PDF(Pubmed)
Abstract：
China is a major player in the marine fish trade. The price prediction of marine fish is of great significance to socio-economic development and the fisheries industry. However, due to the complexity and uncertainty of the marine fish market, traditional forecasting methods often struggle to accurately predict price fluctuations. Therefore, this study adopts an intelligent combination model to enhance the accuracy of food product price prediction. Firstly, three decomposition methods, namely empirical wavelet transform, singular spectrum analysis, and variational mode decomposition, are applied to decompose complex original price series. Secondly, a combination of bidirectional long short-term memory artificial neural network, extreme learning machine, and exponential smoothing prediction methods are applied to the decomposed results for cross-prediction. Subsequently, the predicted results are input into the PSO-CS intelligence algorithm for weight allocation and to generate combined prediction results. Empirical analysis is conducted using data illustrating the daily sea purchase price of larimichthys crocea in Ningde City, Fujian Province, China. The combination prediction accuracy with PSO-CS weight allocation is found to be higher than that of single model predictions, yielding superior results. With the implementation of weight allocation intelligent combinatorial modelling, the prediction of marine fish prices demonstrates higher accuracy and stability, enabling better adaptation to market changes and price fluctuations.
摘要：
中国是海洋鱼类贸易的主要参与者。海洋鱼类的价格预测对社会经济发展和渔业产业具有重要意义。然而,由于海洋鱼类市场的复杂性和不确定性，传统的预测方法往往难以准确预测价格波动。因此,本研究采用智能组合模型来提高食品价格预测的准确性。首先,三种分解方法，即经验小波变换，奇异谱分析,和变分模式分解，适用于分解复杂的原始价格序列。其次,双向长短期记忆人工神经网络的组合，极限学习机，和指数平滑预测方法应用于分解结果进行交叉预测。随后，将预测结果输入到PSO-CS智能算法中进行权重分配,生成组合预测结果。利用宁德市大黄鱼每日海购价格的数据进行了实证分析，福建省,中国。PSO-CS权重分配的组合预测精度高于单模型预测，产生优越的结果。随着权重分配智能组合建模的实现，海鱼价格预测显示出更高的准确性和稳定性，能够更好地适应市场变化和价格波动。
