Search

Wind energy has become a trend in Brazil, particularly in the northeastern region of the country. Despite its advantages, wind power generation has been hindered by the high volatility of exogenous factors, such as weather, temperature, and air humidity, making long-term forecasting a highly challenging task. Another issue is the need for reliable solutions, especially for large-scale wind farms, as this involves integrating specific optimization tools and restricted-access datasets collected locally at the power plants. Therefore, in this paper, the problem of forecasting the energy generated at the Praia Formosa wind farm, an eco-friendly park located in the state of Ceará, Brazil, which produces around 7% of the state's electricity, was addressed. To proceed with our data-driven analysis, publicly available data were collected from multiple Brazilian official sources, combining them into a unified database to perform exploratory data analysis and predictive modeling. Specifically, three machine-learning-based approaches were applied: Extreme Gradient Boosting, Random Forest, and Long Short-Term Memory Network, as well as feature-engineering strategies to enhance the precision of the machine intelligence models, including creating artificial features and tuning the hyperparameters. Our findings revealed that all implemented models successfully captured the energy-generation trends, patterns, and seasonality from the complex wind data. However, it was found that the LSTM-based model consistently outperformed the others, achieving a promising global MAPE of 4.55%, highlighting its accuracy in long-term wind energy forecasting. Temperature, relative humidity, and wind speed were identified as the key factors influencing electricity production, with peak generation typically occurring from August to November. [ABSTRACT FROM AUTHOR]

Forecasting of PM2.5 concentration is a global concern. Evidence has shown that the ambient PM2.5 concentrations are harmful to human health, climate change, plant species mortality, etc. PM2.5 concentrations are caused by natural and anthropogenic activities, and it is challenging to predict them due to many uncertain factors. Current research has focused on developing a new model while overlooking the fact that every single model for PM2.5 prediction has its own strengths and weaknesses. This paper proposes an ensemble framework which combines four diverse learning models for PM2.5 forecasting in Puli, Taiwan. It explores the synergy between parametric and non-parametric learning, and short-term and long-term learning. The feature set covers periodic, meteorological, and autoregression variables which are selected by a spiral validation process. The experimental dataset, spanning from 1 January 2008 to 31 December 2019, from Puli Township in central Taiwan, is used in this study. The experimental results show the proposed multi-model framework can synergize the advantages of the embedded models and obtain an improved forecasting result. Further, the benefit obtained by blending short-term learning with long-term learning is validated, in surpassing the performance obtained by using just single type of learning. Our multi-model framework compares favorably with deep-learning models on Puli dataset. It also shows high adaptivity, such that our multi-model framework is comparable to the leading methods for PM2.5 forecasting in Delhi, India. [ABSTRACT FROM AUTHOR]

The COVID-19 data analysis is essential for policymakers to analyze the outbreak and manage the containment. Many approaches based on traditional time series clustering and forecasting methods, such as hierarchical clustering and exponential smoothing, have been proposed to cluster and forecast the COVID-19 data. However, most of these methods do not scale up with the high volume of cases. Moreover, the interactive nature of the application demands further critically complex yet compelling clustering and forecasting techniques. In this paper, we propose a web-based interactive tool to cluster and forecast the available data of Taiwan COVID-19 confirmed infection cases. We apply the Model-based (MOB) tree and domain-relevant attributes to cluster the dataset and display forecasting results using the Ordinary Least Square (OLS) method. In this OLS model, we apply a model produced by the MOB tree to forecast all series in each cluster. Our user-friendly parametric forecasting method is computationally cheap. A web app based on R's Shiny App makes it easier for practitioners to find clustering and forecasting results while choosing different parameters such as domain-relevant attributes. These results could help in determining the spread pattern and be utilized by medical researchers. [ABSTRACT FROM AUTHOR]

The Taiwanese government altered its corporate social responsibility (CSR) report management policy from voluntary disclosure and assurance of CSR reports to partial mandatory disclosure and partial mandatory assurance. This paper examines this policy's effects on analyst forecast. The empirical results showed that the mandatory disclosure policy on CSR reports significantly increased analyst forecast accuracy and reduced analyst forecast dispersion. Furthermore, the study found that analyst forecast accuracy was further increased when CSR reports were forced to undergo accountant assurance than those without mandatory accountant assurance which means that the mandatory assurance policy on CSR reports significantly further increased analyst forecast accuracy. [ABSTRACT FROM AUTHOR]

In response to relatively little evidence on the determinants of the financial distress in cooperative financial institutions (e.g., Credit Unions), this paper proposes a distress indicator of Merton Distance to default (Merton DD), which was constructed with a z-score, possessed improved predictive capability, but reducing equity volatility. This model possesses the advantages of both hazard and modified Merton DD model, which could timely reflect market volatility and predict when distress would occur. As a demonstration, we applied this model to forecast the financial distress of credit unions in Taiwan. The results can provide more information to researchers. [ABSTRACT FROM AUTHOR]

In recent years, the development and application of artificial intelligence have both been topics of concern. In the medical field, an important direction of medical technology development is the extraction and use of applicable information from existing medical records to provide more accurate and helpful diagnosis suggestions. Therefore, this paper proposes using the development of diseases with easily discernible symptoms to predict the development of other medically related but distinct diseases that lack similar data. The aim of this study is to improve the ease of assessing the development of diseases in which symptoms are difficult to detect, and to improve the utilization of medical data. First, a time series model was used to capture the continuous manifestations of diseases with symptoms that could be easily found at different time intervals. Then, through transfer learning and attention mechanism, the general features captured were applied to the predictive model of the development of diseases with insufficient data and symptoms that are difficult to detect. Finally, we conducted a comprehensive experimental study based on a dataset collected from the National Health Insurance Research Database in Taiwan. The results demonstrate that the effectiveness of our transfer learning approach outperforms state-of-the-art deep learning prediction models for disease course prediction. [ABSTRACT FROM AUTHOR]

Short-term hourly reliable prediction of significant wave height is an important research topic in coastal engineering. Many researchers have carried out in-depth studies in many ocean regions. Generally, most of this work is implemented through numerical models. However, as for numerical models, with the increase of hourly prediction duration, the accumulation of wave randomness leads to the poor prediction effect. In this paper, four buoy stations in the Taiwan Strait are taken as the research objects. We propose a significant wave height prediction algorithm, which combines numerical weather prediction model WRF and deep-learning model, called WRF-CLSF(Convolution-LSTM-FC). WRF can forecast 24-h wind speed in real-time, based on a variety of interpretable physical mechanisms. CLSF aims to extract the information of historical wind-wave interaction scale and the trend of wind-wave coherence, with the help of convolution operation and the time series model(LSTM), respectively. In the experiment, the proposed model was compared with the state-of-the-art prediction model. The results show that WRF-CLSF has an outstanding prediction effect at four buoy observation stations along with the Taiwan Strait. [ABSTRACT FROM AUTHOR]

