scholarly journals Retraction Note to: Coastline geological parameters and beach motion image simulation based on particle swarm optimization

2021 ◽  
Vol 14 (24) ◽  
Author(s):  
Lihua Zou
Mathematics ◽  
2021 ◽  
Vol 9 (18) ◽  
pp. 2236
Author(s):  
Hsien-Pin Hsu ◽  
Chia-Nan Wang ◽  
Hsin-Pin Fu ◽  
Thanh-Tuan Dang

The joint scheduling of quay cranes (QCs), yard cranes (YCs), and yard trucks (YTs) is critical to achieving good overall performance for a container terminal. However, there are only a few such integrated studies. Especially, those who have taken the vessel stowage plan (VSP) into consideration are very rare. The VSP is a plan assigning each container a stowage position in a vessel. It affects the QC operations directly and considerably. Neglecting this plan will cause problems when loading/unloading containers into/from a ship or even congest the YT and YC operations in the upstream. In this research, a framework of simulation-based optimization methods have been proposed firstly. Then, four kinds of heuristics/metaheuristics has been employed in this framework, such as sort-by-bay (SBB), genetic algorithm (GA), particle swarm optimization (PSO), and multiple groups particle swarm optimization (MGPSO), to deal with the yard crane scheduling problem (YCSP), yard truck scheduling problem (YTSP), and quay crane scheduling problem (QCSP) simultaneously for export containers, taking operational constraints into consideration. The objective aims to minimize makespan. Each of the simulation-based optimization methods includes three components, load-balancing heuristic, sequencing method, and simulation model. Experiments have been conducted to investigate the effectiveness of different simulation-based optimization methods. The results show that the MGPSO outperforms the others.


2014 ◽  
Vol 599-601 ◽  
pp. 807-813
Author(s):  
Zhi Xun Zhang ◽  
Juan Wang ◽  
Yong Dong Wang

Existing Adaboost methods for face detection based on particle swarm optimization (PSO) do not consider that PSO suffers from easily trapping in local optimum and slow convergence speed. This paper presents an improved Adaboost method for face detection to solve this problem. In this method, self-adaptive escape PSO (AEPSO) is introduced into conventional Adaboost face detection, meanwhile, Haar-Like rectangular features are represented by particles, so that features selection and classifiers construction could be resolved by using AEPSO. Results of simulation based on Matlab indicate the improved method obtains better detection performance.


Sign in / Sign up

Export Citation Format

Share Document