KATSA: KNN Ameliorated Tree Seed Algorithm for complex optimization problems

• Published in: Expert systems with applications Vol. 280; p. 127465
• Main Authors: Jiang, Jianhua, Wu, Jiaqi, Luo, Jinmeng, Meng, Xianqiu, Qian, Lize, Li, Keqin
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 25.06.2025
• Subjects: KATSA; KNN; Optimization problem; Swarm intelligence; Tree Seed Algorithm; KNN; Swarm intelligence; KATSA; Tree Seed Algorithm; Optimization problem
• ISSN: 0957-4174
• DOI: 10.1016/j.eswa.2025.127465

Tree Seed Algorithm (TSA) is an outstanding algorithm for optimization problems, but it inevitably falls into the local optimum and has a low convergence speed in solving complex problems. This paper aims to address these above defects. Inspired by efficient learning from neighbors, a K-Nearest Neighbor (KNN) mechanism is adopted to enhance the tree or seed generation strategies for achieving the balance between exploitation and exploration. The proposed algorithm is named the KNN Ameliorated Tree Seed Algorithm (KATSA). First, based on the current best tree, the search space is divided into best and non-best neighbor areas by the KNN mechanism. Based on this division approach, the proposed seed generation strategy has a precise heuristic, and the convergence speed can be accelerated. Second, the proposed seed generation and tree migration strategies integrate the proposed dynamic regulation mechanism, which reduces the possibility of falling into a local optimum. Third, the proposed feedback mechanism can effectively balance exploration and exploitation. With these enhancements from the KNN mechanism, KATSA can converge to the global optima more effectively during its evolutionary process. The results obtained from IEEE CEC 2014 benchmark function evaluation verify the excellent performance of the KATSA when compared with some recent variants, including STSA, EST-TSA, fb_TSA, and MTSA. In addition, GWO, PSO, BOA, BA, GA, LSHADE, and RSA are also adopted for some benchmark comparative experiments. The applicability of the proposed KATSA is demonstrated by three real complex and constrained problems when compared to TSA, fb_TSA, LSHADE, RSA, GWO, ABC, and PSO. The experimental results show that the proposed KATSA can obtain stable and optimal results on these complex problems. The source code is available at www.jianhuajiang.com. •Neighbor information inspired from KNN is learned to guide seed generation.•An effective tree migration mechanism is integrated into the proposed KATSA.•Novel feedback mechanism accelerates the convergence speed of KATSA.•KATSA is verified in IEEE CEC 2014 benchmark functions and 3 engineering problems.