Education competitiveness is a key feature of national competitiveness. It is crucial for nations to develop and enhance student and teacher potential to increase national competitiveness. The decreasing population of children has caused a series of social problems in many developed countries, directly affecting education and com.petitiveness in an international environment. In Taiwan, a low birthrate has had a large impact on schools at every level because of a substantial decrease in enrollment and a surplus of teachers. Therefore, close attention must be paid to these trends. In this study, combining a whale optimization algorithm (WOA) and support vector regression (WOASVR) was proposed to determine trends of student and teacher numbers in Taiwan for higher accuracy in time-series forecasting analysis. To select the most suitable support vector kernel parameters, WOA was applied. Data collected from the Ministry of Education datasets of student and teacher numbers between 1991 and 2018 were used to examine the proposed method. Analysis revealed that the numbers of students and teachers decreased annually except in private primary schools. A comparison of the forecasting results obtained from WOASVR and other common models indicated that WOASVR provided the lowest mean absolute percentage error (MAPE) and root mean square error (RMSE) for all analyzed datasets. Forecasting performed using the WOASVR method can provide accurate data for use in developing education policies and responses., Competing Interests: The authors declare that there are no conflicts of interest regarding the publication of this paper., (Copyright © 2020 Stephanie Yang et al.)

Short-term load forecast (STLF) plays an important role in power system operations. This paper proposes a spline bases-assisted Recurrent Neural Network (RNN) for STLF with a semi-parametric model being adopted to determine the suitable spline bases for constructing the RNN model. To reduce the exposure to real-time uncertainties, interpolation is achieved by an adapted mean adjustment and exponentially weighted moving average (EWMA) scheme for finer time interval forecast adjustment. To circumvent the effects of forecasted apparent temperature bias, the forecasted temperatures issued by the weather bureau are adjusted using the average of the forecast errors over the preceding 28 days. The proposed RNN model is trained using 15-min interval load data from the Taiwan Power Company (TPC) and has been used by system operators since 2019. Forecast results show that the spline bases-assisted RNN-STLF method accurately predicts the short-term variations in power demand over the studied time period. The proposed real-time short-term load calibration scheme can help accommodate unexpected changes in load patterns and shows great potential for real-time applications. [ABSTRACT FROM AUTHOR]

Dengue and influenza-like illness (ILI) are two of the leading causes of viral infection in the world and it is estimated that more than half the world's population is at risk for developing these infections. It is therefore important to develop accurate methods for forecasting dengue and ILI incidences. Since data from multiple sources (such as dengue and ILI case counts, electronic health records and frequency of multiple internet search terms from Google Trends) can improve forecasts, standard time series analysis methods are inadequate to estimate all the parameter values from the limited amount of data available if we use multiple sources. In this paper, we use a computationally efficient implementation of the known variable selection method that we call the Autoregressive Likelihood Ratio (ARLR) method. This method combines sparse representation of time series data, electronic health records data (for ILI) and Google Trends data to forecast dengue and ILI incidences. This sparse representation method uses an algorithm that maximizes an appropriate likelihood ratio at every step. Using numerical experiments, we demonstrate that our method recovers the underlying sparse model much more accurately than the lasso method. We apply our method to dengue case count data from five countries/states: Brazil, Mexico, Singapore, Taiwan, and Thailand and to ILI case count data from the United States. Numerical experiments show that our method outperforms existing time series forecasting methods in forecasting the dengue and ILI case counts. In particular, our method gives a 18 percent forecast error reduction over a leading method that also uses data from multiple sources. It also performs better than other methods in predicting the peak value of the case count and the peak time., Competing Interests: The authors have declared that no competing interests exist.

Purpose – The purpose of this paper is to propose an occurrence-based model to improve the forecasting of regime switches so as to assist decision making. Design/methodology/approach – This paper proposes a novel model where occurrences of relationships are taken into account when forecasting. Taiwan Stock Exchange Capitalization Weighted Stock Index is taken as the forecasting target. Findings – Due to the consideration of occurrences of relationships in forecasting, the out of sample forecasting is improved. Practical implications – The proposed model can be applied to forecast other time series for regime switches. In addition, it can be integrated with other time series models to improve forecasting performance. Originality/value – The empirical results show that the proposed model can improve the forecasting performance. [ABSTRACT FROM AUTHOR]

Background: The province of Formosa, Argentina, is endemic for leprosy. In the present paper, we assessed the trend (T, 2002–2016 time series) and the forecast for 2022 of new case detection rate (NCDR) and determined the spatial distribution of new cases detected (NCD) of leprosy. Methodology/Principal findings: This is a descriptive observational study of 713 NCD of leprosy from provincial medical records between January 2002 and December 2016. The whole dataset from the provincial medical record was used to independently estimate the NCDR trends of the general population, age groups, sexes and Departments. This same database was used to estimate the NCDR forecast of the general population for 2022, applying a dynamic linear model with a local linear trend, using the MCMC algorithm. The NCDR was higher in men (p<0.05), increased with age (0.20, 8.17, 21.04, and 29.49 for the 0–14, 15–44, 45–64 and over 65-year-old age groups, respectively; p<0.05) and showed a downward trend (negative values) of estimated slopes for the whole province and each Department. Bermejo Department showed the highest (T:-1.02, 95%CI: [-1.42, -0.66]) and Patiño the lowest decreasing trend (T:-0.45, 95%CI: [-0.74, -0.11]). The NCDR trend for both sexes was similar (T:-0.55, 95%CI: [-0.64, -0.46]), and age groups showed a decreasing trend (S15-44:-103, S45-64:-81, S>65:-61, p<0.05), except for the 0–14 age group (S:-3, p>0.05), which showed no trend. Forecasts predicted that leprosy will not be eliminated by 2022 (3.64, 95%CI: [1.22, 10.25]). Conclusions/Significance: Our results highlight the status of leprosy in Formosa and provide information to the provincial public health authorities on high-risk populations, stressing the importance of timely detection of new cases for further elimination of the disease in the province. Author summary: Leprosy, a neglected tropical disease, is a public health problem in northern Argentina, causing permanent damage, stigmatization and discrimination. The Program for the Control of Leishmaniasis and Leprosy in Formosa province (PCLyLF) is responsible for the diagnosis and treatment of the disease and the active search for household contacts. The present study aimed to determine the spatial distribution of new cases of leprosy and the status of the disease using new case detection rate (NCDR) as the main epidemiological indicator. We determined the NCDR trends (2002–2016 time series) of the general population, age groups, sexes and Departments, and the NCDR forecast for the province by 2022. Our results indicated that leprosy was spread throughout Formosa, with higher rates in men and in patients over 65 years old. The NCDR showed a downward trend in the whole province and in each Department. The Departments of Bermejo and Matacos had the highest decreasing trend and the Department of Patiño the lowest one. Future projections show that leprosy will not be eliminated by 2022. [ABSTRACT FROM AUTHOR]

