Danang Ariyanto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Danang Ariyanto has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
A'YUnin Sofro
5 shared publications- Affiati Oktaviarina
Department of Actuarial Science, Faculty of Mathematics and Natural Sciences, Universitas Negeri Surabaya, Indonesia
2 shared publications - Asri Maharani
Division of Nursing, Midwifery and Social Work, University of Manchester
2 shared publications - Dimas Avian Maulana
Universitas Negeri Surabaya
2 shared publications Riska Wahyu Romadhonia
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Surabaya, Indonesia
2 shared publications- Affi Oktaviarina
Universitas Negeri Surabaya, Surabaya
1 shared publication
Latest Publications
- Open Access
- 26 January 2026
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 20 (2)
TRADITIONAL LOGISTIC REGRESSION AND MACHINE LEARNING APPROACHES OF SOCIODEMOGRAPHIC AND ANTHROPOMETRIC FACTORS INFLUENCING HYPERTENSION IN ATHLETES
The type and intensity of exercise performed by athletes play an important role in affecting blood pressure stability, putting them at risk of developing hypertension. Hypertension, or high blood pressure, is a medical condition in which the blood pressure in the arteries rises above normal limits. Hypertension in athletes becomes an essential factor in real cases if not detected early. Therefore, this study aims to model and analyse the sociodemographic and anthropometric factors that influence the incidence of hypertension. The data used in this study are primary data from 200 athlete selection participants at the University of Surabaya and the Indonesian National Sports Committee (INSC) of East Java. This research method proposes to compare the traditional approach with machine learning to prove the accuracy comparison of the model's goodness, where both approaches are proposed by considering the novelty proposed through the machine learning approach but still maximizing the traditional approach. The proposed methods are binary logistic regression, binary logistic regression with the addition of random effects, highly randomized tree, and support vector classification. The binary logistic regression model is better than the binary logistic regression model with random effects, random trees, and support vector classification because the accuracy, sensitivity, specificity, and F1-score value (68.5%, 69%, 68%, and 68.8%) is highest than the others. Other results showed that the waist circumference variable, the father's occupation variable, and the salary variable significantly affected hypertension at the 5% significance level.
- 26 January 2026
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 20 (2)
Open AccessTRADITIONAL LOGISTIC REGRESSION AND MACHINE LEARNING APPROACHES OF SOCIODEMOGRAPHIC AND ANTHROPOMETRIC FACTORS INFLUENCING HYPERTENSION IN ATHLETES
The type and intensity of exercise performed by athletes play an important role in affecting blood pressure stability, putting them at risk of developing hypertension. Hypertension, or high blood pressure, is a medical condition in which the blood pressure in the arteries rises above normal limits. Hypertension in athletes becomes an essential factor in real cases if not detected early. Therefore, this study aims to model and analyse the sociodemographic and anthropometric factors that influence the incidence of hypertension. The data used in this study are primary data from 200 athlete selection participants at the University of Surabaya and the Indonesian National Sports Committee (INSC) of East Java. This research method proposes to compare the traditional approach with machine learning to prove the accuracy comparison of the model's goodness, where both approaches are proposed by considering the novelty proposed through the machine learning approach but still maximizing the traditional approach. The proposed methods are binary logistic regression, binary logistic regression with the addition of random effects, highly randomized tree, and support vector classification. The binary logistic regression model is better than the binary logistic regression model with random effects, random trees, and support vector classification because the accuracy, sensitivity, specificity, and F1-score value (68.5%, 69%, 68%, and 68.8%) is highest than the others. Other results showed that the waist circumference variable, the father's occupation variable, and the salary variable significantly affected hypertension at the 5% significance level.
- Open Access
- 26 January 2026
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 20 (2)
SPATIAL INTERPOLATION OF RAINFALL DATA USING COKRIGING AND RECURRENT NEURAL NETWORKS FOR HYDROLOGICAL APPLICATIONS IN SURABAYA, INDONESIA
Urban hydrological challenges, such as flooding and water resource management, require accurate rainfall data to support sustainable development. This study investigates the use of Recurrent Neural Networks (RNN) for spatial interpolation of monthly rainfall data across 31 districts in Surabaya, Indonesia, and compares its performance with the geostatistical method Cokriging. Elevation data were incorporated as an additional variable to account for geographical variability. The dataset was divided into training (26 locations) and testing (5 locations) subsets, with testing locations treated as missing data points to simulate real-world conditions. The results show that the RNN-based interpolation method achieved progressively lower Root Mean Square Error (RMSE) values from January (48.65) to April (13.78), indicating higher accuracy compared to the Cokriging method. These findings underscore the potential of RNN in addressing data gaps and spatial variability, offering robust solutions for hydrological applications in urban environments. This approach not only supports flood risk mitigation strategies but also contributes to optimizing drainage systems and water resource planning. Further research is recommended to incorporate additional environmental variables and extend the application to broader spatial and temporal contexts.
