This thesis presents a procedure to collect, process, and analyse data for use in machine learning models within the rifle marksmanship domain. The machine learning model, features, and analysis presented in this thesis provide a first step towards models that can provide automated assistance for rifle marksmanship practice.A quasi-experiment is designed with eye movement and rifle handling as independent variables, and shooting result as dependent variable. The data is collected by letting 14 participants with different levels of marksmanship experience perform a rifle shooting exercise. Eye movement data is gathered using a Tobii Pro Glasses 3 eye tracker, and rifle handling data is gathered using an iCubeX Orient3D IMU. Analysis from the data shows a stratification of participant rifle marksmanship experience into five classes. The highest performing group, to a larger degree than the other groups, aimed with both eyes open, has a faster rifle acceleration, has a lower time between peak motion and shot, and are overall more consistent with their shots. A prototype random forest classification model trained to predict these classes shows a Cohen’s Kappa of 0.526, balanced accuracy of 0.599 and a one-vs-all AUC between 0.83 and 0.95 for the classes.

There is a lack of data-driven training instructions for sports shooters, as instruction has commonly been based on subjective assessments. Many studies have correlated body posture and balance to shooting performance in rifle shooting tasks, but most of them have focused on single aspects of postural control. This thesis has focused on finding relevant rifle shooting factors by examining the entire body over sequences of time. We performed a data collection with 13 human participants who carried out live rifle shooting scenarios while being recorded with multiple biometric sensors, including several body trackers. An experiment was conducted to identify what aspects of rifle shooting could be predicted and explained using these data. We employed a pre-processing pipeline to produce a novel skeleton sequence representation, and used it to train a transformer model. The predictions from this model could be explained on a per sample basis using the attention mechanism, and visualised in an interactive format for humans to interpret. It was possible to separate the different phases of a shooting scenario from body posture with a high classification accuracy (81%). However, no correlation could be shown between shooting performance and body posture from our data. Future work could focus on novel feature engineering, and on examining alternative machine learning approaches. The dataset and pre-processing pipeline, as well as the techniques for generating explainable predictions presented in this thesis has laid the groundwork for future research in the sports shooting domain.