Missing values are common in the Internet of Things (IoT) environment for various reasons, including regular maintenance or malfunction. In time-series prediction in the IoT, missing values may have a relationship with the target labels, and their missing patterns result in informative missingness. Thus, missing values can be a barrier to achieving high accuracy of prediction and analysis in data mining in the IoT. Although several methods have been proposed to estimate values that are missing, few studies have investigated the comparison of interpolation methods using conventional and deep learning models. There has thus far been relatively little research into interpolation methods in the IoT environment. To address these problems, this paper presents the use of linear regression, support vector regression, artificial neural networks, and long short-term memory to make time-series predictions for missing values. Finally, a full comparison and analysis of interpolation methods are presented. We believe that these findings can be of value to future work in IoT applications. [ABSTRACT FROM AUTHOR]

This study develops a novel periodic regime-switching model (the PRS model) to improve the forecasting of stock market volatility by accounting for the information from non-trading and trading periods, including regular trading and after-hour trading. Empirical analysis of the Taiwan Futures Exchange (TAIFEX) demonstrates the significant improvements of the PRS model in both in-sample and out-of-sample periods. Our results also show that the introduction of after-hour trading sessions has provided valuable information for volatility forecasting in subsequent regular trading sessions, emphasizing the importance of considering diverse information flows across different trading and non-trading times. The PRS model effectively captures the dynamics of non-trading and trading sessions and the influence of unusual news arrivals and jumps on market volatility, contributing to investment and risk management strategies. [ABSTRACT FROM AUTHOR]

Daily peak load forecasting is crucial for the operation of bulk power systems, including economic dispatch and unit commitment. It is also essential for peak load shaving and load management in distribution systems. In power markets, peak load forecasting helps participants develop bidding strategies. This paper proposes a new method, using a hybrid convolutional neural network (CNN) that is cascaded with a fully-connected network, for making week-ahead daily peak load forecasts. The proposed method uses three loops to obtain the optimal CNN: The outer loop performs crossover/mutation operations and tournament selection to produce chromosomes to optimize the network topology and hyperparameters (such as kernel size) of the hybrid CNN by genetic algorithms; the middle loop deals with the order of chromosomes; the inner loop optimizes the synaptic weights and parameters (e.g. values of a kernel) using Adam optimizer. Daily peak load data and corresponding meteorological data for Taiwan are explored. Simulation results show that the proposed method outperforms the traditional CNN, multi-layer neural network, recurrent neural network, support vector regression and vector autoregressive moving average model. [ABSTRACT FROM AUTHOR]

Copyright of Taiwan Economic Forecast & Policy is the property of Institute of Economics, Academia Sinica, Taiwan Economic Forecast & Policy and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper investigates the relationship between candidates’ online popularity and election results, as a step towards creating a model to forecast the results of Taiwanese elections even in the absence of reliable opinion polls on a district-by-district level. 253 of 354 legislative candidates of single-member districts in Taiwan’s 2016 general election had active public Facebook pages during the election period. Hypothesizing that the relative popularity of candidates’ Facebook posts will be positively related to their election results, I calculated each candidate’s Like Ratio (i.e. proportions of all likes on Facebook posts obtained by candidates in their district). In order to have a measure of online interest without the influence of subjective positivity, I similarly calculated the proportion of daily average page views for each candidate’s Wikipedia page. I ran a regression analysis, incorporating data on results of previous elections and available opinion poll data. I found the models could describe the result of the election well and reject the null hypothesis. My models successfully predicted 80% of winners in single-member districts and were effective in districts without local opinion polls with a predictive power approaching that of traditional opinion polls. The models also showed good accuracy when run on data for the 2014 Taiwanese municipal mayors election. [ABSTRACT FROM AUTHOR]

Purpose – Because quantile regression gets more popular and provides more comprehensive interpretations, it is important to advance quantile regression for forecasting. By extending the convention quantile regression, the purpose of this paper is to propose a quantile regression-forecasting model to forecast information and communication technology (ICT) development. Design/methodology/approach – This paper proposes an approach to forecasting based on quantile regression method. Findings – Via quantile information criterion, the proposed approach can identify whether the independent variables are predictable. For those which are predictable, the proposed approach can be used to forecast these variables. Practical implications – The proposed approach is used to forecast ICT development. It can also be used to forecast other problem domains. Originality/value – Based on the empirical results, the proposed approach advances the application of quantile regression model to forecast. The applicability of quantile regression model is greatly enhanced. [ABSTRACT FROM AUTHOR]

A hypothesis testing approach, based on the theorem of probability integral transformation and the Kolmogorov–Smirnov one-sample test, for performance evaluation of probabilistic seasonal rainfall forecasts is proposed in this study. By considering the probability distribution of monthly rainfalls, the approach transforms the tercile forecast probabilities into a forecast distribution and tests whether the observed data truly come from the forecast distribution. The proposed approach provides not only a quantitative measure for performance evaluation but also a cumulative probability plot for insightful interpretations of forecast characteristics such as overconfident, underconfident, mean-overestimated, and mean-underestimated. The approach has been applied for the performance evaluation of probabilistic season rainfall forecasts in northern Taiwan, and it was found that the forecast performance is seasonal dependent. Probabilistic seasonal rainfall forecasts of the Meiyu season are likely to be overconfident and mean-underestimated, while forecasts of the winter-to-spring season are overconfident. A relatively good forecast performance is observed for the summer season. [ABSTRACT FROM AUTHOR]

Due to the impact of the COVID-19 pandemic, people have reduced eating out, resulting in a severe drop in the revenue of the catering industry. Health risks have become a major factor affecting the revenue of this industry. Predicting the revenue of the catering industry during the COVID-19 pandemic will not only allow practitioners to adjust their business strategies, but also provide a reference for governments to formulate relief measures. To this end, this study proposes a fuzzy big data analytics approach in which random forests, recursive feature elimination, fuzzy c-means, and deep neural networks are jointly applied. First, random forests and recursive feature elimination are used to select the most influential factors. The data is then divided into clusters by fuzzy c-means. Subsequently, a deep neural network is built for each cluster to make predictions. The prediction results of individual clusters are then aggregated to improve prediction accuracy. The proposed methodology has been applied to forecast the revenue of the catering industry in Taiwan. The results of the experiment showed that the impact of new deaths on the revenue of the catering industry was far greater than the number of newly diagnosed COVID-19 cases. [ABSTRACT FROM AUTHOR]

