C. Tamilselvi, M. Yeasin, R. Paul, Amrit Kumar Paul
Denoising is an integral part of the data pre-processing pipeline that often works in conjunction with model development for enhancing the quality of data, improving model accuracy, preventing overfitting, and contributing to the overall robustness of predictive models. Algorithms based on a combination of wavelet with deep learning, machine learning, and stochastic model have been proposed. The denoised series are fitted with various benchmark models, including long short-term memory (LSTM), support vector regression (SVR), artificial neural network (ANN), and autoregressive integrated moving average (ARIMA) models. The effectiveness of a wavelet-based denoising approach was investigated on monthly wholesale price data for three major spices (turmeric, coriander, and cumin) for various markets in India. The predictive performance of these models is assessed using root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The wavelet LSTM model with Haar filter at level 6 emerged as a robust choice for accurate price predictions across all spices. It was found that the wavelet LSTM model had a significant gain in accuracy than the LSTM model by more than 30% across all accuracy metrics. The results clearly highlighted the efficacy of a wavelet-based denoising approach in enhancing the accuracy of price forecasting.
{"title":"Can Denoising Enhance Prediction Accuracy of Learning Models? A Case of Wavelet Decomposition Approach","authors":"C. Tamilselvi, M. Yeasin, R. Paul, Amrit Kumar Paul","doi":"10.3390/forecast6010005","DOIUrl":"https://doi.org/10.3390/forecast6010005","url":null,"abstract":"Denoising is an integral part of the data pre-processing pipeline that often works in conjunction with model development for enhancing the quality of data, improving model accuracy, preventing overfitting, and contributing to the overall robustness of predictive models. Algorithms based on a combination of wavelet with deep learning, machine learning, and stochastic model have been proposed. The denoised series are fitted with various benchmark models, including long short-term memory (LSTM), support vector regression (SVR), artificial neural network (ANN), and autoregressive integrated moving average (ARIMA) models. The effectiveness of a wavelet-based denoising approach was investigated on monthly wholesale price data for three major spices (turmeric, coriander, and cumin) for various markets in India. The predictive performance of these models is assessed using root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The wavelet LSTM model with Haar filter at level 6 emerged as a robust choice for accurate price predictions across all spices. It was found that the wavelet LSTM model had a significant gain in accuracy than the LSTM model by more than 30% across all accuracy metrics. The results clearly highlighted the efficacy of a wavelet-based denoising approach in enhancing the accuracy of price forecasting.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":" 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139619437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aymane Ahajjam, Jaakko Putkonen, Emmanuel Chukwuemeka, Robert Chance, T. Pasch
Local weather forecasts in the Arctic outside of settlements are challenging due to the dearth of ground-level observation stations and high computational costs. During winter, these forecasts are critical to help prepare for potentially hazardous weather conditions, while in spring, these forecasts may be used to determine flood risk during annual snow melt. To this end, a hybrid VMD-WT-InceptionTime model is proposed for multi-horizon multivariate forecasting of remote-region temperatures in Alaska over short-term horizons (the next seven days). First, the Spearman correlation coefficient is employed to analyze the relationship between each input variable and the forecast target temperature. The most output-correlated input sequences are decomposed using variational mode decomposition (VMD) and, ultimately, wavelet transform (WT) to extract time-frequency patterns intrinsic in the raw inputs. The resulting sequences are fed into a deep InceptionTime model for short-term forecasting. This hybrid technique has been developed and evaluated using 35+ years of data from three locations in Alaska. Different experiments and performance benchmarks are conducted using deep learning models (e.g., Time Series Transformers, LSTM, MiniRocket), and statistical and conventional machine learning baselines (e.g., GBDT, SVR, ARIMA). All forecasting performances are assessed using four metrics: the root mean squared error, the mean absolute percentage error, the coefficient of determination, and the mean directional accuracy. Superior forecasting performance is achieved consistently using the proposed hybrid technique.
