TY - JOUR
T1 - Learning–interaction–diversification framework for swarm intelligence optimizers
T2 - a unified perspective
AU - Chu, Xianghua
AU - Wu, Teresa
AU - Weir, Jeffery D.
AU - Shi, Yuhui
AU - Niu, Ben
AU - Li, Li
N1 - Funding Information:
This work was partially supported by the Major Project for National Natural Science Foundation of China (Grant No. 71790615, the design for Decision-making System of National Security Management), the Key Project of National Nature Science Foundation of China (Grant No. 71431006, Decision Support Theory and Platform of the Embedded Service for Environmental Management), the National Natural Science Foundation of China (Grant No. 71501132, 71701079, 71571120, 71371127 and 61273367), the Natural Science Foundation of Guangdong Province (2016A030310067), and the 2016 Tencent “Rhinoceros Birds”—Scientific Research Foundation for Young Teachers of Shenzhen University.
Publisher Copyright:
© 2018, The Natural Computing Applications Forum.
PY - 2020/3/1
Y1 - 2020/3/1
N2 - Due to the efficiency and efficacy in performance to tackle complex optimization problems, swarm intelligence (SI) optimizers, newly emerged as nature-inspired algorithms, have gained great interest from researchers over different fields. A large number of SI optimizers and their extensions have been developed, which drives the need to comprehensively review the characteristics of each algorithm. Hence, a generalized framework laid upon the fundamental principles from which SI optimizers are developed is crucial. This research takes a multidisciplinary view by exploring research motivations from biology, psychology, computing and engineering. A learning–interaction–diversification (LID) framework is proposed where learning is to understand the individual behavior, interaction is to describe the swarm behavior, and diversification is to control the population performance. With the LID framework, 22 state-of-the-art SI algorithms are characterized, and nine representative ones are selected to review in detail. To investigate the relationships between LID properties and algorithmic performance, LID-driven experiments using benchmark functions and real-world problems are conducted. Comparisons and discussions on learning behaviors, interaction relations and diversity control are given. Insights of the LID framework and challenges are also discussed for future research directions.
AB - Due to the efficiency and efficacy in performance to tackle complex optimization problems, swarm intelligence (SI) optimizers, newly emerged as nature-inspired algorithms, have gained great interest from researchers over different fields. A large number of SI optimizers and their extensions have been developed, which drives the need to comprehensively review the characteristics of each algorithm. Hence, a generalized framework laid upon the fundamental principles from which SI optimizers are developed is crucial. This research takes a multidisciplinary view by exploring research motivations from biology, psychology, computing and engineering. A learning–interaction–diversification (LID) framework is proposed where learning is to understand the individual behavior, interaction is to describe the swarm behavior, and diversification is to control the population performance. With the LID framework, 22 state-of-the-art SI algorithms are characterized, and nine representative ones are selected to review in detail. To investigate the relationships between LID properties and algorithmic performance, LID-driven experiments using benchmark functions and real-world problems are conducted. Comparisons and discussions on learning behaviors, interaction relations and diversity control are given. Insights of the LID framework and challenges are also discussed for future research directions.
KW - Evolutionary algorithm
KW - Meta-heuristic algorithm
KW - Nature-inspired algorithm
KW - Swarm intelligence
UR - http://www.scopus.com/inward/record.url?scp=85051676590&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051676590&partnerID=8YFLogxK
U2 - 10.1007/s00521-018-3657-0
DO - 10.1007/s00521-018-3657-0
M3 - Article
AN - SCOPUS:85051676590
VL - 32
SP - 1789
EP - 1809
JO - Neural Computing and Applications
JF - Neural Computing and Applications
SN - 0941-0643
IS - 6
ER -