Biometrics recognition technology utilizes unique biological characteristics such as fingerprints, iris patterns, facial features, or voiceprints to identify and authenticate individuals. Through advanced algorithms and pattern recognition techniques, biometric systems capture and analyze these physiological or behavioral traits to verify a person's identity. This technology offers high levels of security and accuracy, making it valuable for various applications including access control, time and attendance tracking, border security, and digital payments. The construction of an athletes' physical condition monitoring and analysis system utilizing biometric recognition technology represents a significant advancement in sports science. By integrating cutting-edge biometric sensors and recognition algorithms, this system provides real-time insights into athletes' physiological parameters and performance metrics. Athlete performance monitoring and analysis play pivotal roles in optimizing training strategies, preventing injuries, and enhancing overall athletic performance. In this paper, we propose a novel approach leveraging the Hybrid Multi-Instance Ensemble Classifier (HMIEC) combined with biometric recognition technology to accurately classify athlete data and assess their physical condition. Our study explores the effectiveness of HMIEC across multiple biometric modalities, including ECG-based, fingerprint-based, and facial recognition, in identifying athletes and monitoring their physical parameters. Through a series of experiments and analyses, demonstrate HMIEC's superior classification performance compared to other classifiers, with high accuracy, sensitivity, specificity, and area under the curve (AUC). The reductions in heart rate from 75 to 65 beats per minute, increase in oxygen saturation levels from 98% to 99%, decreases in blood pressure readings from 120/80 mmHg to 110/70 mmHg, and enhancements in flexibility from 30 to 35 centimeters, muscle strength from 100 lbs to 120 lbs, and endurance capacity from 20 to 25 minutes.