniques that simulate the behavior and ecosystem of living organisms or natural phenomena. One such technique is the “Photosynthesis Spectrum Algorithm,” which was developed by mimicking the process by which photons behave as a population in plants. This optimization technique has three stages that mimic the structure of leaves and the fluorescence phenomenon. Each stage updates the fitness of the solution by using a mathematical equation to direct the photon to the reaction center. Three stages of testing have been conducted to test the efficacy of this approach. In the first stage, functions from the CEC 2019 and CEC 2021 competitions are used to evaluate the performance and convergence of the proposed method. The statistical results from non-parametric Friedman and Kendall’s W tests show that the proposed method is superior to other methods in terms of obtaining the best average of solutions and achieving stability in finding solutions. In other sections, the experiment is designed for data clustering. The proposed method is compared with recent data clustering and classification metaheuristic algorithms, indicating that this method can achieve significant performance for clustering in less than 10 s of CPU time and with an accuracy of over 90%.

Key words: Data clustering , · Photosynthesis spectrum algorithm , · Nature-inspired algorithm , · Metaheuristic