Ahmad M. Khachan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ahmad M. Khachan has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Ahmet Özmen
Sakarya University, Faculty of Computer and Information Sciences, Department of Software Engineering
1 shared publication - Ceyda Aksoy Tırmıkçı
Sakarya University
1 shared publication - Devrim Akgun
Software Engineering Department, Sakarya University, Sakarya, Turkey
1 shared publication - Elfatih Abdelrahman Ahmed Elsheikh
Department of Electrical Engineering, College of Engineering, King Khalid University, Abha 61421, Saudi Arabia
1 shared publication - Eltahir Idris Eltahir Mohamed
Department of Information Systems and Technology, Sakarya University, Esentepe Campus, Sakarya 54050, Türkiye
1 shared publication - Sohaib Ashri
Department of Applied Physics and Mathematics, Faculty of Applied Sciences and Computer, Omdurman Ahlia University, Omdurman P.O. Box 786, Khartoum, Sudan
1 shared publication
Latest Publications
- Open Access
Horizon-Dependent Solar Irradiance Forecasting with Boosted Trees, and Seasonal Baselines Based on Measurements in Sudan
Solar irradiance forecasting accuracy depends on the prediction horizon because the use of recent observations, meteorological variables, and seasonal patterns changes with lead time. However, weak persistence baselines, temporally unreliable validation, and inconsistent test samples can overstate the advantage of complex models. This paper presents a leakage-safe, horizon-specific solar irradiance forecasting framework combining boosted trees, validation-weighted convex forecast combinations, and seasonal reference models. Direct forecasts are evaluated at 10-min and 1-, 3-, 6-, 12-, and 24-h horizons. Models are tuned using expanding-window validation; preprocessing is fitted only to the training data; and every method is evaluated on a predefined canonical test support. XGBoost achieves the lowest root mean square error (RMSE), 10.78 W/m2, at 10 min, whereas CatBoost achieves the lowest RMSE, 16.08 W/m2, at 1 h. At 3, 12, and 24 h, the lowest RMSE is obtained by seasonally guided forecast combinations. At 6 h, the XGBoost and two-day seasonal-mean combination ranks first by RMSE, although its gain over the two-day seasonal mean results in a larger mean absolute error (MAE). Daily-block significance tests show an improvement over the reference models at 10 min, while improvements over seasonal references at longer horizons are not statistically significant after adjustment. The framework provides a reproducible benchmark for horizon-dependent solar irradiance forecasting.
Open AccessHorizon-Dependent Solar Irradiance Forecasting with Boosted Trees, and Seasonal Baselines Based on Measurements in Sudan
Solar irradiance forecasting accuracy depends on the prediction horizon because the use of recent observations, meteorological variables, and seasonal patterns changes with lead time. However, weak persistence baselines, temporally unreliable validation, and inconsistent test samples can overstate the advantage of complex models. This paper presents a leakage-safe, horizon-specific solar irradiance forecasting framework combining boosted trees, validation-weighted convex forecast combinations, and seasonal reference models. Direct forecasts are evaluated at 10-min and 1-, 3-, 6-, 12-, and 24-h horizons. Models are tuned using expanding-window validation; preprocessing is fitted only to the training data; and every method is evaluated on a predefined canonical test support. XGBoost achieves the lowest root mean square error (RMSE), 10.78 W/m2, at 10 min, whereas CatBoost achieves the lowest RMSE, 16.08 W/m2, at 1 h. At 3, 12, and 24 h, the lowest RMSE is obtained by seasonally guided forecast combinations. At 6 h, the XGBoost and two-day seasonal-mean combination ranks first by RMSE, although its gain over the two-day seasonal mean results in a larger mean absolute error (MAE). Daily-block significance tests show an improvement over the reference models at 10 min, while improvements over seasonal references at longer horizons are not statistically significant after adjustment. The framework provides a reproducible benchmark for horizon-dependent solar irradiance forecasting.
- 4 January 2019
- Published by Wiley in Computer Applications in Engineering Education
- Vol. 27 (3) , 543-552
IMSSAP: After‐school interactive mobile learning student support application
Traditional methods intended for education are no longer suitable for it, since they are unable to meet the students’ learning needs. M‐learning is becoming a global interest. Various studies were conducted in many countries such as South Korea, Taiwan, UK, Malaysia, Serbia, European Union, and Saudi Arabia investigating student's readiness to adopt M‐learning. Our study aims to introduce a new mobile bite‐sized learning tool and to explore student's readiness to adopt M‐learning and to investigate the motivational and acceptance factors related to it. We introduced our learning tool (IMSSAP), after‐school interactive M‐learning student support Application, to university students from different majors in Turkey. Analysis of the questionnaire data revealed that an easy to use tool with social media collaboration and sharing capabilities appears to be the vital factors that will motivate students to adopt M‐learning. An improvement in the relation between the students, the teachers and the academic institution was obvious. Student's performance got much better added to better analytical and critical skills advancement. We have compared IMSSAP with another learning tool in the same class for clarity and reliability of the results.Highlights: A cloud‐based mobile application built with Google‐Firebase platform in the model of Backend as a Service (BaaS). Bite‐sized learning methodology used to fulfill student's needs in a social circle era. Lightweight learning tool created for knowledge sharing and a learning process monitoring facility.
- 4 January 2019
- Published by Wiley in Computer Applications in Engineering Education
- Vol. 27 (3) , 543-552
IMSSAP: After‐school interactive mobile learning student support application
Traditional methods intended for education are no longer suitable for it, since they are unable to meet the students’ learning needs. M‐learning is becoming a global interest. Various studies were conducted in many countries such as South Korea, Taiwan, UK, Malaysia, Serbia, European Union, and Saudi Arabia investigating student's readiness to adopt M‐learning. Our study aims to introduce a new mobile bite‐sized learning tool and to explore student's readiness to adopt M‐learning and to investigate the motivational and acceptance factors related to it. We introduced our learning tool (IMSSAP), after‐school interactive M‐learning student support Application, to university students from different majors in Turkey. Analysis of the questionnaire data revealed that an easy to use tool with social media collaboration and sharing capabilities appears to be the vital factors that will motivate students to adopt M‐learning. An improvement in the relation between the students, the teachers and the academic institution was obvious. Student's performance got much better added to better analytical and critical skills advancement. We have compared IMSSAP with another learning tool in the same class for clarity and reliability of the results.Highlights: A cloud‐based mobile application built with Google‐Firebase platform in the model of Backend as a Service (BaaS). Bite‐sized learning methodology used to fulfill student's needs in a social circle era. Lightweight learning tool created for knowledge sharing and a learning process monitoring facility.