Classification of physical exercises is an important task in many applications, particularly within health services. Innowearable AB has developed a device called Inno-X that collects data using an accelerometer and sEMG sensors. To optimizeInno-X, a Machine Learning AI must be implemented for real-time exercise classification, balancing simplicity and flexibility for maximum market impact. This enhances efficiency and accuracy in analysis. This thesis investigates how raw data from Inno-X can be used to implement a pipeline and a machine-learning AI with the purpose of classifying physical exercises in real time. Starting from implementing a protocol for collecting data to a finished end-to-end pipeline and AI that can perform the classification, this thesis includes all the steps in between. Comparison of different machine learning algorithms and the execution of transitioning from a training environment to a real-time environment has led to the obtained result. The highest accuracy achieved in the training and real-time environment was 96.98% and 90.00%, respectively. This thesis concludes that the more complex machine-learning algorithms perform better in the training environment, and the less complex algorithms perform better in the real-time environment.