{"title":"Predictive Analytics of Air Temperature in Alaskan Permafrost Terrain Leveraging Two-Level Signal Decomposition and Deep Learning","authors":"Aymane Ahajjam, Jaakko Putkonen, Emmanuel Chukwuemeka, Robert Chance, T. Pasch","doi":"10.3390/forecast6010004","DOIUrl":"https://doi.org/10.3390/forecast6010004","url":null,"abstract":"Local weather forecasts in the Arctic outside of settlements are challenging due to the dearth of ground-level observation stations and high computational costs. During winter, these forecasts are critical to help prepare for potentially hazardous weather conditions, while in spring, these forecasts may be used to determine flood risk during annual snow melt. To this end, a hybrid VMD-WT-InceptionTime model is proposed for multi-horizon multivariate forecasting of remote-region temperatures in Alaska over short-term horizons (the next seven days). First, the Spearman correlation coefficient is employed to analyze the relationship between each input variable and the forecast target temperature. The most output-correlated input sequences are decomposed using variational mode decomposition (VMD) and, ultimately, wavelet transform (WT) to extract time-frequency patterns intrinsic in the raw inputs. The resulting sequences are fed into a deep InceptionTime model for short-term forecasting. This hybrid technique has been developed and evaluated using 35+ years of data from three locations in Alaska. Different experiments and performance benchmarks are conducted using deep learning models (e.g., Time Series Transformers, LSTM, MiniRocket), and statistical and conventional machine learning baselines (e.g., GBDT, SVR, ARIMA). All forecasting performances are assessed using four metrics: the root mean squared error, the mean absolute percentage error, the coefficient of determination, and the mean directional accuracy. Superior forecasting performance is achieved consistently using the proposed hybrid technique.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"94 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139444526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daily data on COVID-19 infections and deaths tend to possess weekly oscillations. The purpose of this work is to forecast COVID-19 data with partially cyclical fluctuations. A partially periodic oscillating ARIMA model is suggested to enhance the predictive performance. The model, optimized for improved prediction, characterizes and forecasts COVID-19 time series data marked by weekly oscillations. Parameter estimation and out-of-sample forecasting are carried out with data on daily COVID-19 infections and deaths between January 2021 and October 2022 in the USA, Germany, and Brazil, in which the COVID-19 data exhibit the strongest weekly cycle behaviors. Prediction accuracy measures, such as RMSE, MAE, and HMAE, are evaluated, and 95% prediction intervals are constructed. It was found that predictions of daily COVID-19 data can be improved considerably: a maximum of 55–65% in RMSE, 58–70% in MAE, and 46–60% in HMAE, compared to the existing models. This study provides a useful predictive model for the COVID-19 pandemic, and can help institutions manage their healthcare systems with more accurate statistical information.
