Review
Agronomy
Feihu Sun, Xianyong Meng, Yan Zhang, Yan Wang, Hongtao Jiang, Pingzeng Liu
Summary: This article discusses the research methods and challenges in agricultural price prediction and identifies future trends, including using combination models for prediction, integrating different types of data for improved accuracy and precision. It is hoped that this article will provide assistance in the development of research in this field.
Article
Economics
Lili Guo, Xinya Huang, Yanjiao Li, Houjian Li
Summary: This paper introduces artificial intelligence methods to evaluate the optimal forecasting strategy for China's crude oil futures price. Using machine learning and considering historical information, volatility, and non-linear features, the study examines the forecasting effects of various models. Results show that the GRU model outperforms other models in terms of forecast accuracy and performance. Additionally, considering multiple influencing factors improves the forecasting accuracy of the proposed models.
Article
Computer Science, Artificial Intelligence
Sourav Kumar Purohit, Sibarama Panigrahi, Prabira Kumar Sethy, Santi Kumari Behera
Summary: Accurate prediction of crop prices is crucial for farmers and government. This study proposes hybrid methods to predict the prices of three commonly used vegetable crops in India, showing superiority over statistical models and machine learning models through extensive statistical analyses.
APPLIED ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Luca Di Persio, Matteo Garbelli, Fatemeh Mottaghi, Kai Wallbaum
Summary: We propose a hybrid method that combines statistical models and Recurrent Neural Networks (RNNs) to compute volatility forecasts for a multi-asset portfolio. The method incorporates the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) approach and RNN architectures (GRU, LSTM, and a mixed model) to achieve accurate and efficient volatility predictions. We also present a simplified version of the Risk Parity method for portfolio allocation, which shows promising results compared to standard risk/return strategies.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Environmental Sciences
Xiang Wang, Yaqi Mao, Yonghui Duan, Yibin Guo
Summary: This paper proposes an innovative hybrid forecasting method for predicting coal price indexes by combining machine learning models, feature selections, data decomposition, and model interpretation. The method achieves high forecasting accuracy and good interpretability, and studies the important indicators affecting coal prices.
FRONTIERS IN ENVIRONMENTAL SCIENCE
(2022)
Article
Economics
Jue Wang, Zhen Wang, Xiang Li, Hao Zhou
Summary: This study utilizes the Artificial Bee Colony Algorithm to achieve satisfactory results in predicting agricultural commodity futures prices. By combining various denoising techniques and forecasting models, diverse forecasting sub-models are generated, leading to three forecast combination strategies: heterogeneous, semi-heterogeneous, and homogeneous combination.
INTERNATIONAL JOURNAL OF FORECASTING
(2022)
Article
Engineering, Civil
Laleh Parviz, Kabir Rasouli, Ali Torabi Haghighi
Summary: This research aims to improve precipitation forecast in semi-arid climates by using an ensemble of linear and nonlinear models. The results show that the proposed hybrid models have a better representation of observations than the traditional hybrid models.
WATER RESOURCES MANAGEMENT
(2023)
Article
Business
Yeming Dai, Xinyu Yang, Mingming Leng
Summary: In this paper, a hybrid power load prediction method is proposed, which consists of three main steps: data decomposition, data processing, and support vector machine prediction. The method is applied to a real dataset from the electricity market in Singapore, and the results are compared with other forecasting methods, demonstrating a high accuracy in power load prediction.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2022)
Article
Computer Science, Artificial Intelligence
Guo-Feng Fan, Ying-Ying Han, Jing-Jing Wang, Hao-Li Jia, Li-Ling Peng, Hsin-Pou Huang, Wei-Chiang Hong
Summary: This article proposes a bidirectional memory feature hybrid model based on a new intelligent optimization method, combining statistical analysis of load and meteorological factors with convolutional neural networks and bidirectional short-term memory neural networks for load forecasting, achieving higher prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Gourav Kumar, Uday Pratap Singh, Sanjeev Jain
Summary: This paper proposes a hybrid evolutionary intelligent system for predicting the future close price of stock market, comparing its forecasting efficiency with other methods, and showing superior accuracy.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Article
Thermodynamics
Shuai Hu, Yue Xiang, Da Huo, Shafqat Jawad, Junyong Liu
Summary: This paper presents a hybrid forecasting method combining PCA and DBN to improve the accuracy of wind power generation forecasting. The proposed improved DBN and wind speed correction model demonstrated an average increase in forecasting accuracy of 15.8975% and 29.3725%, respectively, compared to traditional methods.
Article
Economics
Stavros Degiannakis, George Filis, Tony Klein, Thomas Walther
Summary: The study forecasts the volatility of agricultural commodities using variants of the HAR model and finds that while the extended models perform better in-sample, they do not offer superior predictive ability out-of-sample, indicating that there is no need to include more complexity in forecasting models.
INTERNATIONAL JOURNAL OF FORECASTING
(2022)
Article
Thermodynamics
Ghali Yakoub, Sathyajith Mathew, Joao Leal
Summary: This paper presents short- and medium-term wind power forecasting systems for the Nordic energy market. Multiple numerical weather prediction sources are integrated to predict power at the individual turbine level. Both direct and indirect forecasting approaches are considered and compared, using an automated machine-learning pipeline. The proposed forecasting schemes reduce forecasting errors by 8% to 22% when using inputs from multiple NWP sources, and the wind downscaling model significantly improves accuracy.
Article
Engineering, Electrical & Electronic
Olatunji Ahmed Lawal, Jiashen Teh
Summary: Optimal transmission line rating use is guaranteed with dynamic line rating (DLR), which is a smart grid technology that adjusts line rating based on predicted variations in meteorological conditions. This study compared different DLR forecasting techniques, including ensemble means forecasting, recurrent neural network (RNN), and convolution neural network (CNN), and found that ensemble forecasting is the most reliable and secure method.
ELECTRIC POWER SYSTEMS RESEARCH
(2023)
Article
Automation & Control Systems
Heng Wang, Wei Li, Zhenzhen Zhao, Zhenfeng Wang, Menghan Li, Defeng Li
Summary: With the development of smart cities, the demand for fresh agricultural products has greatly increased. This study establishes models for the speed characteristics of refrigerated vehicles based on road conditions, a penalty cost function based on time windows, and a customer satisfaction evaluation model using fuzzy logic. It also proposes an improved optimization algorithm to minimize distribution costs and maximize customer satisfaction. The results show that the model effectively balances the relationship between distribution costs and customer satisfaction in smart city FAP distribution.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)