In this paper, we present a new method to forecast the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) using fuzzy time series and automatically generated weights of multiple factors. The proposed method uses the variation magnitudes of adjacent historical data to generate fuzzy variation groups of the main factor (i.e., the TAIEX) and the elementary secondary factors (i.e., the Dow Jones, the NASDAQ and the M1B), respectively. Based on the variation magnitudes of the main factor TAIEX and the elementary secondary factors of a particular trading day, it constructs the occurrence vector of the main factor and the occurrence vectors of the elementary secondary factors on the trading day, respectively. By calculating the correlation coefficients between the numerical data series of the main factor and the numerical data series of each elementary secondary factor, respectively, it calculates the relevance degree between the forecasted variation of the main factor and the forecasted variation of each elementary secondary factor. Based on the correlation coefficients between the numerical data series of the main factor and the numerical data series of each elementary secondary factor on a trading day, it automatically generates the weights of the occurrence vector of the main factor and the occurrence vector of each elementary secondary factor on the trading day, respectively. Then, it calculates the forecasted variation of the main factor and the forecasted variation of each elementary secondary factor on the trading day, respectively, to obtain the final forecasted variation on the trading day. Finally, based on the closing index of the TAIEX on the trading day and the final forecasted variation on the trading day, it generates the forecasted value of the next trading day. The experimental results show that the proposed method outperforms the existing methods. [ABSTRACT FROM PUBLISHER]

The ultimate goal of an electric utility is to create maximum profit while maintaining reliability and security of the power supply. The operation and control of power system is sensitive to system demand. Therefore, improvements in load-forecasting accuracy will lead to cost savings and enhance system security. Due to Taiwan's distinct climate characteristics, it is difficult to obtain satisfactory load-forecasting results by treating the whole island as a single region. In addition, weather factors, such as temperature, relative humidity, and the Heat Index (HI) (a human-perceived equivalent temperature) may also affect load-consumption patterns. This paper proposes a multiregion short-term load-forecasting methodology, taking into account the HI to improve load-forecasting accuracy in Taiwan Power Company's (Taipower's) system. The results show that adopting the HI as a parameter can effectively improve the accuracy if the temperature of the region under investigation is above 27 ^\circ\C (80 ^ \circ\F). By considering both the load/weather diversity and the HI, further improvements to the load forecasting for the Taipower system during summer can be achieved. [ABSTRACT FROM AUTHOR]

Reservoirs in Taiwan often provide hydroelectric power, irrigation water, municipal water, and flood control for the whole year. Taiwan has the climatic characteristics of concentrated rainy seasons, instantaneous heavy rains due to typhoons and rainy seasons. In addition, steep rivers in mountainous areas flow fast and furiously. Under such circumstances, reservoirs have to face sudden heavy rainfall and surges in water levels within a short period of time, which often causes the water level to continue to rise to the full level even though hydroelectric units are operating at full capacity, and as reservoirs can only drain the flood water, this results in the waste of hydropower resources. In recent years, the impact of climate change has caused extreme weather events to occur more frequently, increasing the need for flood control, and the reservoir operation has faced severe challenges in order to fulfil its multipurpose requirements. Therefore, in order to avoid the waste of hydropower resources and improve the effectiveness of the reservoir operation, this paper proposes a real-time 48-h ahead water level forecasting system, based on fuzzy neural networks with multi-stage architecture. The proposed multi-stage architecture provides reservoir inflow estimation, 48-h ahead reservoir inflow forecasting, and 48-h ahead water level forecasting. The proposed method has been implemented at the Techi hydropower plant in Taiwan. Experimental results show that the proposed method can effectively increase energy efficiency and allow the reservoir water resources to be fully utilized. In addition, the proposed method can improve the effectiveness of the hydropower plant, especially when rain is heavy. [ABSTRACT FROM AUTHOR]

This paper presents a prediction model based on an improved fuzzy time series (IFTS) and a modified group search optimizer to effectively solve forecasting problems. IFTS can accurately predict whether subsequent predicted data will increase or decrease according to ratio value in the fuzzy logical relationship. In addition, the modified group search optimizer is used to adjust the length of an interval. The proposed prediction model is also used to forecast the enrollments of the University of Alabama the enrollments of a university of technology in central Taiwan, and the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) Experimental results show that the proposed model obtains the smallest prediction error than those of other methods. [ABSTRACT FROM AUTHOR]

Up until now montane cloud forest (MCF) in Taiwan has only been mapped for selected areas of vegetation plots. This paper presents the first comprehensive map of MCF distribution for the entire island. For its creation, a Random Forest model was trained with vegetation plots from the National Vegetation Database of Taiwan that were classified as “MCF” or “non-MCF”. This model predicted the distribution of MCF from a raster data set of parameters derived from a digital elevation model (DEM), Landsat channels and texture measures derived from them as well as ground fog frequency data derived from the Moderate Resolution Imaging Spectroradiometer. While the DEM parameters and Landsat data predicted much of the cloud forest’s location, local deviations in the altitudinal distribution of MCF linked to the monsoonal influence as well as the Massenerhebung effect (causing MCF in atypically low altitudes) were only captured once fog frequency data was included. Therefore, our study suggests that ground fog data are most useful for accurately mapping MCF. [ABSTRACT FROM AUTHOR]

This research models and forecasts bounded ordinal time series data that can appear in various contexts, such as air quality index (AQI) levels, economic situations, and credit ratings. This class of time series data is characterized by being bounded and exhibiting a concentration of large probabilities on a few categories, such as states 0 and 1. We propose using Bayesian methods for modeling and forecasting in zero-one-inflated bounded Poisson autoregressive (ZOBPAR) models, which are specifically designed to capture the dynamic changes in such ordinal time series data. We innovatively extend models to incorporate exogenous variables, marking a new direction in Bayesian inferences and forecasting. Simulation studies demonstrate that the proposed methods accurately estimate all unknown parameters, and the posterior means of parameter estimates are robustly close to the actual values as the sample size increases. In the empirical study we investigate three datasets of daily AQI levels from three stations in Taiwan and consider five competing models for the real examples. The results exhibit that the proposed method reasonably predicts the AQI levels in the testing period, especially for the Miaoli station. [ABSTRACT FROM AUTHOR]

