4 July 2023 in Computers and Education: Artificial Intelligence
9 July 2021 in IEEE Access
Educational process mining is one of the research domains that utilizes students’ learning behavior to match students’ actual courses taken and the designed curriculum. While most works attempt to deal with the case perspective (i.e., traces of the cases), the temporal case perspective has not been discussed. The temporal case perspective aims to understand the temporal patterns of cases (e.g., students’ learning behavior in a semester). This study proposes modified cluster evolution analysis, called profile-based cluster evolution analysis, for students’ learning behavior based on profiles. The results show three salient features: (1) cluster generation; (2) within-cluster generation; and (3) time-based between-cluster generation. The cluster evolution phase modifies the existing cluster evolution analysis with a dynamic profiler. The model was tested on actual educational data of the Information System Department in Indonesia. The results showed the learning behavior of students who graduated on time, the learning behavior of students who graduated late, and the learning behavior of students who dropped out. Students changed their learning behavior by observing the migration of students from cluster to cluster for each semester. Furthermore, there were distinct learning behavior migration patterns for each category of students based on their performance. The migration pattern can suggest to academic stakeholders to understand about students who are likely to drop out, graduate on time or graduate late. These results can be used as recommendations to academic stakeholders for curriculum assessment and development and dropout prevention.
11 July 2026 in SSRN Electronic Journal
The critical frequency of the F2 layer (𝑓𝑜𝐹2) derived from ionograms is a crucial parameter for operational space weather analysis. However, existing methods for determining 𝑓𝑜𝐹2 values still struggle to balance speed, accuracy, and reduced manpower. To address this requirement, various methods have been proposed, including the use of Frequency-Time-Intensity (FTI) plots to determine daily 𝑓𝑜𝐹2 for operational information. This research proposes an automated approach using deep learning-based image segmentation on FTI ionogram plots. We evaluated four segmentation decoder architecturesFeature Pyramid Network (FPN), DeepLabV3, UNet, and PSPNet combined with three encoders: ResNet, EfficientNet, and Con-vNeXT. Our proposed method achieves a 66% reduction in residual error compared to traditional methods and a 3,000x increase in operational speed due to instantaneous computational processing. Consequently, our approach significantly reduces the time required for ionogram analysis while delivering greater accuracy.