{"title":"Improvement on Forecasting of Propagation of the COVID-19 Pandemic through Combining Oscillations in ARIMA Models","authors":"Eunju Hwang","doi":"10.3390/forecast6010002","DOIUrl":"https://doi.org/10.3390/forecast6010002","url":null,"abstract":"Daily data on COVID-19 infections and deaths tend to possess weekly oscillations. The purpose of this work is to forecast COVID-19 data with partially cyclical fluctuations. A partially periodic oscillating ARIMA model is suggested to enhance the predictive performance. The model, optimized for improved prediction, characterizes and forecasts COVID-19 time series data marked by weekly oscillations. Parameter estimation and out-of-sample forecasting are carried out with data on daily COVID-19 infections and deaths between January 2021 and October 2022 in the USA, Germany, and Brazil, in which the COVID-19 data exhibit the strongest weekly cycle behaviors. Prediction accuracy measures, such as RMSE, MAE, and HMAE, are evaluated, and 95% prediction intervals are constructed. It was found that predictions of daily COVID-19 data can be improved considerably: a maximum of 55–65% in RMSE, 58–70% in MAE, and 46–60% in HMAE, compared to the existing models. This study provides a useful predictive model for the COVID-19 pandemic, and can help institutions manage their healthcare systems with more accurate statistical information.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"21 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139155297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Southeast Asia (SEA), known for its diverse climate and broad coastal regions, is particularly vulnerable to the effects of climate change. The purpose of this study is to enhance the spatial resolution of temperature projections over Southeast Asia (SEA) by employing three machine learning methods: Random Forest (RF), Gradient Boosting Machine (GBM), and Decision Tree (DT). Preliminary analyses of raw General Circulation Model (GCM) data between the years 1990 and 2014 have shown an underestimation of temperatures, which is mostly due to the insufficient amount of precision in its spatial resolution. Our findings show that the RF method has a significant concordance with high-resolution observational data, as evidenced by a low mean squared error (MSE) value of 2.78 and a high Pearson correlation coefficient of 0.94. The GBM method, while effective, had a broader range of predictions, indicated by a mean squared error (MSE) score of 5.90. The Decision Tree (DT) method performed the best, with the lowest mean squared error (MSE) value of 2.43, which closely matched the actual data. The first General Circulation Model (GCM) data, on the other hand, exhibited significant forecast errors, as evidenced by a mean squared error (MSE) value of 7.84. The promise of machine learning methods, notably the Random Forest (RF) and Decision Tree (DT) algorithms, in improving temperature predictions for the Southeast Asian region is highlighted in the present study.
{"title":"Advancements in Downscaling Global Climate Model Temperature Data in Southeast Asia: A Machine Learning Approach","authors":"Teerachai Amnuaylojaroen","doi":"10.3390/forecast6010001","DOIUrl":"https://doi.org/10.3390/forecast6010001","url":null,"abstract":"Southeast Asia (SEA), known for its diverse climate and broad coastal regions, is particularly vulnerable to the effects of climate change. The purpose of this study is to enhance the spatial resolution of temperature projections over Southeast Asia (SEA) by employing three machine learning methods: Random Forest (RF), Gradient Boosting Machine (GBM), and Decision Tree (DT). Preliminary analyses of raw General Circulation Model (GCM) data between the years 1990 and 2014 have shown an underestimation of temperatures, which is mostly due to the insufficient amount of precision in its spatial resolution. Our findings show that the RF method has a significant concordance with high-resolution observational data, as evidenced by a low mean squared error (MSE) value of 2.78 and a high Pearson correlation coefficient of 0.94. The GBM method, while effective, had a broader range of predictions, indicated by a mean squared error (MSE) score of 5.90. The Decision Tree (DT) method performed the best, with the lowest mean squared error (MSE) value of 2.43, which closely matched the actual data. The first General Circulation Model (GCM) data, on the other hand, exhibited significant forecast errors, as evidenced by a mean squared error (MSE) value of 7.84. The promise of machine learning methods, notably the Random Forest (RF) and Decision Tree (DT) algorithms, in improving temperature predictions for the Southeast Asian region is highlighted in the present study.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"75 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139169242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Amirhossein Sohrabbeig, Omid Ardakanian, Petr Musilek
Over the past few years, there has been growing attention to the Long-Term Time Series Forecasting task and solving its inherent challenges like the non-stationarity of the underlying distribution. Notably, most successful models in this area use decomposition during preprocessing. Yet, much of the recent research has focused on intricate forecasting techniques, often overlooking the critical role of decomposition, which we believe can significantly enhance the performance. Another overlooked aspect is the presence of multiseasonal components in many time series datasets. This study introduced a novel forecasting model that prioritizes multiseasonal trend decomposition, followed by a simple, yet effective forecasting approach. We submit that the right decomposition is paramount. The experimental results from both real-world and synthetic data underscore the efficacy of the proposed model, Decompose&Conquer, for all benchmarks with a great margin, around a 30–50% improvement in the error.