One of the most important sources of energy is the sun. Taiwan is located at a 22–25° north latitude. Due to its proximity to the equator, it experiences only a small angle of sunlight incidence. Its unique geographical location can obtain sustainable and stable solar resources. This study uses research on solar radiation forecasts to maximize the benefits of solar power generation, and it develops methods that can predict future solar radiation patterns to help reduce the costs of solar power generation. This study built supervised machine learning models, known as a deep neural network (DNN) and a long–short-term memory neural network (LSTM). A hybrid supervised and unsupervised model, namely a cluster-based artificial neural network (k-means clustering- and fuzzy C-means clustering-based models) was developed. After establishing these models, the study evaluated their prediction results. For different prediction periods, the study selected the best-performing model based on the results and proposed combining them to establish a real-time-updated solar radiation forecast system capable of predicting the next 12 h. The study area covered Kaohsiung, Hualien, and Penghu in Taiwan. Data from ground stations of the Central Weather Administration, collected between 1993 and 2021, as well as the solar angle parameters of each station, were used as input data for the model. The results of this study show that different models offer advantages and disadvantages in predicting different future times. The hybrid prediction system can predict future solar radiation more accurately than a single model. [ABSTRACT FROM AUTHOR]

Taiwan is highly susceptible to global warming, experiencing a 1.4 °C increase in air temperature from 1911 to 2005, which is twice the average for the Northern Hemisphere. This has potentially led to higher rates of respiratory and cardiovascular mortality. Accurately predicting maximum temperatures during the summer season is crucial, but numerical weather models become less accurate and more uncertain beyond five days. To enhance the reliability of a forecast, post-processing techniques are essential for addressing systematic errors. In September 2020, the NOAA NCEP implemented the Global Ensemble Forecast System version 12 (GEFSv12) to help manage climate risks. This study developed a Hybrid statistical post-processing method that combines Artificial Neural Networks (ANN) and quantile mapping (QQ) approaches to predict daily maximum temperatures (Tmax) and their extremes in Taiwan during the summer season. The Hybrid technique, utilizing deep learning techniques, was applied to the GEFSv12 reforecast data and evaluated against ERA5 reanalysis. The Hybrid technique was the most effective among the three techniques tested. It had the lowest bias and RMSE and the highest correlation coefficient and Index of Agreement. It successfully reduced the warm bias and overestimation of Tmax extreme days. This led to improved prediction skills for all forecast lead times. Compared to ANN and QQ, the Hybrid method proved to be more effective in predicting daily Tmax, including extreme Tmax during summer, on extended-range time-scale deterministic and ensemble probabilistic forecasts over Taiwan. [ABSTRACT FROM AUTHOR]

In this paper, we present a new method to predict the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) based on fuzzy-trend logical relationship groups (FTLRGs). The proposed method divides fuzzy logical relationships into FTLRGs based on the trend of adjacent fuzzy sets appearing in the antecedents of fuzzy logical relationships. First, we apply an automatic clustering algorithm to cluster the historical data into intervals of different lengths. Then, we define fuzzy sets based on these intervals of different lengths. Then, the historical data are fuzzified into fuzzy sets to derive fuzzy logical relationships. Then, we divide the fuzzy logical relationships into FTLRGs for forecasting the TAIEX. Moreover, we also apply the proposed method to forecast the enrollments and the inventory demand, respectively. The experimental results show that the proposed method gets higher average forecasting accuracy rates than the existing methods.

This paper presents an observing system simulation experiment (OSSE) study to examine the impact of dropsonde data assimilation (DA) on rainfall forecasts for a heavy rain event in Taiwan. The rain event was associated with strong southwesterly flows over the northern South China Sea (SCS) after a weakening tropical cyclone (TC) made landfall over southeastern China. With DA of synthetic dropsonde data over the northern SCS, the model reproduces more realistic initial fields and a better simulated TC track that can help in producing improved low-level southwesterly flows and rainfall forecasts in Taiwan. Dropsonde DA can also aid the model in reducing the ensemble spread, thereby producing more converged ensemble forecasts. The sensitivity studies suggest that dropsonde DA with a 12-h cycling interval is the best strategy for deriving skillful rainfall forecasts in Taiwan. Increasing the DA interval to 6 h is not beneficial. However, if the flight time is limited, a 24-h interval of DA cycling is acceptable, because rainfall forecasts in Taiwan appear to be satisfactory. It is also suggested that 12 dropsondes with a 225-km separation distance over the northern SCS set a minimum requirement for enhancing the model regarding rainfall forecasts. Although more dropsonde data can help the model to obtain better initial fields over the northern SCS, they do not provide more assistance to the forecasts of the TC track and rainfall in Taiwan. These findings can be applied to the future field campaigns and model simulations in the nearby regions. [ABSTRACT FROM AUTHOR]

Performance forecasting is central to aligning an organization’s operations with its strategic direction. Despite the panoply of approaches to performance predictions, relatively few published studies address model development of financial performance predictions for the construction industry. By analyzing the preceding relationship between financial and economic variables and financial performance, this paper proposes an innovative approach to predicting firm financial performance. First, hypothesis tests using data for 42 development and construction corporations listed in the construction sector of the Taiwan Stock Exchange between 1997 Q1 and 2006 Q4 uncover useful relationships between financial performance and financial and economic variables. Second, based on these relationships, a three-stage mathematical modeling procedure is used for cross-sectional model estimation, which is subsequently refined to create firm-specific financial performance-forecasting models for four sample firms. The out-of-sample forecasting accuracy is evaluated using mean absolute percentage error (MAPE). The results show that the cross-sectional model explains 78.9% of the variation in the cross-sectional performance data, and the MAPE values in the forecasting models range from 9.54 to 19.69%. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, six univariate forecasting models for the container throughput volumes in Taiwan’s three major ports are presented. The six univariate models include the classical decomposition model, the trigonometric regression model, the regression model with seasonal dummy variables, the grey model, the hybrid grey model, and the SARIMA model. The purpose of this paper is to search for a model that can provide the most accurate prediction of container throughput. By applying monthly data to these models and comparing the prediction results based on mean absolute error, mean absolute percent error and root mean squared error, we find that in general the classical decomposition model appears to be the best model for forecasting container throughput with seasonal variations. The result of this study may be helpful for predicting the short-term variation in demand for the container throughput of other international ports. [Copyright &y& Elsevier]

