.png){kind=icon}
Return
Jump Rope Exercise Assistance Program
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3496510.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Jump rope exercise requires a fast tempo and breathing, which often leads to the problem of users forgetting their jump count during the workout. To address this issue, we propose a jump rope exercise assistance program that recognizes the user's jump rope motions and analyzes the impact of joint coordinates on these motions. The proposed solution extracts frame-by-frame joint coordinate data from jump rope performance videos. It then utilizes artificial intelligence models to recognize jump rope motions and measure the jump count through motion recognition. We employed five machine learning models and two deep learning models to validate the jump rope motion recognition and count measurement. We analyzed the joint coordinates significantly influencing each jump rope motion using SHAP. Furthermore, we used Odds Ratios to analyze the jump rope motion occurrence probability based on joint coordinate values. Through these methods, we confirmed that the proposed solution effectively performs jump rope motion recognition and joint coordinate impact analysis for jump rope motions.
Keywords:
Data models
Training
Data mining
Analytical models
Accuracy
Real-time systems
Random forests
Long short term memory
Boosting
Artificial intelligence
Exercise assistance program
artificial intelligence
jump rope recognition
jump rope factor analysis
jump rope odd ratio
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
Organization
Cited Papers
ShareSaveShareSaveShareSaveTowards understanding of electrolyte degradation in lithium-mediated non-aqueous electrochemical ammonia synthesis with gas chromatography-mass spectrometry.png)
RSC Advances
OAAI
RSC AdvancesIF0
OAAIShareSaveShareSaveShareSaveShareSave no more
no more