Search

An important way to protect public health is to forecast air quality by giving early warnings about air pollution. Management of air quality is highly dependent on data from time series collected at air monitoring stations. However, data input must be processed first in time series observations for several reasons, such as measurement errors, to prevent misleading results during forecast analysis. Data obtained from different measurements brings a degree of uncertainty that contributes to uncertainty in the data. Therefore, by constructing the Fuzzy Symmetry Triangular Fuzzy number data using the standard deviation and percentage error methods, the procedure for preparing data containing uncertain information is presented in this paper. ARIMA then uses the pre-processed data to create a predictive model. The findings of this study suggest that smaller prediction errors have resulted in the use of the proposed method to create fuzzy numbers for ARIMA. This implies that, with fewer prediction errors, the accuracy of the prediction model is higher. [ABSTRACT FROM AUTHOR]

The basic goal of time series modeling is to collect and analyze historical time-series observations to build a model that accurately describes series trends. More attention is required while fitting this newly developed forecasting model to a timely data set. The fitting of the model is very important because it allows the model to capture complex interactions between its parameters, which allows for better prediction results. Hence, this research provides a systematic ARIMA model fitting procedure. The proposed model fitting procedure is very important during the data preparation phase as it can eliminate unreliable models. The result shows that the fitting in ARIMA model buildings has a significant impact. When the experimental results and performance were compared with the benchmark results, it was found that the proposed model showed better performance in terms of accuracy. As a result, the predictive accuracy of ARIMA fitting techniques can be improved. [ABSTRACT FROM AUTHOR]

The prediction models of association football can be categorized into three natural clusters, which are the statistical models, the machine learning and probabilistic graphical models and rating systems. The prediction may focus on matches outcomes prediction (win, draw and lose) or the number of goals scored obtained by home and away team. Match result prediction is very important as a benchmark for the management team to assess the chances of winning, drawing and losing for a particular team before the match starts. In the 2017 soccer challenge, the conventional machine learning and ensemble methods, as well as probabilistic graphical models such as k-Nearest Neighbor (k-NN), Gradient Boosting Tree (GBT) and Bayesian Networks (BN) have been a choice of researchers that participate the challenge and successfully dominate the challenge. Even so, there are some well-known techniques such as Neural Networks (NN) and Deep Neural Networks (DNN) that are left in this challenge although this technique has advantages in producing good results in many fields including solving real world problems which the results are comparable and sometimes superior to expert knowledge in some cases. In this paper, we propose a football match outcome prediction based on pi-rating system using TabNet, a DNN architecture for tabular data. The experiment cover two parts namely: (1) generates pi-rating system from 216,743 instances of raw football dataset and (2) predicts 206 football match outcomes using TabNet. As a result, the proposed prediction model based on the pi-rating system using TabNet successfully overcomes the existing model for football match outcomes for both scoring rules, in terms of accuracy and Rank Probability Score (RPS). The findings from this study are important because they can be used for future researchers in developing new football match outcome prediction models that incorporate several new features along with other features. This is important to improve the predictive performance of football prediction models using other advanced techniques. [ABSTRACT FROM AUTHOR]