Due to the enhancement by its steep mesoscale topography, the overall rainfall amount and distribution in Taiwan from typhoons, to a first degree, are determined by the storm track relative to the island. Therefore, the quality of typhoon quantitative precipitation forecasts (QPFs) from numerical models is often controlled by track errors, with better quality from those with smaller track errors. However, the present work demonstrates that in daily QPFs over Taiwan made by a cloud-resolving model during five seasons of 2012–2016, targeted for 84 days during 27 typhoons and at ranges of day one (0–24 h) to day eight (168–192 h), the control of track errors on QPF quality is reduced for typhoons associated with southwesterly flow, compared to those without, and decent QPFs could still be obtained with large track errors in some cases. Subsequently, the circumstances and reasons for good (or bad) QPFs in selected examples are further investigated to deepen our understanding of typhoon QPFs in Taiwan. Some common ingredients are found in three cases where good QPFs were produced at a longer range (day 7 or 8) without a good track: these typhoons passed near northern Taiwan and the southwesterly flow prevailed over much of the island during the accumulation period. Responsible for much of the rainfall in Taiwan, the southwesterly flow was reasonably captured, resulting in good QPFs. In another example where the typhoon moved across southern Taiwan, on the contrary, the rainfall was produced by the storm's circulation, and the QPF was degraded without a good enough track prediction. [ABSTRACT FROM AUTHOR]

This paper examines the usefulness of statistical methods in forecasting the financial energy of households. The study's objective is to create the innovative ratios that combine both financial and demographic information of households and implement them in the forecasting models. To conduct this objective, six forecasting models are developed using three different methods—discriminant analysis, logit analysis, and decision trees separately for households in Poland and Taiwan. Such a research approach will answer the question whether the implementation of constructed ratios can increase effectiveness of the forecasting model and its' versatility between different economic regions. The research relies on four samples of households—two learning samples and two testing samples (one for each country) consisting of 2400 households from both countries. This study is one of the first attempts in the literature globally to develop forecasting models based on ratios constructed with a combination of two different types of variables—one financial with one demographic variable. Findings confirm the high usability of the proposed innovative approach for forecasting the financial energy of households by taking into account a wide spectrum of diagnostic variables representing the financial strength of consumers. [ABSTRACT FROM AUTHOR]

The shear wave velocity profile and dynamic soil properties are known to be affected by aleatory uncertainty. This paper aims to investigate the effect of a statistical variation in the initial stiffness profile, stiffness degradation and damping curves on ground response predictions by conducting stochastic analysis. The Large Scale Seismic Test site in Lotung, Taiwan, is back-analysed with a fully-coupled finite element procedure using an advanced kinematic hardening soil model. Two ground motions recorded at the site, one strong and one weak, are applied at bedrock level. The results reveal that the site response prediction is sensitive to the seismic intensity of the input motion. When the level of induced shear strain is higher, i.e. in the case of the stronger motion, the spatial variability of the stiffness degradation and damping curves has a pronounced effect on the predicted site response. In contrast, when the weaker motion is considered the prediction is particularly sensitive to the statistical variation in the initial stiffness profile. This is mainly due to the stiffness degradation at very small strains shown by the laboratory data on LSST soils, which is captured in the paper by assuming an appropriate elastic domain in the constitutive model calibration. [ABSTRACT FROM AUTHOR]

The high utilization of renewable energy to manage climate change and provide green energy requires short-term photovoltaic (PV) power forecasting. In this paper, a novel forecasting strategy that combines a convolutional neural network (CNN) and a salp swarm algorithm (SSA) is proposed to forecast PV power output. First, the historical PV power data and associated weather information are classified into five weather types, such as rainy, heavy cloudy, cloudy, light cloudy and sunny. The CNN classification is then used to determine the prediction for the next day's weather type. Five models of CNN regression are established to accommodate the prediction for different weather types. Each CNN regression is optimized using a salp swarm algorithm (SSA) to tune the best parameter. To evaluate the performance of the proposed method, comparisons were made to the SSA based support vector machine (SVM-SSA) and long short-term memory neural network (LSTM-SSA) methods. The proposed method was tested on a PV power generation system with a 500 kWp capacity located in south Taiwan. The results showed that the proposed CNN-SSA could accommodate the actual generation pattern better than the SVM-SSA and LSTM-SSA methods. [ABSTRACT FROM AUTHOR]

The progress of industrial development naturally leads to the demand for more electrical power. Unfortunately, due to the fear of the safety of nuclear power plants, many countries have relied on thermal power plants, which will cause more air pollutants during the process of coal burning. This phenomenon as well as increased vehicle emissions around us, have constituted the primary factors of serious air pollution. Inhaling too much particulate air pollution may lead to respiratory diseases and even death, especially PM $_{2.5}$ 2. 5 . By predicting the air pollutant concentration, people can take precautions to avoid overexposure to air pollutants. Consequently, accurate PM $_{2.5}$ 2. 5 prediction becomes more important. In this study, we propose a PM $_{2.5}$ 2. 5 prediction system, which utilizes the dataset from EdiGreen Airbox and Taiwan EPA. Autoencoder and Linear interpolation are adopted for solving the missing value problem. Spearman’s correlation coefficient is used to identify the most relevant features for PM $_{2.5}$ 2. 5 . Two prediction models (i.e., LSTM and LSTM based on K-means) are implemented which predict PM $_{2.5}$ 2. 5 value for each Airbox device. To assess the performance of the model prediction, the daily average error and the hourly average accuracy for the duration of a week are calculated. The experimental results show that LSTM based on K-means has the best performance among all methods. Therefore, LSTM based on K-means is chosen to provide real-time PM $_{2.5}$ 2. 5 prediction through the Linebot. [ABSTRACT FROM AUTHOR]

Accurate real-time forecasts of inundation depth and extent during typhoon flooding are crucial to disaster emergency response. To manage disaster risk, the development of a flood inundation forecasting model has been recognized as essential. In this paper, a forecasting model by integrating a hydrodynamic model, k-means clustering algorithm and support vector machines (SVM) is proposed. The task of this study is divided into four parts. First, the SOBEK model is used in simulating inundation hydrodynamics. Second, the k-means clustering algorithm classifies flood inundation data and identifies the dominant clusters of flood gauging stations. Third, SVM yields water level forecasts with 1–3 h lead time. Finally, a spatial expansion module produces flood inundation maps, based on forecasted information from flood gauging stations and consideration of flood causative factors. To demonstrate the effectiveness of the proposed forecasting model, we present an application to the Yilan River basin, Taiwan. The forecasting results indicate that the simulated water level forecasts from the point forecasting module are in good agreement with the observed data, and the proposed model yields the accurate flood inundation maps for 1–3 h lead time. These results indicate that the proposed model accurately forecasts not only flood inundation depth but also inundation extent. This flood inundation forecasting model is expected to be useful in providing early flood warning information for disaster emergency response. [ABSTRACT FROM AUTHOR]

