This study explores the application of machine learning techniques to accurately classify human activities using sensor data. The research focuses on extracting meaningful features from accelerometer signals and training various machine learning models to recognize activities such as walking, sitting, lying, and standing. The process involves collecting accelerometer data from smartphones, preprocessing the data, and extracting relevant features. These features are then used to train four different machine learning templates: Naive Bayes classifier, K-Nearest Neighbors classifier (KNN), Decision Tree, and Discriminant Analysis classifier. The performance of each model is evaluated based on its accuracy in classifying human activities. The results show that the Naive Bayes model achieves an accuracy of 92.6%, KNN achieves 89.8%, Decision Tree achieves 95.9%, and Discriminant Analysis achieves 85.4%. The Decision Tree model achieved the highest accuracy (95.9%) in recognizing activities. The findings of this study demonstrate the effectiveness of machine learning in recognizing human activities using sensor data. The results have implications for various applications, including health monitoring, fitness tracking, and smart home automation.