Dehghani Moslem, Aly Mokhtar, Rodriguez Jose, Sheybani Ehsan, Javidi Giti
Facultad de Ingeniería, Arquitectura y Diseño, Universidad San Sebastián, Bellavista 7, Santiago 8420524, Chile.
School of Information Systems and Management, Muma College of Business, University of South Florida, Tampa, FL 33620, USA.
Biomimetics (Basel). 2025 Jun 7;10(6):379. doi: 10.3390/biomimetics10060379.
This paper introduces a novel nature-inspired optimization algorithm called the Grizzly Bear Fat Increase Optimizer (GBFIO). The GBFIO algorithm mimics the natural behavior of grizzly bears as they accumulate body fat in preparation for winter, drawing on their strategies of hunting, fishing, and eating grass, honey, etc. Hence, three mathematical steps are modeled and considered in the GBFIO algorithm to solve the optimization problem: (1) finding food sources (e.g., vegetables, fruits, honey, oysters), based on past experiences and olfactory cues; (2) hunting animals and protecting offspring from predators; and (3) fishing. Thirty-one standard benchmark functions and thirty CEC2017 test benchmark functions are applied to evaluate the performance of the GBFIO, such as unimodal, multimodal of high dimensional, fixed dimensional multimodal, and also the rotated and shifted benchmark functions. In addition, four constrained engineering design problems such as tension/compression spring design, welded beam design, pressure vessel design, and speed reducer design problems have been considered to show the efficiency of the proposed GBFIO algorithm in solving constrained problems. The GBFIO can successfully solve diverse kinds of optimization problems, as shown in the results of optimization of objective functions, especially in high dimension objective functions in comparison to other algorithms. Additionally, the performance of the GBFIO algorithm has been compared with the ability and efficiency of other popular optimization algorithms in finding the solutions. In comparison to other optimization algorithms, the GBFIO algorithm offers yields superior or competitive quasi-optimal solutions relative to other well-known optimization algorithms.
本文介绍了一种新颖的受自然启发的优化算法，称为灰熊脂肪增加优化器（GBFIO）。GBFIO算法模仿了灰熊在为冬季积累身体脂肪时的自然行为，借鉴了它们狩猎、捕鱼以及吃草、蜂蜜等的策略。因此，GBFIO算法中建模并考虑了三个数学步骤来解决优化问题：（1）根据过去的经验和嗅觉线索寻找食物来源（如蔬菜、水果、蜂蜜、牡蛎）；（2）猎杀动物并保护后代免受捕食者侵害；（3）捕鱼。应用31个标准基准函数和30个CEC2017测试基准函数来评估GBFIO的性能，如单峰、高维多峰、固定维多峰以及旋转和平移基准函数。此外，还考虑了四个约束工程设计问题，如拉伸/压缩弹簧设计、焊接梁设计、压力容器设计和减速器设计问题，以展示所提出的GBFIO算法在解决约束问题方面的效率。GBFIO能够成功解决各种优化问题，如目标函数优化结果所示，特别是在高维目标函数方面与其他算法相比。此外，还将GBFIO算法的性能与其他流行优化算法在寻找解决方案时的能力和效率进行了比较。与其他优化算法相比，GBFIO算法相对于其他知名优化算法能提供更优或具有竞争力的准最优解。