Air pollution is a global problem and can be perceived as a modern-day curse. One way of dealing with it is by finding economical ways to monitor and forecast air quality. Accurately monitoring and forecasting fine particulate matter (PM2.5) concentrations is a challenging prediction task but Internet of Things (IoT) can help in developing economical and agile ways to design such systems. In this paper, we use a historical data-based approach to perform PM2.5 forecasting. A forecasting method is developed which uses exponential smoothing with drift. Experiments and evaluation were performed using the real-time PM2.5 data obtained from large scale deployment of IoT devices in Taichung region in Taiwan. We used the data from 132 monitoring stations to evaluate our model's performance. A comparison of prediction accuracy and computation time between the proposed model and three widely used forecasting models was done. The results suggest that our method can perform PM2.5 forecast for 132 monitoring stations with error as low as 0.16 μ g/ m 3 and also with an acceptable computation time of 30 s. Further evaluation was done by forecasting PM2.5 for next 3 h. The results show that 90 % of the monitoring stations have error under 1.5 μ g/ m 3 which is significantly low. [ABSTRACT FROM AUTHOR]

This study aimed to assess the effective spatial characteristics of input features by using physics-informed, machine learning (ML)-based inundation forecasting models. To achieve this aim, inundation depth data were simulated using a numerical hydrodynamic model to obtain training and testing data for these ML-based models. Effective spatial information was identified using a back-propagation neural network, an adaptive neuro-fuzzy inference system, support vector machine, and a hybrid model combining support vector machine and a multi-objective genetic algorithm. The conventional average rainfall determined using the Thiessen polygon method, raingauge observations, radar-based rainfall data, and typhoon characteristics were used as the inputs of the aforementioned ML models. These models were applied in inundation forecasting for Yilan County, Taiwan, and the hybrid model had the best forecasting performance. The results show that the hybrid model with crucial features and appropriate lag lengths gave the best performance. [ABSTRACT FROM AUTHOR]

Deep learning networks (DLNs) use multilayer neural networks for multiclass classification that exhibit better results in wind-power forecasting applications. However, improving the training process using proper parameter hyperisations and techniques, such as regularisation and Adam-based optimisation, remains a challenge in the design of DLNs for processing time-series data. Moreover, the most appropriate parameter for the DLN model is to solve the wind-power forecasting problem by considering the excess training algorithms, such as the optimiser, activation function, batch size, and dropout. Reinforcement learning (RN) schemes constitute a smart approach to explore the proper initial parameters for the developed DLN model, considering a balance between exploration and exploitation processes. Therefore, the present study focuses on determining the proper hyperparameters for DLN models using a Q-learning scheme for four developed models. To verify the effectiveness of the developed temporal convolution network (TCN) models, experiments with five different sets of initial parameters for the TCN model were determined by the output results of Q-learning computation. The experimental results showed that the TCN accuracy for 168 h wind power prediction reached a mean absolute percentage error of 1.41%. In evaluating the effectiveness of selection of hyperparameters for the proposed model, the performance of four DLN-based prediction models for power forecasting—TCN, long short-term memory (LSTM), recurrent neural network (RNN), and gated recurrence unit (GRU) models—were compared. The overall detection accuracy of the TCN model exhibited higher prediction accuracy compared to canonical recurrent networks (i.e., the GRU, LSTM, and RNN models). [ABSTRACT FROM AUTHOR]

One of the most critical aspects of integrating renewable energy sources into the smart grid is photovoltaic (PV) power generation forecasting. This ensemble forecasting technique combines several forecasting models to increase the forecasting accuracy of the individual models. This study proposes a regression-based ensemble method for day-ahead PV power forecasting. The general framework consists of three steps: model training, creating the optimal set of weights, and testing the model. In step 1, a Random forest (RF) with different parameters is used for a single forecasting method. Five RF models (RF1, RF2, RF3, RF4, and RF5) and a support vector machine (SVM) for classification are established. The hyperparameters for the regression-based method involve learners (linear regression (LR) or support vector regression (SVR)), regularization (least absolute shrinkage and selection operator (LASSO) or Ridge), and a penalty coefficient for regularization (λ). Bayesian optimization is performed to find the optimal value of these three hyperparameters based on the minimum function. The optimal set of weights is obtained in step 2 and each set of weights contains five weight coefficients and a bias. In the final step, the weather forecasting data for the target day is used as input for the five RF models and the average daily weather forecasting data is also used as input for the SVM classification model. The SVM output selects the weather conditions, and the corresponding set of weight coefficients from step 2 is combined with the output from each RF model to obtain the final forecasting results. The stacking recurrent neural network (RNN) is used as a benchmark ensemble method for comparison. Historical PV power data for a PV site in Zhangbin Industrial Area, Taiwan, with a 2000 kWp capacity is used to test the methodology. The results for the single best RF model, the stacking RNN, and the proposed method are compared in terms of the mean relative error (MRE), the mean absolute error (MAE), and the coefficient of determination (R2) to verify the proposed method. The results for the MRE show that the proposed method outperforms the best RF method by 20% and the benchmark method by 2%. [ABSTRACT FROM AUTHOR]

The automotive industry is the leading producer of machines in Taiwan and worldwide. Developing effective methods for forecasting car sales can allow car companies to arrange their production and sales plans. Capitalizing on the growth of social media and deep learning algorithms, this research aimed to improve the overall performance of the forecasting of Taiwan car sales movement direction forecasting by using online sentiment data and CNN-LSTM method. First, the historical sales volumes and multi-channel online sentiment data for six car brands in Taiwan were collected and preprocessed for labeling of car sales movement direction. Then, three models, namely, the classical, sentimental, and CNN-LSTM models, were constructed and trained/fitted for forecasting car sales movement directions in Taiwan. Finally, the performance of the three prediction models were compared to verify the effects of online sentiment data and the CNN-LSTM model on forecasting performance. The results showed that four forecasting performance indices, i.e., accuracy, precision, recall and F1-score, improved by 27.78% (from 41.67% to 69.45%), 0.39 (from 0.38 to 0.77), 0.27 (from 0.42 to 0.69) and 0.33 (from 0.35 to 0.68), respectively. Therefore, the online sentiment data and CNN-LSTM method can indeed improve the overall performance of car sales movement direction in Taiwan. [ABSTRACT FROM AUTHOR]