{"title":"Decompose and Conquer: Time Series Forecasting with Multiseasonal Trend Decomposition Using Loess","authors":"Amirhossein Sohrabbeig, Omid Ardakanian, Petr Musilek","doi":"10.3390/forecast5040037","DOIUrl":"https://doi.org/10.3390/forecast5040037","url":null,"abstract":"Over the past few years, there has been growing attention to the Long-Term Time Series Forecasting task and solving its inherent challenges like the non-stationarity of the underlying distribution. Notably, most successful models in this area use decomposition during preprocessing. Yet, much of the recent research has focused on intricate forecasting techniques, often overlooking the critical role of decomposition, which we believe can significantly enhance the performance. Another overlooked aspect is the presence of multiseasonal components in many time series datasets. This study introduced a novel forecasting model that prioritizes multiseasonal trend decomposition, followed by a simple, yet effective forecasting approach. We submit that the right decomposition is paramount. The experimental results from both real-world and synthetic data underscore the efficacy of the proposed model, Decompose&Conquer, for all benchmarks with a great margin, around a 30–50% improvement in the error.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"274 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139183066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dimitrios K. Nasiopoulos, Dimitrios A. Arvanitidis, Dimitrios M. Mastrakoulis, N. Kanellos, Thomas Fotiadis, Dimitrios E. Koulouriotis
Globalization has gotten increasingly intense in recent years, necessitating accurate forecasting. Traditional supply chains have evolved into transnational networks that grow with time, becoming more vulnerable. These dangers have the potential to disrupt the flow of goods or several planned actions. For this reason, increased resilience against various types of risks that threaten the viability of an organization is of major importance. One of the ways to determine the magnitude of the risk an organization runs is to measure how popular it is with the buying public. Although risk is impossible to eliminate, effective forecasting and supply chain risk management can help businesses identify, assess, and reduce it. As a result, good supply chain risk management, including forecasting, is critical for every company. To measure the popularity of an organization, there are some discrete values (bounce rate, global ranking, organic traffic, non-branded traffic, branded traffic), known as KPIs. Below are some hypotheses that affect these values and a model for the way in which these values interact with each other. As a result of the research, it is clear how important it is for an organization to increase its popularity, to increase promotion in the shareholder community, and to be in a position to be able to predict its future requirements.
{"title":"Exploring the Role of Online Courses in COVID-19 Crisis Management in the Supply Chain Sector—Forecasting Using Fuzzy Cognitive Map (FCM) Models","authors":"Dimitrios K. Nasiopoulos, Dimitrios A. Arvanitidis, Dimitrios M. Mastrakoulis, N. Kanellos, Thomas Fotiadis, Dimitrios E. Koulouriotis","doi":"10.3390/forecast5040035","DOIUrl":"https://doi.org/10.3390/forecast5040035","url":null,"abstract":"Globalization has gotten increasingly intense in recent years, necessitating accurate forecasting. Traditional supply chains have evolved into transnational networks that grow with time, becoming more vulnerable. These dangers have the potential to disrupt the flow of goods or several planned actions. For this reason, increased resilience against various types of risks that threaten the viability of an organization is of major importance. One of the ways to determine the magnitude of the risk an organization runs is to measure how popular it is with the buying public. Although risk is impossible to eliminate, effective forecasting and supply chain risk management can help businesses identify, assess, and reduce it. As a result, good supply chain risk management, including forecasting, is critical for every company. To measure the popularity of an organization, there are some discrete values (bounce rate, global ranking, organic traffic, non-branded traffic, branded traffic), known as KPIs. Below are some hypotheses that affect these values and a model for the way in which these values interact with each other. As a result of the research, it is clear how important it is for an organization to increase its popularity, to increase promotion in the shareholder community, and to be in a position to be able to predict its future requirements.","PeriodicalId":508737,"journal":{"name":"Forecasting","volume":"16 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139259657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：