Intelligent Community Sports: Integrating IoT and Artificial Intelligence to Enhance Physical Activity Monitoring

Community sports are essential for encouraging social contact, physical fitness, and community involvement. They offer easily accessible chances for people of all ages, backgrounds, and abilities to engage in competitive and recreational sports. Intelligent Community Sports is a novel concept that potentially alters how physical activity is tracked, assessed, and optimized in local communities through the use of Internet of Things (IoT) devices and Artificial Intelligence (AI) algorithms. The goal of the research is to develop intelligent community sports that improve physical activity monitoring by using AI and the IoT. We propose a novel Efficient Bumble Bee Mating Kernelized Support Vector Machine (EBBM-KSVM) to predict the soccer player’s physical activity and identify key patterns related to intensity and positioning. The model reflects player attributes and activity patterns by using accelerometer-based wearables to record vital information on activities like sprinting, kicking, dribbling, and running. Data were collected through IoT-enabled wearable devices that capture activity data from soccer players. The data were preprocessed using Kalman filtering to remove noise from sensor data. Short-Time Fourier Transform (STFT) is used to extract the features from preprocessed data. The proposed system was validated using various metrics such as accuracy (98.5%), precision (97.5%), recall (93.1%), and F1-score (95.1%). The findings show that the proposed model performs better than other traditional algorithms in predicting physical activity. The research demonstrates the potential of IoT and AI technologies in enhancing community sports by improving performance monitoring, personalized feedback, and inclusive participation strategies.