Summary of performance metrics for a five-activity classification model. The table presents the F1 score, precision, recall, and support for each activity class—other, eating, exercise, medication, and smoking—over multiple folds of the data. The ‘macro avg’ represents the average performance metrics computed by averaging the scores of all classes, treating all classes equally. The ‘weighted avg’ provides an average score weighted by the support (the number of true instances for each label), reflecting the influence of each class on the overall metric. These statistics demonstrate the model’s balanced performance across different types of activities, highlighting its potential applicability in diverse real-world scenarios.