The Need for Bees: Colony Prediction and Analysis based on ARIMA and Entropy Weight -TOPSIS
DOI:
https://doi.org/10.54097/hset.v35i.7045Keywords:
ARIMA; Entropy Weight -TOPSIS; Pearson Correlation Coefficient; BP Dynamic Neural Network; Sensitivity Analysis.Abstract
In this paper, firstly, the ARIMA time-series differential autoregression algorithm was used to establish the change model of the number of bee colonies, and then the entropy weight method TOPSIS and Pearson correlation matrix were fused to analyze the index sensitivity. Finally, the prediction model of the number of bee colonies was established based on BP dynamic neural network, to complete the prediction and index analysis of bee colonies. Finally, we will discuss the findings from mathematical modeling of the blog summary writing, which show that the colony's optimal temperature, climate, feed supply, and other environmental conditions have a significant impact on the rate of soft production.
Downloads
References
Baoyu, Tian, Nibal H, et al. Long-term exposure to antibiotics has caused accumulation of resistance determinants in the gut microbiota of honeybees. [J]. mBio, 2012.
Period, T. F. "Experimental Wing Damage Affects Foraging Effort and Foraging Distance in Honeybees." (2011).
Yan X, Han R C. Diagnostic technologies of common pathogens of honeybees in China[J]. Chinese Bulletin of Entomology, 2008, 45(3):483-488.
Xiang-Jun L I. Time Series Models for Portfolio[J]. Journal of Wenzhou Teachers College, 2003.
Yang Z B, Zhou R X, Zhang Q, et al. A Portfolio Optimization Model Based on Information Entropy and Fuzzy Time Series[C]// 2013 Sixth International Conference on Business Intelligence and Financial Engineering. 0.
Meng X. Discount-Weighted Bayesian Model Averaging for Portfolio Decisions in Matrix Variate Dynamic Linear Models.
Liu X T. Study on Data Normalization in BP Neural Network[J]. Mechanical Engineering & Automation, 2010.
Huang Y, Meng S, Hwang S W, et al. Neural Network for Classification of Chinese Zither Panel Wood via Near-infrared Spectroscopy[J]. 2020(1).
Li, Q, and Z. Xu. "Parameter Identification Method Research Based on the BP Neural Network and Space Search." 2014 International Conference on Advances in Materials Science and Information Technologies in Industry (AMSITI 2014) 0.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
