View in EDS

Enhanced backpropagation neural network accuracy through an improved genetic algorithm for tourist flow prediction in an ecological village.

Saved in:
Bibliographic Details
Title: Enhanced backpropagation neural network accuracy through an improved genetic algorithm for tourist flow prediction in an ecological village.
Authors: Chen X; Faculty of Humanities and Social Sciences, Macao Polytechnic University, Macao, 999078, China., Wong CUI; Faculty of Humanities and Social Sciences, Macao Polytechnic University, Macao, 999078, China., Zhang H; Faculty of Humanities and Social Sciences, Macao Polytechnic University, Macao, 999078, China. hfengzhang@mpu.edu.mo., Song Z; Faculty of Humanities and Social Sciences, Macao Polytechnic University, Macao, 999078, China.
Source: Scientific reports [Sci Rep] 2025 Oct 15; Vol. 15 (1), pp. 36087. Date of Electronic Publication: 2025 Oct 15.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
Imprint Name(s): Original Publication: London : Nature Publishing Group, copyright 2011-
MeSH Terms: Neural Networks, Computer* , Algorithms* , Tourism*, Humans ; Genetic Algorithms
Abstract: Competing Interests: Declarations. Competing interests: The authors declare no competing interests.
Extant tourism studies on predicting tourist flow often adopt Backpropagation Neural Network (BP-NN) and Genetic Algorithm-Backpropagation Neural Network (GABP-NN). However, those models cannot well address the challenge of nonlinear complexity of tourists' mobility, and fuzzy decision-making due to abrupt urgencies and foul weather. The current study proposes "Adaptive Multi-population Genetic Algorithm Backpropagation (AMGA-BP)", which features a novel double-layer ladder-structured chromosome design for simultaneous optimization of network structure and weights. Experimental results demonstrate the AMGA-BP model achieves superior performance with a Mean Absolute Percentage Error (MAPE) of 5.32% and coefficient of determination (r²) of 0.9869, significantly outperforming traditional BP (25.22% MAPE) and GA-BP (13.61% MAPE) models. The model maintains robust accuracy during peak seasons (6.00% MAPE) and adverse weather conditions (5.50% MAPE), while also surpassing LSTM (8.20% MAPE) and Random Forest (9.80% MAPE) approaches. This advancement provides tourism managers with more reliable tools for visitor flow prediction, particularly in ecological sensitive areas like Banliang Ancient Village, contributing to sustainable tourism development and effective resource management.
(© 2025. The Author(s).)
References: Math Biosci Eng. 2022 May 24;19(8):7669-7686. (PMID: 35801440)
Neural Netw. 2013 Aug;44:101-6. (PMID: 23587719)
Ann Oper Res. 2021 Apr 21;:1-28. (PMID: 33897083)
Chemosphere. 2023 Aug;331:138764. (PMID: 37094720)
Neural Netw. 2021 Jun;138:14-32. (PMID: 33611065)
Comput Intell Neurosci. 2022 Jun 2;2022:3726696. (PMID: 35694569)
Adv Biomed Res. 2025 May 31;14:47. (PMID: 40519575)
Grant Information: RP/FCHS-02/2025 Macao Polytechnic University; RP/FCHS-02/2025 Macao Polytechnic University; RP/FCHS-02/2025 Macao Polytechnic University; RP/FCHS-02/2025 Macao Polytechnic University
Contributed Indexing: Keywords: Adaptive optimization; BP neural network; Ecological scenic area; Genetic algorithm; Nonlinear forecasting; Ourist flow prediction
Entry Date(s): Date Created: 20251015 Date Completed: 20251015 Latest Revision: 20251019
Update Code: 20251019
PubMed Central ID: PMC12528398
DOI: 10.1038/s41598-025-20007-8
PMID: 41093987
Database: MEDLINE
Description
Abstract:Competing Interests: Declarations. Competing interests: The authors declare no competing interests.<br />Extant tourism studies on predicting tourist flow often adopt Backpropagation Neural Network (BP-NN) and Genetic Algorithm-Backpropagation Neural Network (GABP-NN). However, those models cannot well address the challenge of nonlinear complexity of tourists' mobility, and fuzzy decision-making due to abrupt urgencies and foul weather. The current study proposes "Adaptive Multi-population Genetic Algorithm Backpropagation (AMGA-BP)", which features a novel double-layer ladder-structured chromosome design for simultaneous optimization of network structure and weights. Experimental results demonstrate the AMGA-BP model achieves superior performance with a Mean Absolute Percentage Error (MAPE) of 5.32% and coefficient of determination (r²) of 0.9869, significantly outperforming traditional BP (25.22% MAPE) and GA-BP (13.61% MAPE) models. The model maintains robust accuracy during peak seasons (6.00% MAPE) and adverse weather conditions (5.50% MAPE), while also surpassing LSTM (8.20% MAPE) and Random Forest (9.80% MAPE) approaches. This advancement provides tourism managers with more reliable tools for visitor flow prediction, particularly in ecological sensitive areas like Banliang Ancient Village, contributing to sustainable tourism development and effective resource management.<br /> (© 2025. The Author(s).)
ISSN:2045-2322
DOI:10.1038/s41598-025-20007-8