Framework Internet of Things (IoT) Untuk Memprediksi Kecepatan Optimal Dalam Balap Sepeda Pada Road Bike

Abstract

This study aims to develop an Internet of Things (IoT) system framework to predict the optimal cycling speed for road bike athletes using multisensor data and machine learning. The primary issue addressed is the absence of an intelligent system capable of integrating physiological, performance, and environmental data in real-time to recommend context-aware optimal speed for cyclists. The proposed framework comprises four functional layers: Data Acquisition Layer, Data Processing & Feature Layer, Predictive Modeling Layer, and Recommendations & Ouput Layer. The modeling process using algorithms Gradient Boosting Regression. An end-to-end implementation was validated using real-world cycling activity data from the Garmin Connect platform. Experimental results demonstrate that the system can deliver precise optimal speed estimates and effective pacing zone recommendations that positively impact athlete performance strategies. This research contributes novel elements including adaptive multivariable data integration, personalized context-based prediction, and a modular IoT architecture deployable on both cloud and edge platforms.