This contribution presents an overview of engineering techniques to collect human behavior data, highlighting the main research trends and challenges. From our research it emerged that wearable and smartphone sensors are popular for monitoring movement and vital signs, although accuracy can be influenced by environmental factors. Combining multiple sensors improves data accuracy, while machine learning algorithms enable pattern detection and behavior analysis. Non-invasive techniques, such as video monitoring and speech analysis, offer a comprehensive view of behavior. Despite all the positive advancements, there are still remaining challenges that require further research, including the need to enhance sensor accuracy, develop sensor fusion methods, and refine machine learning algorithms for improved data analysis in human activity monitoring.