The development of estate price prediction systems is one of the issues that researchers are paying the most attention to. A good estate price prediction system can shorten the time it takes buyers to consider estates and invigorate the estate market. Generally speaking, an estate price prediction system considers the temporal and spatial features of the estate. In addition, the estate price prediction system can also be launched online for users to make instant online queries with, which means that it needs short run time. However, most existing studies only considered either temporal or spatial features and could not consider both, thereby resulting in questionable prediction accuracy. Although deep learning may increase prediction accuracy, it does not meet the short run time requirement. We therefore presented three ideas in this study to overcome these issues: (1) designing a novel spatiotemporal data structure, the Space-Time Influencing Figure (STIF), to quantify the influence of changes in the facilities surrounding each estate on estate price, (2) designing a novel CNN-LSTM model to go with the STIFs for estate price prediction, and (3) designing a new framework to extract the most important features to estate price for certain types of estates and combining these features with a shallow RNN for modeling. The computation cost of this model is far lower than that of a CNN-LSTM model, making it suitable for practical application. Finally, we used actual estate data from Taiwan to verify that the proposed approach can effectively and swiftly predict estate prices. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we proposed a modified turbulent particle swarm optimization (named MTPSO) method for the temperature prediction and the Taiwan Futures Exchange (TAIFEX) forecasting, based on the two-factor fuzzy time series and particle swarm optimization. The MTPSO model can be dealt with two main factors easily and accurately, which are the lengths of intervals and the content of forecast rules. The experimental results of the temperature prediction and the TAIFEX forecasting show that the proposed model is better than any existing models and it can get better quality solutions based on the high-order fuzzy time series, respectively. [Copyright &y& Elsevier]

An operational regional wave forecasting system was established to fulfill the demands of maritime engineering applications on the northeastern coast of Taiwan. This Mixed system consisted of a nested SWAN numerical wave model and experienced marine meteorologists who were sent to the construction site as the in situ predictors to validate output from the numerical model so as to improve the forecasting accuracy. This paper will offer an evaluation of this regional wave forecasting system. Records of hourly forecasts from June to October 2004 obtained by direct numerical model and the in situ predictors' modifications are comprehensively compared. First, the nested SWAN is verified with the observational data. The Alves and Banner's (2003) wave energy dissipation term is adopted for better wave period simulation. The error analysis is then carried out to discriminate the performances of the system to the direct numerical model. It is found that the in situ predictors provided invaluable modifications which reduced the root mean square error by 30% to the deviated model outputs as well as the quality of the forecasted wind fields used to drive the wave model played key role to the wave prediction. About 20% of the errors of +3 days wave predictions were incurred by the uncertainties of wind fields. As the miss-predicted trajectory of typhoon centers exceeding 90 km, the wave predictions would not be valid, and the benefits from in situ predictors became marginal. Finally, land and sea breezes are important factors in regional wave forecasts for engineering applications as both can induce diurnal wave heights oscillations, which is not destructive, but crucial to the quality of marine engineering. As the scale of the land/sea breeze is not resolved in the operational forecasted wind fields issued by Central Weather Bureau. Currently, the implementation of in situ predictors is necessary. [ABSTRACT FROM AUTHOR]

Abstract: Accurate and immediate forecast in the short product life cycle of semiconductor market is difficult, but important. This paper proposed a grey model with factor analysis techniques to deal with the multi-factor forecasting problems. In the grey modeling, the use of genetic algorithm has the ability to search global optimum solution to construct two improved multivariable grey forecasting models that are AGAGM(1,N) and GAGM(1,N). These two models are applied for forecasting Taiwanese integrated circuit output. The results of the factor analysis show that the major factors of Taiwan’s integrated circuit output comprise R&D intensity, foreign investment, index of industrial production, trade specialization coefficient, and intra-industry trade coefficient. The improved multivariable grey forecasting models are found to be feasible and effective. [Copyright &y& Elsevier]

Abstract: In our daily life, we often use some forecasting techniques to predict weather, temperature, stock, earthquake, economy, etc. Based on these forecasting results, we can prevent damages to occur or get benefits from the forecasting activities. In fact, an event in the real-world can be affected by many factors. The more the facts we consider, the higher the forecasting accuracy rate. Moreover the length of each interval in the universe of discourse also affects the forecasting results. In this paper, we present a new method to predict the temperature and the Taiwan Futures Exchange (TAIFEX), based on automatic clustering techniques and two-factors high-order fuzzy time series. The proposed method gets higher average forecasting accuracy rates than the existing methods. [Copyright &y& Elsevier]

PM2.5 prediction has received much attention from researchers in recent years, as PM2.5 has been proven to have a major impact on human health. High-precision PM2.5 predictions would greatly benefit both the general public and governments. However, most of the existing studies on predicting PM2.5 or other air pollutants focus on model design and rarely discuss feature selection. Conventionally, researchers either simply choose a few types of meteorological data based on suggestions from experts or conduct simple correlation analyses to identify the types of meteorological data that are most correlated with the predicted pollutant. However, these methods suffer from two shortcomings. (1) Changes in PM2.5 values are influenced by low-frequency pollution from other places and high-frequency pollution from the local area. Furthermore, the meteorological data associated with the two pollution sources are generally different. In this case, changes with different frequencies in each type of meteorological data should be considered separately to precisely identify the correlated meteorological data of pollutants with different frequencies. (2) Datasets used for PM2.5 predictions generally contain high-dimensional meteorological data. Conventional correlation analysis methods are not effective at identifying features in such datasets, making it difficult to select useful features and negatively affecting prediction accuracy. This study therefore proposes two concepts to address this issue: (1) a wavelet model to decompose each type of meteorological data into multiple sub-time series with different frequencies and (2) the design of a novel radial basis function long short-term memory model that can analyze the outputs of the radial basis function to extract key features identified by deep learning models. This approach is faster and simpler than other methods using deep learning models to extract key features. Application of these concepts will greatly enhance prediction accuracy and reduce costs regardless of the prediction model used. We use three years of historical meteorological data from Central Taiwan to demonstrate the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

The influenza problem has always been an important global issue. It not only affects people's health problems but is also an essential topic of governments and health care facilities. Early prediction and response is the most effective control method for flu epidemics. It can effectively predict the influenza-like illness morbidity, and provide reliable information to the relevant facilities. For social facilities, it is possible to strengthen epidemic prevention and care for highly sick groups. It can also be used as a reminder for the public. This study collects information on the influenza-like illness emergency department visits to the Taiwan Centers for Disease Control, and the PM2.5 open-source data from the Taiwan Environmental Protection Administration's air quality monitoring network. By using deep learning techniques, the relevance of short-term estimates and the outbreak calculation method can be determined. The techniques are published by the WHO to determine whether the influenza-like illness situation is still in a stage of reasonable control. Finally, historical data and future forecasted data are integrated on the web page for visual presentation, to show the actual regional air quality situation and influenza-like illness data and to predict whether there is an outbreak of influenza in the region. [ABSTRACT FROM AUTHOR]