AI Empowers Traditional Physical Education Teaching in Higher Vocational Education: Exploring New Paths for the Integration of Health Education

Summary

This protocol describes the integration of an AI-guided atomization sensing system that monitors respiration, temperature, and motion to adapt health education content in real-time during vocational physical education, and evaluates its effects through a six-week quasi-experiment.

Abstract

This study evaluates an AI-guided atomization sensing system designed to integrate adaptive health education into vocational physical education. A quasi-experimental design was conducted with 356 participants allocated to either an intervention group (n = 178) or a control group (n = 178). The system used wearable atomization sensors (monitoring respiratory patterns, ambient temperature, and motion) connected to an AI engine that applied rule-based and machine-learning logic to adjust instructional content in real time-for example, reducing complexity or switching to audiovisual demonstrations when signs of fatigue were detected. Sessions were delivered in classroom settings twice per week for six weeks, with surveys administered immediately before and after the intervention. Five outcomes were assessed using validated instruments: knowledge retention, engagement, behavioral intention, self-efficacy, and technology acceptance. Statistical analyses included ANOVA, paired-sample t-tests, Pearson correlations, and χ² tests, with results reported as F(df1, df2), p, η², and 95% confidence intervals where applicable. The intervention group achieved significantly greater improvements than the control group in knowledge retention (Δ = +21.7 vs. +10.6; F(1, 354) = 46.21, p < 0.001, η² = 0.21), engagement (F(1, 354) = 39.87, p < 0.001, η² = 0.18), behavioral intention (F(1, 354) = 42.55, p < 0.001, η² = 0.19), self-efficacy (F(1, 354) = 27.63, p < 0.001, η² = 0.13), and technology acceptance (F(1, 354) = 35.12, p < 0.001, η² = 0.17). These findings demonstrate that combining real-time sensing with AI-guided decision support provides a reproducible, adaptive framework for enhancing health education outcomes in vocational PE settings.

Introduction

Health education is a cornerstone of modern public health, improving individuals' knowledge, attitudes, and health-related behaviors¹. Strengthening self-management skills enables people to make informed decisions, adopt preventive practices, and engage in healthier lifestyles². However, conventional delivery methods, such as classroom lectures, printed materials, and generic online modules, often provide limited interactivity and personalization³. These approaches typically fail to respond to learners' real-time needs, resulting in modest engagement and constrained behavioral change

Protocol

This study was reviewed and approved by the Institutional Review Board of Shijiazhuang Institute of Railway Technology. All procedures complied with the Declaration of Helsinki and relevant local regulations. The equipment and software used are listed in the Table of Materials.

1. Methodology

This study used a quasi-experimental design to evaluate an AI-guided atomization sensing system for digital health education in higher-education settings. Data were collected before and after the intervention to assess knowledge retention, engagement, behavioral intention, self-efficacy, and technology accepta....

Results

Experimental results

To assess the effectiveness of the AI-driven atomization sensing system, multiple statistical analyses were conducted.

The ANOVA findings revealed clear group differences across all five outcomes, with participants in the intervention group achieving consistently higher post-test scores than those in the control group (Table 2; Figure 3).

When within-grou.......

Discussion

The findings of this study provide supportive evidence that integrating AI-powered intelligent atomization sensing technology into health education can enhance learning outcomes across multiple dimensions. Compared with the control group, participants in the intervention group exhibited statistically significant improvements in all five measured variables, with the largest gains observed in knowledge retention (F = 18.73, SS = 62.47, p < 0.001), followed by behavioral intention (F = 16.95, SS = 54.32, p < 0.001),.......

Materials

List of materials used in this article

Name	Company	Catalog Number	Comments
AtomWear X100 wearable sensors	Shenzhen AtomTech Co., Ltd., China	X100	Wearable sensor for monitoring respiratory frequency, ambient temperature, and motion signals (sampling rate: 100 Hz, accuracy: ±0.1).
AI Engine (rule-based + SVM classifier)	Custom implementation	Python 3.9 with TensorFlow 2.10 and scikit-learn 0.24	Algorithm for adaptive decision support: integrates sensor data and adjusts instructional delivery.
Behavioral Intention Scale	Adapted from Ajzen (1991), Theory of Planned Behavior	3 items	Assesses intention to adopt health practices.
Engagement Scale	Adapted from Sun et al. (2019)	5 items	Measures attention, interaction, emotional involvement, persistence, and satisfaction.
Knowledge Retention Test (15-item MCQ)	Custom, aligned with instructional content		15-item multiple-choice test on aerobic exercise and health knowledge.
Multimedia Classroom Setup	Standard higher education classrooms		Classroom (~50 m²), projector, base stations for sensor connectivity.
Python	Python Software Foundation	Version 3.9	Programming environment for AI engine and preprocessing.
scikit-learn	Open source	Version 0.24	Machine learning library for SVM classification.
Self-Efficacy Scale	Adapted from Bandura (1997)	4 items	Assesses confidence in performing health exercises.
SPSS Statistics Software	IBM Corp., Armonk, NY, USA	Version 25	Statistical analysis (ANOVA, t-tests, correlation, χ² tests).
Technology Acceptance Scale	Adapted from UTAUT (Venkatesh et al., 2003)	6 items	Covers performance expectancy, effort expectancy, social influence, and facilitating conditions.
TensorFlow	Google Brain	Version 2.10	Deep learning library used in AI engine.