Optimization Method of College Students' Entrepreneurial Path Based on Improved Multi-Objective Gray Wolf Algorithm

The traditional entrepreneurial resource decision-making model that relies on empirical decision-making or simple template matching is difficult to adapt to the current complex social environment. Therefore, the multi-objective grey wolf algorithm (MOGWO) is used to solve the Pareto frontier of the...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of cases on information technology Ročník 26; číslo 1; s. 1 - 20
Hlavný autor: Qiu, Baorong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Hershey IGI Global 01.01.2024
Predmet:
Algorithms
College students
Convergence
Decision making
Decision making models
Entrepreneurship
Machine learning
Multiple objective analysis
Objectives
Optimization
Social environment
Template matching
ISSN:1548-7717, 1548-7725
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The traditional entrepreneurial resource decision-making model that relies on empirical decision-making or simple template matching is difficult to adapt to the current complex social environment. Therefore, the multi-objective grey wolf algorithm (MOGWO) is used to solve the Pareto frontier of the problem model, replacing the optimal solution with the optimal solution set, and then selecting the optimal scheduling plan according to the actual situation, so as to make the decision-making plan more scientific and reasonable. In order to optimize this algorithm, two improvement strategies are proposed on the basis of analysing the movement of individual grey wolves. The research in this paper provides an important reference for the machine learning algorithm and the improved multi-objective grey wolf algorithm. The experimental results show that the MOGWO algorithm can overcome the shortcomings of the basic grey wolf algorithm (GWO) in terms of insufficient exploratory ability and local convergence, and has higher search efficiency, better optimality finding ability and stability.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1548-7717
1548-7725
DOI:10.4018/JCIT.349738