Yomna M.I. Hassan

Dr. Yomna M.I. Hassan

Media Engineering and Technology, German University in Cairo, Cairo, Al Qāhirah, Egypt
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 May 2022 in IEEE Access
Verified
Journal Article
Open access
Yomna M.I. HassanYomna M.I. Hassan
Yomna M.I. Hassan
AEAbeer Elkorany
Abeer Elkorany
Khaled WassifKhaled Wassif
Khaled Wassif
The importance of e-learning has exceeded expectations over the past decade. Accordingly, several systems have been developed in completing intelligent assistive tools where students’ behavior can be tracked and followed with suitable recommendations to enhance students’ performance. This paper has two main objectives. First, the Community of Inquiry framework (CoI) is utilized as one of the most prominent student behavioral modeling to select features that best represent the students. According to experts’ annotation, this study filters students’ measured attributes from the StudentLife dataset to the CoI model, focusing on social presence. Second, the research looks at improving the accuracy and runtime of the Grade Point Average (GPA) prediction by introducing a hybrid model that combines combining k-means clustering phase based on student similarity with regression-based prediction. The clustering was performed on both static and Spatio-temporal (spatial time -series) students’ attributes. Results show that LassoCV outperforms other regression techniques such as Standard Linear, Lasso, and Ridge Regression with an RMSE averaged around 0.15 and an average Adjusted R2 of 0.935 overall trials. Selecting the features according to the CoI reduces the number of features by 62.8%. Time-series clustering on its own was not beneficial; however, when conducted with the selection phase, it raised the quality of the model achieved by 2-3%.

10 October 2026 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
Yomna M.I. HassanYomna M.I. Hassan
Yomna M.I. Hassan
MAMahy Ayman
Mahy Ayman
MOMariam Othman
Mariam Othman
NMNour Mahmoud
Nour Mahmoud
ZTZeina Tamer
Zeina Tamer
This study presents a weather-based anomaly detection framework for wind-turbine monitoring using public EDP (Energias de Portugal) measurements and failure records. Principal Component Analysis (PCA) groups related variables, and Seasonal-Trend decomposition using LOESS "Locally Estimated Scatterplot Smoothing" (STL) separates regular patterns from unusual changes in five weather variables. Performance is compared with matches that could occur by chance. Incomplete days are excluded from alert generation without replacing missing values with zeros; interpolation is used only to fit STL. The 2016 dataset contains 364 complete days and 16 failures across five turbines. The evaluation includes 181 dated alert–failure matches and 24 parameter settings. The setting with the largest average improvement over a shifted-date baseline achieves precision of 0.71–0.87 and an average combined event score, F1*, of 0.80, compared with 0.72 for the baseline (p=0.20). Humidity alerts precede all 16 failures, with 27 true alerts and four false alerts. Pre-failure windows cover 69.7% of the year and 76.0% of days available for evaluation. The results support further investigation, while performance on future data remains unproven. Clear missing-data rules, dated matches, parameter comparisons, and chance baselines support future integration with turbine operating data.