Regression model-based predictions of diel, diurnal and nocturnal dissolved oxygen dynamics after wavelet denoising of noisy time series

Abstract: One of the busiest airports in Indonesia managed by PT. Angkasa Pura I is Juanda International Airport. Besides, Juanda International Airport is also one of the gateways for the Indonesian state to other countries. The number of passengers at the departure terminal at Juanda International Airport from 2012 to 2013, both domestic and international routes, has increased by about 6.74%. Meanwhile, the arrival terminal experienced an increase of about 8.31%. From 2013 to 2014 the departure route decreased by 2.51%. Meanwhile, the arrival route decreased by 1.99%. In 2014 to 2015 the departure route decreased by 11.31%. Meanwhile, the arrival route decreased by 0.78%. There is an increase and decrease in the number of passengers at Juanda International Airport, it is necessary to research forecasting the number of passengers at Juanda International Airport, both from domestic routes and international routes. The purpose of this study is to balance number of passengers and number of flights in the future with the availability of the number of aircraft and airport capacity. The data used is data on the number of passengers each month at Juanda International Airport. Where the data was obtained from PT. Angkasa Pura I (Persero). The criteria for selecting the best model based on the RMSE value shows that the best model selected by the ARIMA model has 14 routes, while the selected Time Series Regression model has 9 routes and the selected TBATS model has 7 routes.Abstrak: Salah satu bandara tersibuk di Indonesia yang diolah PT. Angkasa Pura I adalah Bandara Internasional Juanda. Selain itu, Bandara Internasional Juanda juga merupakan salah satu pintu gerbang negara Indonesia menuju negara-negara lain. Jumlah penumpang di terminal keberangkatan Bandara Internasional Juanda dari tahun 2012 hingga tahun 2013 baik rute domestik maupun internasional mengalami peningkatan sekitar 6,74%. Sedangkan di terminal kedatangan mengalami kenaikan sekitar 8,31%. Pada tahun 2013 hingga tahun 2014 pada rute keberangkatan mengalami penurunan sebesar 2,51%. Sedangkan pada rute kedatangan mengalami penurunan sebesar 1,99%.Pada tahun 2014 hingga tahun 2015 pada rute keberangkatan mengalami penurunan sebesar 11,31%. Sedangkan pada rute kedatangan mengalami penurunan sebesar 0,78%. Adanya kenaikan dan penurunan jumlah penumpang di Bandara Internasional Juanda, maka perlu diadakan penelitian mengenai peramalan jumlah penumpang di Bandara Internasional Juanda, baik dari rute domestik maupun rute internasional. Tujuan dari penelitian ini adalah untuk menyeimbangkan jumlah penumpang dan jumlah penerbangan pada masa mendatang dengan ketersediaan jumlah pesawat dan kapasitas bandar udara.Data yang digunakan adalah data jumlah penumpang tiap bulan di Bandara Internasional Juanda. Dimana data tersebut diperoleh dari PT. Angkasa Pura I (Persero). Kriteria pemilihan model terbaik berdasarkan nilai RMSE menunjukkan bahwa Model terbaik yang terpilih model ARIMA terdapat 14 rute sedangkan yang terpilih model Regresi Time Series terdapat 9 rute dan yang terpilih model TBATS terdapat 7 rute.

Download Full-text

Using Convolutional Neural Network and Candlestick Representation to Predict Sports Match Outcomes

Applied Sciences ◽

10.3390/app11146594 ◽

2021 ◽

Vol 11 (14) ◽

pp. 6594

Author(s):

Yu-Chia Hsu

Keyword(s):

Neural Network ◽

Time Series ◽

Pattern Recognition ◽

Logistic Regression ◽

Regression Model ◽

Convolutional Neural Network ◽

Logistic Regression Model ◽

National Football League ◽

Performance Metrics ◽

Betting Market

The interdisciplinary nature of sports and the presence of various systemic and non-systemic factors introduce challenges in predicting sports match outcomes using a single disciplinary approach. In contrast to previous studies that use sports performance metrics and statistical models, this study is the first to apply a deep learning approach in financial time series modeling to predict sports match outcomes. The proposed approach has two main components: a convolutional neural network (CNN) classifier for implicit pattern recognition and a logistic regression model for match outcome judgment. First, the raw data used in the prediction are derived from the betting market odds and actual scores of each game, which are transformed into sports candlesticks. Second, CNN is used to classify the candlesticks time series on a graphical basis. To this end, the original 1D time series are encoded into 2D matrix images using Gramian angular field and are then fed into the CNN classifier. In this way, the winning probability of each matchup team can be derived based on historically implied behavioral patterns. Third, to further consider the differences between strong and weak teams, the CNN classifier adjusts the probability of winning the match by using the logistic regression model and then makes a final judgment regarding the match outcome. We empirically test this approach using 18,944 National Football League game data spanning 32 years and find that using the individual historical data of each team in the CNN classifier for pattern recognition is better than using the data of all teams. The CNN in conjunction with the logistic regression judgment model outperforms the CNN in conjunction with SVM, Naïve Bayes, Adaboost, J48, and random forest, and its accuracy surpasses that of betting market prediction.

Download Full-text