- 26 January 2026
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 20 (2)
Open AccessSPATIAL INTERPOLATION OF RAINFALL DATA USING COKRIGING AND RECURRENT NEURAL NETWORKS FOR HYDROLOGICAL APPLICATIONS IN SURABAYA, INDONESIA
Urban hydrological challenges, such as flooding and water resource management, require accurate rainfall data to support sustainable development. This study investigates the use of Recurrent Neural Networks (RNN) for spatial interpolation of monthly rainfall data across 31 districts in Surabaya, Indonesia, and compares its performance with the geostatistical method Cokriging. Elevation data were incorporated as an additional variable to account for geographical variability. The dataset was divided into training (26 locations) and testing (5 locations) subsets, with testing locations treated as missing data points to simulate real-world conditions. The results show that the RNN-based interpolation method achieved progressively lower Root Mean Square Error (RMSE) values from January (48.65) to April (13.78), indicating higher accuracy compared to the Cokriging method. These findings underscore the potential of RNN in addressing data gaps and spatial variability, offering robust solutions for hydrological applications in urban environments. This approach not only supports flood risk mitigation strategies but also contributes to optimizing drainage systems and water resource planning. Further research is recommended to incorporate additional environmental variables and extend the application to broader spatial and temporal contexts.
- Open Access
- 17 November 2025
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 11 (4) , 691-703
Enhanced diabetes and hypertension prediction using bat-optimized k-means and comparative machine learning models
This research aims to develop an analytical approach to classification statistics. The proposed approach combines machine learning with optimization. Considering the urgency of research related to exploring the best methods to apply to sports data. This study proposes a novel framework that combines the k-means clustering results with the bat algorithm to optimize performance prediction for athletes in Indonesia. The proposed method aims to explore the data by comparing the classification performance of random forests, extremely randomized trees, and support vector machines. We conducted a case study using primary data from 200 respondents at Surabaya State University and the East Java National Sports Committee. The accuracy results in this study indicate that, based on the performance evaluation metric, the best approach is random forest clustering using k-means with bat algorithm optimization, achieving 81.25% accuracy, compared with other machine learning approaches. This research contributes to the field of classification statistics by introducing a novel hybrid framework that integrates machine learning, clustering, and optimization techniques to improve predictive accuracy, particularly in sports analytics. Beyond sports science, the proposed approach can be adapted to other domains that require robust performance prediction and decision support, such as health analytics, educational assessment, and human resource selection.
- 17 November 2025
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 11 (4) , 691-703
Open AccessEnhanced diabetes and hypertension prediction using bat-optimized k-means and comparative machine learning models
This research aims to develop an analytical approach to classification statistics. The proposed approach combines machine learning with optimization. Considering the urgency of research related to exploring the best methods to apply to sports data. This study proposes a novel framework that combines the k-means clustering results with the bat algorithm to optimize performance prediction for athletes in Indonesia. The proposed method aims to explore the data by comparing the classification performance of random forests, extremely randomized trees, and support vector machines. We conducted a case study using primary data from 200 respondents at Surabaya State University and the East Java National Sports Committee. The accuracy results in this study indicate that, based on the performance evaluation metric, the best approach is random forest clustering using k-means with bat algorithm optimization, achieving 81.25% accuracy, compared with other machine learning approaches. This research contributes to the field of classification statistics by introducing a novel hybrid framework that integrates machine learning, clustering, and optimization techniques to improve predictive accuracy, particularly in sports analytics. Beyond sports science, the proposed approach can be adapted to other domains that require robust performance prediction and decision support, such as health analytics, educational assessment, and human resource selection.
- Open Access
- 13 January 2025
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 19 (1) , 97-106
STOCK PRICE PREDICTION AND SIMULATION USING GEOMETRIC BROWNIAN MOTION-KALMAN FILTER: A COMPARISON BETWEEN KALMAN FILTER ALGORITHMS
Stocks have high-profit potential but also have high risk. Many people have ways to forecast stock prices. The Geometric Brownian Motion (GBM) method forecasts stock prices. The data used in this study are closing stock price data from July 1, 2021 to August 31, 2021 taken from Yahoo! Finance. The stocks used in this research are Bank Rakyat Indonesia (BBRI), Indofood Sukses Makmur (INDF), and Telkom Indonesia (TLKM). A strategy is carried out to improve prediction accuracy by utilising the Kalman Filter (KF). This research will compare the mean absolute percentage error (MAPE) value between GBM-KF, which was manually computed and computed using the Python library. As an example of this research, for BBRI stock, the high GBM MAPE value of 9.02% can be reduced to 3.52% with manually computed GBM-KF and 3.68% with Python library computed GBM-KF. Similarly, INDF and TLKM stocks are showing a significant reduction in MAPE values to deficient levels in some cases. The GBM-KF method employing manual computing may enhance the overall precision of stock price forecasting. Future research may enhance this study by using the GBM-KF model on alternative financial instruments, integrating supplementary market data, or evaluating its efficacy under extreme market conditions.
