Related Experiment Video
Updated: Jan 7, 2026
12:55
Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties
Published on: September 27, 2020
8.9K
Beyond peak accuracy: a stability-centric framework for reliable multimodal student engagement assessment
Ismail Said Almuniri1,2, Hitham Alhussian3, Norshakirah Aziz3
1Department of Computing, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia. Almuniri4444@gmail.com.
Scientific Reports
|January 4, 2026
Summary
This study introduces a new multimodal framework for assessing student engagement in technology-enhanced learning. It improves accuracy and interpretability by addressing class imbalance and enhancing model stability.
Area of Science:
- Educational Technology
- Artificial Intelligence
- Machine Learning
Background:
- Accurate student engagement assessment is crucial for technology-enhanced learning.
- Existing models struggle with class imbalance, instability, and limited interpretability.
Purpose of the Study:
- To develop a robust multimodal engagement assessment framework.
- To enhance model stability, interpretability, and address class imbalance.
Main Methods:
- Utilized class-aware loss functions for imbalanced data.
- Employed temporal data augmentation and heterogeneous ensembling for stability.
- Applied SHAP-based analysis for model interpretability.
Main Results:
- Achieved mean accuracy of 0.901 ± 0.043 and mean macro F1 of 0.847 ± 0.068.
- Outperformed baseline models like ResNet, Inception, and LightGBM.
- Identified temporal augmentation and ensemble diversity as key contributors to performance.
Conclusions:
- Balanced evaluation and ensemble stability are essential for reliable student engagement assessment.
- The proposed framework offers a significant advancement in multimodal engagement assessment.
- MCNN and TimeCNN architectures are optimal for deployment due to efficiency and accuracy.
Related Concept Videos
01:29Self-Evaluation Maintenance Model
248
The Self-Evaluation Maintenance (SEM) model offers a psychological framework to understand how individuals’ self-esteem is influenced by the achievements of others, particularly those with whom they share close personal bonds. The SEM model operates when personal rather than social identity guides individuals. Central to this model is the notion that individuals have an inherent desire to preserve a favorable self-image, which is continuously shaped by interpersonal comparisons and...
248
01:29Reliability and Validity
13.7K
Reliability and validity are two important considerations that must be made with any type of data collection. Reliability refers to the ability to consistently produce a given result. In the context of psychological research, this would mean that any instruments or tools used to collect data do so in consistent, reproducible ways.
13.7K
01:14Stability of structures
431
In mechanical engineering, the stability of systems under various forces is critical for designing durable and efficient structures. One fundamental way to explore these concepts is by analyzing systems like two rods connected at a pivot point, O, with a torsional spring of spring constant k at the pivot point. This system is similar in appearance to a scissor jack used to change tires on a car. In this case, the arms of the linkage (equivalent to the rods in this system) are entirely vertical,...
431
01:14Rotter's Locus of Control
840
Julian Rotter introduced the concept of locus of control, a cognitive factor that significantly influences personality development and learning. Locus of control refers to an individual's beliefs about the extent of control they have over events in their lives. According to Rotter, this belief system can be categorized into two types: internal and external locus of control.
Individuals with an internal locus of control believe that their personal efforts and decisions directly affect their...
Individuals with an internal locus of control believe that their personal efforts and decisions directly affect their...
840
01:28Stability
348
The time response of a linear time-invariant (LTI) system can be divided into transient and steady-state responses. The transient response represents the system's initial reaction to a change in input and diminishes to zero over time. In contrast, the steady-state response is the behavior that persists after the transient effects have faded.
The stability of an LTI system is determined by the roots of its characteristic equation, known as poles. A system is stable if it produces a bounded...
The stability of an LTI system is determined by the roots of its characteristic equation, known as poles. A system is stable if it produces a bounded...
348
01:24Pole and System Stability
857
The transfer function is a fundamental concept representing the ratio of two polynomials. The numerator and denominator encapsulate the system's dynamics. The zeros and poles of this transfer function are critical in determining the system's behavior and stability.
Simple poles are unique roots of the denominator polynomial. Each simple pole corresponds to a distinct solution to the system's characteristic equation, typically resulting in exponential decay terms in the system's...
Simple poles are unique roots of the denominator polynomial. Each simple pole corresponds to a distinct solution to the system's characteristic equation, typically resulting in exponential decay terms in the system's...
857