Article
Environmental Sciences
Dehe Xu, Qi Zhang, Yan Ding, De Zhang
Summary: Drought forecasting is crucial for risk reduction, and a hybrid model combining ARIMA and LSTM models has been shown to improve short-term prediction accuracy in China. Among the three hybrid models tested, ARIMA-LSTM showed the highest accuracy for long-term drought forecasting in China.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Mathematics
Lihki Rubio, Keyla Alba
Summary: This paper proposes a hybrid model combining ARIMA and support vector regression (SVR) models to forecast the daily and cumulative returns of selected Colombian companies traded on the New York Stock Exchange (NYSE).
Article
Mathematics
Shiwei Su
Summary: In recent years, the interconnectedness of global financial markets has led to stronger correlations between financial assets, faster information transmission, and an increased risk of systemic risk. This paper integrates the linear and nonlinear components of financial markets using the ARIMA and SVR models for forecasting, with the combined ARIMA-SVR model showing better forecast accuracy compared to single models.
JOURNAL OF MATHEMATICS
(2021)
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
Lucas Rabelo de Araujo Morais, Gecynalda Soares da Silva Gomes
Summary: The study aims to capture the linear and non-linear structures of daily Covid-19 cases worldwide using a hybrid forecasting model. The proposed methodology consists of analyzing the linear part using an ARIMA model and modeling the non-linear part using a neural network model. The combination of models with the capture of weekly seasonality shows good error metrics within two weeks.
APPLIED SOFT COMPUTING
(2022)
Article
Economics
Tanujit Chakraborty, Ashis Kumar Chakraborty, Munmun Biswas, Sayak Banerjee, Shramana Bhattacharya
Summary: This paper proposes an integrated approach based on linear and nonlinear models for unemployment rate prediction, which can accurately reflect the asymmetry of unemployment rates and outperform conventional methods. The results of applying the hybrid model to various countries' unemployment rate data sets demonstrate its effectiveness and superiority in forecasting unemployment rates accurately.
COMPUTATIONAL ECONOMICS
(2021)
Article
Multidisciplinary Sciences
Amit Saha, K. N. Singh, Mrinmoy Ray, Santosha Rathod, Sharani Choudhury
Summary: In this study, the tuned-support vector regression (Tuned-SVR) model was used to model and forecast cotton production in India, and it outperformed auto regressive integrated moving average and classical SVR models in both modeling and forecasting.
Article
Mathematics
Yongchao Jin, Renfang Wang, Xiaodie Zhuang, Kenan Wang, Honglian Wang, Chenxi Wang, Xiyin Wang
Summary: This study used an ARIMA-LSTM combined model to analyze the spread of COVID-19, proposed a new method of parallel model, and predicted a steady decline in the epidemic situation in China in the next 60 days with high accuracy.
Article
Multidisciplinary Sciences
Paulo S. G. de Mattos Neto, George D. C. Cavalcanti, Domingos S. de O. Santos, Eraylson G. Silva
Summary: The sea surface temperature (SST) is an important indicator for predicting climate, weather, and atmospheric events. Single machine learning models are generally more accurate than traditional statistical models for SST time series modeling. This study proposes using hybrid systems to improve SST forecasting performance and provides experimental evidence of their effectiveness.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Interdisciplinary Applications
Liang Guo, Weiguo Fang, Qiuhong Zhao, Xu Wang
Summary: Demand forecasting is crucial in supply chain management and involves seasonality; this study combines Prophet and SVR models to improve accuracy in predicting manufacturing time series demands.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Transportation Science & Technology
V. Rajalakshmi, S. Ganesh Vaidyanathan
Summary: Traffic flow forecast is critical for constructing traffic plans and reducing congestion on roadways. This research uses time-series forecasting models to estimate future traffic but minimizing prediction error is challenging. Hybrid ARIMA-MLP and ARIMA-RNN models are proposed to anticipate future traffic flow using real-time data from vehicles and roadways, using UK Highways dataset for validation.
PROMET-TRAFFIC & TRANSPORTATION
(2022)
Article
Energy & Fuels
T. Gonzalez Grandon, J. Schwenzer, T. Steens, J. Breuing
Summary: This article presents a novel hybrid approach using classic statistics and machine learning to forecast the national demand of electricity. The proposed methodology combines multiple regression models and a LSTM hybrid model to accurately predict long-term electricity consumption.
Article
Computer Science, Artificial Intelligence
Li Jiang-ning, Shi Xian-liang, Huang An-qiang, He Ze-fang, Kang Yu-xuan, Li Dong
Summary: Accurate prediction is essential for emergency medicine reserve management. This paper proposes a new forecasting model, the EMD-ELMAN-ARIMA (ELA) model, which utilizes empirical mode decomposition to identify components of observed data, and employs Elman neural network and ARIMA models to forecast these components. The results of an empirical study on influenza data from Beijing demonstrate the superiority of the ELA algorithm over traditional ARIMA and Elman models.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Green & Sustainable Science & Technology
Fabio Di Nunno, Francesco Granata, Quoc Bao Pham, Giovanni de Marinis
Summary: This study shows that reliable models for precipitation prediction can be developed using a machine learning approach. A hybrid model based on M5P and support vector regression algorithms achieved the best predictions in this study, with high R-2 values for the stations of Rangpur and Sylhet.
Article
Management
Siddharth Arora, James W. Taylor, Ho-Yin Mak
Summary: This study focuses on estimating the probability distribution of individual patient waiting times in an emergency department using a machine learning approach. The proposed method provides more accurate probabilistic forecasts compared to existing methods that only focus on point forecasts. This can improve overall patient satisfaction and prevent patient abandonment.
M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT
(2023)