- 13 January 2025
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 19 (1) , 97-106
Open AccessSTOCK PRICE PREDICTION AND SIMULATION USING GEOMETRIC BROWNIAN MOTION-KALMAN FILTER: A COMPARISON BETWEEN KALMAN FILTER ALGORITHMS
Stocks have high-profit potential but also have high risk. Many people have ways to forecast stock prices. The Geometric Brownian Motion (GBM) method forecasts stock prices. The data used in this study are closing stock price data from July 1, 2021 to August 31, 2021 taken from Yahoo! Finance. The stocks used in this research are Bank Rakyat Indonesia (BBRI), Indofood Sukses Makmur (INDF), and Telkom Indonesia (TLKM). A strategy is carried out to improve prediction accuracy by utilising the Kalman Filter (KF). This research will compare the mean absolute percentage error (MAPE) value between GBM-KF, which was manually computed and computed using the Python library. As an example of this research, for BBRI stock, the high GBM MAPE value of 9.02% can be reduced to 3.52% with manually computed GBM-KF and 3.68% with Python library computed GBM-KF. Similarly, INDF and TLKM stocks are showing a significant reduction in MAPE values to deficient levels in some cases. The GBM-KF method employing manual computing may enhance the overall precision of stock price forecasting. Future research may enhance this study by using the GBM-KF model on alternative financial instruments, integrating supplementary market data, or evaluating its efficacy under extreme market conditions.
- Open Access
- 31 July 2024
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 18 (3) , 1391-1402
LOGISTIC AND PROBIT REGRESSION MODELING TO PREDICT THE OPPORTUNITIES OF DIABETES IN PROSPECTIVE ATHLETES
Diabetes is among the most prevalent chronic diseases globally, posing significant health risks to individuals. The identification of individuals at risk of developing these conditions is of paramount importance, particularly in high-stress and physically demanding activities such as athletic training. To find out the chances of a prospective athlete suffering from diabetes or not, models for binary data can be used, including logistic regression and probit models. The data used is primary data from prospective athletes in East Java, including prospective athletes from the State University of Surabaya and East Java Koni Athletes. This study aimed to develop an early prediction model for diabetes in prospective athletic candidates using a bivariate logistic and probit regression approach while considering the influence of socio-demographic and anthropometric factors. To selecting the best model between logistic regression and probit regression using Akaike’s Information Criterion (AIC) value, the smaller the AIC value gets means that the model is closer to the actual value or being the best model. Logistic regression has a smaller AIC value (129,85) than probit regression, this means that the logistic model is the best model. In this paper, an attempt is made to explore the use of logistic and probit regression to determine the factors which significantly influence the diabetes disease and we got that the logistic model as the best model because it has a smaller AIC value than the probit model. Based on the result of analysis and discussion, it can be concluded that there are two factors called mother’s job and finance which are influenced to the response variable, diabetes disease at significance level of 5%.
- 31 July 2024
- Published by Universitas Pattimura in BAREKENG: Jurnal Ilmu Matematika dan Terapan
- Vol. 18 (3) , 1391-1402
Open AccessLOGISTIC AND PROBIT REGRESSION MODELING TO PREDICT THE OPPORTUNITIES OF DIABETES IN PROSPECTIVE ATHLETES
Diabetes is among the most prevalent chronic diseases globally, posing significant health risks to individuals. The identification of individuals at risk of developing these conditions is of paramount importance, particularly in high-stress and physically demanding activities such as athletic training. To find out the chances of a prospective athlete suffering from diabetes or not, models for binary data can be used, including logistic regression and probit models. The data used is primary data from prospective athletes in East Java, including prospective athletes from the State University of Surabaya and East Java Koni Athletes. This study aimed to develop an early prediction model for diabetes in prospective athletic candidates using a bivariate logistic and probit regression approach while considering the influence of socio-demographic and anthropometric factors. To selecting the best model between logistic regression and probit regression using Akaike’s Information Criterion (AIC) value, the smaller the AIC value gets means that the model is closer to the actual value or being the best model. Logistic regression has a smaller AIC value (129,85) than probit regression, this means that the logistic model is the best model. In this paper, an attempt is made to explore the use of logistic and probit regression to determine the factors which significantly influence the diabetes disease and we got that the logistic model as the best model because it has a smaller AIC value than the probit model. Based on the result of analysis and discussion, it can be concluded that there are two factors called mother’s job and finance which are influenced to the response variable, diabetes disease at significance level of 5%.