The AI coach

Abstract

The study aims to investigate the effect of a 5-week artificial intelligence-generated calisthenics training program (AIGCTP) on health-related physical fitness components, including flexibility, cardiovascular endurance, and muscular endurance. Utilizing a quasi-experimental design, the study employed a one-group pre-test-post-test design for within-group comparisons and a two-group pre-test-post-test design for between-group comparisons. Participants included 87 untrained collegiate students, divided into the AIGCTP group (43 participants) and a human-made calisthenics training program (HMCTP) group (44 participants), selected via purposive sampling. A paired t-test was used for within-group comparisons, and an independent sample t-test was used for between-group comparisons. The findings indicated that the AIGCTP effectively improved the flexibility of the lower extremities and the muscular endurance of the core and upper extremities. However, female participants did not show significant improvements in any health-related physical fitness components, whereas male participants demonstrated improvements in the flexibility of the lower extremities and muscular endurance of the upper extremities. The HMCTP was effective in improving the flexibility and muscular endurance of the lower and upper extremities for all participants. Between-group comparisons revealed that the cardiovascular endurance of the HMCTP group was significantly superior to that of the AIGCTP group, irrespective of sex. Additionally, males in the HMCTP group exhibited significantly higher muscular endurance of the lower extremities compared to those in the AIGCTP group. The study suggests that AI can be used for fitness training, but professional-made programs are superior in some areas. Future research should replicate these findings, examine more fitness components, and explore longer training durations for further validation.