Table 5 Experimental configuration parameters for control and experimental groups.
From: Intelligent optimization of track and field teaching using machine learning and wearable sensors
Parameter category | Control group configuration | Experimental group configuration | Measurement frequency |
|---|---|---|---|
Instructional modality | Traditional demonstration-based teaching with verbal feedback | ML-optimized adaptive sequence with sensor-based feedback | Continuous |
Performance assessment | Standard rubric-based evaluation (5-point Likert) | Quantitative biomechanical metrics with ML error classification | Bi-weekly |
Feedback latency | Instructor-dependent (M = 7.6s, SD = 4.2s) | Automated real-time (M = 67ms, SD = 12ms) | Measured per session |
Technique sequencing | Fixed curriculum progression based on established pedagogy | Adaptive progression based on individual learning trajectories | Updated daily |
Difficulty calibration | Instructor judgment | Algorithmic optimization (α = 0.65, β = 0.85, η = 0.03) | Per-technique execution |
Model update schedule | N/A | Incremental training (batch = 32) after each session | Daily |
Evaluation metrics | Subjective technical proficiency, standardized performance | Biomechanical alignment, performance metrics, injury risk | Weekly |
Data collection | Manual performance recording | Multimodal sensor array with automated synchronization | Continuous (200 Hz) |
